In [1]:

    

import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn import svm
import matplotlib.pyplot as plt
from sklearn.cross_validation import KFold
import sys
train_path = "data/titanic_survive_prediction_train.csv"
test_path = "data/titanic_survive_prediction_test.csv"
train_data = pd.read_csv(train_path,delimiter=',')
test_data = pd.read_csv(test_path,delimiter=',')


    

    




/home/hackpython/anaconda3/lib/python3.5/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.
  "This module will be removed in 0.20.", DeprecationWarning)

In [2]:

    

train_data['Sex'].replace(['male','female'],['0','1'],inplace=True)
train_data['Age'].fillna((train_data['Age'].mean()),inplace=True)
data = np.array(train_data.iloc[:,4:6])
label = np.array(train_data.iloc[:,1:2])


    

In [3]:

    

kf = KFold(n=len(data),n_folds=5,shuffle=True)
for train_index,test_index in kf:
    X_train, X_test = data[train_index], data[test_index]
    y_train, y_test = label[train_index], label[test_index]
    clf = svm.SVC(kernel='linear',gamma=2)
    clf.fit(X_train,y_train)
    accuracy=clf.score(X_test,y_test)
    print(accuracy)


    

    




/home/hackpython/anaconda3/lib/python3.5/site-packages/sklearn/utils/validation.py:526: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)






    




0.798882681564
0.775280898876
0.825842696629
0.780898876404
0.752808988764

In [4]:

    

test_data['Sex'].replace(['male','female'],[ '0','1'],inplace=True)
test_data['Age'].fillna((test_data['Age'].mean()),inplace=True)
t_data = np.array(test_data.iloc[:,3:5])


    

In [5]:

    

clf.predict(t_data)


    

    
Out[5]:





array([0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1,
       0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0,
       0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0,
       1, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0,
       1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,
       0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,
       1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1,
       0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0,
       1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1,
       0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0,
       0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0,
       0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1,
       0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0,
       0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0,
       0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,
       1, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1,
       1, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0,
       1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0,
       1, 0, 0, 0])