notebook.community

Edit and run

Table of content

IMPORT & LOAD

back





In [1]:



    


####Import libraries
# SQL
import sqlite3
# Data Manipulation
import numpy as np
import pandas as pd
# Visualization
import seaborn as sns
import matplotlib.pyplot as plt
import missingno as msno   #NaNs
#Nice Tables
from ipy_table import *

# Import and suppress warnings
import warnings
warnings.filterwarnings('ignore')

pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)



    











In [2]:



    


#load data (make sure you have downloaded database.sqlite)
with sqlite3.connect(r'C:/Users/ernest.chocholowski/Desktop/Datasets/Soccer/database.sqlite') as con:
    country_df = pd.read_sql_query("SELECT * from Country", con)
    matches_df = pd.read_sql_query("SELECT * from Match", con)
    league_df = pd.read_sql_query("SELECT * from League", con)
    team_df = pd.read_sql_query("SELECT * from Team", con)
    player_df = pd.read_sql_query("select * from Player", con)
    player_stats_df = pd.read_sql_query("select * from player_attributes", con)

#load past results
super_table=[["Name", 'Regression function', "Train Acc", 'Validation Acc', "r2_score", "conf_matrix", 'Cross-Valid.'],]
df_load = pd.read_csv(r'C:/Users/ernest.chocholowski/Desktop/GIT/SoccerAnalysis/out/results_table.csv')
for row in df_load.values.tolist():
    super_table.append(row)



    











In [3]:



    


all_df = [country_df, matches_df, league_df, team_df, player_df]
country_df.dfname = 'country_df'
matches_df.dfname = 'matches_df'
league_df.dfname = 'league_df' 
team_df.dfname = 'team_df' 
player_df.dfname = 'player_df'
player_stats_df.dfname = 'player_stats_df'

DATA EXPLORATION

back





In [4]:



    


for df in all_df:
    print(df.dfname)
    print(df.info())
    print('-'*40)



    


















    






country_df
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 11 entries, 0 to 10
Data columns (total 2 columns):
id      11 non-null int64
name    11 non-null object
dtypes: int64(1), object(1)
memory usage: 256.0+ bytes
None
----------------------------------------
matches_df
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 25979 entries, 0 to 25978
Columns: 115 entries, id to BSA
dtypes: float64(96), int64(9), object(10)
memory usage: 22.8+ MB
None
----------------------------------------
league_df
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 11 entries, 0 to 10
Data columns (total 3 columns):
id            11 non-null int64
country_id    11 non-null int64
name          11 non-null object
dtypes: int64(2), object(1)
memory usage: 344.0+ bytes
None
----------------------------------------
team_df
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 299 entries, 0 to 298
Data columns (total 5 columns):
id                  299 non-null int64
team_api_id         299 non-null int64
team_fifa_api_id    288 non-null float64
team_long_name      299 non-null object
team_short_name     299 non-null object
dtypes: float64(1), int64(2), object(2)
memory usage: 11.8+ KB
None
----------------------------------------
player_df
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 11060 entries, 0 to 11059
Data columns (total 7 columns):
id                    11060 non-null int64
player_api_id         11060 non-null int64
player_name           11060 non-null object
player_fifa_api_id    11060 non-null int64
birthday              11060 non-null object
height                11060 non-null float64
weight                11060 non-null int64
dtypes: float64(1), int64(4), object(2)
memory usage: 604.9+ KB
None
----------------------------------------

















In [7]:



    


msno.matrix(matches_df)



    


















    
























In [8]:



    


matches_df.dropna(thresh=80, inplace=True)



    











In [9]:



    


msno.matrix(matches_df)



    


















    
























In [8]:



    


msno.dendrogram(matches_df)



    


















    
























In [9]:



    


matches_df.hist(figsize = (100, 100))
plt.show()



    


















    
























In [10]:



    


bookies = ['B365', 'BW', 'IW', 'LB', 'PS', 'WH', 'SJ', 'VC', 'GB', 'BS']
bookies_H = [bookie+'H' for bookie in bookies]
bookies_A = [bookie+'A' for bookie in bookies]
bookies_D = [bookie+'D' for bookie in bookies]
bookies_types = {'Home odds':bookies_H, 'Draw odds':bookies_D, 'Away odds':bookies_A}



    











In [11]:



    


for home, draw, away in zip(bookies_H,bookies_A,bookies_D):
    fig, ax = plt.subplots()
    for odds in [home, draw, away]:
        sns.distplot(matches_df[odds].dropna(), ax=ax, label=odds, hist = False)
    #set title
    plt.title(home[:-1], fontsize=16)
    #remove x label
    ax.set_xlabel('')
    ax.set_xlim([0, 8])
    plt.show()



    


















    

















    

















    

















    

















    

















    

















    

















    

















    

















    
























In [12]:



    


plt.rc('legend',fontsize=30)
#_______All bookmakers - Home/Draw/Away odds | KDE + BOXPLOTS
bookies_types = {'Home odds':bookies_H, 'Draw odds':bookies_D, 'Away odds':bookies_A}
for bookie_type, bookie_list in bookies_types.items():
    fig, axes = plt.subplots(ncols=2, figsize=(30,15))
    axes[0].set_xlim([0, 8])
    if bookie_type=='Home odds':
        axes[0].set_ylim([0, 0.65])
    elif bookie_type =='Draw odds':
        axes[0].set_ylim([0, 2.3])
    else:
        axes[0].set_ylim([0, 0.35])
    for bookie in bookie_list:
        sns.distplot(matches_df[bookie].dropna(), ax = axes[0], label=bookie, hist = False)
    #remove x label
    axes[0].set_xlabel('')
    #locate legend 
    plt.legend(loc='best')
    col_sel = bookie_list
    bookie_sel_df = matches_df[bookie_list]
    axes[1] = sns.boxplot(data=bookie_sel_df, palette='Set2', showmeans=True)
    if bookie_type=='Home odds':
        axes[1].set_ylim([1, 5])
    elif bookie_type =='Draw odds':
        axes[1].set_ylim([1, 10])
    else:
        axes[1].set_ylim([1, 5.5])
    
    plt.suptitle(str(bookie_type), fontsize=80)
    plt.show()



    


















    

















    

















    
























In [13]:



    


#How many goals - Home\Away
goals_df = matches_df[['home_team_goal', 'away_team_goal']]
color = ['red', 'lime']
fig, ax = plt.subplots()
ax.set_xlim([0, 10])
ax.set_ylim([0, 9500])
sns.distplot(goals_df.dropna(), ax = ax, kde = False, color = color)
plt.show()

#Contingency table
goals_home_vs_away = pd.crosstab(index = matches_df["home_team_goal"],
                                 columns = matches_df["away_team_goal"])
print(goals_home_vs_away)



    


















    

















    






away_team_goal     0     1     2    3    4   5   6  7  8  9
home_team_goal                                             
0               1678  1580  1026  450  194  58  17  5  3  1
1               2238  2556  1429  640  218  64  17  2  1  0
2               1807  1879  1120  411  144  38  14  1  1  0
3                972  1017   524  230   46  16   7  0  0  0
4                456   412   205   78   26   9   0  0  0  0
5                152   157    62   20    5   2   0  0  0  0
6                 55    52    24    4    1   0   1  0  0  0
7                 20    12     1    3    0   0   0  0  0  0
8                  5     3     1    0    0   0   0  0  0  0
9                  1     2     1    0    0   0   0  0  0  0
10                 1     0     1    0    0   0   0  0  0  0

















In [182]:



    


from pivottablejs import pivot_ui
matches_df['nobonus_expect_elo_cat'] = pd.cut(matches_df['nobonus_expect_elo'], bins=10, labels=False)
matches_df['100bonus_expect_elo_cat'] = pd.cut(matches_df['100bonus_expect_elo'], bins=10, labels=False)
matches_df['200bonus_expect_elo_cat'] = pd.cut(matches_df['200bonus_expect_elo'], bins=10, labels=False)
pivot_ui(matches_df[['elo_home', 'elo_away', 'elo_home_cat', 'elo_away_cat', 'nobonus_expect_elo_cat', 
            '100bonus_expect_elo_cat','200bonus_expect_elo_cat', 'VSPointDiff', 'RESULT']])



    


















    
Out[182]:

FEATURE ENGINEERING

back





In [4]:



    


def get_last_matches_against_eachother(matches, date, home_team, away_team, x = 1000, concat=False):
    ''' Get the last x matches of two given teams. '''
    
    #Find matches of both teams
    home_matches = matches[(matches['home_team_api_id'] == home_team) & (matches['away_team_api_id'] == away_team)]    
    away_matches = matches[(matches['home_team_api_id'] == away_team) & (matches['away_team_api_id'] == home_team)]  
    
    #Get last x matches
    if(concat == True):
        total_matches = pd.concat([home_matches, away_matches])
        try:    
            last_matches = total_matches[total_matches.date < date].\
            sort_values(by = 'date', ascending = False).iloc[0:x,:]
        except:
            last_matches = total_matches[total_matches.date < date].\
            sort_values(by = 'date', ascending = False).iloc[0:total_matches.shape[0],:]

            #Check for error in data
            if(last_matches.shape[0] > x):
                print("Error in obtaining matches")
            #Return data
            return last_matches
    else:
        try:    
            last_home_matches = home_matches[home_matches.date < date].\
            sort_values(by = 'date', ascending = False).iloc[0:x,:]
        except:
            last_home_matches = home_matches[home_matches.date < date].\
            sort_values(by = 'date', ascending = False).iloc[0:home_matches.shape[0],:]

            #Check for error in data
            if(last_matches.shape[0] > x):
                print("Error in obtaining matches")
        try:    
            last_away_matches = away_matches[away_matches.date < date].\
            sort_values(by = 'date', ascending = False).iloc[0:x,:]
        except:
            last_away_matches = away_matches[away_matches.date < date].\
            sort_values(by = 'date', ascending = False).iloc[0:away_matches.shape[0],:]

            #Check for error in data
            if(last_matches.shape[0] > x):
                print("Error in obtaining matches")
        #Return data
        return (home_matches, away_matches)



    











In [5]:



    


def label_point_diff_against_eachother(row, df):
    last_matches = get_last_matches_against_eachother(df, row.date, row.home_team_api_id,
                                                  row.away_team_api_id)
    d_home = {'WIN': 3, 'DRAW': 0, 'LOSE': -3}
    last_matches[0]['POINTS'] = last_matches[0]['RESULT'].map(d_home)
    d_away = {'WIN': -3, 'DRAW': 0, 'LOSE': 3}
    last_matches[1]['POINTS'] = last_matches[1]['RESULT'].map(d_away)
    return (last_matches[0]['POINTS'].sum()+last_matches[1]['POINTS'].sum())



    











In [6]:



    


def impute_numeric (dataset, formula):
    """
    Impute numeric values in a dataset usinng linear regression
    dataset = Pandas Dataframe
    formula e.g. 'Y ~ X1 + X2'
    """
    import statsmodels.formula.api as smf
    import pandas as pd
    
    lm = smf.ols(formula = formula, data = dataset)
    res = lm.fit()
    
    temp_train = dataset[pd.isnull(dataset).any(axis=1)].copy()
    temp_train = temp_train.drop(formula.split(None, 1)[0], axis=1).copy()
    
    var_pred = res.predict(temp_train)
    var_pred = var_pred.round(decimals=0)
    
    dataset[formula.split(None, 1)[0]].fillna(var_pred, inplace=True)



    











In [7]:



    


def label_win (row):
    if row['home_team_goal'] > row['away_team_goal']:
        return 'WIN'
    if row['home_team_goal'] == row['away_team_goal']:
        return 'DRAW'
    if row['home_team_goal'] < row['away_team_goal']:
        return 'LOSE'



    











In [8]:



    


def label_position (row, X, Y):
        posY = row[Y]
        posX = row[X]
        if (posY==1.0 and posX==1.0):#GOALKEEPERS
            return 'GK'
        elif (posY == 2.0):
            return 'SW'
        elif (posY == 3.0): #CB and RBs
            if (posX < 4.0):
                return 'RB'
            elif (posX < 7.0):
                return 'CB'
            else:
                return 'LB'
        elif (posY == 4.0): #DM and RWBs
            if (posX < 4.0):
                return'RWB'
            elif (posX < 7.0):
                return 'DM'
            else:
                return 'LWB'
        elif (posY < 7.0): #CM and RWs
            if (posX < 4.0):
                return 'RW'
            elif (posX < 7.0):
                return 'CM'
            else:
                return 'LW'
        elif (posY < 9.0): #AM and RWs
            if (posX < 4.0):
                return 'RW'
            elif (posX < 7.0):
                return 'AM'
            else:
                return 'LW'
        else:
            if (posX < 4.0):
                return 'RWF'
            elif (posX < 7.0):
                return 'CF'
            else:
                return 'LWF'



    











In [9]:



    


def label_formation (row, home_flag):
    #Check if home or away
    if home_flag == True:
        prefix = 'home'
    else:
        prefix = 'away'
    #Define the vectors needed     
    players_lst = ['_player_2_', '_player_3_',
       '_player_4_', '_player_5_',
       '_player_6_', '_player_7_',
       '_player_8_', '_player_9_',
       '_player_10_', '_player_11_']
    player_positions = [prefix+player+'position' for player in players_lst]
    #roles on the playfield
    defenders = ['SW', 'RB', 'CB', 'LB', 'RWB', 'LWB']
    midfielders = ['DM', 'CM', 'LW', 'RW', 'AM']
    forwarders = ['RWF', 'CF', 'LWF']
    formation = [0, 0, 0]
    
    for position in player_positions:
        pos = row[position]
        if pos in defenders:
            formation[0] += 1
        elif home in midfielders:
            formation[1] += 1
        else:
            formation[2] += 1
    formation_string = '{}-{}-{}'.format(away_formation[0], away_formation[1], away_formation[2])
    return formation_string



    











In [10]:



    


def calculate_age(row, which_player):
    from datetime import date, datetime
    birthday_date = which_player + '_birthDate'
    birthday_date = datetime.strptime(row[birthday_date][:10], "%Y-%m-%d").date()
    match_date = datetime.strptime(row.date[:10], "%Y-%m-%d").date()
    return(match_date.year - birthday_date.year - ((match_date.month, match_date.day)
                                                   < (birthday_date.month, birthday_date.day)))



    











In [11]:



    


def match_entropy(row):
    from scipy.stats import entropy
    bookies = ['B365', 'BW', 'IW', 'LB', 'WH', 'VC', 'BS']
    odds_h = [row[bookie+'H'] for bookie in bookies]
    odds_d = [row[bookie+'D'] for bookie in bookies]
    odds_a = [row[bookie+'A'] for bookie in bookies]
    odds = [np.mean(odds_h), np.mean(odds_d), np.mean(odds_a)]
    #change odds to probability
    probs = [1/o for o in odds]
    #normalize to sum to 1
    norm = sum(probs)
    probs = [p/norm for p in probs]
    return entropy(probs)



    











In [80]:



    


def calc_probs(row, where):
    odds = [row['Home_odds'], row['Draw_odds'], row['Away_odds']]
    probs = [1/o for o in odds]
    #normalize to sum to 1
    norm = sum(probs)
    probs = [p/norm for p in probs]
    if where == 'home':
        return probs[0]
    elif where == 'draw':
        return probs[1]
    elif where == 'away':
        return probs[2]
    else: return None



    











In [12]:



    


def calculate_group_ratings (row, home_flag, role):
    import numpy as np
    
    #Define the vectors needed    
    if home_flag == True:
        prefix = 'home'
    else:
        prefix = 'away'
    
    players_lst = ['_player_2_', '_player_3_',
       '_player_4_', '_player_5_',
       '_player_6_', '_player_7_',
       '_player_8_', '_player_9_',
       '_player_10_', '_player_11_']
    player_positions = [prefix+player+'position' for player in players_lst]
    player_ratings = [prefix+player+'overall_rating' for player in players_lst]
    
    if role == 'defenders':
        role_list = ['SW', 'RB', 'CB', 'LB', 'RWB', 'LWB']
    elif role == 'midfielders':
        role_list = ['DM', 'CM', 'LW', 'RW', 'AM']
    elif role == 'forwarders':
        role_list = ['RWF', 'CF', 'LWF']

    scores_vector = []

#Counts the number of players in Defenders, Midfielders, Forwarders    
    for position, rank in zip(player_positions, player_ratings):
        pos = row[position]
        if pos in role_list:
            rtng = row[rank]
            scores_vector.append(rtng)

#Counts the average of overall rating in Defeders/Midfieldes/Forwarders    
    return np.mean(scores_vector)



    











In [13]:



    


def rate_elo(winner, loser, times=10):
    from elo import rate_1vs1
    winn=winner
    los = loser
    for i in range (times):
        winn, los = rate_1vs1(winn, los)
    return winn, los



    











In [14]:



    


def fetch_elo(team_id, date, df):
    #DEBUG
    if fetch_elo.counter is None:
        fetch_elo.counter = 1
    else:
        fetch_elo.counter += 1 #debug

    #Find matches
    home_matches_df = df[(df['home_team_api_id'] == team_id)]    
    away_matches_df = df[(df['away_team_api_id'] == team_id)]  
    total_matches_df = pd.concat([home_matches_df, away_matches_df])
    #Get last match with this team
    last_match_df = total_matches_df[total_matches_df.date < date].\
             sort_values(by = 'date', ascending = False).iloc[0:1,:]

    #calculate new elo rating
    try:
        home_id = last_match_df.iloc[0]['home_team_api_id']
        away_id = last_match_df.iloc[0]['away_team_api_id']
        result = last_match_df.iloc[0]['RESULT']
    except:
        #print ('#', fetch_elo.counter, 'Exception when trying to fetch last match of', team_id, 'in fetch_elo(). Assigning 1500 ELO')
        return 1500.0

    #are they home team?
    if (home_id == team_id):
        last_elo_ = last_match_df.iloc[0]['elo_home']
        last_elo_opponent = last_match_df.iloc[0]['elo_away']
        if result == 'DRAW': #if last match result was draw, then whatever, elo stays the same
            return last_elo_
        elif result == 'WIN':
            return rate_elo(last_elo_, last_elo_opponent)[0]
        elif result == 'LOSE':
            return rate_elo(last_elo_opponent, last_elo_)[1]
        else:
            print ('#', fetch_elo.counter, "ERROR:: Can't fetch result!")
            return np.nan

    #are they away team?
    elif (away_id == team_id):
        last_elo_ = last_match_df.iloc[0]['elo_away']
        last_elo_opponent = last_match_df.iloc[0]['elo_home']
        if result == 'DRAW': #if last match result was draw, then whatever, elo stays the same
            return last_elo_
        elif result == 'LOSE':
            return rate_elo(last_elo_, last_elo_opponent)[0]
        elif result == 'WIN':
            return rate_elo(last_elo_opponent, last_elo_)[1]
        else:
            print ('#', fetch_elo.counter, "ERROR:: Can't fetch result!")
            return np.nan

    else:
        print ('#', fetch_elo.counter, "ERROR:: Can't find home_team_api_id in last_match_df")
        return np.nan



    











In [15]:



    


def calculate_elo_ratings(row, df):
    home_id = row['home_team_api_id']
    away_id = row['away_team_api_id']
    date = row['date']
    #Fetch elo_home
    elo_home = fetch_elo(home_id, date, df)
    #fetch elo_away
    elo_away = fetch_elo(away_id, date, df)
    return elo_home, elo_away



    











In [16]:



    


def label_expect_elo(row, bonus=0):
    from elo import expect
    return expect(row['elo_home']+bonus,row['elo_away'])

end of function declarations

back





In [17]:



    


#FREAKING CHEATING NO WAITING SO GOOD
matches_df = pd.DataFrame().from_csv('saved_matches_df')



    











In [199]:



    


matches_df.head()



    


















    
Out[199]:











  
    

      
      id
      country_id
      league_id
      season
      stage
      date
      match_api_id
      home_team_api_id
      away_team_api_id
      home_team_goal
      away_team_goal
      home_player_X1
      home_player_X2
      home_player_X3
      home_player_X4
      home_player_X5
      home_player_X6
      home_player_X7
      home_player_X8
      home_player_X9
      home_player_X10
      home_player_X11
      away_player_X1
      away_player_X2
      away_player_X3
      away_player_X4
      away_player_X5
      away_player_X6
      away_player_X7
      away_player_X8
      away_player_X9
      away_player_X10
      away_player_X11
      home_player_Y1
      home_player_Y2
      home_player_Y3
      home_player_Y4
      home_player_Y5
      home_player_Y6
      home_player_Y7
      home_player_Y8
      home_player_Y9
      home_player_Y10
      home_player_Y11
      away_player_Y1
      away_player_Y2
      away_player_Y3
      away_player_Y4
      away_player_Y5
      away_player_Y6
      away_player_Y7
      away_player_Y8
      away_player_Y9
      away_player_Y10
      away_player_Y11
      home_player_1
      home_player_2
      home_player_3
      home_player_4
      home_player_5
      home_player_6
      home_player_7
      home_player_8
      home_player_9
      home_player_10
      home_player_11
      away_player_1
      away_player_2
      away_player_3
      away_player_4
      away_player_5
      away_player_6
      away_player_7
      away_player_8
      away_player_9
      away_player_10
      away_player_11
      B365H
      B365D
      B365A
      BWH
      BWD
      BWA
      IWH
      IWD
      IWA
      LBH
      LBD
      LBA
      PSH
      PSD
      PSA
      WHH
      WHD
      WHA
      SJH
      SJD
      SJA
      VCH
      VCD
      VCA
      GBH
      GBD
      GBA
      BSH
      BSD
      BSA
      RESULT
      home_player_1_position
      home_player_2_position
      home_player_3_position
      home_player_4_position
      home_player_5_position
      home_player_6_position
      home_player_7_position
      home_player_8_position
      home_player_9_position
      home_player_10_position
      home_player_11_position
      away_player_1_position
      away_player_2_position
      away_player_3_position
      away_player_4_position
      away_player_5_position
      away_player_6_position
      away_player_7_position
      away_player_8_position
      away_player_9_position
      away_player_10_position
      away_player_11_position
      VSPointDiff
      home_player_1_overall_rating
      home_player_2_overall_rating
      home_player_3_overall_rating
      home_player_4_overall_rating
      home_player_5_overall_rating
      home_player_6_overall_rating
      home_player_7_overall_rating
      home_player_8_overall_rating
      home_player_9_overall_rating
      home_player_10_overall_rating
      home_player_11_overall_rating
      away_player_1_overall_rating
      away_player_2_overall_rating
      away_player_3_overall_rating
      away_player_4_overall_rating
      away_player_5_overall_rating
      away_player_6_overall_rating
      away_player_7_overall_rating
      away_player_8_overall_rating
      away_player_9_overall_rating
      away_player_10_overall_rating
      away_player_11_overall_rating
      home_formation
      away_formation
      home_player_1_birthDate
      home_player_2_birthDate
      home_player_3_birthDate
      home_player_4_birthDate
      home_player_5_birthDate
      home_player_6_birthDate
      home_player_7_birthDate
      home_player_8_birthDate
      home_player_9_birthDate
      home_player_10_birthDate
      home_player_11_birthDate
      away_player_1_birthDate
      away_player_2_birthDate
      away_player_3_birthDate
      away_player_4_birthDate
      away_player_5_birthDate
      away_player_6_birthDate
      away_player_7_birthDate
      away_player_8_birthDate
      away_player_9_birthDate
      away_player_10_birthDate
      away_player_11_birthDate
      home_player_1_Age
      home_player_2_Age
      home_player_3_Age
      home_player_4_Age
      home_player_5_Age
      home_player_6_Age
      home_player_7_Age
      home_player_8_Age
      home_player_9_Age
      home_player_10_Age
      home_player_11_Age
      away_player_1_Age
      away_player_2_Age
      away_player_3_Age
      away_player_4_Age
      away_player_5_Age
      away_player_6_Age
      away_player_7_Age
      away_player_8_Age
      away_player_9_Age
      away_player_10_Age
      away_player_11_Age
      entropy
      home_defenders_score
      home_midfielders_score
      home_forwarders_score
      away_defenders_score
      away_midfielders_score
      away_forwarders_score
      elo_home
      elo_away
      nobonus_expect_elo
      200bonus_expect_elo
      100bonus_expect_elo
    

  
  
    

      9531
      9532
      7809
      7809
      2013/2014
      29
      2014-04-05
      1479252
      8406
      9823
      1
      0
      1.0
      2.0
      4.0
      6.0
      8.0
      4.0
      6.0
      3.0
      5.0
      7.0
      5.0
      1.0
      4.0
      6.0
      8.0
      2.0
      4.0
      6.0
      3.0
      5.0
      7.0
      5.0
      1.0
      3.0
      3.0
      3.0
      3.0
      6.0
      6.0
      8.0
      8.0
      8.0
      11.0
      1.0
      3.0
      3.0
      3.0
      3.0
      6.0
      6.0
      8.0
      8.0
      8.0
      11.0
      114737.0
      26618.0
      27425.0
      245526.0
      240348.0
      303905.0
      37319.0
      147735.0
      35997.0
      215170.0
      95094.0
      27299.0
      33085.0
      37410.0
      174018.0
      298823.0
      30872.0
      95078.0
      176300.0
      25366.0
      266523.0
      75447.0
      7.5
      5.00
      1.36
      7.50
      5.0
      1.36
      7.3
      4.4
      1.40
      8.5
      5.0
      1.33
      8.84
      5.04
      1.41
      9.0
      3.8
      1.44
      7.5
      4.5
      1.36
      8.0
      5.00
      1.44
      8.01750
      4.71750
      1.38750
      8.01750
      4.71750
      1.38750
      WIN
      GK
      RB
      CB
      CB
      LB
      CM
      CM
      RW
      AM
      LW
      CF
      GK
      CB
      CB
      LB
      RB
      CM
      CM
      RW
      AM
      LW
      CF
      -12
      70.0
      65.0
      73.0
      63.0
      57.0
      82.0
      73.0
      65.0
      72.0
      70.0
      71.0
      72.0
      69.0
      72.0
      70.0
      69.0
      71.0
      75.0
      71.0
      62.0
      74.0
      65.0
      4-5-1
      4-5-1
      1992-03-04 00:00:00
      1991-09-23 00:00:00
      1986-01-25 00:00:00
      1989-05-15 00:00:00
      1985-10-24 00:00:00
      1989-02-25 00:00:00
      1987-06-16 00:00:00
      1992-09-27 00:00:00
      1990-07-08 00:00:00
      1988-12-20 00:00:00
      1978-01-04 00:00:00
      1992-03-04 00:00:00
      1990-04-12 00:00:00
      1986-01-25 00:00:00
      1989-02-03 00:00:00
      1990-05-29 00:00:00
      1990-03-16 00:00:00
      1990-08-16 00:00:00
      1987-04-23 00:00:00
      1991-05-28 00:00:00
      1989-12-17 00:00:00
      1986-05-21 00:00:00
      22
      22
      28
      24
      28
      25
      26
      21
      23
      25
      36
      22
      23
      28
      25
      23
      24
      23
      26
      22
      24
      27
      0.837057
      64.50
      72.4
      71.0
      70.00
      70.6
      65.0
      1502
      2103
      0.030483
      0.090434
      0.052951
    

    

      9517
      9518
      7809
      7809
      2013/2014
      27
      2014-03-25
      1479237
      8177
      9823
      1
      3
      1.0
      2.0
      4.0
      6.0
      8.0
      4.0
      6.0
      3.0
      5.0
      7.0
      5.0
      1.0
      2.0
      4.0
      6.0
      8.0
      5.0
      2.0
      4.0
      6.0
      8.0
      5.0
      1.0
      3.0
      3.0
      3.0
      3.0
      6.0
      6.0
      8.0
      8.0
      8.0
      11.0
      1.0
      3.0
      3.0
      3.0
      3.0
      6.0
      8.0
      8.0
      8.0
      8.0
      11.0
      36878.0
      12330.0
      29543.0
      278831.0
      40985.0
      20125.0
      27307.0
      40108.0
      394462.0
      212960.0
      50345.0
      27299.0
      27303.0
      36183.0
      38432.0
      121633.0
      30894.0
      30834.0
      30872.0
      95078.0
      177714.0
      116772.0
      13.0
      6.50
      1.20
      11.00
      7.0
      1.20
      12.0
      5.5
      1.22
      11.0
      6.5
      1.22
      15.25
      6.98
      1.23
      13.0
      6.0
      1.22
      10.0
      5.8
      1.22
      13.0
      6.50
      1.25
      12.28125
      6.34750
      1.22000
      12.28125
      6.34750
      1.22000
      LOSE
      GK
      RB
      CB
      CB
      LB
      CM
      CM
      RW
      AM
      LW
      CF
      GK
      RB
      CB
      CB
      LB
      CM
      RW
      AM
      AM
      LW
      CF
      -30
      74.0
      68.0
      76.0
      63.0
      57.0
      76.0
      71.0
      74.0
      76.0
      69.0
      73.0
      70.0
      71.0
      70.0
      69.0
      72.0
      70.0
      75.0
      73.0
      79.0
      65.0
      70.0
      4-5-1
      4-5-1
      1992-03-04 00:00:00
      1990-04-12 00:00:00
      1984-09-28 00:00:00
      1989-05-15 00:00:00
      1985-10-24 00:00:00
      1985-09-07 00:00:00
      1989-09-16 00:00:00
      1990-08-13 00:00:00
      1993-08-06 00:00:00
      1985-10-23 00:00:00
      1983-08-12 00:00:00
      1992-03-04 00:00:00
      1992-06-16 00:00:00
      1994-01-19 00:00:00
      1989-02-03 00:00:00
      1990-05-29 00:00:00
      1989-09-16 00:00:00
      1982-06-06 00:00:00
      1986-05-28 00:00:00
      1988-01-03 00:00:00
      1987-06-10 00:00:00
      1983-10-02 00:00:00
      22
      23
      29
      24
      28
      28
      24
      23
      20
      28
      30
      22
      21
      20
      25
      23
      24
      31
      27
      26
      26
      30
      0.680009
      66.00
      73.2
      73.0
      70.50
      72.4
      70.0
      1419
      2102
      0.019234
      0.058394
      0.033699
    

    

      9508
      9509
      7809
      7809
      2013/2014
      26
      2014-03-22
      1479228
      9905
      9823
      0
      2
      1.0
      2.0
      4.0
      6.0
      8.0
      6.0
      3.0
      5.0
      7.0
      4.0
      5.0
      1.0
      2.0
      4.0
      6.0
      8.0
      4.0
      6.0
      3.0
      5.0
      7.0
      5.0
      1.0
      3.0
      3.0
      3.0
      3.0
      6.0
      8.0
      8.0
      8.0
      6.0
      11.0
      1.0
      3.0
      3.0
      3.0
      3.0
      6.0
      6.0
      8.0
      8.0
      8.0
      11.0
      287894.0
      33823.0
      193901.0
      36806.0
      130667.0
      237542.0
      97747.0
      201888.0
      95082.0
      180126.0
      20694.0
      27299.0
      30894.0
      37410.0
      36183.0
      121633.0
      95078.0
      30872.0
      30834.0
      116772.0
      30924.0
      75447.0
      11.0
      6.50
      1.22
      9.75
      6.0
      1.25
      10.0
      5.2
      1.27
      11.0
      6.5
      1.22
      13.00
      6.21
      1.28
      12.0
      5.0
      1.29
      9.0
      5.8
      1.25
      10.5
      6.50
      1.29
      10.78125
      5.96375
      1.25875
      10.78125
      5.96375
      1.25875
      LOSE
      GK
      RB
      CB
      CB
      LB
      CM
      RW
      AM
      LW
      CM
      CF
      GK
      RB
      CB
      CB
      LB
      CM
      CM
      RW
      AM
      LW
      CF
      -15
      70.0
      65.0
      76.0
      64.0
      65.0
      76.0
      72.0
      68.0
      69.0
      70.0
      74.0
      72.0
      70.0
      71.0
      70.0
      72.0
      72.0
      71.0
      74.0
      81.0
      68.0
      70.0
      4-5-1
      4-5-1
      1992-03-04 00:00:00
      1990-04-12 00:00:00
      1985-09-07 00:00:00
      1994-01-19 00:00:00
      1985-10-24 00:00:00
      1988-09-02 00:00:00
      1984-05-18 00:00:00
      1987-04-23 00:00:00
      1993-09-20 00:00:00
      1986-05-28 00:00:00
      1983-08-12 00:00:00
      1992-03-04 00:00:00
      1993-03-03 00:00:00
      1994-01-19 00:00:00
      1989-02-03 00:00:00
      1991-03-14 00:00:00
      1991-12-05 00:00:00
      1982-02-12 00:00:00
      1993-08-17 00:00:00
      1985-08-04 00:00:00
      1988-08-21 00:00:00
      1983-10-02 00:00:00
      22
      23
      28
      20
      28
      25
      29
      26
      20
      27
      30
      22
      21
      20
      25
      23
      22
      32
      20
      28
      25
      30
      0.720415
      67.50
      71.0
      74.0
      70.75
      73.2
      70.0
      1656
      2095
      0.073981
      0.201685
      0.124396
    

    

      9486
      9487
      7809
      7809
      2013/2014
      24
      2014-03-08
      1479206
      8721
      9823
      1
      6
      1.0
      2.0
      4.0
      6.0
      8.0
      4.0
      6.0
      3.0
      5.0
      7.0
      5.0
      1.0
      2.0
      4.0
      6.0
      8.0
      5.0
      2.0
      4.0
      6.0
      8.0
      5.0
      1.0
      3.0
      3.0
      3.0
      3.0
      6.0
      6.0
      8.0
      8.0
      8.0
      11.0
      1.0
      3.0
      3.0
      3.0
      3.0
      6.0
      8.0
      8.0
      8.0
      8.0
      11.0
      30820.0
      27472.0
      28480.0
      259296.0
      115591.0
      298915.0
      119838.0
      163670.0
      169200.0
      188498.0
      104045.0
      27299.0
      27303.0
      36183.0
      38432.0
      121633.0
      30894.0
      30834.0
      176300.0
      95078.0
      30924.0
      116772.0
      9.0
      5.75
      1.29
      8.50
      5.5
      1.30
      8.0
      5.0
      1.33
      10.0
      5.0
      1.30
      10.78
      5.79
      1.33
      7.5
      5.5
      1.33
      8.5
      5.0
      1.30
      9.5
      5.75
      1.33
      8.97250
      5.41125
      1.31375
      8.97250
      5.41125
      1.31375
      LOSE
      GK
      RB
      CB
      CB
      LB
      CM
      CM
      RW
      AM
      LW
      CF
      GK
      RB
      CB
      CB
      LB
      CM
      RW
      AM
      AM
      LW
      CF
      -33
      70.0
      65.0
      81.0
      66.0
      69.0
      73.0
      69.0
      69.0
      73.0
      65.0
      73.0
      73.0
      71.0
      66.0
      70.0
      72.0
      71.0
      74.0
      73.0
      78.0
      74.0
      70.0
      4-5-1
      4-5-1
      1992-04-30 00:00:00
      1990-04-12 00:00:00
      1994-01-19 00:00:00
      1988-06-09 00:00:00
      1990-07-11 00:00:00
      1987-09-11 00:00:00
      1988-01-02 00:00:00
      1995-09-18 00:00:00
      1985-04-19 00:00:00
      1985-02-28 00:00:00
      1983-08-12 00:00:00
      1992-03-04 00:00:00
      1992-01-11 00:00:00
      1991-08-08 00:00:00
      1988-06-09 00:00:00
      1990-06-05 00:00:00
      1987-09-26 00:00:00
      1992-01-05 00:00:00
      1989-11-27 00:00:00
      1987-06-11 00:00:00
      1988-12-20 00:00:00
      1977-06-27 00:00:00
      21
      23
      20
      25
      23
      26
      26
      18
      28
      29
      30
      22
      22
      22
      25
      23
      26
      22
      24
      26
      25
      36
      0.781728
      70.25
      69.8
      73.0
      69.75
      74.0
      70.0
      1623
      2086
      0.065056
      0.180354
      0.110112
    

    

      9467
      9468
      7809
      7809
      2013/2014
      22
      2014-02-23
      1479186
      9904
      9823
      0
      4
      1.0
      2.0
      4.0
      6.0
      8.0
      2.0
      4.0
      6.0
      8.0
      4.0
      6.0
      1.0
      2.0
      4.0
      6.0
      8.0
      4.0
      6.0
      3.0
      5.0
      7.0
      5.0
      1.0
      3.0
      3.0
      3.0
      3.0
      7.0
      7.0
      7.0
      7.0
      10.0
      10.0
      1.0
      3.0
      3.0
      3.0
      3.0
      6.0
      6.0
      8.0
      8.0
      8.0
      11.0
      41087.0
      69833.0
      78908.0
      25483.0
      38795.0
      39045.0
      36186.0
      94916.0
      260470.0
      79982.0
      72735.0
      33473.0
      27303.0
      36183.0
      37410.0
      121633.0
      30872.0
      30894.0
      116772.0
      172949.0
      177714.0
      75447.0
      10.0
      7.00
      1.22
      10.00
      6.0
      1.25
      9.0
      6.0
      1.25
      10.0
      6.0
      1.25
      13.26
      6.59
      1.26
      12.0
      5.5
      1.25
      10.0
      5.5
      1.25
      12.0
      6.50
      1.25
      10.78250
      6.13625
      1.24750
      10.78250
      6.13625
      1.24750
      LOSE
      GK
      RB
      CB
      CB
      LB
      RW
      AM
      AM
      LW
      CF
      CF
      GK
      RB
      CB
      CB
      LB
      CM
      CM
      RW
      AM
      LW
      CF
      -33
      74.0
      67.0
      69.0
      65.0
      69.0
      65.0
      72.0
      73.0
      70.0
      67.0
      72.0
      69.0
      69.0
      62.0
      60.0
      73.0
      66.0
      73.0
      69.0
      83.0
      65.0
      69.0
      4-4-2
      4-5-1
      1992-04-30 00:00:00
      1992-01-11 00:00:00
      1983-05-15 00:00:00
      1988-06-09 00:00:00
      1990-06-05 00:00:00
      1984-05-18 00:00:00
      1990-09-18 00:00:00
      1986-05-28 00:00:00
      1991-05-28 00:00:00
      1986-04-07 00:00:00
      1983-08-12 00:00:00
      1992-04-30 00:00:00
      1992-01-11 00:00:00
      1983-05-15 00:00:00
      1985-02-14 00:00:00
      1990-06-05 00:00:00
      1990-05-22 00:00:00
      1988-05-25 00:00:00
      1992-07-14 00:00:00
      1983-04-18 00:00:00
      1987-06-10 00:00:00
      1987-11-29 00:00:00
      21
      22
      30
      25
      23
      29
      23
      27
      22
      27
      30
      21
      22
      30
      29
      23
      23
      25
      21
      30
      26
      26
      0.713719
      67.50
      70.0
      69.5
      66.00
      71.2
      69.0
      1437
      2070
      0.025485
      0.076382
      0.044438
    

  




















In [ ]:



    


#Win Labelling
matches_df['RESULT'] = matches_df.apply(lambda row: label_win(row), axis=1)



    











In [ ]:



    


#Position Labelling
positionX = ['home_player_X1', 'home_player_X2', 'home_player_X3', 'home_player_X4', 'home_player_X5', 
             'home_player_X6', 'home_player_X7', 'home_player_X8', 'home_player_X9', 'home_player_X10',
             'home_player_X11', 'away_player_X1', 'away_player_X2', 'away_player_X3', 'away_player_X4',
             'away_player_X5', 'away_player_X6', 'away_player_X7', 'away_player_X8', 'away_player_X9', 
             'away_player_X10', 'away_player_X11']
positionY = ['home_player_Y1', 'home_player_Y2', 'home_player_Y3', 'home_player_Y4', 'home_player_Y5', 
             'home_player_Y6', 'home_player_Y7', 'home_player_Y8', 'home_player_Y9', 'home_player_Y10', 
             'home_player_Y11', 'away_player_Y1', 'away_player_Y2', 'away_player_Y3', 'away_player_Y4',
             'away_player_Y5', 'away_player_Y6', 'away_player_Y7', 'away_player_Y8', 'away_player_Y9', 
             'away_player_Y10', 'away_player_Y11']

for X,Y in zip(positionX, positionY):
    player_pos = matches_df [[X, Y]]
    feature_name=X[:-2]+X[-1]+'_position'
    matches_df[feature_name] = player_pos.apply(lambda row: label_position(row, X, Y), axis=1)
    
matches_df = matches_df.rename(columns={'home_player_X0_position': 'home_player_10_position',
                        'home_player_X1_position': 'home_player_11_position', 
                        'away_player_X0_position': 'away_player_10_position', 
                        'away_player_X1_position': 'away_player_11_position'})



    











In [281]:



    


#Formations labelling
matches_df['home_formation'] = matches_df.apply(lambda row: label_formation(row, home_flag=True), axis=1)
matches_df['away_formation'] = matches_df.apply(lambda row: label_formation(row, home_flag=False), axis=1)



    











In [26]:



    


#Difference in points against each other [from Home POV]
matches_df['VSPointDiff'] = matches_df.apply(lambda row: label_point_diff_against_eachother(row, matches_df), axis=1)



    











In [163]:



    


#imputation for less popular bookies
bookies_types = {'Home odds':bookies_H, 'Draw odds':bookies_D, 'Away odds':bookies_A}
for bookie_type, bookie_list in bookies_types.items():
    bookie_sel_df = ml_matches_df[bookie_list]
    bookie_sel_df = bookie_sel_df.apply(lambda x: x.fillna(x.mean()),axis=1)
    matches_df[bookie_list]=bookie_sel_df.copy()



    











In [58]:



    


#Calculate match entropy from bookkeepers' odds
matches_df['entropy'] = matches_df.apply(match_entropy,axis=1)



    











In [4]:



    


player_vector = ['home_player_1', 'home_player_2',
       'home_player_3', 'home_player_4', 'home_player_5', 'home_player_6',
       'home_player_7', 'home_player_8', 'home_player_9', 'home_player_10',
       'home_player_11', 'away_player_1', 'away_player_2', 'away_player_3',
       'away_player_4', 'away_player_5', 'away_player_6', 'away_player_7',
       'away_player_8', 'away_player_9', 'away_player_10',
       'away_player_11']



    











In [207]:



    


#players ratings
for player in player_vector:
    player_stat = pd.merge(matches_df, player_stats_df, left_on = player, 
                                right_on = "player_api_id")
    matches_df[player+'_overall_rating'] = player_stat['overall_rating'].copy()



    











In [21]:



    


#ratings for position_groups
for is_home in (True, False):
    #Define the vectors needed    
    if is_home == True:
        prefix = 'home'
    else:
        prefix = 'away'
    for role in ('defenders', 'midfielders', 'forwarders'):
        feature_name=prefix+'_'+role+'_score'
        matches_df[feature_name] = matches_df.apply(lambda row: calculate_group_ratings(row, is_home, role), axis=1)



    











In [349]:



    


#Importing birth dates for players
for player in player_vector:
    player_stat = pd.merge(matches_df, player_df, left_on = player, 
                                right_on = "player_api_id")
    matches_df[player+'_birthDate'] = player_stat['birthday'].copy()



    











In [352]:



    


for player in player_vector:
    matches_df[player+'_Age'] = matches_df.apply(lambda row: calculate_age(row, player), axis=1)



    











In [141]:



    


#Calculated matches ELO Rating for teams
matches_df['elo_home'] = 1500
matches_df['elo_away'] = 1500
matches_df['date'] = pd.to_datetime(matches_df.date)
matches_df=matches_df.sort_values(by='date')
for i, row in matches_df.iterrows():
    out_tuple=calculate_elo_ratings(row, matches_df)
    matches_df.set_value(i, 'elo_home', out_tuple[0])
    matches_df.set_value(i, 'elo_away', out_tuple[1])



    











In [181]:



    


matches_df['nobonus_expect_elo'] = matches_df.apply (lambda row: label_expect_elo (row, 0),axis=1)
matches_df['100bonus_expect_elo'] = matches_df.apply (lambda row: label_expect_elo (row, bonus=100),axis=1)
matches_df['200bonus_expect_elo'] = matches_df.apply (lambda row: label_expect_elo (row, bonus=200),axis=1)



    











In [200]:



    


#SAVE YOURSELF THE EFFORT LATER
matches_df.to_csv('saved_matches_df')

ML DataFrame Selection!

back





In [170]:



    


def reduce_dim (matches_df):
    #CREATE SHORT_DF
    short_df = matches_df[['B365H', 'B365D', 'B365A', 'BWH', 'BWD', 'BWA',   #
           'IWH', 'IWD', 'IWA', 'LBH', 'LBD', 'LBA', 'PSH', 'PSD', 'PSA',    # bookkeepers
           'WHH', 'WHD', 'WHA', 'SJH', 'SJD', 'SJA', 'VCH', 'VCD', 'VCA',    #
           'GBH', 'GBD', 'GBA', 'BSH', 'BSD', 'BSA',                         #
            'home_player_1_overall_rating', 'away_player_1_overall_rating',        # goalkeepers
            'home_defenders_score', 'home_midfielders_score', 'home_forwarders_score',  #team roles
            'away_defenders_score', 'away_midfielders_score', 'away_forwarders_score',  #comparison
            'home_player_2_Age', 'home_player_3_Age', 'home_player_4_Age', #
           'home_player_5_Age', 'home_player_6_Age', 'home_player_7_Age',  #
           'home_player_8_Age', 'home_player_9_Age', 'home_player_10_Age', #
           'home_player_11_Age', 'away_player_2_Age',                      # AGES
           'away_player_3_Age', 'away_player_4_Age', 'away_player_5_Age',  #
           'away_player_6_Age', 'away_player_7_Age', 'away_player_8_Age',  #
           'away_player_9_Age', 'away_player_10_Age', 'away_player_11_Age']]# #OTHER STATS?

    #GET MEAN AGE FOR BOTH TEAM - EXCLUDING GOALKEEPER, FOR REASONS
    short_df['Age_home'] = short_df[['home_player_2_Age', 'home_player_3_Age', 'home_player_4_Age', 
          'home_player_5_Age', 'home_player_6_Age', 'home_player_7_Age',
          'home_player_8_Age', 'home_player_9_Age', 'home_player_10_Age', 
          'home_player_11_Age']].mean(axis=1)
    short_df['Age_away'] = short_df[['away_player_2_Age',
          'away_player_3_Age', 'away_player_4_Age', 'away_player_5_Age',  
          'away_player_6_Age', 'away_player_7_Age', 'away_player_8_Age',  
          'away_player_9_Age', 'away_player_10_Age', 'away_player_11_Age']].mean(axis=1)
    
    #WE DON'T NEED AGES ANYMORE
    short_df.drop(['home_player_2_Age', 'home_player_3_Age', 'home_player_4_Age', 
           'home_player_5_Age', 'home_player_6_Age', 'home_player_7_Age',
           'home_player_8_Age', 'home_player_9_Age', 'home_player_10_Age', 
           'home_player_11_Age', 'away_player_2_Age',
           'away_player_3_Age', 'away_player_4_Age', 'away_player_5_Age',  
           'away_player_6_Age', 'away_player_7_Age', 'away_player_8_Age',  
           'away_player_9_Age', 'away_player_10_Age', 'away_player_11_Age'], inplace = True, axis=1)
   # short_df['AgeCatHome'] = pd.cut(short_df['Age_home'], 10)
   # short_df['AgeCatAway'] = pd.cut(short_df['Age_away'], 10)
    #BOOKKEEPERS MEAN FOR EACH MATCH
    bookies = ['B365', 'BW', 'IW', 'LB', 'PS', 'WH', 'SJ', 'VC', 'GB', 'BS']
    bookies_H = [bookie+'H' for bookie in bookies]
    bookies_A = [bookie+'A' for bookie in bookies]
    bookies_D = [bookie+'D' for bookie in bookies]
    bookies_types = {'Home_odds':bookies_H, 'Draw_odds':bookies_D, 'Away_odds':bookies_A}
    for feature_name, feature_list in bookies_types.items():
        short_df[feature_name] = short_df[feature_list].mean(axis=1)
        short_df.drop(feature_list, inplace = True, axis=1)
        
    #Categorize elos
    elo_cats = [-1,]
    for i in range(1050,2200,50):
        elo_cats.append(i)
    short_df['elo_home_cat'] = pd.cut(matches_df['elo_home'], bins=elo_cats, labels=False)
    short_df['elo_away_cat'] = pd.cut(matches_df['elo_away'], bins=elo_cats, labels=False)
    
    #Categorize expects
    #short_df['NoBonus_cat'] = pd.cut(matches_df['nobonus_expect_elo'], bins=10, labels=False)
    #short_df['100Bonus_cat'] = pd.cut(matches_df['100bonus_expect_elo'], bins=10, labels=False)
    #short_df['200Bonus_cat'] = pd.cut(matches_df['200bonus_expect_elo'], bins=10, labels=False)
    
    #OTHERS
    short_df['home_formation'] = matches_df['home_formation']
    short_df['away_formation'] = matches_df['away_formation']
    short_df['NoBonus'] = matches_df['nobonus_expect_elo']
    short_df['VSPointDiff'] = matches_df['VSPointDiff']
    short_df['entropy'] = matches_df['entropy']
    short_df['RESULT'] = matches_df['RESULT']
        
    return short_df



    











In [199]:



    


def create_dummy_df(origin_df, categorize):
    #New data set for categorized features
    category_short_df = pd.DataFrame()
    for category in categorize:
        category_short_df[category] = pd.cut(origin_df[category], bins = 7, precision = 1)

    #Creating Dataframes with Dummy variables: 1 Dataset = All columns for 1 variable
    dummy_dfs = []
    for category in categorize:
        dummy_dfs.append(pd.get_dummies(category_short_df[category], prefix = category, drop_first = True))

    output_df = pd.DataFrame()
    output_df = pd.concat(dummy_dfs, axis=1)

    #Adding the rest of the variables from the origin_df that didn't need categorization
    vars_to_add = [var for var in origin_df.columns.values if var not in categorize]
    for add_var in vars_to_add:
        output_df[add_var] = origin_df[add_var]
    return output_df



    











In [171]:



    


short_df = reduce_dim(matches_df)



    











In [200]:



    


categorize = ['home_player_1_overall_rating', 'away_player_1_overall_rating',
       'home_defenders_score', 'home_midfielders_score',
       'home_forwarders_score', 'away_defenders_score',
       'away_midfielders_score', 'away_forwarders_score', 'Age_home', 'Age_away', 'home_formation',
       'away_formation', 'elo_home_cat', 'elo_away_cat']
dummied_df = create_dummy_df(short_df, categorize)



    











In [201]:



    


ml_matches_df = dummied_df



    











In [202]:



    


ml_matches_df.head()



    


















    
Out[202]:











  
    

      
      home_player_1_overall_rating_(52.6, 58.1]
      home_player_1_overall_rating_(58.1, 63.7]
      home_player_1_overall_rating_(63.7, 69.3]
      home_player_1_overall_rating_(69.3, 74.9]
      home_player_1_overall_rating_(74.9, 80.4]
      home_player_1_overall_rating_(80.4, 86.0]
      away_player_1_overall_rating_(52.6, 58.1]
      away_player_1_overall_rating_(58.1, 63.7]
      away_player_1_overall_rating_(63.7, 69.3]
      away_player_1_overall_rating_(69.3, 74.9]
      away_player_1_overall_rating_(74.9, 80.4]
      away_player_1_overall_rating_(80.4, 86.0]
      home_defenders_score_(58.4, 61.5]
      home_defenders_score_(61.5, 64.6]
      home_defenders_score_(64.6, 67.7]
      home_defenders_score_(67.7, 70.8]
      home_defenders_score_(70.8, 73.9]
      home_defenders_score_(73.9, 77.0]
      home_midfielders_score_(58.9, 62.4]
      home_midfielders_score_(62.4, 65.9]
      home_midfielders_score_(65.9, 69.4]
      home_midfielders_score_(69.4, 73.0]
      home_midfielders_score_(73.0, 76.5]
      home_midfielders_score_(76.5, 80.0]
      home_forwarders_score_(48.9, 54.7]
      home_forwarders_score_(54.7, 60.6]
      home_forwarders_score_(60.6, 66.4]
      home_forwarders_score_(66.4, 72.3]
      home_forwarders_score_(72.3, 78.1]
      home_forwarders_score_(78.1, 84.0]
      away_defenders_score_(58.0, 61.2]
      away_defenders_score_(61.2, 64.4]
      away_defenders_score_(64.4, 67.6]
      away_defenders_score_(67.6, 70.8]
      away_defenders_score_(70.8, 74.0]
      away_defenders_score_(74.0, 77.2]
      away_midfielders_score_(59.5, 63.1]
      away_midfielders_score_(63.1, 66.6]
      away_midfielders_score_(66.6, 70.1]
      away_midfielders_score_(70.1, 73.7]
      away_midfielders_score_(73.7, 77.2]
      away_midfielders_score_(77.2, 80.8]
      away_forwarders_score_(53.4, 58.9]
      away_forwarders_score_(58.9, 64.3]
      away_forwarders_score_(64.3, 69.7]
      away_forwarders_score_(69.7, 75.1]
      away_forwarders_score_(75.1, 80.6]
      away_forwarders_score_(80.6, 86.0]
      Age_home_(19.0, 21.8]
      Age_home_(21.8, 24.5]
      Age_home_(24.5, 27.2]
      Age_home_(27.2, 29.9]
      Age_home_(29.9, 32.7]
      Age_home_(32.7, 35.4]
      Age_away_(18.6, 21.4]
      Age_away_(21.4, 24.2]
      Age_away_(24.2, 26.9]
      Age_away_(26.9, 29.7]
      Age_away_(29.7, 32.5]
      Age_away_(32.5, 35.3]
      home_formation_(1.0, 2.0]
      home_formation_(2.0, 3.0]
      home_formation_(3.0, 4.0]
      home_formation_(4.0, 5.0]
      home_formation_(5.0, 6.0]
      home_formation_(6.0, 7.0]
      away_formation_(1.0, 2.0]
      away_formation_(2.0, 3.0]
      away_formation_(3.0, 4.0]
      away_formation_(4.0, 5.0]
      away_formation_(5.0, 6.0]
      away_formation_(6.0, 7.0]
      elo_home_cat_(4.0, 7.0]
      elo_home_cat_(7.0, 10.0]
      elo_home_cat_(10.0, 13.0]
      elo_home_cat_(13.0, 16.0]
      elo_home_cat_(16.0, 19.0]
      elo_home_cat_(19.0, 22.0]
      elo_away_cat_(4.0, 7.0]
      elo_away_cat_(7.0, 10.0]
      elo_away_cat_(10.0, 13.0]
      elo_away_cat_(13.0, 16.0]
      elo_away_cat_(16.0, 19.0]
      elo_away_cat_(19.0, 22.0]
      Away_odds
      Draw_odds
      Home_odds
      NoBonus
      VSPointDiff
      entropy
      RESULT
    

  
  
    

      9531
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      0
      0
      0
      1
      1.38750
      4.71750
      8.01750
      0.030483
      -12
      0.837057
      1
    

    

      9517
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      0
      0
      0
      1
      1.22000
      6.34750
      12.28125
      0.019234
      -30
      0.680009
      -1
    

    

      9508
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      0
      0
      1
      1.25875
      5.96375
      10.78125
      0.073981
      -15
      0.720415
      -1
    

    

      9486
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      0
      0
      1
      1.31375
      5.41125
      8.97250
      0.065056
      -33
      0.781728
      -1
    

    

      9467
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      1
      0
      0
      0
      1
      0
      0
      0
      0
      0
      0
      0
      0
      0
      1
      1.24750
      6.13625
      10.78250
      0.025485
      -33
      0.713719
      -1

Last changes - labelling and Scalling





In [174]:



    


#preprocessing libraries
from sklearn.preprocessing import LabelEncoder, StandardScaler, Imputer, OneHotEncoder
from imblearn.over_sampling import SMOTE



    











In [175]:



    


#labelling
results = {'WIN': 1, 'DRAW': 0, 'LOSE': -1, 1:1, 0:0, -1:-1}
ml_matches_df['RESULT']=ml_matches_df['RESULT'].map(results)

le = LabelEncoder()
for col in ml_matches_df.columns.values:
   # Encoding only categorical variables
    if ml_matches_df[col].dtypes=='object':
   # Using whole data to form an exhaustive list of levels
        data=ml_matches_df[col].append(ml_matches_df[col])
        le.fit(data.values)
        ml_matches_df[col]=le.transform(ml_matches_df[col])



    











In [177]:



    


NoScalling = ['entropy','RESULT']
#scale Features
scaled_features = StandardScaler(with_mean=True, with_std=True)\
                                .fit_transform(ml_matches_df.drop(NoScalling, axis=1).values)
scaled_features_df = pd.DataFrame(scaled_features, index=ml_matches_df.drop(NoScalling, axis=1).index, 
                                  columns=ml_matches_df.drop(NoScalling, axis=1).columns)

scaled_features_df[NoScalling] = ml_matches_df[NoScalling]

scaled_features_df.head()



    


















    
Out[177]:











  
    

      
      home_player_1_overall_rating
      away_player_1_overall_rating
      home_defenders_score
      home_midfielders_score
      home_forwarders_score
      away_defenders_score
      away_midfielders_score
      away_forwarders_score
      Age_home
      Age_away
      Away_odds
      Draw_odds
      Home_odds
      elo_home_cat
      elo_away_cat
      home_formation
      away_formation
      NoBonus
      VSPointDiff
      entropy
      RESULT
    

  
  
    

      9531
      -0.045861
      0.224695
      -1.221238
      0.991310
      0.085073
      0.912986
      0.308791
      -1.179658
      -0.029473
      -0.502648
      -0.968220
      1.141530
      3.736614
      0.062927
      3.930793
      0.990026
      0.951837
      -1.900825
      -1.050839
      0.837057
      1
    

    

      9517
      0.543923
      -0.067073
      -0.661090
      1.258152
      0.504282
      1.100666
      0.910630
      -0.130791
      -0.067774
      -0.197757
      -1.021143
      3.011540
      6.637625
      -0.589265
      3.930793
      0.990026
      0.951837
      -1.947141
      -2.623042
      0.680009
      -1
    

    

      9508
      -0.045861
      0.224695
      -0.100943
      0.524335
      0.713886
      1.194506
      1.178114
      -0.130791
      -0.106075
      -0.464537
      -1.008900
      2.571285
      5.617041
      1.041216
      3.604670
      0.990026
      0.951837
      -1.721728
      -1.312873
      0.720415
      -1
    

    

      9486
      -0.045861
      0.370579
      0.925995
      0.124071
      0.504282
      0.819146
      1.445598
      -0.130791
      -0.412482
      -0.273980
      -0.991522
      1.937431
      4.386386
      0.715120
      3.604670
      0.990026
      0.951837
      -1.758476
      -2.885076
      0.781728
      -1
    

    

      9467
      0.543923
      -0.212956
      -0.100943
      0.190782
      -0.229334
      -0.588453
      0.509404
      -0.340564
      -0.029473
      -0.121534
      -1.012454
      2.769185
      5.617891
      -0.589265
      3.604670
      0.170994
      0.951837
      -1.921402
      -2.885076
      0.713719
      -1

Feature pre-selection





In [165]:



    


from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_selection import SelectFromModel
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from sklearn.feature_selection import chi2
from sklearn.feature_selection import SelectKBest

matches_data = ml_matches_df.drop('RESULT', 1)
matches_target = ml_matches_df[['RESULT']]
X_train, X_test, y_train, y_test = train_test_split(matches_data, np.ravel(matches_target), test_size = 0.20, 
                                                    random_state = 101)

#Tree
clf = RandomForestClassifier(n_estimators=500, criterion='gini', max_depth=15, min_samples_split=20, 
                                        min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features='sqrt', 
                                        max_leaf_nodes=None, min_impurity_split=1e-07, bootstrap=True, oob_score=False,
                                        n_jobs=-1, random_state=None, verbose=0, warm_start=False, class_weight=None)
clf = clf.fit(X_train, y_train)
features_tree = pd.DataFrame()
features_tree['feature'] = matches_data.columns
features_tree['importance'] = clf.feature_importances_
features_tree.sort_values(by=['importance'], ascending=True, inplace=True)
features_tree.set_index('feature', inplace=True)

#Chi2
x = X_train.values #returns a numpy array
min_max_scaler = MinMaxScaler()
x_scaled = min_max_scaler.fit_transform(X_train)
x_scaled_df = pd.DataFrame(x_scaled)
features_chi = pd.DataFrame()
features_chi['feature'] = matches_data.columns
features_chi2 = chi2(x_scaled_df, y_train)
features_chi['importance'] = features_chi2[0]
features_chi.sort_values(by=['importance'], ascending=True, inplace=True)
features_chi.set_index('feature', inplace=True)

features_chi.plot(kind='barh', figsize=(20, 20))
plt.show()

features_tree.plot(kind='barh', figsize=(20, 20))
plt.show()

MODEL LEARNING

IMPORTS AND FUNCTIONS

back





In [36]:



    


# machine learning models
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import LogisticRegression 
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.multiclass import OneVsRestClassifier

import lightgbm as lgb



    











In [28]:



    


#Split data for train and test
def split_data(data, targ):
    #set target for training
    target = data[targ]

    # Import the train_test_split method
    from sklearn.model_selection import train_test_split
    # Split data into train (3/4th of data) and test (1/4th of data)
    return train_test_split(data.drop('RESULT', axis=1), target, train_size = 0.75, random_state=0);



    











In [29]:



    


def regr_equation(logreg, train, target):
    if type(model) is LogisticRegression:
        coef = logreg.coef_[0]
        intercept = "{:.2f}".format(logreg.intercept_[0])
    else:
        coef = logreg.coef_
        intercept = "{:.2f}".format(logreg.intercept_)
    try:    
        output = target.name + ' = ' + str(intercept) + ' + '
    except:
        output = 'TARGET' + ' = ' + str(intercept) + ' + '
    coeff_df = pd.DataFrame(train.columns.delete(0))
    coeff_df.columns = ['Feature']
    coeff_df["Correlation"] = pd.Series(logreg.coef_[0])
    features = coeff_df['Feature'].tolist()
    coefficients = coeff_df['Correlation'].tolist()
    
    for coeff, feature in zip(coefficients, features):
        coeff_str = "{:.2f}".format(coeff)
        output += coeff_str + "*" + str(feature) + " + "
    return output[:-3]



    











In [30]:



    


def plot_confusion_matrix(cm, classes,
                          normalize=False,
                          title='Confusion matrix',
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    Normalization can be applied by setting `normalize=True`.
    """
    import itertools
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=45)
    plt.yticks(tick_marks, classes)

    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
        print("Normalized confusion matrix")
    else:
        print('Confusion matrix, without normalization')

    print(cm)

    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, cm[i, j],
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')
    plt.show()



    











In [31]:



    


def conf_matrix_str (conf, normalize=True):
    if normalize:
            conf = conf.astype('float') / conf.sum(axis=1)[:, np.newaxis]

    conf_matrix = 'Pred \tLose\tDraw\tWin\n'+\
                  'True \n'+\
                  'Lose \t{:.2f}\t{:.2f}\t{:.2f}\n'.format(conf[0][0], conf[0][1], conf[0][2])+\
                  'Draw \t{:.2f}\t{:.2f}\t{:.2f}\n'.format(conf[1][0], conf[1][1], conf[1][2])+\
                  'Win \t{:.2f}\t{:.2f}\t{:.2f}'.format(conf[2][0], conf[2][1], conf[2][2])
    return conf_matrix



    











In [53]:



    


#gridSearch for the best params
def exhaustive_grid_search (data, methods, param_Grids):
    from sklearn.model_selection import GridSearchCV
    models = {}
    for method, prefix in methods.items():
        train, test, target_train, target_test = data
        model = method
        param_grid = param_Grids[prefix]
        grid = GridSearchCV(model, param_grid, refit=True, verbose = 3, n_jobs=-1)
        grid.fit(train, target_train)
        print(grid.best_estimator_)
        models[prefix] = grid.best_estimator_
    return dict((value, key) for key, value in models.items())



    











In [32]:



    


def test_model (model, data, target, submission_name = None, test=None, cross_valid=True):
   
    if test is None:
        from sklearn.metrics import accuracy_score, confusion_matrix, r2_score
        train, test, target_train, target_test = data
        model.fit(train, target_train)
        #Calc parameters
        if type(model) is LogisticRegression:
            function_str = regr_equation(model, train, target_train)
        elif type(model) is LinearRegression:
            function_str = regr_equation(model, train, target_train)
        else :
            function_str = "NA"    

        if type(model) is not LinearRegression:
            trainset_acc = round(accuracy_score(target_train, model.predict(train)) * 100, 2)
            testset_acc = round(accuracy_score(target_test, model.predict(test)) * 100, 2)
            confusion_matrix = confusion_matrix(target_test, model.predict(test))
            conf_matrix = conf_matrix_str(confusion_matrix)
                    
        else:
            trainset_acc = 'NA'
            testset_acc = 'NA'
            conf_matrix = "NA"

        r2_score = r2_score(target_train, model.predict(train))
        kaggle = "not_tested"
        
          #Perform k-fold cross-validation with 5 folds
        if cross_valid == True:
            from sklearn.cross_validation import KFold   #For K-fold cross validation
            X=pd.concat([train,test])
            Y=pd.concat([target_train, target_test])
            data_df = pd.concat([X,Y], axis=1)
            kf = KFold(data_df.shape[0], n_folds=5)
            error = []
            predictors = list(data_df.columns.values)
            del predictors[-1]
            for train, test in kf:
                # Filter training data
                train_predictors = (data_df[predictors].iloc[train,:])

                # The target we're using to train the algorithm.
                train_target = data_df[target].iloc[train]

                # Training the algorithm using the predictors and target.
                model.fit(train_predictors, train_target)

                #Record error from each cross-validation run
                error.append(model.score(data_df[predictors].iloc[test,:], data_df[target].iloc[test]))
        else:
            error=[0,0]
        #Fit the model again so that it can be refered
        #prints
        print("-"*40)
        print('Submission name:', submission_name )
        print('Regression function:\n', function_str)
        print('Accuracy on train set:', trainset_acc,"%")
        print('Accuracy on test set:', testset_acc,"%")
        print ("Cross-Validation Score : %s" % "{0:.3%}".format(np.mean(error)))
        print("R2 score:", r2_score)
        print("Confusion matrix:\n", conf_matrix)
        classes=['Lose','Draw','Win']
        plot_confusion_matrix(confusion_matrix, classes=classes,
                              normalize=True, title = 'Confusion matrix '+submission_name, cmap=plt.cm.Blues)
        return [submission_name, function_str, str(trainset_acc), str(testset_acc), r2_score, conf_matrix, np.mean(error)]

SETUP

back





In [71]:



    


#train, test, target_train, target_test = split_data(scaled_features_df, 'RESULT')
train, test, target_train, target_test = split_data(scaled_features_df, 'RESULT')
#Try to oversample?
#from imblearn.over_sampling import SMOTE
#oversampler=SMOTE(random_state=0)
#smote_train, smote_target = oversampler.fit_sample(train,target_train)
#data = (smote_train, test, smote_target, target_test)

data = (train, test, target_train, target_test)



    











In [30]:



    


methodMLP = MLPClassifier()
methodLogReg = LogisticRegression()
methodLinReg = LinearRegression()
methodSVC = SVC()
methodlinSVC = LinearSVC()
methodKN = KNeighborsClassifier()
methodGNB = GaussianNB()
methodPercp = Perceptron()
methodSGD = SGDClassifier()
methodTree = DecisionTreeClassifier()
methodRndForest = RandomForestClassifier()
methodXTree = ExtraTreesClassifier()
methodGBRT = GradientBoostingClassifier()
methods = {
          #methodRndForest: 'RandomForest',
          #methodLogReg : 'LogReg',
          #methodXTree : 'xTrees',
          #methodSVC : 'SVM',
          #methodKN  : 'KNC'
          methodGBRT : 'GBRT'
         }

param_Grids = {
   # 'RandomForest': {'n_estimators': [10, 500, 1000], 'criterion': ['gini'], 
   #                  'max_depth': [5, 10, 15, 20], 'min_samples_split': [2, 10, 20, 50], 
   #                  'min_samples_leaf': [1, 8], 'max_features':['sqrt', 'log2'], 
   #                 },
   # 'xTrees': {'n_estimators': [10, 500, 1000], 'criterion': ['gini'], 
   #                  'max_depth': [5, 10, 15, 20], 'min_samples_split': [2, 10, 20, 50], 
   #            'min_samples_leaf': [1, 8], 'max_features':['sqrt', 'log2'], 
   #           },
   # 'LogReg': {'C': [1, 10, 100, 250, 1000], 'solver' : ['newton-cg', 'liblinear']}
   # 'SVM': {'C': [0.1, 1, 10, 100, 1000], 'gamma': [1,0.1,0.01, 0.001, 0.0001], 
   #         'kernel': ['linear', 'rbf', 'poly'], 'degree': [2, 3]},
   # 'KNC': {'metrics': ['minkowski', 'euclidean', 'manhattan'], 'n_neighbors': [5,10,15], 
   #         'weights' : ['uniform','distance']}
    'GBRT': {'learning_rate': [0.1, 0.05, 0.02, 0.01],
             'max_depth': [3, 10, 15],
             'min_samples_leaf': [3, 5, 9, 17],
             'max_features': [1.0, 0.3, 0.1, 'sqrt'],
             'subsample': [1.0, 0.99, 0.9],
             'n_estimators': [10, 100, 1000]
            }
    }



    











In [ ]:



    


estimators = exhaustive_grid_search(data, methods, param_Grids)



    


















    






Fitting 3 folds for each of 1728 candidates, totalling 5184 fits










    






[Parallel(n_jobs=-1)]: Done  24 tasks      | elapsed:   58.6s
[Parallel(n_jobs=-1)]: Done 120 tasks      | elapsed:  4.3min
[Parallel(n_jobs=-1)]: Done 280 tasks      | elapsed:  7.2min
[Parallel(n_jobs=-1)]: Done 504 tasks      | elapsed: 17.0min
[Parallel(n_jobs=-1)]: Done 792 tasks      | elapsed: 34.8min
[Parallel(n_jobs=-1)]: Done 1144 tasks      | elapsed: 61.4min
[Parallel(n_jobs=-1)]: Done 1560 tasks      | elapsed: 76.0min
[Parallel(n_jobs=-1)]: Done 2040 tasks      | elapsed: 114.8min
[Parallel(n_jobs=-1)]: Done 2584 tasks      | elapsed: 192.3min

















In [166]:



    


train, test, target_train, target_test = split_data(scaled_features_df, 'RESULT')
#Try to oversample?
#from imblearn.over_sampling import SMOTE
#oversampler=SMOTE(random_state=0)
#smote_train, smote_target = oversampler.fit_sample(train,target_train)
#data = (smote_train, test, smote_target, target_test)

data = (train, test, target_train, target_test)



    











In [167]:



    


#Setup
suffix = '_shortECH_ELO{NoBonus}_SCALED{~entropy}_PROBS'
modelMLP = MLPClassifier(hidden_layer_sizes=(104, 104, 104), activation='logistic', solver='sgd', alpha=0.0001, 
                         batch_size='auto', learning_rate='adaptive', learning_rate_init=1, power_t=0.5, 
                         max_iter=2000, shuffle=True, random_state=None, tol=0.0001, verbose=False, warm_start=False, 
                         momentum=0.9, nesterovs_momentum=True, early_stopping=False, validation_fraction=0.1, 
                         beta_1=0.9, beta_2=0.999, epsilon=1e-08)

modelLogReg = LogisticRegression(n_jobs = -1, class_weight=None)
modelLinReg = LinearRegression()
modelSVC = SVC()
modellinSVC = LinearSVC()
modelKN = KNeighborsClassifier(n_neighbors = 3)
modelGNB = GaussianNB()
modelPercp = Perceptron()
modelSGD = SGDClassifier()
modelTree = DecisionTreeClassifier(criterion='gini', splitter='random', max_depth=None, 
                                   min_samples_split=16, min_samples_leaf=8, min_weight_fraction_leaf=0.0, 
                                   max_features='sqrt', random_state=None, max_leaf_nodes=None, 
                                   min_impurity_split=1e-07, class_weight=None, presort=False)
modelRndForest = RandomForestClassifier(n_estimators=800, criterion='gini', max_depth=15, min_samples_split=20, 
                                        min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features='sqrt', 
                                        max_leaf_nodes=None, min_impurity_split=1e-07, bootstrap=True, oob_score=False,
                                        n_jobs=-1, random_state=None, verbose=0, warm_start=False, class_weight=None)
modelXTree = ExtraTreesClassifier(n_estimators=800, criterion='gini', max_depth=None, min_samples_split=16, 
                                  min_samples_leaf=5, min_weight_fraction_leaf=0.0, max_features='sqrt', 
                                  max_leaf_nodes=None, min_impurity_split=1e-07, bootstrap=False, oob_score=False, 
                                  n_jobs=-1, random_state=None, verbose=0, warm_start=False, class_weight=None)

modelGBRT = GradientBoostingClassifier()

lgbmmodel = lgb.LGBMClassifier(boosting_type='gbdt', colsample_bytree=1, learning_rate=0.1,
                             max_bin=200, max_depth=8, min_child_samples=10, min_child_weight=5,
                             min_split_gain=0, n_estimators=10, nthread=-1, num_leaves=20,
                             objective='multiclass', reg_alpha=0, reg_lambda=0.095, seed=77,
                             silent=False, subsample=0.8,
                             subsample_freq=1)
 

models = {
          modelRndForest: "RandomForest",
          modelLogReg : "logreg",
          modelXTree : 'xTrees',
          modelGBRT: "GradientBoosting",
          lgbmmodel: "LightGBM"
         }



    











In [168]:



    


outputs = []
for model, prefix in models.items():
    name=prefix+suffix
    outputs.append(test_model(model, data, target='RESULT', submission_name=name))
outputs.sort(key=lambda x: x[0])



    


















    






----------------------------------------
Submission name: logreg_shortECH_ELO{NoBonus}_SCALED{~entropy}_PROBS
Regression function:
 RESULT = -0.64 + 0.03*away_player_1_overall_rating + -0.03*home_defenders_score + -0.03*home_midfielders_score + -0.01*home_forwarders_score + -0.01*away_defenders_score + 0.00*away_midfielders_score + -0.02*away_forwarders_score + 0.01*Age_home + 0.04*Age_away + -0.02*elo_home_cat + -0.19*elo_away_cat + 0.07*home_formation + 0.04*away_formation + 0.02*NoBonus + 0.24*VSPointDiff + -0.80*entropy + -0.08*home_probs + -1.47*draw_probs + -0.26*away_probs
Accuracy on train set: 56.06 %
Accuracy on test set: 55.73 %
Cross-Validation Score : 56.022%
R2 score: -0.381117330463
Confusion matrix:
 Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.42
Draw 	0.31	0.00	0.68
Win 	0.15	0.00	0.85
Normalized confusion matrix
[[  5.83589744e-01   0.00000000e+00   4.16410256e-01]
 [  3.10690423e-01   4.45434298e-03   6.84855234e-01]
 [  1.46356784e-01   6.28140704e-04   8.53015075e-01]]










    

















    






----------------------------------------
Submission name: xTrees_shortECH_ELO{NoBonus}_SCALED{~entropy}_PROBS
Regression function:
 NA
Accuracy on train set: 74.03 %
Accuracy on test set: 55.73 %
Cross-Validation Score : 55.943%
R2 score: 0.198130626601
Confusion matrix:
 Pred 	Lose	Draw	Win
True 
Lose 	0.59	0.01	0.40
Draw 	0.32	0.01	0.67
Win 	0.15	0.01	0.85
Normalized confusion matrix
[[ 0.58564103  0.01025641  0.40410256]
 [ 0.31625835  0.01002227  0.67371938]
 [ 0.14572864  0.00565327  0.84861809]]










    

















    






----------------------------------------
Submission name: LightGBM_shortECH_ELO{NoBonus}_SCALED{~entropy}_PROBS
Regression function:
 NA
Accuracy on train set: 58.67 %
Accuracy on test set: 56.74 %
Cross-Validation Score : 56.397%
R2 score: -0.261431302021
Confusion matrix:
 Pred 	Lose	Draw	Win
True 
Lose 	0.67	0.02	0.31
Draw 	0.40	0.04	0.56
Win 	0.18	0.02	0.80
Normalized confusion matrix
[[ 0.66974359  0.02461538  0.30564103]
 [ 0.40089087  0.03786192  0.56124722]
 [ 0.18090452  0.01570352  0.80339196]]










    

















    






----------------------------------------
Submission name: GradientBoosting_shortECH_ELO{NoBonus}_SCALED{~entropy}_PROBS
Regression function:
 NA
Accuracy on train set: 59.82 %
Accuracy on test set: 56.39 %
Cross-Validation Score : 56.253%
R2 score: -0.212124981049
Confusion matrix:
 Pred 	Lose	Draw	Win
True 
Lose 	0.62	0.07	0.32
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.80
Normalized confusion matrix
[[ 0.61846154  0.06564103  0.31589744]
 [ 0.35077951  0.09242762  0.55679287]
 [ 0.16771357  0.03580402  0.79648241]]










    

















    






----------------------------------------
Submission name: RandomForest_shortECH_ELO{NoBonus}_SCALED{~entropy}_PROBS
Regression function:
 NA
Accuracy on train set: 76.04 %
Accuracy on test set: 56.51 %
Cross-Validation Score : 56.145%
R2 score: 0.228389848239
Confusion matrix:
 Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.05	0.33
Draw 	0.37	0.06	0.57
Win 	0.16	0.03	0.81
Normalized confusion matrix
[[ 0.62974359  0.04512821  0.32512821]
 [ 0.36636971  0.06347439  0.5701559 ]
 [ 0.16143216  0.03015075  0.80841709]]










    
























In [169]:



    


for out in outputs:
    super_table.append(out)



    











In [157]:



    


new_tabl = [[row[0], row[-1], row[-2]] for row in super_table]



    











In [158]:



    


make_table(new_tabl[::-1])
apply_theme('basic')



    


















    
Out[158]:







xTrees_shortECH_ELO{NoBonus}_SCALED{~entropy}0.560943351127Pred 	Lose	Draw	Win
True 
Lose 	0.59	0.01	0.40
Draw 	0.33	0.01	0.66
Win 	0.15	0.01	0.84
logreg_shortECH_ELO{NoBonus}_SCALED{~entropy}0.559500037234Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.41
Draw 	0.30	0.00	0.70
Win 	0.15	0.00	0.85
RandomForest_shortECH_ELO{NoBonus}_SCALED{~entropy}0.562675838136Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.04	0.32
Draw 	0.38	0.06	0.57
Win 	0.17	0.03	0.81
LightGBM_shortECH_ELO{NoBonus}_SCALED{~entropy}0.565562648186Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.04	0.31
Draw 	0.40	0.04	0.56
Win 	0.18	0.02	0.80
GradientBoosting_shortECH_ELO{NoBonus}_SCALED{~entropy}0.563325266898Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.79
xTrees_shortECH_elodiffcat_ELO{NoBonus}_NotSCALED0.557407294578Pred 	Lose	Draw	Win
True 
Lose 	0.59	0.02	0.39
Draw 	0.33	0.01	0.66
Win 	0.15	0.01	0.84
logreg_shortECH_elodiffcat_ELO{NoBonus}_NotSCALED0.555963772384Pred 	Lose	Draw	Win
True 
Lose 	0.57	0.00	0.43
Draw 	0.31	0.00	0.69
Win 	0.14	0.00	0.86
RandomForest_shortECH_elodiffcat_ELO{NoBonus}_NotSCALED0.560005686603Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.05	0.32
Draw 	0.38	0.06	0.56
Win 	0.17	0.03	0.80
LightGBM_shortECH_elodiffcat_ELO{NoBonus}_NotSCALED0.560438665148Pred 	Lose	Draw	Win
True 
Lose 	0.67	0.04	0.29
Draw 	0.43	0.04	0.53
Win 	0.20	0.02	0.78
GradientBoosting_shortECH_elodiffcat_ELO{NoBonus}_NotSCALED0.559283899468Pred 	Lose	Draw	Win
True 
Lose 	0.62	0.07	0.31
Draw 	0.36	0.09	0.56
Win 	0.17	0.04	0.79
xTrees_shortECH_elodiffcat_ELO{NoBonus}_SCALED0.556180378826Pred 	Lose	Draw	Win
True 
Lose 	0.59	0.01	0.40
Draw 	0.33	0.02	0.66
Win 	0.15	0.01	0.84
logreg_shortECH_elodiffcat_ELO{NoBonus}_SCALED0.55574719198Pred 	Lose	Draw	Win
True 
Lose 	0.57	0.00	0.43
Draw 	0.30	0.00	0.69
Win 	0.14	0.00	0.86
RandomForest_shortECH_elodiffcat_ELO{NoBonus}_SCALED0.560510685033Pred 	Lose	Draw	Win
True 
Lose 	0.62	0.06	0.32
Draw 	0.37	0.07	0.56
Win 	0.17	0.03	0.80
LightGBM_shortECH_elodiffcat_ELO{NoBonus}_SCALED0.560799441546Pred 	Lose	Draw	Win
True 
Lose 	0.67	0.04	0.29
Draw 	0.42	0.04	0.54
Win 	0.20	0.02	0.78
GradientBoosting_shortECH_elodiffcat_ELO{NoBonus}_SCALED0.559283925506Pred 	Lose	Draw	Win
True 
Lose 	0.62	0.07	0.31
Draw 	0.36	0.09	0.56
Win 	0.17	0.04	0.79
xTrees_shortECH_elodiff_ELO{NoBonus}_SCALED0.556396907155Pred 	Lose	Draw	Win
True 
Lose 	0.59	0.01	0.40
Draw 	0.32	0.01	0.66
Win 	0.15	0.01	0.84
logreg_shortECH_elodiff_ELO{NoBonus}_SCALED0.55574719198Pred 	Lose	Draw	Win
True 
Lose 	0.57	0.00	0.43
Draw 	0.30	0.00	0.69
Win 	0.14	0.00	0.86
RandomForest_shortECH_elodiff_ELO{NoBonus}_SCALED0.558634314481Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.05	0.32
Draw 	0.38	0.06	0.56
Win 	0.17	0.03	0.80
LightGBM_shortECH_elodiff_ELO{NoBonus}_SCALED0.560799441546Pred 	Lose	Draw	Win
True 
Lose 	0.67	0.04	0.29
Draw 	0.42	0.04	0.54
Win 	0.20	0.02	0.78
GradientBoosting_shortECH_elodiff_ELO{NoBonus}_SCALED0.559283925506Pred 	Lose	Draw	Win
True 
Lose 	0.62	0.07	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.79
xTrees_shortECH_elodiff_ELO{NoBonus}_NOTSCALED0.555964032759Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.01	0.40
Draw 	0.32	0.02	0.66
Win 	0.16	0.01	0.84
logreg_shortECH_elodiff_ELO{NoBonus}_NOTSCALED0.555891570237Pred 	Lose	Draw	Win
True 
Lose 	0.57	0.00	0.43
Draw 	0.30	0.00	0.69
Win 	0.14	0.00	0.85
RandomForest_shortECH_elodiff_ELO{NoBonus}_NOTSCALED0.558129237938Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.05	0.32
Draw 	0.37	0.06	0.57
Win 	0.17	0.03	0.80
LightGBM_shortECH_elodiff_ELO{NoBonus}_NOTSCALED0.561881953004Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.04	0.30
Draw 	0.41	0.05	0.54
Win 	0.20	0.02	0.78
GradientBoosting_shortECH_elodiff_ELO{NoBonus}_NOTSCALED0.559500453835Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.07	0.31
Draw 	0.36	0.09	0.56
Win 	0.17	0.04	0.79
xTrees_shortECH_ELO{NoBonus}_SCALED_noFormation0.561159619081Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.01	0.39
Draw 	0.34	0.02	0.64
Win 	0.15	0.01	0.84
logreg_shortECH_ELO{NoBonus}_SCALED_noFormation0.559932833516Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.42
Draw 	0.30	0.00	0.70
Win 	0.14	0.00	0.86
RandomForest_shortECH_ELO{NoBonus}_SCALED_noFormation0.562098403221Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.05	0.32
Draw 	0.37	0.06	0.57
Win 	0.17	0.03	0.80
LightGBM_shortECH_ELO{NoBonus}_SCALED_noFormation0.563902467475Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.03	0.31
Draw 	0.40	0.04	0.56
Win 	0.18	0.02	0.80
GradientBoosting_shortECH_ELO{NoBonus}_SCALED_noFormation0.563036484346Pred 	Lose	Draw	Win
True 
Lose 	0.62	0.07	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.80
xTrees_shortECH_ELO{200Bonus}_NOTSCALED0.561736975883Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.01	0.39
Draw 	0.33	0.02	0.65
Win 	0.15	0.01	0.84
logreg_shortECH_ELO{200Bonus}_NOTSCALED0.559572239381Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.41
Draw 	0.30	0.00	0.70
Win 	0.14	0.00	0.85
RandomForest_shortECH_ELO{200Bonus}_NOTSCALED0.5610159178Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.04	0.32
Draw 	0.37	0.06	0.57
Win 	0.16	0.03	0.81
LightGBM_shortECH_ELO{200Bonus}_NOTSCALED0.564624410835Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.04	0.30
Draw 	0.39	0.05	0.56
Win 	0.18	0.02	0.80
GradientBoosting_shortECH_ELO{200Bonus}_NOTSCALED0.563469567042Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.79
xTrees_shortECH_ELO{100Bonus}_NOTSCALED0.560510528807Pred 	Lose	Draw	Win
True 
Lose 	0.59	0.01	0.40
Draw 	0.33	0.02	0.66
Win 	0.15	0.00	0.85
logreg_shortECH_ELO{100Bonus}_NOTSCALED0.559067032651Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.41
Draw 	0.30	0.00	0.70
Win 	0.14	0.00	0.85
RandomForest_shortECH_ELO{100Bonus}_NOTSCALED0.563108660456Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.05	0.32
Draw 	0.38	0.06	0.57
Win 	0.16	0.03	0.81
LightGBM_shortECH_ELO{100Bonus}_NOTSCALED0.565201663487Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.04	0.30
Draw 	0.39	0.05	0.56
Win 	0.18	0.02	0.80
GradientBoosting_shortECH_ELO{100Bonus}_NOTSCALED0.563613893224Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.79
xTrees_shortECH_ELO{noBonus}_NOTSCALED0.560366124513Pred 	Lose	Draw	Win
True 
Lose 	0.59	0.01	0.39
Draw 	0.33	0.02	0.66
Win 	0.15	0.01	0.84
logreg_shortECH_ELO{noBonus}_NOTSCALED0.559211332795Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.41
Draw 	0.30	0.00	0.70
Win 	0.15	0.00	0.85
RandomForest_shortECH_ELO{noBonus}_NOTSCALED0.56159309234Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.04	0.32
Draw 	0.37	0.06	0.57
Win 	0.17	0.03	0.80
LightGBM_shortECH_ELO{noBonus}_NOTSCALED0.564985239309Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.04	0.30
Draw 	0.40	0.04	0.56
Win 	0.18	0.02	0.80
GradientBoosting_shortECH_ELO{noBonus}_NOTSCALED0.563613893224Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.79
xTrees_DUMMIES+ELO_NOTSCALED0.5404478876510634Pred 	Lose	Draw	Win
True 
Lose 	0.49	0.03	0.48
Draw 	0.28	0.03	0.69
Win 	0.13	0.02	0.85
logreg_DUMMIES+ELO_NOTSCALED0.5553138489082192Pred 	Lose	Draw	Win
True 
Lose 	0.56	0.02	0.42
Draw 	0.31	0.02	0.67
Win 	0.14	0.01	0.85
RandomForest_DUMMIES+ELO_NOTSCALED0.5595721352307422Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.04	0.37
Draw 	0.35	0.04	0.61
Win 	0.16	0.02	0.82
LightGBM_DUMMIES+ELO_NOTSCALED0.5644077783558116Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.04	0.31
Draw 	0.38	0.06	0.56
Win 	0.18	0.02	0.80
GradientBoosting_DUMMIES+ELO_NOTSCALED0.5586341061801183Pred 	Lose	Draw	Win
True 
Lose 	0.62	0.06	0.31
Draw 	0.35	0.08	0.56
Win 	0.17	0.04	0.79
LightGBM_shortECH_elo{No,100,200}_SCALED_ResCorr0.5657067921052042Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.04	0.30
Draw 	0.40	0.04	0.56
Win 	0.18	0.02	0.80
WvL_xTrees_balanced_shortECH_elo{No,100,200}_SCALED_ResCorr0.7394205443371378[[&nbsp0.7544757  &nbsp0.2455243 ]
 [&nbsp0.26791277 &nbsp0.73208723]]
WvL_logreg_balanced_shortECH_elo{No,100,200}_SCALED_ResCorr0.7474978050921861[[&nbsp0.74936061 &nbsp0.25063939]
 [&nbsp0.26323988 &nbsp0.73676012]]
WvL_RandomForest_balanced_shortECH_elo{No,100,200}_SCALED_ResCorr0.7473222124670764[[&nbsp0.76214834 &nbsp0.23785166]
 [&nbsp0.26323988 &nbsp0.73676012]]
WvD_xTrees_balanced_shortECH_elo{No,100,200}_SCALED_ResCorr0.6212651786467942[[&nbsp0.66151685 &nbsp0.33848315]
 [&nbsp0.40566038 &nbsp0.59433962]]
WvD_logreg_balanced_shortECH_elo{No,100,200}_SCALED_ResCorr0.6342542588065866[[&nbsp0.66853933 &nbsp0.33146067]
 [&nbsp0.37578616 &nbsp0.62421384]]
WvD_RandomForest_balanced_shortECH_elo{No,100,200}_SCALED_ResCorr0.6296165566758483[[&nbsp0.66994382 &nbsp0.33005618]
 [&nbsp0.38836478 &nbsp0.61163522]]
DvL_xTrees_balanced_shortECH_elo{No,100,200}_SCALED_ResCorr0.6206839032527106[[&nbsp0.62081784 &nbsp0.37918216]
 [&nbsp0.38872832 &nbsp0.61127168]]
DvL_logreg_balanced_shortECH_elo{No,100,200}_SCALED_ResCorr0.62418682235196[[&nbsp0.63320942 &nbsp0.36679058]
 [&nbsp0.35693642 &nbsp0.64306358]]
DvL_RandomForest_balanced_shortECH_elo{No,100,200}_SCALED_ResCorr0.6160133444537114[[&nbsp0.65055762 &nbsp0.34944238]
 [&nbsp0.40751445 &nbsp0.59248555]]
WvL_xTrees_shortECH_elo{No,100,200}_SCALED_ResCorr0.7390693590869184[[&nbsp0.80179028 &nbsp0.19820972]
 [&nbsp0.34267913 &nbsp0.65732087]]
WvL_logreg_shortECH_elo{No,100,200}_SCALED_ResCorr0.7476733977172958[[&nbsp0.80179028 &nbsp0.19820972]
 [&nbsp0.3364486  &nbsp0.6635514 ]]
WvL_RandomForest_shortECH_elo{No,100,200}_SCALED_ResCorr0.7438103599648815[[&nbsp0.78644501 &nbsp0.21355499]
 [&nbsp0.30373832 &nbsp0.69626168]]
WvL_GradientBoosting_shortECH_elo{No,100,200}_SCALED_ResCorr0.7508340649692713[[&nbsp0.79411765 &nbsp0.20588235]
 [&nbsp0.28816199 &nbsp0.71183801]]
WvD_xTrees_shortECH_elo{No,100,200}_SCALED_ResCorr0.6182960294778839[[&nbsp0.71769663 &nbsp0.28230337]
 [&nbsp0.47641509 &nbsp0.52358491]]
WvD_logreg_shortECH_elo{No,100,200}_SCALED_ResCorr0.6299883032473561[[&nbsp0.74578652 &nbsp0.25421348]
 [&nbsp0.4418239  &nbsp0.5581761 ]]
WvD_RandomForest_shortECH_elo{No,100,200}_SCALED_ResCorr0.6259032253063291[[&nbsp0.69382022 &nbsp0.30617978]
 [&nbsp0.42138365 &nbsp0.57861635]]
WvD_GradientBoosting_shortECH_elo{No,100,200}_SCALED_ResCorr0.6303591884968724[[&nbsp0.66853933 &nbsp0.33146067]
 [&nbsp0.37893082 &nbsp0.62106918]]
DvL_xTrees_shortECH_elo{No,100,200}_SCALED_ResCorr0.6201834862385323[[&nbsp0.65923172 &nbsp0.34076828]
 [&nbsp0.43063584 &nbsp0.56936416]]
DvL_logreg_shortECH_elo{No,100,200}_SCALED_ResCorr0.6221851542952461[[&nbsp0.6802974  &nbsp0.3197026 ]
 [&nbsp0.42919075 &nbsp0.57080925]]
DvL_RandomForest_shortECH_elo{No,100,200}_SCALED_ResCorr0.6128440366972476[[&nbsp0.66542751 &nbsp0.33457249]
 [&nbsp0.4349711  &nbsp0.5650289 ]]
DvL_GradientBoosting_shortECH_elo{No,100,200}_SCALED_ResCorr0.6191826522101752[[&nbsp0.68153656 &nbsp0.31846344]
 [&nbsp0.45375723 &nbsp0.54624277]]
GradientBoosting_1000Est_0.01LR_shortECH_elo{No,100,200}_SCALED_ResCorr0.5621705272553341Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.07	0.31
Draw 	0.35	0.10	0.56
Win 	0.17	0.04	0.79
GradientBoosting_10Est_0.9MF_shortECH_elo{No,100,200}_SCALED_ResCorr0.5625314078038726Pred 	Lose	Draw	Win
True 
Lose 	0.65	0.00	0.34
Draw 	0.39	0.00	0.61
Win 	0.18	0.00	0.82
GradientBoosting_10Est_0.9MF_shortECH_elo{No,100,200}_SCALED_ResCorr0.5635419774900107Pred 	Lose	Draw	Win
True 
Lose 	0.65	0.00	0.35
Draw 	0.38	0.00	0.62
Win 	0.18	0.00	0.82
GradientBoosting_10Est_shortECH_elo{No,100,200}_SCALED_ResCorr0.563036536421596Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.00	0.36
Draw 	0.37	0.00	0.63
Win 	0.18	0.00	0.82
GradientBoosting_superbasic_shortECH_elo{No,100,200}_SCALED_ResCorr0.5636860693338499Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.79
xTrees_shortECH_elo{100}_SCALED_ResCorr_SMOTE0.0Pred 	Lose	Draw	Win
True 
Lose 	0.37	0.42	0.21
Draw 	0.20	0.43	0.38
Win 	0.08	0.25	0.67
logreg_shortECH_elo{100}_SCALED_ResCorr_SMOTE0.0Pred 	Lose	Draw	Win
True 
Lose 	0.28	0.55	0.17
Draw 	0.12	0.54	0.34
Win 	0.04	0.33	0.63
RandomForest_shortECH_elo{100}_SCALED_ResCorr_SMOTE0.0Pred 	Lose	Draw	Win
True 
Lose 	0.43	0.33	0.24
Draw 	0.23	0.35	0.42
Win 	0.09	0.20	0.71
xTrees_shortECH_elo{100}_SCALED_ResCorr0.5598613343831677Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.01	0.39
Draw 	0.36	0.02	0.63
Win 	0.17	0.01	0.83
logreg_shortECH_elo{100}_SCALED_ResCorr0.5605106329574031Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.00	0.40
Draw 	0.34	0.00	0.65
Win 	0.15	0.00	0.85
RandomForest_shortECH_elo{100}_SCALED_ResCorr0.5624596222575291Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.04	0.33
Draw 	0.38	0.07	0.55
Win 	0.18	0.03	0.80
xTrees_manbalanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorr0.5566862104574122Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.07	0.33
Draw 	0.37	0.08	0.55
Win 	0.17	0.05	0.78
logreg_manbalanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorr0.5618097248194686Pred 	Lose	Draw	Win
True 
Lose 	0.61	0.01	0.37
Draw 	0.36	0.03	0.61
Win 	0.16	0.01	0.82
RandomForest_manbalanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorr0.5593567265165966Pred 	Lose	Draw	Win
True 
Lose 	0.61	0.11	0.28
Draw 	0.38	0.12	0.50
Win 	0.16	0.07	0.77
xTrees_balanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorr0.5433366244806158Pred 	Lose	Draw	Win
True 
Lose 	0.62	0.19	0.19
Draw 	0.40	0.24	0.36
Win 	0.19	0.15	0.66
logreg_balanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorr0.558851285448182Pred 	Lose	Draw	Win
True 
Lose 	0.65	0.08	0.26
Draw 	0.41	0.13	0.46
Win 	0.19	0.06	0.75
RandomForest_balanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorr0.5450679658366413Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.16	0.21
Draw 	0.39	0.21	0.40
Win 	0.18	0.13	0.69
xTrees_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorr0.5592120618464899Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.02	0.38
Draw 	0.37	0.02	0.61
Win 	0.17	0.01	0.82
logreg_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorr0.5595005840224173Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.00	0.39
Draw 	0.34	0.00	0.65
Win 	0.16	0.00	0.84
RandomForest_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorr0.561160504357906Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.38	0.07	0.55
Win 	0.17	0.03	0.79
xTrees_shortECH_eloCat{nobonus,100,200}_NotSCALED_ResCorr0.5546651231602513Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.01	0.41
Draw 	0.32	0.02	0.67
Win 	0.14	0.01	0.85
logreg_shortECH_eloCat{nobonus,100,200}_NotSCALED_ResCorr0.5589949346535417Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.01	0.41
Draw 	0.30	0.01	0.69
Win 	0.14	0.00	0.85
RandomForest_shortECH_eloCat{nobonus,100,200}_NotSCALED_ResCorr0.5611601398320994Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.05	0.32
Draw 	0.37	0.05	0.58
Win 	0.17	0.03	0.80
xTrees_shortECH_eloCat{nobonus,100,200}_SCALED_ResCorr0.554809527454782Pred 	Lose	Draw	Win
True 
Lose 	0.57	0.01	0.42
Draw 	0.31	0.01	0.68
Win 	0.15	0.01	0.85
logreg_shortECH_eloCat{nobonus,100,200}_SCALED_ResCorr0.5589228106189492Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.01	0.42
Draw 	0.30	0.01	0.69
Win 	0.14	0.00	0.85
RandomForest_shortECH_eloCat{nobonus,100,200}_SCALED_ResCorr0.5607270831738533Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.04	0.33
Draw 	0.37	0.06	0.57
Win 	0.17	0.03	0.81
xTrees_balanced_shortECH_elo{nobonus,100,200}_SCALED_ResCorr0.5395821909354929Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.17	0.21
Draw 	0.36	0.25	0.39
Win 	0.18	0.15	0.67
logreg_balanced_shortECH_elo{nobonus,100,200}_SCALED_ResCorr0.5600050617012002Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.09	0.28
Draw 	0.37	0.12	0.52
Win 	0.18	0.05	0.77
RandomForest_balanced_shortECH_elo{nobonus,100,200}_SCALED_ResCorr0.5476651861711407Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.14	0.23
Draw 	0.36	0.18	0.46
Win 	0.17	0.11	0.72
xTrees_shortECH_elo{nobonus,100,200}_SCALED_ResCorr0.5570466223299135Pred 	Lose	Draw	Win
True 
Lose 	0.57	0.01	0.41
Draw 	0.31	0.01	0.67
Win 	0.14	0.01	0.85
logreg_shortECH_elo{nobonus,100,200}_SCALED_ResCorr0.5591392087602842Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.41
Draw 	0.30	0.00	0.70
Win 	0.15	0.00	0.85
RandomForest_shortECH_elo{nobonus,100,200}_SCALED_ResCorr0.5621702929173156Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.05	0.32
Draw 	0.37	0.06	0.57
Win 	0.16	0.03	0.81
xTrees_shortECH_elo{nobonus,100,200}_NOTSCALED0.5574794446501411Pred 	Lose	Draw	Win
True 
Lose 	0.01	0.32	0.67
Draw 	0.01	0.58	0.41
Win 	0.00	0.15	0.85
logreg_shortECH_elo{nobonus,100,200}_NOTSCALED0.5592113848699919Pred 	Lose	Draw	Win
True 
Lose 	0.00	0.30	0.70
Draw 	0.00	0.58	0.41
Win 	0.00	0.15	0.85
RandomForest_shortECH_elo{nobonus,100,200}_NOTSCALED0.5600776283742721Pred 	Lose	Draw	Win
True 
Lose 	0.05	0.37	0.57
Draw 	0.04	0.63	0.33
Win 	0.02	0.17	0.81
xTrees_shortECH_elo{nobonus,100,200}_SCALED0.5556752502079099Pred 	Lose	Draw	Win
True 
Lose 	0.01	0.32	0.67
Draw 	0.01	0.58	0.41
Win 	0.01	0.15	0.84
logreg_shortECH_elo{nobonus,100,200}_SCALED0.5591392087602842Pred 	Lose	Draw	Win
True 
Lose 	0.00	0.30	0.70
Draw 	0.00	0.58	0.41
Win 	0.00	0.15	0.85
RandomForest_shortECH_elo{nobonus,100,200}_SCALED0.5618100112326023Pred 	Lose	Draw	Win
True 
Lose 	0.05	0.37	0.57
Draw 	0.05	0.63	0.32
Win 	0.03	0.16	0.81
xTrees_shortECH_OVR0.5583470941825326Pred 	Lose	Draw	Win
True 
Lose 	0.03	0.34	0.63
Draw 	0.04	0.60	0.37
Win 	0.01	0.15	0.84
logreg_shortECH_OVR0.5553881861352089Pred 	Lose	Draw	Win
True 
Lose 	0.01	0.31	0.68
Draw 	0.00	0.58	0.42
Win 	0.00	0.14	0.86
RandomForest_shortECH_OVR0.558274709772364Pred 	Lose	Draw	Win
True 
Lose 	0.07	0.35	0.58
Draw 	0.06	0.61	0.32
Win 	0.03	0.16	0.82
xTreesshortECH_StandardScaler_gridParams_Formation_ResultLabelCorrected_VSPoints_Entropy_MeanOdds_MeanAge_GK_RolesOverallScore)0.5582749701479403Pred 	Lose	Draw	Win
True 
Lose 	0.03	0.33	0.63
Draw 	0.04	0.60	0.36
Win 	0.01	0.15	0.84
logregshortECH_StandardScaler_gridParams_Formation_ResultLabelCorrected_VSPoints_Entropy_MeanOdds_MeanAge_GK_RolesOverallScore)0.5553881861352089Pred 	Lose	Draw	Win
True 
Lose 	0.01	0.31	0.68
Draw 	0.00	0.58	0.42
Win 	0.00	0.14	0.86
RandomForestshortECH_StandardScaler_gridParams_Formation_ResultLabelCorrected_VSPoints_Entropy_MeanOdds_MeanAge_GK_RolesOverallScore)0.5582753086361892Pred 	Lose	Draw	Win
True 
Lose 	0.07	0.35	0.58
Draw 	0.08	0.61	0.32
Win 	0.04	0.15	0.81
xTrees_droppedMeaningless_StandardScaler_gridParams_Positions_ResultLabelCorrected_VSPoints_OverallScore_OverallScoreGrouped_Entropy0.5393670425969235Pred 	Lose	Draw	Win
True 
Lose 	0.03	0.28	0.69
Draw 	0.02	0.49	0.49
Win 	0.01	0.14	0.85
logreg_droppedMeaningless_StandardScaler_gridParams_Positions_ResultLabelCorrected_VSPoints_OverallScore_OverallScoreGrouped_Entropy0.5541609318946021Pred 	Lose	Draw	Win
True 
Lose 	0.06	0.28	0.66
Draw 	0.06	0.55	0.38
Win 	0.03	0.13	0.84
RandomForest_droppedMeaningless_StandardScaler_gridParams_Positions_ResultLabelCorrected_VSPoints_OverallScore_OverallScoreGrouped_Entropy0.553872383681117Pred 	Lose	Draw	Win
True 
Lose 	0.03	0.29	0.68
Draw 	0.03	0.54	0.43
Win 	0.01	0.14	0.85
xTrees_droppedMeaningless_StandardScaler_addedParams_Positions_ResultLabel_VSPoints_OverallScore0.5406751640820203Pred 	Lose	Draw	Win
True 
Lose 	0.48	0.02	0.50
Draw 	0.29	0.01	0.69
Win 	0.14	0.01	0.86
logreg_droppedMeaningless_StandardScaler_addedParams_Positions_ResultLabel_VSPoints_OverallScore0.5538859370731686Pred 	Lose	Draw	Win
True 
Lose 	0.54	0.03	0.43
Draw 	0.31	0.03	0.66
Win 	0.14	0.01	0.85
RandomForest_droppedMeaningless_StandardScaler_addedParams_Positions_ResultLabel_VSPoints_OverallScore0.5508904408367933Pred 	Lose	Draw	Win
True 
Lose 	0.54	0.04	0.42
Draw 	0.32	0.05	0.63
Win 	0.15	0.03	0.82
logreg_droppedMeaningless_StandardScaler_addedParams_Positions_ResultLabel0.5274214157935088Pred 	Lose	Draw	Win
True 
Lose 	0.43	0.01	0.56
Draw 	0.23	0.01	0.76
Win 	0.14	0.00	0.86
RandomForest_droppedMeaningless_StandardScaler_addedParams_Positions_ResultLabel0.523843598262203Pred 	Lose	Draw	Win
True 
Lose 	0.46	0.03	0.51
Draw 	0.27	0.04	0.69
Win 	0.16	0.03	0.82
xTrees_droppedMeaningless_noScaler_addedParams_playerOverallRating0.530514956098139TN:&nbsp2412,&nbspFP:&nbsp298,&nbspFN:&nbsp2,&nbspTP:&nbsp3201
logreg_droppedMeaningless_noScaler_addedParams_playerOverallRating0.5185347625610509TN:&nbsp6,&nbspFP:&nbsp881,&nbspFN:&nbsp4,&nbspTP:&nbsp1789
RandomForest_droppedMeaningless_noScaler_addedParams_playerOverallRating0.5258748380967383TN:&nbsp3533,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp3997
logreg_balanced_firstTry_droppedMeaningless_StandardScaler_addedParams0.5049333353192677TN:&nbsp799,&nbspFP:&nbsp1161,&nbspFN:&nbsp677,&nbspTP:&nbsp2244
xTrees_firstTry_droppedMeaningless_StandardScaler_addedParams0.5280405830912323TN:&nbsp2409,&nbspFP:&nbsp350,&nbspFN:&nbsp3,&nbspTP:&nbsp3331
RandomForest_firstTry_droppedMeaningless_StandardScaler_addedParams0.5266602541891456TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp4234
MLPerc_firstTry_droppedMeaningless_StandardScaler_addedParams0.4634243283230301TN:&nbsp3703,&nbspFP:&nbsp1,&nbspFN:&nbsp0,&nbspTP:&nbsp4234
DTree_firstTry_droppedMeaningless_StandardScaler_addedParams0.4560088886240977TN:&nbsp1683,&nbspFP:&nbsp768,&nbspFN:&nbsp758,&nbspTP:&nbsp2404
logreg_firstTry_droppedMeaningless_StandardScaler_corr0.5259445469639505TN:&nbsp109,&nbspFP:&nbsp1008,&nbspFN:&nbsp72,&nbspTP:&nbsp2038
xTrees_firstTry_droppedMeaningless_StandardScaler0.4553448810190143TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp4234
RandomForest_firstTry_droppedMeaningless_StandardScaler0.4734931592400561TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp4,&nbspTP:&nbsp4230
MLPerc_firstTry_droppedMeaningless_StandardScaler0.4587692589904033TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp4234
LogReg_firstTry_droppedMeaningless_StandardScaler0.5259445469639505TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp4234
DTree_firstTry_droppedMeaningless_StandardScaler0.4123000804303415TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp4234
xTrees_firstTry_droppedMeaningless0.4639329496299106TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp4234
RandomForest_firstTry_droppedMeaningless0.4630133052375883TN:&nbsp3703,&nbspFP:&nbsp1,&nbspFN:&nbsp3,&nbspTP:&nbsp4231
MLPerc_firstTry_droppedMeaningless0.4508442703441989TN:&nbsp3498,&nbspFP:&nbsp203,&nbspFN:&nbsp3483,&nbspTP:&nbsp725
LogReg_firstTry_droppedMeaningless0.5285518044042797TN:&nbsp3387,&nbspFP:&nbsp317,&nbspFN:&nbsp366,&nbspTP:&nbsp2231
DTree_firstTry_droppedMeaningless0.4133221310957079TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp4234
xTrees_firstTry_justdroppedAllThere0.6283109065155807TN:&nbsp330,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp380
RandomForest_firstTry_justdroppedAllThere0.7560294875096576TN:&nbsp330,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp379
MLPerc_firstTry_justdroppedAllThere0.4472685423641514TN:&nbsp212,&nbspFP:&nbsp71,&nbspFN:&nbsp48,&nbspTP:&nbsp290
LogReg_firstTry_justdroppedAllThere0.8656563868143188TN:&nbsp330,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp380
DTree_firstTry_justdroppedAllThere0.9971639196497554TN:&nbsp330,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp380
NameCross-Valid.conf_matrix

















In [60]:



    


make_table(super_table)
apply_theme('basic')



    


















    
Out[60]:







NameRegression&nbspfunctionTrain&nbspAccValidation&nbspAccr2_scoreconf_matrixCross-Valid.
DTree_firstTry_justdroppedAllTherenan100.0100.01.0TN:&nbsp330,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp3800.9971639196497554
LogReg_firstTry_justdroppedAllThereRESULT =&nbsp0.00 +&nbsp0.00*country_id +&nbsp0.00*league_id +&nbsp0.00*season +&nbsp0.00*stage +&nbsp-0.05*date +&nbsp0.01*match_api_id +&nbsp-0.00*home_team_api_id +&nbsp0.00*away_team_api_id +&nbsp-0.00*home_team_goal +&nbsp0.42*away_team_goal +&nbsp-0.87*home_player_X1 +&nbsp0.00*home_player_X2 +&nbsp0.01*home_player_X3 +&nbsp-0.02*home_player_X4 +&nbsp-0.01*home_player_X5 +&nbsp-0.06*home_player_X6 +&nbsp-0.02*home_player_X7 +&nbsp0.05*home_player_X8 +&nbsp0.03*home_player_X9 +&nbsp0.01*home_player_X10 +&nbsp0.02*home_player_X11 +&nbsp0.07*away_player_X1 +&nbsp0.00*away_player_X2 +&nbsp-0.00*away_player_X3 +&nbsp0.02*away_player_X4 +&nbsp-0.03*away_player_X5 +&nbsp0.06*away_player_X6 +&nbsp0.01*away_player_X7 +&nbsp0.05*away_player_X8 +&nbsp0.11*away_player_X9 +&nbsp0.07*away_player_X10 +&nbsp-0.01*away_player_X11 +&nbsp-0.05*home_player_Y1 +&nbsp0.00*home_player_Y2 +&nbsp0.00*home_player_Y3 +&nbsp0.00*home_player_Y4 +&nbsp0.00*home_player_Y5 +&nbsp0.02*home_player_Y6 +&nbsp0.00*home_player_Y7 +&nbsp-0.08*home_player_Y8 +&nbsp-0.04*home_player_Y9 +&nbsp-0.01*home_player_Y10 +&nbsp-0.04*home_player_Y11 +&nbsp-0.03*away_player_Y1 +&nbsp0.00*away_player_Y2 +&nbsp0.00*away_player_Y3 +&nbsp0.00*away_player_Y4 +&nbsp0.00*away_player_Y5 +&nbsp-0.01*away_player_Y6 +&nbsp0.04*away_player_Y7 +&nbsp-0.05*away_player_Y8 +&nbsp0.00*away_player_Y9 +&nbsp0.02*away_player_Y10 +&nbsp0.02*away_player_Y11 +&nbsp0.07*home_player_1 +&nbsp0.00*home_player_2 +&nbsp0.00*home_player_3 +&nbsp-0.00*home_player_4 +&nbsp0.00*home_player_5 +&nbsp-0.00*home_player_6 +&nbsp-0.00*home_player_7 +&nbsp-0.00*home_player_8 +&nbsp0.00*home_player_9 +&nbsp-0.00*home_player_10 +&nbsp0.00*home_player_11 +&nbsp-0.00*away_player_1 +&nbsp-0.00*away_player_2 +&nbsp0.00*away_player_3 +&nbsp-0.00*away_player_4 +&nbsp-0.00*away_player_5 +&nbsp-0.00*away_player_6 +&nbsp-0.00*away_player_7 +&nbsp0.00*away_player_8 +&nbsp-0.00*away_player_9 +&nbsp0.00*away_player_10 +&nbsp0.00*away_player_11 +&nbsp-0.00*goal +&nbsp-0.00*shoton +&nbsp-0.00*shotoff +&nbsp-0.00*foulcommit +&nbsp0.00*card +&nbsp-0.00*cross +&nbsp-0.00*corner +&nbsp-0.00*possession +&nbsp-0.00*B365H +&nbsp0.11*B365D +&nbsp0.05*B365A +&nbsp0.09*BWH +&nbsp0.03*BWD +&nbsp-0.01*BWA +&nbsp-0.01*IWH +&nbsp-0.05*IWD +&nbsp-0.01*IWA +&nbsp-0.03*LBH +&nbsp0.01*LBD +&nbsp-0.02*LBA +&nbsp0.01*PSH +&nbsp0.00*PSD +&nbsp-0.00*PSA +&nbsp0.00*WHH +&nbsp0.01*WHD +&nbsp0.00*WHA +&nbsp0.03*SJH +&nbsp-0.02*SJD +&nbsp0.02*SJA +&nbsp0.01*VCH +&nbsp-0.05*VCD +&nbsp0.00*VCA +&nbsp-0.05*GBH +&nbsp0.03*GBD +&nbsp-0.01*GBA +&nbsp-0.01*BSH +&nbsp-0.05*BSD +&nbsp0.07*BSA +&nbsp0.00*RESULT100.0100.01.0TN:&nbsp330,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp3800.8656563868143188
MLPerc_firstTry_justdroppedAllTherenan69.3448.530.06720900266300145TN:&nbsp212,&nbspFP:&nbsp71,&nbspFN:&nbsp48,&nbspTP:&nbsp2900.4472685423641514
RandomForest_firstTry_justdroppedAllTherenan99.9296.60.9988652177647968TN:&nbsp330,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp3790.7560294875096576
xTrees_firstTry_justdroppedAllTherenan100.097.281.0TN:&nbsp330,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp3800.6283109065155807
DTree_firstTry_droppedMeaninglessnan100.0100.01.0TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp42340.4133221310957079
LogReg_firstTry_droppedMeaninglessRESULT =&nbsp0.00 +&nbsp-0.00*league_id +&nbsp-0.00*season +&nbsp0.00*stage +&nbsp-0.00*date +&nbsp0.00*home_team_api_id +&nbsp0.00*away_team_api_id +&nbsp0.00*home_player_X1 +&nbsp0.00*home_player_X2 +&nbsp-0.01*home_player_X3 +&nbsp-0.01*home_player_X4 +&nbsp0.00*home_player_X5 +&nbsp-0.01*home_player_X6 +&nbsp0.01*home_player_X7 +&nbsp-0.00*home_player_X8 +&nbsp0.01*home_player_X9 +&nbsp-0.01*home_player_X10 +&nbsp0.01*home_player_X11 +&nbsp0.02*away_player_X1 +&nbsp0.00*away_player_X2 +&nbsp-0.00*away_player_X3 +&nbsp-0.00*away_player_X4 +&nbsp0.01*away_player_X5 +&nbsp0.00*away_player_X6 +&nbsp0.01*away_player_X7 +&nbsp-0.00*away_player_X8 +&nbsp0.00*away_player_X9 +&nbsp0.01*away_player_X10 +&nbsp0.00*away_player_X11 +&nbsp-0.01*home_player_Y1 +&nbsp0.00*home_player_Y2 +&nbsp0.00*home_player_Y3 +&nbsp-0.00*home_player_Y4 +&nbsp-0.00*home_player_Y5 +&nbsp0.00*home_player_Y6 +&nbsp0.00*home_player_Y7 +&nbsp0.01*home_player_Y8 +&nbsp-0.00*home_player_Y9 +&nbsp0.01*home_player_Y10 +&nbsp0.01*home_player_Y11 +&nbsp0.00*away_player_Y1 +&nbsp0.00*away_player_Y2 +&nbsp0.00*away_player_Y3 +&nbsp0.00*away_player_Y4 +&nbsp0.00*away_player_Y5 +&nbsp0.01*away_player_Y6 +&nbsp0.01*away_player_Y7 +&nbsp0.01*away_player_Y8 +&nbsp0.01*away_player_Y9 +&nbsp-0.00*away_player_Y10 +&nbsp0.01*away_player_Y11 +&nbsp0.02*home_player_1 +&nbsp0.00*home_player_2 +&nbsp0.00*home_player_3 +&nbsp-0.00*home_player_4 +&nbsp0.00*home_player_5 +&nbsp0.00*home_player_6 +&nbsp-0.00*home_player_7 +&nbsp-0.00*home_player_8 +&nbsp0.00*home_player_9 +&nbsp-0.00*home_player_10 +&nbsp0.00*home_player_11 +&nbsp0.00*away_player_1 +&nbsp-0.00*away_player_2 +&nbsp-0.00*away_player_3 +&nbsp-0.00*away_player_4 +&nbsp-0.00*away_player_5 +&nbsp-0.00*away_player_6 +&nbsp-0.00*away_player_7 +&nbsp-0.00*away_player_8 +&nbsp0.00*away_player_9 +&nbsp0.00*away_player_10 +&nbsp-0.00*away_player_11 +&nbsp-0.00*B365H +&nbsp0.01*B365D +&nbsp-0.01*B365A +&nbsp0.00*BWH +&nbsp-0.02*BWD +&nbsp-0.00*BWA +&nbsp0.03*IWH +&nbsp-0.01*IWD +&nbsp-0.00*IWA +&nbsp0.01*LBH +&nbsp0.01*LBD +&nbsp-0.00*LBA +&nbsp0.01*PSH +&nbsp0.00*PSD +&nbsp-0.00*PSA +&nbsp-0.00*WHH +&nbsp-0.01*WHD +&nbsp-0.01*WHA +&nbsp0.01*SJH +&nbsp-0.00*SJD +&nbsp0.00*SJA +&nbsp0.00*VCH +&nbsp0.00*VCD +&nbsp0.00*VCA +&nbsp0.01*GBH +&nbsp-0.00*GBD +&nbsp0.00*GBA +&nbsp-0.00*BSH +&nbsp-0.00*BSD +&nbsp0.00*BSA +&nbsp-0.00*RESULT82.481.560.7368259494499363TN:&nbsp3387,&nbspFP:&nbsp317,&nbspFN:&nbsp366,&nbspTP:&nbsp22310.5285518044042797
MLPerc_firstTry_droppedMeaninglessnan28.9828.34-2.028336257123525TN:&nbsp3498,&nbspFP:&nbsp203,&nbspFN:&nbsp3483,&nbspTP:&nbsp7250.4508442703441989
RandomForest_firstTry_droppedMeaninglessnan99.9798.220.9995922942671572TN:&nbsp3703,&nbspFP:&nbsp1,&nbspFN:&nbsp3,&nbspTP:&nbsp42310.4630133052375883
xTrees_firstTry_droppedMeaninglessnan100.099.751.0TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp42340.4639329496299106
DTree_firstTry_droppedMeaningless_StandardScalernan100.0100.01.0TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp42340.4123000804303415
LogReg_firstTry_droppedMeaningless_StandardScalerRESULT =&nbsp-5.38 +&nbsp-0.00*league_id +&nbsp-0.00*season +&nbsp-0.01*stage +&nbsp-0.02*date +&nbsp-0.02*home_team_api_id +&nbsp0.01*away_team_api_id +&nbsp0.00*home_player_X1 +&nbsp0.00*home_player_X2 +&nbsp-0.00*home_player_X3 +&nbsp-0.01*home_player_X4 +&nbsp-0.00*home_player_X5 +&nbsp-0.03*home_player_X6 +&nbsp0.02*home_player_X7 +&nbsp0.01*home_player_X8 +&nbsp-0.02*home_player_X9 +&nbsp0.03*home_player_X10 +&nbsp0.02*home_player_X11 +&nbsp0.03*away_player_X1 +&nbsp0.00*away_player_X2 +&nbsp-0.01*away_player_X3 +&nbsp0.02*away_player_X4 +&nbsp0.02*away_player_X5 +&nbsp0.02*away_player_X6 +&nbsp0.01*away_player_X7 +&nbsp-0.01*away_player_X8 +&nbsp-0.00*away_player_X9 +&nbsp-0.01*away_player_X10 +&nbsp-0.02*away_player_X11 +&nbsp0.02*home_player_Y1 +&nbsp0.00*home_player_Y2 +&nbsp0.00*home_player_Y3 +&nbsp0.02*home_player_Y4 +&nbsp0.07*home_player_Y5 +&nbsp-0.01*home_player_Y6 +&nbsp0.02*home_player_Y7 +&nbsp-0.00*home_player_Y8 +&nbsp-0.05*home_player_Y9 +&nbsp0.04*home_player_Y10 +&nbsp0.02*home_player_Y11 +&nbsp0.02*away_player_Y1 +&nbsp0.00*away_player_Y2 +&nbsp0.00*away_player_Y3 +&nbsp0.00*away_player_Y4 +&nbsp0.04*away_player_Y5 +&nbsp0.00*away_player_Y6 +&nbsp0.01*away_player_Y7 +&nbsp0.01*away_player_Y8 +&nbsp0.00*away_player_Y9 +&nbsp-0.03*away_player_Y10 +&nbsp0.02*away_player_Y11 +&nbsp0.06*home_player_1 +&nbsp0.01*home_player_2 +&nbsp0.00*home_player_3 +&nbsp-0.02*home_player_4 +&nbsp0.03*home_player_5 +&nbsp0.01*home_player_6 +&nbsp-0.01*home_player_7 +&nbsp-0.01*home_player_8 +&nbsp-0.00*home_player_9 +&nbsp0.00*home_player_10 +&nbsp0.00*home_player_11 +&nbsp-0.00*away_player_1 +&nbsp-0.00*away_player_2 +&nbsp0.01*away_player_3 +&nbsp-0.01*away_player_4 +&nbsp0.01*away_player_5 +&nbsp-0.01*away_player_6 +&nbsp0.02*away_player_7 +&nbsp0.01*away_player_8 +&nbsp-0.02*away_player_9 +&nbsp-0.00*away_player_10 +&nbsp-0.00*away_player_11 +&nbsp0.00*B365H +&nbsp-0.02*B365D +&nbsp0.04*B365A +&nbsp0.03*BWH +&nbsp-0.02*BWD +&nbsp0.08*BWA +&nbsp0.12*IWH +&nbsp-0.01*IWD +&nbsp0.00*IWA +&nbsp-0.01*LBH +&nbsp0.01*LBD +&nbsp-0.01*LBA +&nbsp-0.01*PSH +&nbsp-0.03*PSD +&nbsp-0.01*PSA +&nbsp0.04*WHH +&nbsp-0.02*WHD +&nbsp-0.01*WHA +&nbsp0.03*SJH +&nbsp-0.01*SJD +&nbsp-0.04*SJA +&nbsp0.01*VCH +&nbsp-0.04*VCD +&nbsp0.06*VCA +&nbsp0.03*GBH +&nbsp0.01*GBD +&nbsp-0.07*GBA +&nbsp-0.00*BSH +&nbsp0.01*BSD +&nbsp-0.03*BSA +&nbsp0.02*RESULT100.099.981.0TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp42340.5259445469639505
MLPerc_firstTry_droppedMeaningless_StandardScalernan100.099.961.0TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp42340.4587692589904033
RandomForest_firstTry_droppedMeaningless_StandardScalernan99.9798.00.9994903678339464TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp4,&nbspTP:&nbsp42300.4734931592400561
xTrees_firstTry_droppedMeaningless_StandardScalernan100.098.981.0TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp42340.4553448810190143
logreg_firstTry_droppedMeaningless_StandardScaler_corrRESULT =&nbsp-1.12 +&nbsp-0.01*league_id +&nbsp-0.01*season +&nbsp0.49*stage +&nbsp0.01*date +&nbsp-0.47*home_team_api_id +&nbsp-0.00*away_team_api_id +&nbsp-0.00*home_player_X1 +&nbsp0.00*home_player_X2 +&nbsp-0.01*home_player_X3 +&nbsp0.00*home_player_X4 +&nbsp0.01*home_player_X5 +&nbsp0.03*home_player_X6 +&nbsp0.14*home_player_X7 +&nbsp0.12*home_player_X8 +&nbsp0.10*home_player_X9 +&nbsp0.17*home_player_X10 +&nbsp0.19*home_player_X11 +&nbsp0.21*away_player_X1 +&nbsp0.00*away_player_X2 +&nbsp0.01*away_player_X3 +&nbsp-0.00*away_player_X4 +&nbsp0.02*away_player_X5 +&nbsp0.09*away_player_X6 +&nbsp0.05*away_player_X7 +&nbsp-0.01*away_player_X8 +&nbsp-0.02*away_player_X9 +&nbsp-0.05*away_player_X10 +&nbsp0.01*away_player_X11 +&nbsp0.00*home_player_Y1 +&nbsp0.00*home_player_Y2 +&nbsp0.00*home_player_Y3 +&nbsp-0.01*home_player_Y4 +&nbsp-0.10*home_player_Y5 +&nbsp-0.03*home_player_Y6 +&nbsp0.04*home_player_Y7 +&nbsp0.03*home_player_Y8 +&nbsp-0.06*home_player_Y9 +&nbsp-0.03*home_player_Y10 +&nbsp0.04*home_player_Y11 +&nbsp0.09*away_player_Y1 +&nbsp0.00*away_player_Y2 +&nbsp0.00*away_player_Y3 +&nbsp0.00*away_player_Y4 +&nbsp0.01*away_player_Y5 +&nbsp0.06*away_player_Y6 +&nbsp0.07*away_player_Y7 +&nbsp0.00*away_player_Y8 +&nbsp-0.01*away_player_Y9 +&nbsp-0.09*away_player_Y10 +&nbsp0.10*away_player_Y11 +&nbsp0.10*home_player_1 +&nbsp-0.01*home_player_2 +&nbsp0.03*home_player_3 +&nbsp-0.03*home_player_4 +&nbsp0.02*home_player_5 +&nbsp0.03*home_player_6 +&nbsp-0.02*home_player_7 +&nbsp-0.04*home_player_8 +&nbsp0.04*home_player_9 +&nbsp-0.00*home_player_10 +&nbsp0.02*home_player_11 +&nbsp0.02*away_player_1 +&nbsp-0.01*away_player_2 +&nbsp-0.00*away_player_3 +&nbsp-0.05*away_player_4 +&nbsp0.00*away_player_5 +&nbsp-0.04*away_player_6 +&nbsp0.00*away_player_7 +&nbsp-0.01*away_player_8 +&nbsp-0.04*away_player_9 +&nbsp0.02*away_player_10 +&nbsp-0.01*away_player_11 +&nbsp0.02*B365H +&nbsp0.36*B365D +&nbsp-0.19*B365A +&nbsp-0.31*BWH +&nbsp0.03*BWD +&nbsp0.01*BWA +&nbsp0.17*IWH +&nbsp0.10*IWD +&nbsp-0.04*IWA +&nbsp-0.01*LBH +&nbsp0.27*LBD +&nbsp0.02*LBA +&nbsp0.03*PSH +&nbsp-0.53*PSD +&nbsp0.06*PSA +&nbsp0.09*WHH +&nbsp-0.32*WHD +&nbsp-0.10*WHA +&nbsp0.02*SJH +&nbsp-0.19*SJD +&nbsp0.02*SJA +&nbsp-0.16*VCH +&nbsp0.32*VCD +&nbsp-0.04*VCA +&nbsp0.01*GBH +&nbsp-0.10*GBD +&nbsp-0.07*GBA +&nbsp-0.27*BSH +&nbsp-0.12*BSD +&nbsp-0.01*BSA53.5751.89-0.5115690045148893TN:&nbsp109,&nbspFP:&nbsp1008,&nbspFN:&nbsp72,&nbspTP:&nbsp20380.5259445469639505
DTree_firstTry_droppedMeaningless_StandardScaler_addedParamsnan61.3845.68-0.2456429402681364TN:&nbsp1683,&nbspFP:&nbsp768,&nbspFN:&nbsp758,&nbspTP:&nbsp24040.4560088886240977
MLPerc_firstTry_droppedMeaningless_StandardScaler_addedParamsnan99.9941.570.9998980735667892TN:&nbsp3703,&nbspFP:&nbsp1,&nbspFN:&nbsp0,&nbspTP:&nbsp42340.4634243283230301
RandomForest_firstTry_droppedMeaningless_StandardScaler_addedParamsnan100.051.811.0TN:&nbsp3704,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp42340.5266602541891456
xTrees_firstTry_droppedMeaningless_StandardScaler_addedParamsnan82.8352.340.454285876589837TN:&nbsp2409,&nbspFP:&nbsp350,&nbspFN:&nbsp3,&nbspTP:&nbsp33310.5280405830912323
logreg_balanced_firstTry_droppedMeaningless_StandardScaler_addedParamsRESULT =&nbsp-0.85 +&nbsp-0.01*league_id +&nbsp-0.01*season +&nbsp0.54*stage +&nbsp0.02*date +&nbsp-0.52*home_team_api_id +&nbsp-0.01*away_team_api_id +&nbsp-0.00*home_player_X1 +&nbsp0.00*home_player_X2 +&nbsp-0.01*home_player_X3 +&nbsp0.00*home_player_X4 +&nbsp0.02*home_player_X5 +&nbsp0.03*home_player_X6 +&nbsp0.14*home_player_X7 +&nbsp0.12*home_player_X8 +&nbsp0.10*home_player_X9 +&nbsp0.17*home_player_X10 +&nbsp0.19*home_player_X11 +&nbsp0.21*away_player_X1 +&nbsp0.00*away_player_X2 +&nbsp0.01*away_player_X3 +&nbsp-0.01*away_player_X4 +&nbsp0.02*away_player_X5 +&nbsp0.08*away_player_X6 +&nbsp0.05*away_player_X7 +&nbsp-0.01*away_player_X8 +&nbsp-0.03*away_player_X9 +&nbsp-0.05*away_player_X10 +&nbsp0.00*away_player_X11 +&nbsp0.00*home_player_Y1 +&nbsp0.00*home_player_Y2 +&nbsp0.00*home_player_Y3 +&nbsp-0.01*home_player_Y4 +&nbsp-0.11*home_player_Y5 +&nbsp-0.02*home_player_Y6 +&nbsp0.04*home_player_Y7 +&nbsp0.03*home_player_Y8 +&nbsp-0.06*home_player_Y9 +&nbsp-0.03*home_player_Y10 +&nbsp0.04*home_player_Y11 +&nbsp0.09*away_player_Y1 +&nbsp0.00*away_player_Y2 +&nbsp0.00*away_player_Y3 +&nbsp0.00*away_player_Y4 +&nbsp0.01*away_player_Y5 +&nbsp0.06*away_player_Y6 +&nbsp0.07*away_player_Y7 +&nbsp0.00*away_player_Y8 +&nbsp-0.01*away_player_Y9 +&nbsp-0.09*away_player_Y10 +&nbsp0.10*away_player_Y11 +&nbsp0.11*home_player_1 +&nbsp-0.01*home_player_2 +&nbsp0.03*home_player_3 +&nbsp-0.03*home_player_4 +&nbsp0.02*home_player_5 +&nbsp0.03*home_player_6 +&nbsp-0.01*home_player_7 +&nbsp-0.04*home_player_8 +&nbsp0.04*home_player_9 +&nbsp-0.00*home_player_10 +&nbsp0.02*home_player_11 +&nbsp0.02*away_player_1 +&nbsp-0.01*away_player_2 +&nbsp-0.00*away_player_3 +&nbsp-0.05*away_player_4 +&nbsp0.00*away_player_5 +&nbsp-0.04*away_player_6 +&nbsp0.00*away_player_7 +&nbsp-0.01*away_player_8 +&nbsp-0.04*away_player_9 +&nbsp0.02*away_player_10 +&nbsp-0.01*away_player_11 +&nbsp0.02*B365H +&nbsp0.37*B365D +&nbsp-0.19*B365A +&nbsp-0.32*BWH +&nbsp0.03*BWD +&nbsp0.01*BWA +&nbsp0.17*IWH +&nbsp0.10*IWD +&nbsp-0.04*IWA +&nbsp-0.01*LBH +&nbsp0.28*LBD +&nbsp0.02*LBA +&nbsp0.02*PSH +&nbsp-0.54*PSD +&nbsp0.06*PSA +&nbsp0.09*WHH +&nbsp-0.33*WHD +&nbsp-0.10*WHA +&nbsp0.02*SJH +&nbsp-0.19*SJD +&nbsp0.02*SJA +&nbsp-0.16*VCH +&nbsp0.32*VCD +&nbsp-0.04*VCA +&nbsp0.01*GBH +&nbsp-0.10*GBD +&nbsp-0.07*GBA +&nbsp-0.27*BSH +&nbsp-0.13*BSD +&nbsp-0.01*BSA51.6850.13-0.5593725016907143TN:&nbsp799,&nbspFP:&nbsp1161,&nbspFN:&nbsp677,&nbspTP:&nbsp22440.5049333353192677
RandomForest_droppedMeaningless_noScaler_addedParams_playerOverallRatingnan100.053.191.0TN:&nbsp3533,&nbspFP:&nbsp0,&nbspFN:&nbsp0,&nbspTP:&nbsp39970.5258748380967383
logreg_droppedMeaningless_noScaler_addedParams_playerOverallRatingRESULT =&nbsp-0.00 +&nbsp-0.00*league_id +&nbsp-0.00*season +&nbsp0.00*stage +&nbsp-0.00*date +&nbsp-0.00*home_team_api_id +&nbsp-0.00*away_team_api_id +&nbsp0.00*home_player_X1 +&nbsp-0.00*home_player_X2 +&nbsp-0.00*home_player_X3 +&nbsp-0.00*home_player_X4 +&nbsp-0.00*home_player_X5 +&nbsp-0.00*home_player_X6 +&nbsp-0.00*home_player_X7 +&nbsp-0.00*home_player_X8 +&nbsp-0.00*home_player_X9 +&nbsp-0.00*home_player_X10 +&nbsp-0.00*home_player_X11 +&nbsp-0.00*away_player_X1 +&nbsp-0.00*away_player_X2 +&nbsp-0.00*away_player_X3 +&nbsp-0.00*away_player_X4 +&nbsp-0.00*away_player_X5 +&nbsp-0.00*away_player_X6 +&nbsp-0.00*away_player_X7 +&nbsp-0.00*away_player_X8 +&nbsp-0.00*away_player_X9 +&nbsp-0.00*away_player_X10 +&nbsp-0.00*away_player_X11 +&nbsp-0.00*home_player_Y1 +&nbsp-0.00*home_player_Y2 +&nbsp-0.00*home_player_Y3 +&nbsp-0.00*home_player_Y4 +&nbsp-0.00*home_player_Y5 +&nbsp-0.00*home_player_Y6 +&nbsp-0.00*home_player_Y7 +&nbsp-0.00*home_player_Y8 +&nbsp-0.00*home_player_Y9 +&nbsp-0.00*home_player_Y10 +&nbsp-0.00*home_player_Y11 +&nbsp-0.00*away_player_Y1 +&nbsp-0.00*away_player_Y2 +&nbsp-0.00*away_player_Y3 +&nbsp-0.00*away_player_Y4 +&nbsp-0.00*away_player_Y5 +&nbsp-0.00*away_player_Y6 +&nbsp-0.00*away_player_Y7 +&nbsp-0.00*away_player_Y8 +&nbsp-0.00*away_player_Y9 +&nbsp-0.00*away_player_Y10 +&nbsp-0.00*away_player_Y11 +&nbsp-0.00*home_player_1 +&nbsp0.00*home_player_2 +&nbsp0.00*home_player_3 +&nbsp-0.00*home_player_4 +&nbsp-0.00*home_player_5 +&nbsp0.00*home_player_6 +&nbsp0.00*home_player_7 +&nbsp-0.00*home_player_8 +&nbsp0.00*home_player_9 +&nbsp0.00*home_player_10 +&nbsp0.00*home_player_11 +&nbsp0.00*away_player_1 +&nbsp-0.00*away_player_2 +&nbsp0.00*away_player_3 +&nbsp-0.00*away_player_4 +&nbsp0.00*away_player_5 +&nbsp-0.00*away_player_6 +&nbsp-0.00*away_player_7 +&nbsp-0.00*away_player_8 +&nbsp-0.00*away_player_9 +&nbsp-0.00*away_player_10 +&nbsp0.00*away_player_11 +&nbsp-0.00*B365H +&nbsp-0.00*B365D +&nbsp-0.00*B365A +&nbsp-0.00*BWH +&nbsp-0.00*BWD +&nbsp-0.00*BWA +&nbsp-0.00*IWH +&nbsp-0.00*IWD +&nbsp-0.00*IWA +&nbsp-0.00*LBH +&nbsp-0.00*LBD +&nbsp-0.00*LBA +&nbsp-0.00*PSH +&nbsp-0.00*PSD +&nbsp-0.00*PSA +&nbsp-0.00*WHH +&nbsp-0.00*WHD +&nbsp-0.00*WHA +&nbsp-0.00*SJH +&nbsp-0.00*SJD +&nbsp-0.00*SJA +&nbsp-0.00*VCH +&nbsp-0.00*VCD +&nbsp-0.00*VCA +&nbsp-0.00*GBH +&nbsp-0.00*GBD +&nbsp-0.00*GBA +&nbsp-0.00*BSH +&nbsp-0.00*BSD +&nbsp-0.00*BSA +&nbsp-0.00*home_player_1_overall_rating +&nbsp-0.00*home_player_2_overall_rating +&nbsp-0.00*home_player_3_overall_rating +&nbsp-0.00*home_player_4_overall_rating +&nbsp-0.00*home_player_5_overall_rating +&nbsp-0.00*home_player_6_overall_rating +&nbsp-0.00*home_player_7_overall_rating +&nbsp-0.00*home_player_8_overall_rating +&nbsp-0.00*home_player_9_overall_rating +&nbsp-0.00*home_player_10_overall_rating +&nbsp-0.00*home_player_11_overall_rating +&nbsp-0.00*away_player_1_overall_rating +&nbsp-0.00*away_player_2_overall_rating +&nbsp-0.00*away_player_3_overall_rating +&nbsp-0.00*away_player_4_overall_rating +&nbsp-0.00*away_player_5_overall_rating +&nbsp-0.00*away_player_6_overall_rating +&nbsp-0.00*away_player_7_overall_rating +&nbsp-0.00*away_player_8_overall_rating +&nbsp-0.00*away_player_9_overall_rating +&nbsp-0.00*away_player_10_overall_rating +&nbsp-0.00*away_player_11_overall_rating52.8354.4-0.5555596240990914TN:&nbsp6,&nbspFP:&nbsp881,&nbspFN:&nbsp4,&nbspTP:&nbsp17890.5185347625610509
xTrees_droppedMeaningless_noScaler_addedParams_playerOverallRatingnan84.2553.170.5003932476692017TN:&nbsp2412,&nbspFP:&nbsp298,&nbspFN:&nbsp2,&nbspTP:&nbsp32010.530514956098139
RandomForest_droppedMeaningless_StandardScaler_addedParams_Positions_ResultLabelnan100.051.611.0Pred 	Lose	Draw	Win
True 
Lose 	0.46	0.03	0.51
Draw 	0.27	0.04	0.69
Win 	0.16	0.03	0.820.523843598262203
logreg_droppedMeaningless_StandardScaler_addedParams_Positions_ResultLabelRESULT =&nbsp-1.11 +&nbsp0.00*league_id +&nbsp0.00*season +&nbsp-0.46*stage +&nbsp-0.05*date +&nbsp0.49*home_team_api_id +&nbsp-0.03*away_team_api_id +&nbsp-0.03*home_player_1_position +&nbsp0.04*home_player_2_position +&nbsp0.02*home_player_3_position +&nbsp0.00*home_player_4_position +&nbsp0.01*home_player_5_position +&nbsp-0.01*home_player_6_position +&nbsp0.00*home_player_7_position +&nbsp0.01*home_player_8_position +&nbsp-0.01*home_player_9_position +&nbsp-0.03*home_player_10_position +&nbsp0.02*home_player_11_position +&nbsp0.00*away_player_1_position +&nbsp0.03*away_player_2_position +&nbsp0.01*away_player_3_position +&nbsp0.00*away_player_4_position +&nbsp0.02*away_player_5_position +&nbsp-0.03*away_player_6_position +&nbsp0.02*away_player_7_position +&nbsp-0.02*away_player_8_position +&nbsp-0.00*away_player_9_position +&nbsp-0.03*away_player_10_position +&nbsp0.00*away_player_11_position +&nbsp0.04*home_player_1 +&nbsp-0.02*home_player_2 +&nbsp0.02*home_player_3 +&nbsp0.01*home_player_4 +&nbsp-0.01*home_player_5 +&nbsp0.00*home_player_6 +&nbsp0.02*home_player_7 +&nbsp-0.01*home_player_8 +&nbsp0.00*home_player_9 +&nbsp-0.01*home_player_10 +&nbsp-0.02*home_player_11 +&nbsp0.02*away_player_1 +&nbsp-0.01*away_player_2 +&nbsp-0.05*away_player_3 +&nbsp-0.01*away_player_4 +&nbsp-0.03*away_player_5 +&nbsp-0.01*away_player_6 +&nbsp0.01*away_player_7 +&nbsp0.03*away_player_8 +&nbsp0.01*away_player_9 +&nbsp0.03*away_player_10 +&nbsp0.02*away_player_11 +&nbsp0.02*B365H +&nbsp0.42*B365D +&nbsp-0.11*B365A +&nbsp-0.12*BWH +&nbsp0.14*BWD +&nbsp-0.11*BWA +&nbsp-0.18*IWH +&nbsp-0.12*IWD +&nbsp0.10*IWA +&nbsp0.07*LBH +&nbsp0.02*LBD +&nbsp0.16*LBA +&nbsp0.25*PSH +&nbsp-0.01*PSD +&nbsp0.39*PSA +&nbsp-0.13*WHH +&nbsp-0.22*WHD +&nbsp0.10*WHA +&nbsp0.20*SJH +&nbsp0.02*SJD +&nbsp0.24*SJA +&nbsp-0.17*VCH +&nbsp0.05*VCD +&nbsp-0.45*VCA +&nbsp-0.03*GBH +&nbsp0.13*GBD +&nbsp0.17*GBA +&nbsp-0.68*BSH +&nbsp-0.08*BSD +&nbsp-0.40*BSA53.4351.96-0.5359402567508378Pred 	Lose	Draw	Win
True 
Lose 	0.43	0.01	0.56
Draw 	0.23	0.01	0.76
Win 	0.14	0.00	0.860.5274214157935088
RandomForest_droppedMeaningless_StandardScaler_addedParams_Positions_ResultLabel_VSPoints_OverallScorenan100.054.461.0Pred 	Lose	Draw	Win
True 
Lose 	0.54	0.04	0.42
Draw 	0.32	0.05	0.63
Win 	0.15	0.03	0.820.5508904408367933
logreg_droppedMeaningless_StandardScaler_addedParams_Positions_ResultLabel_VSPoints_OverallScoreRESULT =&nbsp-1.14 +&nbsp-0.01*league_id +&nbsp-0.01*season +&nbsp-0.50*stage +&nbsp-0.04*date +&nbsp0.55*home_team_api_id +&nbsp0.03*away_team_api_id +&nbsp-0.00*home_player_1_position +&nbsp0.00*home_player_2_position +&nbsp0.03*home_player_3_position +&nbsp-0.01*home_player_4_position +&nbsp0.03*home_player_5_position +&nbsp-0.06*home_player_6_position +&nbsp-0.04*home_player_7_position +&nbsp0.02*home_player_8_position +&nbsp-0.03*home_player_9_position +&nbsp-0.02*home_player_10_position +&nbsp-0.02*home_player_11_position +&nbsp-0.01*away_player_1_position +&nbsp-0.05*away_player_2_position +&nbsp-0.03*away_player_3_position +&nbsp0.00*away_player_4_position +&nbsp-0.02*away_player_5_position +&nbsp-0.01*away_player_6_position +&nbsp0.01*away_player_7_position +&nbsp-0.01*away_player_8_position +&nbsp-0.01*away_player_9_position +&nbsp-0.00*away_player_10_position +&nbsp-0.01*away_player_11_position +&nbsp0.02*home_player_1 +&nbsp-0.01*home_player_2 +&nbsp0.05*home_player_3 +&nbsp0.05*home_player_4 +&nbsp-0.01*home_player_5 +&nbsp-0.01*home_player_6 +&nbsp0.02*home_player_7 +&nbsp0.03*home_player_8 +&nbsp0.01*home_player_9 +&nbsp-0.01*home_player_10 +&nbsp-0.03*home_player_11 +&nbsp0.03*away_player_1 +&nbsp-0.01*away_player_2 +&nbsp-0.04*away_player_3 +&nbsp-0.02*away_player_4 +&nbsp-0.06*away_player_5 +&nbsp-0.01*away_player_6 +&nbsp0.02*away_player_7 +&nbsp0.01*away_player_8 +&nbsp-0.01*away_player_9 +&nbsp0.00*away_player_10 +&nbsp0.01*home_player_1_overall_rating +&nbsp-0.03*home_player_2_overall_rating +&nbsp-0.01*home_player_3_overall_rating +&nbsp-0.01*home_player_4_overall_rating +&nbsp-0.01*home_player_5_overall_rating +&nbsp-0.01*home_player_6_overall_rating +&nbsp0.03*home_player_7_overall_rating +&nbsp-0.01*home_player_8_overall_rating +&nbsp0.02*home_player_9_overall_rating +&nbsp-0.01*home_player_10_overall_rating +&nbsp0.01*home_player_11_overall_rating +&nbsp-0.02*away_player_1_overall_rating +&nbsp-0.01*away_player_2_overall_rating +&nbsp0.04*away_player_3_overall_rating +&nbsp-0.01*away_player_4_overall_rating +&nbsp-0.02*away_player_5_overall_rating +&nbsp-0.03*away_player_6_overall_rating +&nbsp-0.02*away_player_7_overall_rating +&nbsp-0.03*away_player_8_overall_rating +&nbsp-0.01*away_player_9_overall_rating +&nbsp-0.01*away_player_10_overall_rating +&nbsp0.03*away_player_11_overall_rating +&nbsp-0.02*away_player_11 +&nbsp0.03*B365H +&nbsp0.28*B365D +&nbsp-0.02*B365A +&nbsp-0.08*BWH +&nbsp-0.03*BWD +&nbsp-0.00*BWA +&nbsp0.25*IWH +&nbsp-0.23*IWD +&nbsp0.07*IWA +&nbsp0.06*LBH +&nbsp-0.18*LBD +&nbsp0.17*LBA +&nbsp0.31*PSH +&nbsp0.18*PSD +&nbsp0.27*PSA +&nbsp-0.28*WHH +&nbsp0.02*WHD +&nbsp0.08*WHA +&nbsp0.19*SJH +&nbsp0.07*SJD +&nbsp0.02*SJA +&nbsp-0.35*VCH +&nbsp0.04*VCD +&nbsp-0.35*VCA +&nbsp0.30*GBH +&nbsp0.32*GBD +&nbsp0.15*GBA +&nbsp-0.66*BSH +&nbsp-0.23*BSD +&nbsp-0.40*BSA +&nbsp-0.11*VSPointDiff55.8255.4-0.3761755421366153Pred 	Lose	Draw	Win
True 
Lose 	0.54	0.03	0.43
Draw 	0.31	0.03	0.66
Win 	0.14	0.01	0.850.5538859370731686
xTrees_droppedMeaningless_StandardScaler_addedParams_Positions_ResultLabel_VSPoints_OverallScorenan85.053.630.4924065043106429Pred 	Lose	Draw	Win
True 
Lose 	0.48	0.02	0.50
Draw 	0.29	0.01	0.69
Win 	0.14	0.01	0.860.5406751640820203
RandomForest_droppedMeaningless_StandardScaler_gridParams_Positions_ResultLabelCorrected_VSPoints_OverallScore_OverallScoreGrouped_Entropynan83.455.410.4281480990120474Pred 	Lose	Draw	Win
True 
Lose 	0.03	0.29	0.68
Draw 	0.03	0.54	0.43
Win 	0.01	0.14	0.850.553872383681117
logreg_droppedMeaningless_StandardScaler_gridParams_Positions_ResultLabelCorrected_VSPoints_OverallScore_OverallScoreGrouped_EntropyRESULT =&nbsp-1.09 +&nbsp-0.02*league_id +&nbsp-0.02*season +&nbsp0.27*stage +&nbsp-0.02*date +&nbsp-0.26*home_team_api_id +&nbsp0.01*away_team_api_id +&nbsp0.01*home_player_1_position +&nbsp0.00*home_player_2_position +&nbsp0.05*home_player_3_position +&nbsp0.02*home_player_4_position +&nbsp-0.01*home_player_5_position +&nbsp0.09*home_player_6_position +&nbsp0.01*home_player_7_position +&nbsp0.03*home_player_8_position +&nbsp-0.01*home_player_9_position +&nbsp0.05*home_player_10_position +&nbsp-0.02*home_player_11_position +&nbsp0.05*away_player_1_position +&nbsp0.00*away_player_2_position +&nbsp0.01*away_player_3_position +&nbsp-0.00*away_player_4_position +&nbsp-0.04*away_player_5_position +&nbsp0.02*away_player_6_position +&nbsp-0.03*away_player_7_position +&nbsp0.03*away_player_8_position +&nbsp-0.02*away_player_9_position +&nbsp-0.02*away_player_10_position +&nbsp0.02*away_player_11_position +&nbsp-0.02*home_player_1 +&nbsp0.01*home_player_2 +&nbsp0.01*home_player_3 +&nbsp-0.00*home_player_4 +&nbsp-0.03*home_player_5 +&nbsp0.05*home_player_6 +&nbsp-0.03*home_player_7 +&nbsp-0.04*home_player_8 +&nbsp-0.01*home_player_9 +&nbsp0.03*home_player_10 +&nbsp0.05*home_player_11 +&nbsp0.02*away_player_1 +&nbsp-0.01*away_player_2 +&nbsp0.01*away_player_3 +&nbsp-0.04*away_player_4 +&nbsp0.03*away_player_5 +&nbsp0.01*away_player_6 +&nbsp-0.01*away_player_7 +&nbsp-0.06*away_player_8 +&nbsp-0.01*away_player_9 +&nbsp-0.02*away_player_10 +&nbsp0.01*home_player_1_overall_rating +&nbsp0.04*home_player_2_overall_rating +&nbsp0.06*home_player_3_overall_rating +&nbsp0.10*home_player_4_overall_rating +&nbsp0.15*home_player_5_overall_rating +&nbsp0.08*home_player_6_overall_rating +&nbsp-0.03*home_player_7_overall_rating +&nbsp-0.01*home_player_8_overall_rating +&nbsp-0.00*home_player_9_overall_rating +&nbsp-0.04*home_player_10_overall_rating +&nbsp-0.04*home_player_11_overall_rating +&nbsp-0.01*away_player_1_overall_rating +&nbsp-0.02*away_player_2_overall_rating +&nbsp-0.03*away_player_3_overall_rating +&nbsp-0.00*away_player_4_overall_rating +&nbsp0.00*away_player_5_overall_rating +&nbsp-0.01*away_player_6_overall_rating +&nbsp-0.06*away_player_7_overall_rating +&nbsp-0.02*away_player_8_overall_rating +&nbsp-0.09*away_player_9_overall_rating +&nbsp-0.13*away_player_10_overall_rating +&nbsp-0.09*away_player_11_overall_rating +&nbsp-0.09*away_player_11 +&nbsp0.02*B365H +&nbsp0.10*B365D +&nbsp-0.26*B365A +&nbsp-0.11*BWH +&nbsp0.03*BWD +&nbsp-0.17*BWA +&nbsp0.06*IWH +&nbsp0.05*IWD +&nbsp0.02*IWA +&nbsp0.11*LBH +&nbsp-0.07*LBD +&nbsp0.00*LBA +&nbsp-0.01*PSH +&nbsp-0.31*PSD +&nbsp-0.08*PSA +&nbsp0.33*WHH +&nbsp0.02*WHD +&nbsp0.01*WHA +&nbsp-0.22*SJH +&nbsp-0.34*SJD +&nbsp0.18*SJA +&nbsp-0.27*VCH +&nbsp0.33*VCD +&nbsp0.14*VCA +&nbsp-0.10*GBH +&nbsp0.25*GBD +&nbsp-0.10*GBA +&nbsp-0.00*BSH +&nbsp-0.20*BSD +&nbsp-0.09*BSA +&nbsp0.16*VSPointDiff +&nbsp-0.18*entropy +&nbsp-0.06*home_formation +&nbsp0.05*away_formation +&nbsp-0.08*home_defenders_score +&nbsp-0.21*home_midfielders_score +&nbsp0.05*home_forwarders_score +&nbsp0.05*away_defenders_score +&nbsp0.03*away_midfielders_score +&nbsp0.17*away_forwarders_score56.2656.13-0.4187879506295893Pred 	Lose	Draw	Win
True 
Lose 	0.06	0.28	0.66
Draw 	0.06	0.55	0.38
Win 	0.03	0.13	0.840.5541609318946021
xTrees_droppedMeaningless_StandardScaler_gridParams_Positions_ResultLabelCorrected_VSPoints_OverallScore_OverallScoreGrouped_Entropynan85.3454.080.5388336838129374Pred 	Lose	Draw	Win
True 
Lose 	0.03	0.28	0.69
Draw 	0.02	0.49	0.49
Win 	0.01	0.14	0.850.5393670425969235
RandomForestshortECH_StandardScaler_gridParams_Formation_ResultLabelCorrected_VSPoints_Entropy_MeanOdds_MeanAge_GK_RolesOverallScore)nan76.3556.540.2400818108804457Pred 	Lose	Draw	Win
True 
Lose 	0.07	0.35	0.58
Draw 	0.08	0.61	0.32
Win 	0.04	0.15	0.810.5582753086361892
logregshortECH_StandardScaler_gridParams_Formation_ResultLabelCorrected_VSPoints_Entropy_MeanOdds_MeanAge_GK_RolesOverallScore)RESULT =&nbsp-1.08 +&nbsp0.03*away_player_1_overall_rating +&nbsp-0.01*home_defenders_score +&nbsp0.00*home_midfielders_score +&nbsp0.02*home_forwarders_score +&nbsp0.01*away_defenders_score +&nbsp-0.00*away_midfielders_score +&nbsp0.01*away_forwarders_score +&nbsp-0.05*Age_home +&nbsp0.04*Age_away +&nbsp-0.00*Away_odds +&nbsp-0.00*Home_odds +&nbsp-0.12*Draw_odds +&nbsp-0.34*home_formation +&nbsp-0.02*away_formation +&nbsp-0.01*VSPointDiff +&nbsp-0.17*entropy55.2556.31-0.4379205421124577Pred 	Lose	Draw	Win
