In [ ]:

    

import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt
%matplotlib inline


    

In [ ]:

    




    

In [ ]:

    

filename= "../data/kobe/kobe_bryant_shot_data.csv.gz"
df = pd.read_csv(filename, na_values={'shot_made_flag': ''})
df = df.dropna()
df = df.drop([u'game_event_id', u'game_id', 'combined_shot_type',
       u'lat', u'lon', u'team_id', u'team_name', u'game_date',
        u'shot_id'], axis=1)

df = df.drop(['loc_x', 'loc_y', 'shot_type','shot_zone_basic', 'shot_zone_range'], axis=1)


    

In [ ]:

    

df['home'] = df.matchup.apply(lambda matchup: 0 if '@' in matchup else 1)
df = df.drop(['matchup'], axis=1)

df['time_remaining'] = 60 * df['minutes_remaining'] + df['seconds_remaining']
df = df.drop(['minutes_remaining', 'seconds_remaining'], axis=1)

cols = df.columns.tolist()
cols.remove('shot_made_flag')
cols.append('shot_made_flag')

df = df[cols]


    

In [ ]:

    

filename= "../data/kobe/kobe_bryant_shot_data_refined.csv"
df.to_csv(filename, index=False)


    

In [ ]:

    




    

In [ ]:

    

filename= "../data/kobe/kobe_bryant_shot_data_refined.csv"
df = pd.read_csv(filename)


    

In [ ]:

    




    

In [ ]:

    

df


    

In [ ]:

    




    

In [ ]:

    

original_df = df.copy()


    

In [ ]:

    




    

In [ ]:

    

# turn categorical variables into dummy variables
categorical_vars = ['season', 'period', 'shot_zone_area', 'opponent', 'action_type']
for var in categorical_vars:
    df = pd.concat([df, pd.get_dummies(df[var], prefix=var)], 1)
    df = df.drop(var, 1)


    

In [ ]:

    




    

In [ ]:

    

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix, log_loss
from sklearn.cross_validation import train_test_split


    

In [ ]:

    

X_train, X_test, y_train, y_test = train_test_split(df.drop('shot_made_flag', axis=1), 
                                                    df['shot_made_flag'], 
                                                    test_size=0.33, 
                                                    random_state=42)


    

In [ ]:

    




    

In [ ]:

    

model = RandomForestClassifier(n_estimators=45, max_depth=14, criterion='entropy', random_state=42, n_jobs=-1)


    

In [ ]:

    

model.fit(X_train, y_train)


    

In [ ]:

    

y_pred = model.predict(X_test)


    

In [ ]:

    

y_pred_proba = model.predict_proba(X_test)


    

In [ ]:

    

confusion_matrix(y_test, y_pred), log_loss(y_test, y_pred_proba[:,1])


    

In [ ]:

    




    

In [ ]:

    

pd.DataFrame({'feature': X_train.columns, 
              'importance': model.feature_importances_}).sort_values('importance', ascending=False).head()


    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    

pred_df = original_df.join(pd.DataFrame(y_pred, columns=['shot_made_pred'], index=X_test.index))


    

In [ ]:

    

pred_df = pred_df[~pred_df.shot_made_pred.isnull()]


    

In [ ]:

    

pred_df.head()


    

In [ ]:

    




    

In [ ]:

    

pred_df[(pred_df.shot_made_flag != pred_df.shot_made_pred)]


    

In [ ]:

    

# http://scikit-learn.org/stable/modules/ensemble.html#forests-of-randomized-trees


    

In [ ]:

    

# http://scikit-learn.org/stable/auto_examples/classification/plot_classifier_comparison.html


    

In [ ]:

    

# http://scikit-learn.org/stable/tutorial/statistical_inference/supervised_learning.html


    

In [ ]:

    

# http://scikit-learn.org/stable/auto_examples/svm/plot_iris.html#example-svm-plot-iris-py


    

In [ ]: