PassengerId,Survived,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked
1,0,3,"Braund, Mr. Owen Harris",male,22,1,0,A/5 21171,7.25,,S
2,1,1,"Cumings, Mrs. John Bradley (Florence Briggs Thayer)",female,38,1,0,PC 17599,71.2833,C85,C
3,1,3,"Heikkinen, Miss. Laina",female,26,0,0,STON/O2. 3101282,7.925,,S
4,1,1,"Futrelle, Mrs. Jacques Heath (Lily May Peel)",female,35,1,0,113803,53.1,C123,S
5,0,3,"Allen, Mr. William Henry",male,35,0,0,373450,8.05,,S
6,0,3,"Moran, Mr. James",male,,0,0,330877,8.4583,,Q
7,0,1,"McCarthy, Mr. Timothy J",male,54,0,0,17463,51.8625,E46,S
8,0,3,"Palsson, Master. Gosta Leonard",male,2,3,1,349909,21.075,,S
9,1,3,"Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)",female,27,0,2,347742,11.1333,,S
10,1,2,"Nasser, Mrs. Nicholas (Adele Achem)",female,14,1,0,237736,30.0708,,C
11,1,3,"Sandstrom, Miss. Marguerite Rut",female,4,1,1,PP 9549,16.7,G6,S
12,1,1,"Bonnell, Miss. Elizabeth",female,58,0,0,113783,26.55,C103,S
13,0,3,"Saundercock, Mr. William Henry",male,20,0,0,A/5. 2151,8.05,,S
14,0,3,"Andersson, Mr. Anders Johan",male,39,1,5,347082,31.275,,S
15,0,3,"Vestrom, Miss. Hulda Amanda Adolfina",female,14,0,0,350406,7.8542,,S
16,1,2,"Hewlett, Mrs. (Mary D Kingcome) ",female,55,0,0,248706,16,,S
17,0,3,"Rice, Master. Eugene",male,2,4,1,382652,29.125,,Q
18,1,2,"Williams, Mr. Charles Eugene",male,,0,0,244373,13,,S

import pandas #ipython notebook
titanic = pandas.read_csv("titanic_train.csv")
# titanic.head(5)
print (titanic.describe())

titanic["Age"] = titanic["Age"].fillna(titanic["Age"].median())
print (titanic.describe())

print titanic["Sex"].unique() # ['male' 'female']

# Replace all the occurences of male with the number 0. 
titanic.loc[titanic["Sex"] == "male", "Sex"] = 0
titanic.loc[titanic["Sex"] == "female", "Sex"] = 1

print( titanic["Embarked"].unique()) # ['S' 'C' 'Q' nan]
titanic["Embarked"] = titanic["Embarked"].fillna('S')
titanic.loc[titanic["Embarked"] == "S", "Embarked"] = 0
titanic.loc[titanic["Embarked"] == "C", "Embarked"] = 1
titanic.loc[titanic["Embarked"] == "Q", "Embarked"] = 2

from sklearn.linear_model import LinearRegression
from sklearn.model_selection import KFold

from sklearn.linear_model import LinearRegression
from sklearn.model_selection import KFold

# 预备选择的特征
predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]

# 线性回归模型实例化
alg = LinearRegression()
# 交叉验证实例化, 划分三份, 随机打乱种子为 0 
kf = KFold(n_splits=3, shuffle=False, random_state=0)

predictions = []

# 交叉验证划分训练集测试集, 对每一份进行循环
for train, test in kf.split(titanic):
    # 拿到训练数据 (仅特征值列)
    train_predictors = (titanic[predictors].iloc[train,:])
    # 拿到训练数据的目标 (仅目标值列)
    train_target = titanic["Survived"].iloc[train]
    # 训练线性回归
    alg.fit(train_predictors, train_target)
    # 在测试集上进行预测
    test_predictions = alg.predict(titanic[predictors].iloc[test,:])
    predictions.append(test_predictions)

import numpy as np

predictions = np.concatenate(predictions, axis=0)

predictions[predictions > .5] = 1
predictions[predictions <=.5] = 0
accuracy = sum(predictions==titanic['Survived'])/len(predictions)
print(accuracy)  # 0.7833894500561167

from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression

# 实例化, 指定 solver 避免警告提示
alg = LogisticRegression(solver="liblinear",random_state=1)

scores = cross_val_score(alg, titanic[predictors], titanic["Survived"], cv=3)

print(scores.mean())

0.7878787878787877