True 
Lose 	0.01	0.31	0.68
Draw 	0.00	0.58	0.42
Win 	0.00	0.14	0.860.5553881861352089
xTreesshortECH_StandardScaler_gridParams_Formation_ResultLabelCorrected_VSPoints_Entropy_MeanOdds_MeanAge_GK_RolesOverallScore)nan74.9756.650.17517272273856654Pred 	Lose	Draw	Win
True 
Lose 	0.03	0.33	0.63
Draw 	0.04	0.60	0.36
Win 	0.01	0.15	0.840.5582749701479403
RandomForest_shortECH_OVRnan78.656.910.2881258739374261Pred 	Lose	Draw	Win
True 
Lose 	0.07	0.35	0.58
Draw 	0.06	0.61	0.32
Win 	0.03	0.16	0.820.558274709772364
logreg_shortECH_OVRnan55.2556.31-0.4379205421124577Pred 	Lose	Draw	Win
True 
Lose 	0.01	0.31	0.68
Draw 	0.00	0.58	0.42
Win 	0.00	0.14	0.860.5553881861352089
xTrees_shortECH_OVRnan76.6956.620.2256260750933896Pred 	Lose	Draw	Win
True 
Lose 	0.03	0.34	0.63
Draw 	0.04	0.60	0.37
Win 	0.01	0.15	0.840.5583470941825326
RandomForest_shortECH_elo{nobonus,100,200}_SCALEDnan76.4256.310.2267857036829083Pred 	Lose	Draw	Win
True 
Lose 	0.05	0.37	0.57
Draw 	0.05	0.63	0.32
Win 	0.03	0.16	0.810.5618100112326023
logreg_shortECH_elo{nobonus,100,200}_SCALEDRESULT =&nbsp-1.09 +&nbsp0.01*away_player_1_overall_rating +&nbsp-0.01*home_defenders_score +&nbsp-0.01*home_midfielders_score +&nbsp0.01*home_forwarders_score +&nbsp0.01*away_defenders_score +&nbsp-0.01*away_midfielders_score +&nbsp0.01*away_forwarders_score +&nbsp-0.05*Age_home +&nbsp0.01*Age_away +&nbsp0.03*Away_odds +&nbsp0.12*Home_odds +&nbsp-0.02*Draw_odds +&nbsp-0.39*elo_home_cat +&nbsp0.05*elo_away_cat +&nbsp-0.06*home_formation +&nbsp-0.01*away_formation +&nbsp-0.01*NoBonus +&nbsp-0.10*100Bonus +&nbsp0.07*200Bonus +&nbsp-0.02*VSPointDiff +&nbsp-0.17*entropy55.9955.64-0.4191745626652996Pred 	Lose	Draw	Win
True 
Lose 	0.00	0.30	0.70
Draw 	0.00	0.58	0.41
Win 	0.00	0.15	0.850.5591392087602842
xTrees_shortECH_elo{nobonus,100,200}_SCALEDnan74.7455.470.1415696791348765Pred 	Lose	Draw	Win
True 
Lose 	0.01	0.32	0.67
Draw 	0.01	0.58	0.41
Win 	0.01	0.15	0.840.5556752502079099
RandomForest_shortECH_elo{nobonus,100,200}_NOTSCALEDnan76.0356.330.21153802036076885Pred 	Lose	Draw	Win
True 
Lose 	0.05	0.37	0.57
Draw 	0.04	0.63	0.33
Win 	0.02	0.17	0.810.5600776283742721
logreg_shortECH_elo{nobonus,100,200}_NOTSCALEDRESULT =&nbsp-0.91 +&nbsp0.01*away_player_1_overall_rating +&nbsp-0.01*home_defenders_score +&nbsp-0.01*home_midfielders_score +&nbsp0.01*home_forwarders_score +&nbsp0.01*away_defenders_score +&nbsp-0.01*away_midfielders_score +&nbsp0.01*away_forwarders_score +&nbsp-0.05*Age_home +&nbsp0.01*Age_away +&nbsp0.03*Away_odds +&nbsp0.12*Home_odds +&nbsp-0.03*Draw_odds +&nbsp-0.40*elo_home_cat +&nbsp0.07*elo_away_cat +&nbsp-0.07*home_formation +&nbsp-0.01*away_formation +&nbsp-0.01*VSPointDiff +&nbsp-0.17*entropy +&nbsp-0.04*NoBonus +&nbsp-0.22*100Bonus +&nbsp-0.06*200Bonus55.9755.67-0.42074208151150105Pred 	Lose	Draw	Win
True 
Lose 	0.00	0.30	0.70
Draw 	0.00	0.58	0.41
Win 	0.00	0.15	0.850.5592113848699919
xTrees_shortECH_elo{nobonus,100,200}_NOTSCALEDnan74.6155.640.13786463458930984Pred 	Lose	Draw	Win
True 
Lose 	0.01	0.32	0.67
Draw 	0.01	0.58	0.41
Win 	0.00	0.15	0.850.5574794446501411
RandomForest_shortECH_elo{nobonus,100,200}_SCALED_ResCorrnan76.2356.680.2375756833789299Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.05	0.32
Draw 	0.37	0.06	0.57
Win 	0.16	0.03	0.810.5621702929173156
logreg_shortECH_elo{nobonus,100,200}_SCALED_ResCorrRESULT =&nbsp-1.15 +&nbsp0.03*away_player_1_overall_rating +&nbsp-0.03*home_defenders_score +&nbsp-0.03*home_midfielders_score +&nbsp-0.01*home_forwarders_score +&nbsp-0.00*away_defenders_score +&nbsp0.01*away_midfielders_score +&nbsp-0.01*away_forwarders_score +&nbsp0.02*Age_home +&nbsp0.04*Age_away +&nbsp-0.02*Away_odds +&nbsp-0.50*Home_odds +&nbsp0.13*Draw_odds +&nbsp0.11*elo_home_cat +&nbsp-0.03*elo_away_cat +&nbsp-0.08*home_formation +&nbsp0.04*away_formation +&nbsp0.02*NoBonus +&nbsp0.17*100Bonus +&nbsp-0.13*200Bonus +&nbsp0.00*VSPointDiff +&nbsp-0.80*entropy55.9955.64-0.3793612149216421Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.41
Draw 	0.30	0.00	0.70
Win 	0.15	0.00	0.850.5591392087602842
xTrees_shortECH_elo{nobonus,100,200}_SCALED_ResCorrnan74.4355.470.21434092390713247Pred 	Lose	Draw	Win
True 
Lose 	0.57	0.01	0.41
Draw 	0.31	0.01	0.67
Win 	0.14	0.01	0.850.5570466223299135
RandomForest_balanced_shortECH_elo{nobonus,100,200}_SCALED_ResCorrnan80.6755.350.2467615185189427Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.14	0.23
Draw 	0.36	0.18	0.46
Win 	0.17	0.11	0.720.5476651861711407
logreg_balanced_shortECH_elo{nobonus,100,200}_SCALED_ResCorrRESULT =&nbsp-0.99 +&nbsp0.03*away_player_1_overall_rating +&nbsp-0.03*home_defenders_score +&nbsp-0.03*home_midfielders_score +&nbsp-0.01*home_forwarders_score +&nbsp-0.00*away_defenders_score +&nbsp0.01*away_midfielders_score +&nbsp-0.01*away_forwarders_score +&nbsp0.02*Age_home +&nbsp0.04*Age_away +&nbsp-0.02*Away_odds +&nbsp-0.52*Home_odds +&nbsp0.12*Draw_odds +&nbsp0.11*elo_home_cat +&nbsp-0.03*elo_away_cat +&nbsp-0.08*home_formation +&nbsp0.04*away_formation +&nbsp0.01*NoBonus +&nbsp0.17*100Bonus +&nbsp-0.15*200Bonus +&nbsp0.02*VSPointDiff +&nbsp-0.80*entropy56.3556.05-0.2781819425706176Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.09	0.28
Draw 	0.37	0.12	0.52
Win 	0.18	0.05	0.770.5600050617012002
xTrees_balanced_shortECH_elo{nobonus,100,200}_SCALED_ResCorrnan82.7555.010.3193025989628681Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.17	0.21
Draw 	0.36	0.25	0.39
Win 	0.18	0.15	0.670.5395821909354929
RandomForest_shortECH_eloCat{nobonus,100,200}_SCALED_ResCorrnan76.4856.280.2406826570292283Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.04	0.33
Draw 	0.37	0.06	0.57
Win 	0.17	0.03	0.810.5607270831738533
logreg_shortECH_eloCat{nobonus,100,200}_SCALED_ResCorrRESULT =&nbsp-1.15 +&nbsp0.03*away_player_1_overall_rating +&nbsp-0.03*home_defenders_score +&nbsp-0.03*home_midfielders_score +&nbsp-0.01*home_forwarders_score +&nbsp-0.00*away_defenders_score +&nbsp0.01*away_midfielders_score +&nbsp-0.01*away_forwarders_score +&nbsp0.02*Age_home +&nbsp0.04*Age_away +&nbsp-0.02*Away_odds +&nbsp-0.50*Home_odds +&nbsp0.13*Draw_odds +&nbsp0.11*elo_home_cat +&nbsp-0.01*elo_away_cat +&nbsp-0.10*NoBonus_cat +&nbsp0.12*100Bonus_cat +&nbsp0.11*200Bonus_cat +&nbsp-0.21*home_formation +&nbsp0.04*away_formation +&nbsp0.02*VSPointDiff +&nbsp-0.80*entropy56.055.76-0.3839541324916485Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.01	0.42
Draw 	0.30	0.01	0.69
Win 	0.14	0.00	0.850.5589228106189492
xTrees_shortECH_eloCat{nobonus,100,200}_SCALED_ResCorrnan73.9255.410.20029199957534805Pred 	Lose	Draw	Win
True 
Lose 	0.57	0.01	0.42
Draw 	0.31	0.01	0.68
Win 	0.15	0.01	0.850.554809527454782
RandomForest_shortECH_eloCat{nobonus,100,200}_NotSCALED_ResCorrnan75.9456.130.22339167323626288Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.05	0.32
Draw 	0.37	0.05	0.58
Win 	0.17	0.03	0.800.5611601398320994
logreg_shortECH_eloCat{nobonus,100,200}_NotSCALED_ResCorrRESULT =&nbsp-0.91 +&nbsp0.03*away_player_1_overall_rating +&nbsp-0.03*home_defenders_score +&nbsp-0.03*home_midfielders_score +&nbsp-0.01*home_forwarders_score +&nbsp-0.00*away_defenders_score +&nbsp0.01*away_midfielders_score +&nbsp-0.01*away_forwarders_score +&nbsp0.02*Age_home +&nbsp0.04*Age_away +&nbsp-0.02*Away_odds +&nbsp-0.51*Home_odds +&nbsp0.12*Draw_odds +&nbsp0.10*elo_home_cat +&nbsp0.01*elo_away_cat +&nbsp-0.13*home_formation +&nbsp0.04*away_formation +&nbsp0.02*VSPointDiff +&nbsp-0.80*entropy +&nbsp-0.05*NoBonus_cat +&nbsp0.04*100Bonus_cat +&nbsp0.05*200Bonus_cat56.0555.76-0.3812524162739976Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.01	0.41
Draw 	0.30	0.01	0.69
Win 	0.14	0.00	0.850.5589949346535417
xTrees_shortECH_eloCat{nobonus,100,200}_NotSCALED_ResCorrnan74.0155.70.2011025144406433Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.01	0.41
Draw 	0.32	0.02	0.67
Win 	0.14	0.01	0.850.5546651231602513
RandomForest_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorrnan76.8756.190.25127957307969595Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.38	0.07	0.55
Win 	0.17	0.03	0.790.561160504357906
logreg_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorrRESULT =&nbsp-1.14 +&nbsp0.02*away_player_1_overall_rating +&nbsp-0.05*home_defenders_score +&nbsp-0.02*home_midfielders_score +&nbsp-0.00*home_forwarders_score +&nbsp0.02*away_defenders_score +&nbsp-0.00*away_midfielders_score +&nbsp-0.04*away_forwarders_score +&nbsp-0.01*Away_odds +&nbsp-0.38*Home_odds +&nbsp0.19*Draw_odds +&nbsp0.09*elo_home +&nbsp0.02*elo_away +&nbsp-0.18*NoBonus +&nbsp-0.04*100Bonus +&nbsp0.05*200Bonus +&nbsp-0.15*VSPointDiff56.1555.79-0.3734876797142461Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.00	0.39
Draw 	0.34	0.00	0.65
Win 	0.16	0.00	0.840.5595005840224173
xTrees_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorrnan74.2954.980.2032933388213988Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.02	0.38
Draw 	0.37	0.02	0.61
Win 	0.17	0.01	0.820.5592120618464899
RandomForest_balanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorrnan81.455.090.2857485582511489Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.16	0.21
Draw 	0.39	0.21	0.40
Win 	0.18	0.13	0.690.5450679658366413
logreg_balanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorrRESULT =&nbsp-0.98 +&nbsp0.02*away_player_1_overall_rating +&nbsp-0.05*home_defenders_score +&nbsp-0.02*home_midfielders_score +&nbsp-0.00*home_forwarders_score +&nbsp0.02*away_defenders_score +&nbsp-0.00*away_midfielders_score +&nbsp-0.04*away_forwarders_score +&nbsp-0.01*Away_odds +&nbsp-0.38*Home_odds +&nbsp0.19*Draw_odds +&nbsp0.09*elo_home +&nbsp0.03*elo_away +&nbsp-0.18*NoBonus +&nbsp-0.05*100Bonus +&nbsp0.06*200Bonus +&nbsp-0.15*VSPointDiff56.2156.28-0.2790021085972048Pred 	Lose	Draw	Win
True 
Lose 	0.65	0.08	0.26
Draw 	0.41	0.13	0.46
Win 	0.19	0.06	0.750.558851285448182
xTrees_balanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorrnan81.2454.080.284261660851596Pred 	Lose	Draw	Win
True 
Lose 	0.62	0.19	0.19
Draw 	0.40	0.24	0.36
Win 	0.19	0.15	0.660.5433366244806158
RandomForest_manbalanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorrnan79.2955.820.2691223418743304Pred 	Lose	Draw	Win
True 
Lose 	0.61	0.11	0.28
Draw 	0.38	0.12	0.50
Win 	0.16	0.07	0.770.5593567265165966
logreg_manbalanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorrRESULT =&nbsp-1.14 +&nbsp0.02*away_player_1_overall_rating +&nbsp-0.05*home_defenders_score +&nbsp-0.02*home_midfielders_score +&nbsp-0.00*home_forwarders_score +&nbsp0.02*away_defenders_score +&nbsp-0.00*away_midfielders_score +&nbsp-0.04*away_forwarders_score +&nbsp-0.01*Away_odds +&nbsp-0.38*Home_odds +&nbsp0.19*Draw_odds +&nbsp0.09*elo_home +&nbsp0.02*elo_away +&nbsp-0.18*NoBonus +&nbsp-0.04*100Bonus +&nbsp0.05*200Bonus +&nbsp-0.15*VSPointDiff56.2556.08-0.35496904846526944Pred 	Lose	Draw	Win
True 
Lose 	0.61	0.01	0.37
Draw 	0.36	0.03	0.61
Win 	0.16	0.01	0.820.5618097248194686
xTrees_manbalanced_evenshorterECH_elo{nobonus,100,200}_SCALED_ResCorrnan78.4754.890.2551995753148808Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.07	0.33
Draw 	0.37	0.08	0.55
Win 	0.17	0.05	0.780.5566862104574122
RandomForest_shortECH_elo{100}_SCALED_ResCorrnan76.856.390.25073888311622217Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.04	0.33
Draw 	0.38	0.07	0.55
Win 	0.18	0.03	0.800.5624596222575291
logreg_shortECH_elo{100}_SCALED_ResCorrRESULT =&nbsp-1.14 +&nbsp0.02*away_player_1_overall_rating +&nbsp-0.04*home_defenders_score +&nbsp-0.02*home_midfielders_score +&nbsp-0.01*home_forwarders_score +&nbsp0.01*away_defenders_score +&nbsp-0.00*away_midfielders_score +&nbsp-0.05*away_forwarders_score +&nbsp-0.01*Age_home +&nbsp-0.01*Age_away +&nbsp0.01*Away_odds +&nbsp-0.35*Home_odds +&nbsp0.20*Draw_odds +&nbsp0.08*elo_home_cat +&nbsp-0.07*elo_away_cat +&nbsp-0.08*home_formation +&nbsp0.07*away_formation +&nbsp-0.00*NoBonus +&nbsp-0.01*VSPointDiff +&nbsp-0.78*entropy56.0355.82-0.37754285444029945Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.00	0.40
Draw 	0.34	0.00	0.65
Win 	0.15	0.00	0.850.5605106329574031
xTrees_shortECH_elo{100}_SCALED_ResCorrnan74.4155.270.20788920351092588Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.01	0.39
Draw 	0.36	0.02	0.63
Win 	0.17	0.01	0.830.5598613343831677
RandomForest_shortECH_elo{100}_SCALED_ResCorr_SMOTEnan84.5653.560.3943281841566055Pred 	Lose	Draw	Win
True 
Lose 	0.43	0.33	0.24
Draw 	0.23	0.35	0.42
Win 	0.09	0.20	0.710.0
logreg_shortECH_elo{100}_SCALED_ResCorr_SMOTEnan51.650.91-0.08666622931175838Pred 	Lose	Draw	Win
True 
Lose 	0.28	0.55	0.17
Draw 	0.12	0.54	0.34
Win 	0.04	0.33	0.630.0
xTrees_shortECH_elo{100}_SCALED_ResCorr_SMOTEnan84.352.210.3919124756068202Pred 	Lose	Draw	Win
True 
Lose 	0.37	0.42	0.21
Draw 	0.20	0.43	0.38
Win 	0.08	0.25	0.670.0
GradientBoosting_superbasic_shortECH_elo{No,100,200}_SCALED_ResCorrnan60.0656.57-0.2002374296913907Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.790.5636860693338499
GradientBoosting_10Est_shortECH_elo{No,100,200}_SCALED_ResCorrnan56.5955.87-0.3546405115301368Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.00	0.36
Draw 	0.37	0.00	0.63
Win 	0.18	0.00	0.820.563036536421596
GradientBoosting_10Est_0.9MF_shortECH_elo{No,100,200}_SCALED_ResCorrnan56.655.96-0.35085810882542545Pred 	Lose	Draw	Win
True 
Lose 	0.65	0.00	0.35
Draw 	0.38	0.00	0.62
Win 	0.18	0.00	0.820.5635419774900107
GradientBoosting_10Est_0.9MF_shortECH_elo{No,100,200}_SCALED_ResCorrnan56.7255.99-0.3476160493642446Pred 	Lose	Draw	Win
True 
Lose 	0.65	0.00	0.34
Draw 	0.39	0.00	0.61
Win 	0.18	0.00	0.820.5625314078038726
GradientBoosting_1000Est_0.01LR_shortECH_elo{No,100,200}_SCALED_ResCorrnan59.9556.51-0.2037496607743368Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.07	0.31
Draw 	0.35	0.10	0.56
Win 	0.17	0.04	0.790.5621705272553341
DvL_GradientBoosting_shortECH_elo{No,100,200}_SCALED_ResCorrnan69.0861.91-0.2388672844113336[[&nbsp0.68153656 &nbsp0.31846344]
 [&nbsp0.45375723 &nbsp0.54624277]]0.6191826522101752
DvL_RandomForest_shortECH_elo{No,100,200}_SCALED_ResCorrnan90.4661.910.6176445575449913[[&nbsp0.66542751 &nbsp0.33457249]
 [&nbsp0.4349711  &nbsp0.5650289 ]]0.6128440366972476
DvL_logreg_shortECH_elo{No,100,200}_SCALED_ResCorrRESULT =&nbsp0.14 +&nbsp0.00*away_player_1_overall_rating +&nbsp0.02*home_defenders_score +&nbsp-0.03*home_midfielders_score +&nbsp0.00*home_forwarders_score +&nbsp0.00*away_defenders_score +&nbsp0.00*away_midfielders_score +&nbsp-0.02*away_forwarders_score +&nbsp-0.05*Age_home +&nbsp0.01*Age_away +&nbsp-0.01*Away_odds +&nbsp0.24*Home_odds +&nbsp-0.14*Draw_odds +&nbsp-0.23*elo_home_cat +&nbsp0.00*elo_away_cat +&nbsp0.14*home_formation +&nbsp-0.07*away_formation +&nbsp-0.00*NoBonus +&nbsp-0.10*100Bonus +&nbsp0.17*200Bonus +&nbsp0.04*VSPointDiff +&nbsp0.45*entropy62.1462.98-0.5169439698331582[[&nbsp0.6802974  &nbsp0.3197026 ]
 [&nbsp0.42919075 &nbsp0.57080925]]0.6221851542952461
