In [2]:

    

import pandas as pd
import numpy as np
import re
import sklearn
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

import plotly.offline as py
import plotly.graph_objs as go
import plotly.tools as tls

# Going to use these 5 base models for the stacking
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier, ExtraTreesClassifier
from sklearn.svm import SVC
from sklearn.cross_validation import KFold;


    

    




C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:44: DeprecationWarning:

This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.

In [18]:

    

train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')

# Store our passenger ID for easy access
PassengerId = test['PassengerI9d']
train.head(3)


    

    
Out[18]:






  

    

      

      
PassengerId
      
Survived
      
Pclass
      
Name
      
Sex
      
Age
      
SibSp
      
Parch
      
Ticket
      
Fare
      
Cabin
      
Embarked
    
  
  

    

      
0
      
1
      
0
      
3
      
Braund, Mr. Owen Harris
      
male
      
22.0
      
1
      
0
      
A/5 21171
      
7.2500
      
NaN
      
S
    
    

      
1
      
2
      
1
      
1
      
Cumings, Mrs. John Bradley (Florence Briggs Th...
      
female
      
38.0
      
1
      
0
      
PC 17599
      
71.2833
      
C85
      
C
    
    

      
2
      
3
      
1
      
3
      
Heikkinen, Miss. Laina
      
female
      
26.0
      
0
      
0
      
STON/O2. 3101282
      
7.9250
      
NaN
      
S
    
  

In [19]:

    

full_data = [train, test]

# Some features of my own that I have added in
# Gives the length of the name
train['Name_length'] = train['Name'].apply(len)
test['Name_length'] = test['Name'].apply(len)
# Feature that tells whether a passenger had a cabin on the Titanic
train['Has_Cabin'] = train["Cabin"].apply(lambda x: 0 if type(x) == float else 1)
test['Has_Cabin'] = test["Cabin"].apply(lambda x: 0 if type(x) == float else 1)

# Feature engineering steps taken from Sina
# Create new feature FamilySize as a combination of SibSp and Parch
for dataset in full_data:
    dataset['FamilySize'] = dataset['SibSp'] + dataset['Parch'] + 1
# Create new feature IsAlone from FamilySize
for dataset in full_data:
    dataset['IsAlone'] = 0
    dataset.loc[dataset['FamilySize'] == 1, 'IsAlone'] = 1
# Remove all NULLS in the Embarked column
for dataset in full_data:
    dataset['Embarked'] = dataset['Embarked'].fillna('S')
# Remove all NULLS in the Fare column and create a new feature CategoricalFare
for dataset in full_data:
    dataset['Fare'] = dataset['Fare'].fillna(train['Fare'].median())
train['CategoricalFare'] = pd.qcut(train['Fare'], 4)
# Create a New feature CategoricalAge
for dataset in full_data:
    age_avg = dataset['Age'].mean()
    age_std = dataset['Age'].std()
    age_null_count = dataset['Age'].isnull().sum()
    age_null_random_list = np.random.randint(age_avg - age_std, age_avg + age_std, size=age_null_count)
    dataset['Age'][np.isnan(dataset['Age'])] = age_null_random_list
    dataset['Age'] = dataset['Age'].astype(int)
train['CategoricalAge'] = pd.cut(train['Age'], 5)
# Define function to extract titles from passenger names
def get_title(name):
    title_search = re.search(' ([A-Za-z]+)\.', name)
    # If the title exists, extract and return it.
    if title_search:
        return title_search.group(1)
    return ""
# Create a new feature Title, containing the titles of passenger names
for dataset in full_data:
    dataset['Title'] = dataset['Name'].apply(get_title)
# Group all non-common titles into one single grouping "Rare"
for dataset in full_data:
    dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col','Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')

    dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')

for dataset in full_data:
    # Mapping Sex
    dataset['Sex'] = dataset['Sex'].map( {'female': 0, 'male': 1} ).astype(int)
    
    # Mapping titles
    title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Rare": 5}
    dataset['Title'] = dataset['Title'].map(title_mapping)
    dataset['Title'] = dataset['Title'].fillna(0)
    
    # Mapping Embarked
    dataset['Embarked'] = dataset['Embarked'].map( {'S': 0, 'C': 1, 'Q': 2} ).astype(int)
    
    # Mapping Fare
    dataset.loc[ dataset['Fare'] <= 7.91, 'Fare']                              = 0
    dataset.loc[(dataset['Fare'] > 7.91) & (dataset['Fare'] <= 14.454), 'Fare'] = 1
    dataset.loc[(dataset['Fare'] > 14.454) & (dataset['Fare'] <= 31), 'Fare']   = 2
    dataset.loc[ dataset['Fare'] > 31, 'Fare']                                  = 3
    dataset['Fare'] = dataset['Fare'].astype(int)
    
    # Mapping Age
    dataset.loc[ dataset['Age'] <= 16, 'Age']                          = 0
    dataset.loc[(dataset['Age'] > 16) & (dataset['Age'] <= 32), 'Age'] = 1
    dataset.loc[(dataset['Age'] > 32) & (dataset['Age'] <= 48), 'Age'] = 2
    dataset.loc[(dataset['Age'] > 48) & (dataset['Age'] <= 64), 'Age'] = 3
    dataset.loc[ dataset['Age'] > 64, 'Age']                           = 4


    

    




C:\Anaconda3\lib\site-packages\ipykernel\__main__.py:32: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy

In [20]:

    

# Feature selection
drop_elements = ['PassengerId', 'Name', 'Ticket', 'Cabin', 'SibSp']
train = train.drop(drop_elements, axis = 1)
train = train.drop(['CategoricalAge', 'CategoricalFare'], axis = 1)
test  = test.drop(drop_elements, axis = 1)
train.head()


    

    
Out[20]:






  

    

      

      
Survived
      
Pclass
      
Sex
      
Age
      
Parch
      
Fare
      
Embarked
      
Name_length
      
Has_Cabin
      
FamilySize
      
IsAlone
      
Title
    
  
  

    

      
0
      
0
      
3
      
1
      
1
      
0
      
0
      
0
      
23
      
0
      
2
      
0
      
1
    
    

      
1
      
1
      
1
      
0
      
2
      
0
      
3
      
1
      
51
      
1
      
2
      
0
      
3
    
    

      
2
      
1
      
3
      
0
      
1
      
0
      
1
      
0
      
22
      
0
      
1
      
1
      
2
    
    

      
3
      
1
      
1
      
0
      
2
      
0
      
3
      
0
      
44
      
1
      
2
      
0
      
3
    
    

      
4
      
0
      
3
      
1
      
2
      
0
      
1
      
0
      
24
      
0
      
1
      
1
      
1
    
  

In [21]:

    

colormap = plt.cm.viridis
plt.figure(figsize=(12,12))
plt.title('Pearson Correlation of Features', y=1.05, size=15)
sns.heatmap(train.astype(float).corr(),linewidths=0.1,vmax=1.0, square=True, cmap=colormap, linecolor='white', annot=True)


    

    
Out[21]:





<matplotlib.axes._subplots.AxesSubplot at 0x1773f81a0f0>






    

In [22]:

    

# Some useful parameters which will come in handy later on
ntrain = train.shape[0]
ntest = test.shape[0]
SEED = 0 # for reproducibility
NFOLDS = 5 # set folds for out-of-fold prediction
kf = KFold(ntrain, n_folds= NFOLDS, random_state=SEED)

# Class to extend the Sklearn classifier
class SklearnHelper(object):
    def __init__(self, clf, seed=0, params=None):
        params['random_state'] = seed
        self.clf = clf(**params)

    def train(self, x_train, y_train):
        self.clf.fit(x_train, y_train)

    def predict(self, x):
        return self.clf.predict(x)
    
    def fit(self,x,y):
        return self.clf.fit(x,y)
    
    def feature_importances(self,x,y):
        print(self.clf.fit(x,y).feature_importances_)


    

In [23]:

    

def get_oof(clf, x_train, y_train, x_test):
    oof_train = np.zeros((ntrain,))
    oof_test = np.zeros((ntest,))
    oof_test_skf = np.empty((NFOLDS, ntest))

    for i, (train_index, test_index) in enumerate(kf):
        x_tr = x_train[train_index]
        y_tr = y_train[train_index]
        x_te = x_train[test_index]

        clf.train(x_tr, y_tr)

        oof_train[test_index] = clf.predict(x_te)
        oof_test_skf[i, :] = clf.predict(x_test)

    oof_test[:] = oof_test_skf.mean(axis=0)
    return oof_train.reshape(-1, 1), oof_test.reshape(-1, 1)


    

In [24]:

    

# Put in our parameters for said classifiers
# Random Forest parameters
rf_params = {
    'n_jobs': -1,
    'n_estimators': 500,
    'max_depth': 6,
    'min_samples_leaf': 2
}

# Extra Trees Parameters
et_params = {
    'n_jobs': -1,
    'n_estimators':500,
    #'max_features': 0.5,
    'max_depth': 8,
    'min_samples_leaf': 2,
    'verbose': 0
}

# AdaBoost parameters
ada_params = {
    'n_estimators': 500,
    'learning_rate' : 0.75
}

# Gradient Boosting parameters
gb_params = {
    'n_estimators': 500,
     #'max_features': 0.2,
    'max_depth': 5,
    'min_samples_leaf': 2,
    'verbose': 0
}

# Support Vector Classifier parameters 
svc_params = {
    'kernel' : 'linear',
    'C' : 0.025
    }


    

In [25]:

    

# Create 5 objects that represent our 4 models
rf = SklearnHelper(clf=RandomForestClassifier, seed=SEED, params=rf_params)
et = SklearnHelper(clf=ExtraTreesClassifier, seed=SEED, params=et_params)
ada = SklearnHelper(clf=AdaBoostClassifier, seed=SEED, params=ada_params)
gb = SklearnHelper(clf=GradientBoostingClassifier, seed=SEED, params=gb_params)
svc = SklearnHelper(clf=SVC, seed=SEED, params=svc_params)


    

In [26]:

    

# Create Numpy arrays of train, test and target ( Survived) dataframes to feed into our models
y_train = train['Survived'].ravel()
train = train.drop(['Survived'], axis=1)
x_train = train.values # Creates an array of the train data
x_test = test.values # Creats an array of the test data


    

In [27]:

    

# Create our OOF train and test predictions. These base results will be used as new features
et_oof_train, et_oof_test = get_oof(et, x_train, y_train, x_test) # Extra Trees
rf_oof_train, rf_oof_test = get_oof(rf,x_train, y_train, x_test) # Random Forest
ada_oof_train, ada_oof_test = get_oof(ada, x_train, y_train, x_test) # AdaBoost 
gb_oof_train, gb_oof_test = get_oof(gb,x_train, y_train, x_test) # Gradient Boost
svc_oof_train, svc_oof_test = get_oof(svc,x_train, y_train, x_test) # Support Vector Classifier

print("Training is complete")


    

    




C:\Anaconda3\lib\site-packages\sklearn\ensemble\forest.py:303: UserWarning:

Warm-start fitting without increasing n_estimators does not fit new trees.







    




Training is complete

In [30]:

    

rf_feature = rf.feature_importances(x_train,y_train)
et_feature = et.feature_importances(x_train, y_train)
ada_feature = ada.feature_importances(x_train, y_train)
gb_feature = gb.feature_importances(x_train,y_train)

print (rf_feature))


    

    




C:\Anaconda3\lib\site-packages\sklearn\ensemble\forest.py:303: UserWarning:

Warm-start fitting without increasing n_estimators does not fit new trees.







    




[ 0.12571126  0.19620988  0.02976163  0.02108849  0.07284272  0.02378681
  0.10872678  0.06487385  0.06693961  0.01328297  0.27677599]
[ 0.12227166  0.38436894  0.02726436  0.01665971  0.0563797   0.0281978
  0.04552098  0.08261217  0.04514454  0.02177524  0.16980489]
[ 0.03   0.01   0.014  0.062  0.038  0.01   0.696  0.014  0.05   0.006
  0.07 ]
[ 0.07467712  0.0510268   0.10219574  0.02616493  0.10777263  0.04179089
  0.3866584   0.01943511  0.07084637  0.0229215   0.09651051]
<class 'NoneType'>

In [32]:

    

rf_features = [ 0.12571126 , 0.19620988 , 0.02976163 , 0.02108849 , 0.07284272 , 0.02378681,
  0.10872678 , 0.06487385 , 0.06693961 , 0.01328297 , 0.27677599]
et_features = [ 0.12227166 , 0.38436894 , 0.02726436 , 0.01665971 , 0.0563797 ,  0.0281978,
  0.04552098 , 0.08261217 , 0.04514454 , 0.02177524 , 0.16980489]
ada_features = [ 0.03  , 0.01  , 0.014,  0.062 , 0.038 , 0.01 ,  0.696 , 0.014 , 0.05  , 0.006,
  0.07 ]
gb_features = [ 0.07467712 , 0.0510268  , 0.10219574  ,0.02616493 , 0.10777263  ,0.04179089,
  0.3866584 ,  0.01943511 , 0.07084637 , 0.0229215 ,  0.09651051]


    

In [33]:

    

cols = train.columns.values
# Create a dataframe with features
feature_dataframe = pd.DataFrame( {'features': cols,
     'Random Forest feature importances': rf_features,
     'Extra Trees  feature importances': et_features,
      'AdaBoost feature importances': ada_features,
    'Gradient Boost feature importances': gb_features
    })


    

In [36]:

    

# Scatter plot 
py.init_notebook_mode()
trace = go.Scatter(
    y = feature_dataframe['Random Forest feature importances'].values,
    x = feature_dataframe['features'].values,
    mode='markers',
    marker=dict(
        sizemode = 'diameter',
        sizeref = 1,
        size = 25,
#       size= feature_dataframe['AdaBoost feature importances'].values,
        #color = np.random.randn(500), #set color equal to a variable
        color = feature_dataframe['Random Forest feature importances'].values,
        colorscale='Portland',
        showscale=True
    ),
    text = feature_dataframe['features'].values
)
data = [trace]

layout= go.Layout(
    autosize= True,
    title= 'Random Forest Feature Importance',
    hovermode= 'closest',
#     xaxis= dict(
#         title= 'Pop',
#         ticklen= 5,
#         zeroline= False,
#         gridwidth= 2,
#     ),
    yaxis=dict(
        title= 'Feature Importance',
        ticklen= 5,
        gridwidth= 2
    ),
    showlegend= False
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig,filename='scatter2010')

# Scatter plot 
trace = go.Scatter(
    y = feature_dataframe['Extra Trees  feature importances'].values,
    x = feature_dataframe['features'].values,
    mode='markers',
    marker=dict(
        sizemode = 'diameter',
        sizeref = 1,
        size = 25,
#       size= feature_dataframe['AdaBoost feature importances'].values,
        #color = np.random.randn(500), #set color equal to a variable
        color = feature_dataframe['Extra Trees  feature importances'].values,
        colorscale='Portland',
        showscale=True
    ),
    text = feature_dataframe['features'].values
)
data = [trace]

layout= go.Layout(
    autosize= True,
    title= 'Extra Trees Feature Importance',
    hovermode= 'closest',
#     xaxis= dict(
#         title= 'Pop',
#         ticklen= 5,
#         zeroline= False,
#         gridwidth= 2,
#     ),
    yaxis=dict(
        title= 'Feature Importance',
        ticklen= 5,
        gridwidth= 2
    ),
    showlegend= False
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig,filename='scatter2010')

# Scatter plot 
trace = go.Scatter(
    y = feature_dataframe['AdaBoost feature importances'].values,
    x = feature_dataframe['features'].values,
    mode='markers',
    marker=dict(
        sizemode = 'diameter',
        sizeref = 1,
        size = 25,
#       size= feature_dataframe['AdaBoost feature importances'].values,
        #color = np.random.randn(500), #set color equal to a variable
        color = feature_dataframe['AdaBoost feature importances'].values,
        colorscale='Portland',
        showscale=True
    ),
    text = feature_dataframe['features'].values
)
data = [trace]

layout= go.Layout(
    autosize= True,
    title= 'AdaBoost Feature Importance',
    hovermode= 'closest',
#     xaxis= dict(
#         title= 'Pop',
#         ticklen= 5,
#         zeroline= False,
#         gridwidth= 2,
#     ),
    yaxis=dict(
        title= 'Feature Importance',
        ticklen= 5,
        gridwidth= 2
    ),
    showlegend= False
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig,filename='scatter2010')

# Scatter plot 
trace = go.Scatter(
    y = feature_dataframe['Gradient Boost feature importances'].values,
    x = feature_dataframe['features'].values,
    mode='markers',
    marker=dict(
        sizemode = 'diameter',
        sizeref = 1,
        size = 25,
#       size= feature_dataframe['AdaBoost feature importances'].values,
        #color = np.random.randn(500), #set color equal to a variable
        color = feature_dataframe['Gradient Boost feature importances'].values,
        colorscale='Portland',
        showscale=True
    ),
    text = feature_dataframe['features'].values
)
data = [trace]

layout= go.Layout(
    autosize= True,
    title= 'Gradient Boosting Feature Importance',
    hovermode= 'closest',
#     xaxis= dict(
#         title= 'Pop',
#         ticklen= 5,
#         zeroline= False,
#         gridwidth= 2,
#     ),
    yaxis=dict(
        title= 'Feature Importance',
        ticklen= 5,
        gridwidth= 2
    ),
    showlegend= False
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig,filename='scatter2010')


    

In [37]:

    

base_predictions_train = pd.DataFrame( {'RandomForest': rf_oof_train.ravel(),
     'ExtraTrees': et_oof_train.ravel(),
     'AdaBoost': ada_oof_train.ravel(),
      'GradientBoost': gb_oof_train.ravel()
    })
base_predictions_train.head()


    

    
Out[37]:






  

    

      

      
AdaBoost
      
ExtraTrees
      
GradientBoost
      
RandomForest
    
  
  

    

      
0
      
0.0
      
0.0
      
0.0
      
0.0
    
    

      
1
      
1.0
      
1.0
      
1.0
      
1.0
    
    

      
2
      
1.0
      
0.0
      
1.0
      
0.0
    
    

      
3
      
1.0
      
1.0
      
1.0
      
1.0
    
    

      
4
      
0.0
      
0.0
      
0.0
      
0.0
    
  

In [38]:

    

data = [
    go.Heatmap(
        z= base_predictions_train.astype(float).corr().values ,
        x=base_predictions_train.columns.values,
        y= base_predictions_train.columns.values,
          colorscale='Portland',
            showscale=True,
            reversescale = True
    )
]
py.iplot(data, filename='labelled-heatmap')


    

In [39]:

    

x_train = np.concatenate(( et_oof_train, rf_oof_train, ada_oof_train, gb_oof_train, svc_oof_train), axis=1)
x_test = np.concatenate(( et_oof_test, rf_oof_test, ada_oof_test, gb_oof_test, svc_oof_test), axis=1)


    

In [ ]: