from sklearn import linear_model

import pandas as pd

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

train.Age = train.Age.fillna(train.Age.mean())

for i, sex in enumerate(train.Sex):
    if sex=='male':
        train.Sex[i]=1
    else:
        train.Sex[i]=0

logiReg = linear_model.LogisticRegression()

y = train['Survived']
print type(y)

X = train[['Age', 'Sex']]
print type(X)

logiReg.fit(X, y)

print logiReg.coef_ # 回帰係数
print logiReg.intercept_ # 切片
print logiReg.score(X, y) # 決定係数

py = logiReg.predict(X) # 当てはめ

table = pd.crosstab(y, py)
table

(468+233)/(468+233+81+109.0)