DvL_xTrees_shortECH_elo{No,100,200}_SCALED_ResCorrnan83.5461.770.3404591435508008[[&nbsp0.65923172 &nbsp0.34076828]
 [&nbsp0.43063584 &nbsp0.56936416]]0.6201834862385323
WvD_GradientBoosting_shortECH_elo{No,100,200}_SCALED_ResCorrnan69.3964.61-0.2282572158975311[[&nbsp0.66853933 &nbsp0.33146067]
 [&nbsp0.37893082 &nbsp0.62106918]]0.6303591884968724
WvD_RandomForest_shortECH_elo{No,100,200}_SCALED_ResCorrnan90.1563.950.6048129572132439[[&nbsp0.69382022 &nbsp0.30617978]
 [&nbsp0.42138365 &nbsp0.57861635]]0.6259032253063291
WvD_logreg_shortECH_elo{No,100,200}_SCALED_ResCorrRESULT =&nbsp-0.22 +&nbsp-0.03*away_player_1_overall_rating +&nbsp0.02*home_defenders_score +&nbsp0.04*home_midfielders_score +&nbsp0.02*home_forwarders_score +&nbsp0.02*away_defenders_score +&nbsp-0.01*away_midfielders_score +&nbsp-0.02*away_forwarders_score +&nbsp0.06*Age_home +&nbsp-0.10*Age_away +&nbsp0.06*Away_odds +&nbsp0.07*Home_odds +&nbsp-0.15*Draw_odds +&nbsp0.21*elo_home_cat +&nbsp0.02*elo_away_cat +&nbsp-0.01*home_formation +&nbsp0.01*away_formation +&nbsp0.05*NoBonus +&nbsp-0.09*100Bonus +&nbsp-0.03*200Bonus +&nbsp0.04*VSPointDiff +&nbsp0.59*entropy63.5765.73-0.4615962989500129[[&nbsp0.74578652 &nbsp0.25421348]
 [&nbsp0.4418239  &nbsp0.5581761 ]]0.6299883032473561
WvD_xTrees_shortECH_elo{No,100,200}_SCALED_ResCorrnan85.8262.610.43104981025926814[[&nbsp0.71769663 &nbsp0.28230337]
 [&nbsp0.47641509 &nbsp0.52358491]]0.6182960294778839
WvL_GradientBoosting_shortECH_elo{No,100,200}_SCALED_ResCorrnan78.3975.70.12519594772123666[[&nbsp0.79411765 &nbsp0.20588235]
 [&nbsp0.28816199 &nbsp0.71183801]]0.7508340649692713
WvL_RandomForest_shortECH_elo{No,100,200}_SCALED_ResCorrnan88.1174.580.5185260470665094[[&nbsp0.78644501 &nbsp0.21355499]
 [&nbsp0.30373832 &nbsp0.69626168]]0.7438103599648815
WvL_logreg_shortECH_elo{No,100,200}_SCALED_ResCorrRESULT =&nbsp-0.10 +&nbsp-0.03*away_player_1_overall_rating +&nbsp0.01*home_defenders_score +&nbsp0.06*home_midfielders_score +&nbsp0.01*home_forwarders_score +&nbsp-0.00*away_defenders_score +&nbsp0.01*away_midfielders_score +&nbsp0.02*away_forwarders_score +&nbsp0.07*Age_home +&nbsp0.01*Age_away +&nbsp-0.04*Away_odds +&nbsp0.23*Home_odds +&nbsp-0.28*Draw_odds +&nbsp0.21*elo_home_cat +&nbsp-0.16*elo_away_cat +&nbsp0.27*home_formation +&nbsp-0.14*away_formation +&nbsp0.07*NoBonus +&nbsp-0.11*100Bonus +&nbsp0.20*200Bonus +&nbsp0.15*VSPointDiff +&nbsp1.12*entropy75.1873.95-0.004650374231299326[[&nbsp0.80179028 &nbsp0.19820972]
 [&nbsp0.3364486  &nbsp0.6635514 ]]0.7476733977172958
WvL_xTrees_shortECH_elo{No,100,200}_SCALED_ResCorrnan83.3173.670.32423045582366383[[&nbsp0.80179028 &nbsp0.19820972]
 [&nbsp0.34267913 &nbsp0.65732087]]0.7390693590869184
DvL_RandomForest_balanced_shortECH_elo{No,100,200}_SCALED_ResCorrnan90.3262.370.612296928979187[[&nbsp0.65055762 &nbsp0.34944238]
 [&nbsp0.40751445 &nbsp0.59248555]]0.6160133444537114
DvL_logreg_balanced_shortECH_elo{No,100,200}_SCALED_ResCorrRESULT =&nbsp0.22 +&nbsp0.00*away_player_1_overall_rating +&nbsp0.02*home_defenders_score +&nbsp-0.03*home_midfielders_score +&nbsp0.00*home_forwarders_score +&nbsp0.00*away_defenders_score +&nbsp0.00*away_midfielders_score +&nbsp-0.01*away_forwarders_score +&nbsp-0.05*Age_home +&nbsp0.01*Age_away +&nbsp-0.01*Away_odds +&nbsp0.24*Home_odds +&nbsp-0.14*Draw_odds +&nbsp-0.23*elo_home_cat +&nbsp0.01*elo_away_cat +&nbsp0.14*home_formation +&nbsp-0.07*away_formation +&nbsp-0.00*NoBonus +&nbsp-0.10*100Bonus +&nbsp0.16*200Bonus +&nbsp0.04*VSPointDiff +&nbsp0.45*entropy62.1963.78-0.5151614269778901[[&nbsp0.63320942 &nbsp0.36679058]
 [&nbsp0.35693642 &nbsp0.64306358]]0.62418682235196
DvL_xTrees_balanced_shortECH_elo{No,100,200}_SCALED_ResCorrnan83.361.640.3306551578468262[[&nbsp0.62081784 &nbsp0.37918216]
 [&nbsp0.38872832 &nbsp0.61127168]]0.6206839032527106
WvD_RandomForest_balanced_shortECH_elo{No,100,200}_SCALED_ResCorrnan90.1864.240.6058058894815523[[&nbsp0.66994382 &nbsp0.33005618]
 [&nbsp0.38836478 &nbsp0.61163522]]0.6296165566758483
WvD_logreg_balanced_shortECH_elo{No,100,200}_SCALED_ResCorrRESULT =&nbsp-0.11 +&nbsp-0.03*away_player_1_overall_rating +&nbsp0.02*home_defenders_score +&nbsp0.04*home_midfielders_score +&nbsp0.02*home_forwarders_score +&nbsp0.02*away_defenders_score +&nbsp-0.01*away_midfielders_score +&nbsp-0.02*away_forwarders_score +&nbsp0.06*Age_home +&nbsp-0.10*Age_away +&nbsp0.05*Away_odds +&nbsp0.07*Home_odds +&nbsp-0.15*Draw_odds +&nbsp0.20*elo_home_cat +&nbsp0.02*elo_away_cat +&nbsp-0.01*home_formation +&nbsp0.01*away_formation +&nbsp0.05*NoBonus +&nbsp-0.09*100Bonus +&nbsp-0.03*200Bonus +&nbsp0.05*VSPointDiff +&nbsp0.59*entropy63.7764.76-0.4536528408035454[[&nbsp0.66853933 &nbsp0.33146067]
 [&nbsp0.37578616 &nbsp0.62421384]]0.6342542588065866
WvD_xTrees_balanced_shortECH_elo{No,100,200}_SCALED_ResCorrnan85.6562.980.4240992843811091[[&nbsp0.66151685 &nbsp0.33848315]
 [&nbsp0.40566038 &nbsp0.59433962]]0.6212651786467942
WvL_RandomForest_balanced_shortECH_elo{No,100,200}_SCALED_ResCorrnan88.6475.070.5403250646205848[[&nbsp0.76214834 &nbsp0.23785166]
 [&nbsp0.26323988 &nbsp0.73676012]]0.7473222124670764
WvL_logreg_balanced_shortECH_elo{No,100,200}_SCALED_ResCorrRESULT =&nbsp0.11 +&nbsp-0.03*away_player_1_overall_rating +&nbsp0.01*home_defenders_score +&nbsp0.06*home_midfielders_score +&nbsp0.01*home_forwarders_score +&nbsp-0.00*away_defenders_score +&nbsp0.02*away_midfielders_score +&nbsp0.02*away_forwarders_score +&nbsp0.07*Age_home +&nbsp0.02*Age_away +&nbsp-0.04*Away_odds +&nbsp0.20*Home_odds +&nbsp-0.29*Draw_odds +&nbsp0.21*elo_home_cat +&nbsp-0.14*elo_away_cat +&nbsp0.26*home_formation +&nbsp-0.14*away_formation +&nbsp0.07*NoBonus +&nbsp-0.14*100Bonus +&nbsp0.21*200Bonus +&nbsp0.15*VSPointDiff +&nbsp1.12*entropy75.1374.37-0.0065459409751318365[[&nbsp0.74936061 &nbsp0.25063939]
 [&nbsp0.26323988 &nbsp0.73676012]]0.7474978050921861
WvL_xTrees_balanced_shortECH_elo{No,100,200}_SCALED_ResCorrnan83.9974.440.3517161736092371[[&nbsp0.7544757  &nbsp0.2455243 ]
 [&nbsp0.26791277 &nbsp0.73208723]]0.7394205443371378
LightGBM_shortECH_elo{No,100,200}_SCALED_ResCorrnan58.5656.33-0.2588646716144141Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.04	0.30
Draw 	0.40	0.04	0.56
Win 	0.18	0.02	0.800.5657067921052042
GradientBoosting_DUMMIES+ELO_NOTSCALEDnan59.2255.93-0.22333710335230528Pred 	Lose	Draw	Win
True 
Lose 	0.62	0.06	0.31
Draw 	0.35	0.08	0.56
Win 	0.17	0.04	0.790.5586341061801183
LightGBM_DUMMIES+ELO_NOTSCALEDnan57.9456.22-0.2769661702726747Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.04	0.31
Draw 	0.38	0.06	0.56
Win 	0.18	0.02	0.800.5644077783558116
RandomForest_DUMMIES+ELO_NOTSCALEDnan69.4255.70.06817807653222152Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.04	0.37
Draw 	0.35	0.04	0.61
Win 	0.16	0.02	0.820.5595721352307422
logreg_DUMMIES+ELO_NOTSCALEDRESULT =&nbsp-0.60 +&nbsp0.13*Age_away_(21.4,&nbsp24.2] +&nbsp0.14*Age_away_(24.2,&nbsp26.9] +&nbsp0.14*Age_away_(26.9,&nbsp29.7] +&nbsp0.09*Age_away_(29.7,&nbsp32.5] +&nbsp0.16*Age_away_(32.5,&nbsp35.3] +&nbsp0.49*home_forwarders_score_(48.9,&nbsp54.7] +&nbsp-0.79*home_forwarders_score_(54.7,&nbsp60.6] +&nbsp0.12*home_forwarders_score_(60.6,&nbsp66.4] +&nbsp-0.21*home_forwarders_score_(66.4,&nbsp72.3] +&nbsp-0.04*home_forwarders_score_(72.3,&nbsp78.1] +&nbsp-0.02*home_forwarders_score_(78.1,&nbsp84.0] +&nbsp-0.15*home_defenders_score_(58.4,&nbsp61.5] +&nbsp-0.11*home_defenders_score_(61.5,&nbsp64.6] +&nbsp-0.26*home_defenders_score_(64.6,&nbsp67.7] +&nbsp-0.20*home_defenders_score_(67.7,&nbsp70.8] +&nbsp-0.28*home_defenders_score_(70.8,&nbsp73.9] +&nbsp-0.31*home_defenders_score_(73.9,&nbsp77.0] +&nbsp-0.22*home_midfielders_score_(58.9,&nbsp62.4] +&nbsp0.08*home_midfielders_score_(62.4,&nbsp65.9] +&nbsp0.27*home_midfielders_score_(65.9,&nbsp69.4] +&nbsp0.30*home_midfielders_score_(69.4,&nbsp73.0] +&nbsp0.30*home_midfielders_score_(73.0,&nbsp76.5] +&nbsp0.20*home_midfielders_score_(76.5,&nbsp80.0] +&nbsp-0.03*away_player_1_overall_rating_(52.6,&nbsp58.1] +&nbsp0.02*away_player_1_overall_rating_(58.1,&nbsp63.7] +&nbsp-0.09*away_player_1_overall_rating_(63.7,&nbsp69.3] +&nbsp-0.08*away_player_1_overall_rating_(69.3,&nbsp74.9] +&nbsp-0.12*away_player_1_overall_rating_(74.9,&nbsp80.4] +&nbsp-0.06*away_player_1_overall_rating_(80.4,&nbsp86.0] +&nbsp-0.18*away_defenders_score_(58.0,&nbsp61.2] +&nbsp0.20*away_defenders_score_(61.2,&nbsp64.4] +&nbsp-0.29*away_defenders_score_(64.4,&nbsp67.6] +&nbsp-0.20*away_defenders_score_(67.6,&nbsp70.8] +&nbsp-0.21*away_defenders_score_(70.8,&nbsp74.0] +&nbsp-0.19*away_defenders_score_(74.0,&nbsp77.2] +&nbsp-0.39*away_midfielders_score_(59.5,&nbsp63.1] +&nbsp0.34*away_midfielders_score_(63.1,&nbsp66.6] +&nbsp0.10*away_midfielders_score_(66.6,&nbsp70.1] +&nbsp0.17*away_midfielders_score_(70.1,&nbsp73.7] +&nbsp0.18*away_midfielders_score_(73.7,&nbsp77.2] +&nbsp0.13*away_midfielders_score_(77.2,&nbsp80.8] +&nbsp-0.60*away_forwarders_score_(53.4,&nbsp58.9] +&nbsp0.01*away_forwarders_score_(58.9,&nbsp64.3] +&nbsp-0.01*away_forwarders_score_(64.3,&nbsp69.7] +&nbsp-0.03*away_forwarders_score_(69.7,&nbsp75.1] +&nbsp0.00*away_forwarders_score_(75.1,&nbsp80.6] +&nbsp0.01*away_forwarders_score_(80.6,&nbsp86.0] +&nbsp-0.14*elo_diff_(-553.4,&nbsp-332.9] +&nbsp-0.45*elo_diff_(-332.9,&nbsp-112.3] +&nbsp-0.36*elo_diff_(-112.3,&nbsp108.3] +&nbsp-0.34*elo_diff_(108.3,&nbsp328.9] +&nbsp-0.17*elo_diff_(328.9,&nbsp549.4] +&nbsp-0.20*elo_diff_(549.4,&nbsp770.0] +&nbsp-1.25*home_player_1_overall_rating_(52.6,&nbsp58.1] +&nbsp0.05*home_player_1_overall_rating_(58.1,&nbsp63.7] +&nbsp0.13*home_player_1_overall_rating_(63.7,&nbsp69.3] +&nbsp0.06*home_player_1_overall_rating_(69.3,&nbsp74.9] +&nbsp0.07*home_player_1_overall_rating_(74.9,&nbsp80.4] +&nbsp0.10*home_player_1_overall_rating_(80.4,&nbsp86.0] +&nbsp0.24*Age_home_(19.0,&nbsp21.8] +&nbsp0.05*Age_home_(21.8,&nbsp24.5] +&nbsp0.03*Age_home_(24.5,&nbsp27.2] +&nbsp-0.02*Age_home_(27.2,&nbsp29.9] +&nbsp0.03*Age_home_(29.9,&nbsp32.7] +&nbsp-0.09*Age_home_(32.7,&nbsp35.4] +&nbsp-0.00*VSPointDiff +&nbsp-0.07*entropy +&nbsp0.15*home_probs +&nbsp-1.46*draw_probs +&nbsp-0.19*away_probs56.2555.41-0.35545102639543197Pred 	Lose	Draw	Win
True 
Lose 	0.56	0.02	0.42
Draw 	0.31	0.02	0.67
Win 	0.14	0.01	0.850.5553138489082192
xTrees_DUMMIES+ELO_NOTSCALEDnan75.6153.620.2397370563530505Pred 	Lose	Draw	Win
True 
Lose 	0.49	0.03	0.48
Draw 	0.28	0.03	0.69
Win 	0.13	0.02	0.850.5404478876510634
GradientBoosting_shortECH_ELO{noBonus}_NOTSCALEDNA60.0656.48-0.200237429691Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.790.563613893224
LightGBM_shortECH_ELO{noBonus}_NOTSCALEDNA58.5656.33-0.258864671614Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.04	0.30
Draw 	0.40	0.04	0.56
Win 	0.18	0.02	0.800.564985239309
RandomForest_shortECH_ELO{noBonus}_NOTSCALEDNA75.9556.220.222310986749Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.04	0.32
Draw 	0.37	0.06	0.57
Win 	0.17	0.03	0.800.56159309234
logreg_shortECH_ELO{noBonus}_NOTSCALEDRESULT =&nbsp-1.15 +&nbsp0.03*away_player_1_overall_rating +&nbsp-0.03*home_defenders_score +&nbsp-0.03*home_midfielders_score +&nbsp-0.01*home_forwarders_score +&nbsp-0.00*away_defenders_score +&nbsp0.01*away_midfielders_score +&nbsp-0.02*away_forwarders_score +&nbsp0.02*Age_home +&nbsp0.04*Age_away +&nbsp-0.02*Away_odds +&nbsp-0.50*Draw_odds +&nbsp0.11*Home_odds +&nbsp0.13*elo_home_cat +&nbsp-0.05*elo_away_cat +&nbsp-0.07*home_formation +&nbsp0.04*away_formation +&nbsp0.02*NoBonus +&nbsp0.06*VSPointDiff +&nbsp-0.80*entropy55.9655.73-0.383008531815Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.41
Draw 	0.30	0.00	0.70
Win 	0.15	0.00	0.850.559211332795
xTrees_shortECH_ELO{noBonus}_NOTSCALEDNA74.0555.870.194348223897Pred 	Lose	Draw	Win
True 
Lose 	0.59	0.01	0.39
Draw 	0.33	0.02	0.66
Win 	0.15	0.01	0.840.560366124513
GradientBoosting_shortECH_ELO{100Bonus}_NOTSCALEDNA60.0656.54-0.200237429691Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.790.563613893224
LightGBM_shortECH_ELO{100Bonus}_NOTSCALEDNA58.5256.45-0.259945358101Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.04	0.30
Draw 	0.39	0.05	0.56
Win 	0.18	0.02	0.800.565201663487
RandomForest_shortECH_ELO{100Bonus}_NOTSCALEDNA76.1756.450.228660019861Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.05	0.32
Draw 	0.38	0.06	0.57
Win 	0.16	0.03	0.810.563108660456
logreg_shortECH_ELO{100Bonus}_NOTSCALEDRESULT =&nbsp-1.15 +&nbsp0.03*away_player_1_overall_rating +&nbsp-0.03*home_defenders_score +&nbsp-0.03*home_midfielders_score +&nbsp-0.01*home_forwarders_score +&nbsp-0.00*away_defenders_score +&nbsp0.01*away_midfielders_score +&nbsp-0.02*away_forwarders_score +&nbsp0.02*Age_home +&nbsp0.04*Age_away +&nbsp-0.02*Away_odds +&nbsp-0.51*Draw_odds +&nbsp0.11*Home_odds +&nbsp0.13*elo_home_cat +&nbsp-0.01*elo_away_cat +&nbsp-0.10*home_formation +&nbsp0.04*away_formation +&nbsp0.02*100Bonus +&nbsp0.00*VSPointDiff +&nbsp-0.80*entropy55.9755.73-0.382873446005Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.41
Draw 	0.30	0.00	0.70
Win 	0.14	0.00	0.850.559067032651
xTrees_shortECH_ELO{100Bonus}_NOTSCALEDNA74.3355.930.211233950257Pred 	Lose	Draw	Win
True 
Lose 	0.59	0.01	0.40
Draw 	0.33	0.02	0.66
Win 	0.15	0.00	0.850.560510528807
GradientBoosting_shortECH_ELO{200Bonus}_NOTSCALEDNA60.0656.51-0.200237429691Pred 	Lose	Draw	Win
True 
Lose 	0.63	0.06	0.31
Draw 	0.35	0.09	0.56
Win 	0.17	0.04	0.790.563469567042
LightGBM_shortECH_ELO{200Bonus}_NOTSCALEDNA58.5256.45-0.259945358101Pred 	Lose	Draw	Win
True 
Lose 	0.66	0.04	0.30
Draw 	0.39	0.05	0.56
Win 	0.18	0.02	0.800.564624410835
RandomForest_shortECH_ELO{200Bonus}_NOTSCALEDNA75.8856.590.219609270532Pred 	Lose	Draw	Win
True 
Lose 	0.64	0.04	0.32
Draw 	0.37	0.06	0.57
Win 	0.16	0.03	0.810.5610159178
logreg_shortECH_ELO{200Bonus}_NOTSCALEDRESULT =&nbsp-1.15 +&nbsp0.03*away_player_1_overall_rating +&nbsp-0.03*home_defenders_score +&nbsp-0.03*home_midfielders_score +&nbsp-0.01*home_forwarders_score +&nbsp-0.00*away_defenders_score +&nbsp0.01*away_midfielders_score +&nbsp-0.02*away_forwarders_score +&nbsp0.02*Age_home +&nbsp0.04*Age_away +&nbsp-0.02*Away_odds +&nbsp-0.52*Draw_odds +&nbsp0.10*Home_odds +&nbsp0.13*elo_home_cat +&nbsp0.01*elo_away_cat +&nbsp-0.13*home_formation +&nbsp0.04*away_formation +&nbsp0.02*200Bonus +&nbsp-0.03*VSPointDiff +&nbsp-0.80*entropy55.9755.73-0.382468188572Pred 	Lose	Draw	Win
True 
Lose 	0.58	0.00	0.41
Draw 	0.30	0.00	0.70
Win 	0.14	0.00	0.850.559572239381
xTrees_shortECH_ELO{200Bonus}_NOTSCALEDNA74.0355.990.196104339438Pred 	Lose	Draw	Win
True 
Lose 	0.60	0.01	0.39
Draw 	0.33	0.02	0.65
Win 	0.15	0.01	0.840.561736975883

















In [202]:



    


df = pd.DataFrame(super_table[1:], columns=super_table[0])
df.to_csv(r'C:/Users/ernest.chocholowski/Desktop/GIT/SoccerAnalysis/out/results_table.csv', 
                      index=False)



    











In [ ]:



    






    











In [ ]:



    






    











In [ ]:



    






    











In [ ]:

Content source: jo9k/SoccerAnalysis

Similar notebooks:

notebook.community | gallery | about