python程式碼:

#-*- coding: UTF-8 -*-
"""
Created on Mon Mar 27 20:26:43 2017

@author: Administrator
"""
#!/usr/bin/python
#-*- coding: UTF-8 -*-
import pandas
titanic = pandas.read_csv('D:\python_code\study\\titanic\Kaggle_Titanic\data\\train.csv')
#print titanic.describe()
print titanic.head()
titanic['Age'] = titanic['Age'].fillna(titanic['Age'].median())#對缺失值用平均值填充
#print titanic.describe()
print titanic['Sex'].unique()
titanic.loc[titanic['Sex'] == 'male','Sex'] = 0 #loc定位到哪一行，將titanic['Sex'] == 'male'的樣本Sex值改為0
titanic.loc[titanic['Sex'] == 'female','Sex'] = 1           
print titanic['Sex'].unique()
print titanic['Embarked'].unique()     
titanic['Embarked'] = titanic['Embarked'].fillna('S')     #用最多的填 
titanic.loc[titanic['Embarked'] == 'S','Embarked'] = 0  
titanic.loc[titanic['Embarked'] == 'C','Embarked'] = 1 
titanic.loc[titanic['Embarked'] == 'Q','Embarked'] = 2   
print titanic['Embarked'].unique()  
from sklearn.linear_model import LinearRegression #線性迴歸
from sklearn.cross_validation import KFold #交叉驗證庫，將測試集進行切分交叉驗證取平均
predictors = ['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked']   #用到的特徵
alg = LinearRegression()
kf = KFold(titanic.shape[0],n_folds=3,random_state=1) #將m個樣本平均分成3份進行交叉驗證
predictions = []
for train, test in kf:
   train_predictors = (titanic[predictors].iloc[train,:])#將predictors作為測試特徵
   train_target = titanic['Survived'].iloc[train]
   alg.fit(train_predictors,train_target)  
   test_prediction = alg.predict(titanic[predictors].iloc[test,:])
   print test_prediction
   predictions.append(test_prediction)       
import numpy as np
#使用線性迴歸得到的結果是在區間【0，1】上的某個值，需要將該值轉換成0或1
predictions = np.concatenate(predictions, axis=0)
predictions[predictions >.5] = 1
predictions[predictions <=.5] = 0
accury = sum(predictions[predictions == titanic['Survived']]) / len(predictions)#測試準確率
print accury           
from sklearn.linear_model import LogisticRegression #邏輯迴歸
from sklearn import cross_validation
alg = LogisticRegression(random_state=1)
scores = cross_validation.cross_val_score(alg, titanic[predictors],titanic['Survived'],cv=3)
print scores.mean()
from sklearn.ensemble import RandomForestClassifier
from sklearn import cross_validation
predictions = ['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked']
alg = RandomForestClassifier(random_state=1,n_estimators=50,min_samples_split=4,min_samples_leaf=2)
kf = cross_validation.KFold(titanic.shape[0],n_folds=3,random_state=1)
scores = cross_validation.cross_val_score(alg,titanic[predictors],titanic['Survived'],cv=kf)
print scores.mean()
##############提特徵######################
titanic['Familysize'] = titanic['SibSp'] + titanic['Parch'] #家庭總共多少人
titanic['NameLength'] = titanic['Name'].apply(lambda x: len(x)) #名字的長度
import re
def get_title(name):
    title_reserch = re.search('([A-Za-z]+)\.',name)
    if title_reserch:
        return title_reserch.group(1)
    return ""
titles = titanic['Name'].apply(get_title)
print pandas.value_counts(titles)    
#將稱號轉換成數值表示
title_mapping = {"Mr":1,"Miss":2,"Mrs":3,"Master":4,"Dr":5,"Rev":6,"Col":7,"Major":8,"Mlle":9,"Countess":10,"Ms":11,"Lady":12,"Jonkheer":13,"Don":14,"Mme":15,"Capt":16,"Sir":17}
for k,v in title_mapping.items():
    titles[titles==k] = v
    print (pandas.value_counts(titles))
titanic["titles"] = titles #新增title特徵
import numpy as np
from sklearn.feature_selection import SelectKBest,f_classif#引入feature_selection看每一個特徵的重要程度
import matplotlib.pyplot as plt
predictors = ['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked','Familysize','NameLength','titles']
selector = SelectKBest(f_classif,k=5)
selector.fit(titanic[predictors],titanic['Survived'])
scores = -np.log10(selector.pvalues_)
plt.bar(range(len(predictors)),scores)
plt.xticks(range(len(predictors)),predictors,rotation='vertical')
plt.show
##########整合分類器#############
from sklearn.ensemble import GradientBoostingClassifier
import numpy as np
algorithas = [
        [GradientBoostingClassifier(random_state=1,n_estimators=25,max_depth=3),['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked','Familysize','NameLength','titles']],
        [LogisticRegression(random_state=1),['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked','Familysize','NameLength','titles']]        
        ]  
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 = []
   for alg,predictors in algorithas:      
       alg.fit(titanic[predictors].iloc[train,:],train_target)  
       test_prediction = alg.predict_proba(titanic[predictors].iloc[test,:].astype(float))[:,1]
       full_test_predictions.append(test_prediction)
   test_predictions = (full_test_predictions[0] + full_test_predictions[1]) / 2
   test_predictions[test_predictions >.5] = 1
   test_predictions[test_predictions <=.5] = 0      
   predictions.append(test_predictions)  
predictions = np.concatenate(predictions,axis=0)    
accury = sum(predictions[predictions == titanic['Survived']]) / len(predictions)#測試準確率
print accury