from sklearn.ensemble import RandomForestRegressor

### 使用 RandomForestClassifier 填补缺失的年龄属性

def set_missing_ages(df):

    # 把已有的数值型特征取出来丢进Random Forest Regressor中

    age_df = df[['Age','Fare', 'Parch', 'SibSp', 'Pclass']]

    # 乘客分成已知年龄和未知年龄两部分

    known_age = age_df[age_df.Age.notnull()].as_matrix()

    unknown_age = age_df[age_df.Age.isnull()].as_matrix()

    # y即目标年龄

    y = known_age[:, 0]

    # X即特征属性值

    X = known_age[:, 1:]

    # fit到RandomForestRegressor之中

    rfr = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs=-1)

    rfr.fit(X, y)

    # 用得到的模型进行未知年龄结果预测

    predictedAges = rfr.predict(unknown_age[:, 1::])

    # 用得到的预测结果填补原缺失数据

    df.loc[ (df.Age.isnull()), 'Age' ] = predictedAges 

    return df, rfr

def set_Cabin_type(df):

    df.loc[ (df.Cabin.notnull()), 'Cabin' ] = "Yes"

    df.loc[ (df.Cabin.isnull()), 'Cabin' ] = "No"

    return df

data_train, rfr = set_missing_ages(data_train)

data_train = set_Cabin_type(data_train)

import numpy as np

from sklearn.feature_selection import SelectKBest,f_classif

import matplotlib.pyplot as plt

predictors = ["Pclass","Sex","Age","SibSp","Parch","Fare","Embarked","FamilySize","Title","NameLength"]  

#Perform feature selection

selector=SelectKBest(f_classif,k=5)

selector.fit(titanic[predictors],titanic["Survived"])  

#Plot the raw p-values for each feature,and transform from p-values into scores

scores=-np.log10(selector.pvalues_)  

#Plot the scores.   See how "Pclass","Sex","Title",and "Fare" are the best?

plt.bar(range(len(predictors)).scores)

plt.xticks(range(len(predictors)).predictors,rotation='vertical')

plt.show()  

#Pick only the four best features.

predictors=["Pclass","Sex","Fare","Title"]  

alg=RandomForestClassifier(random_state=1,n_estimators=50,min_samples_split=8,min_samples_leaf=4)  

//集成多种算法求平均的方法来进行机器学习求解

from sklearn.ensemble import GradientBoostingClassifier

import numpy as  np  

#The algorithms we want to ensemble.

#We're using the more linear predictors for the logistic regression,and everything with the gradient boosting classifier

algorithms=[

    [GradientBoostingClassifier(random_state=1,n_estimators=25,max_depth=3, ["Pclass","Sex","Age","Fare","FamilySize","Title","Age","Embarked"]]

    [LogisticRegression(random_state=1),["Pclass","Sex","Fare","FamilySize","Title","Age","Embarked"]]

]  

#Initialize the cross validation folds

kf=KFold(titanic.shape[0],n_folds=3,random_state=1)  

predictions=[]

for train,test in kf:

    train_target=titanic["Survived"].iloc[train]

    full_test_predictions=[]

    #Make predictions for each algorithm on each fold

    for alg,predictors in algorithms:

        #Fit the algorithm on the training data

        alg.fit(titanic[predictors].iloc[train,:],train_targegt)

        #Select and predict on the test fold

        #The .astype(float) is necessary to convert the dataframe to all floats and sklearn error.

        test_predictions=alg.predict_proba(titanic[predictors].iloc[test,:].astype(float))[:,1]

    #Use a simple ensembling scheme -- just  average the predictions to get the final classification.

    test_predictions=(full_test_predictions[0]+full_test_predictions[1])/2

    #Any value over .5 is assumed to be a 1 prediction,and below .5 is a 0 prediction.

    test_predictions[test_predictions<=0.5]=0

    test_predictions[test_predictions>0.5]=1

    predictions.append(test_predictions)  

#Put all the predictions together into one array.

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

#Compute accuracy by comparing to the training data

accuracy=sum(predictions[predictions==titanic["Survived"]])/len(predictions)

print(accuracy)  

#The gradient boosting classifier generates better predictions,so we weight it higher

predictions=(full_predictions[0]*3+full_predictions[1]*1)/4

predictions