ML之RF：kaggle比賽之利用泰坦尼克號數(shù)據(jù)集建立RF模型對每個人進行獲救是否預(yù)測

?

?

目錄

輸出結(jié)果

實現(xiàn)代碼

---

?

?

?

輸出結(jié)果

后期更新……

?

?

實現(xiàn)代碼

#預(yù)測模型選擇的RF import numpy as np import pandas as pd from pandas import DataFrame from patsy import dmatrices import string from operator import itemgetter import json from sklearn.ensemble import RandomForestClassifier from sklearn.cross_validation import cross_val_score from sklearn.pipeline import Pipeline from sklearn.grid_search import GridSearchCV from sklearn.cross_validation import train_test_split,StratifiedShuffleSplit,StratifiedKFold from sklearn import preprocessing from sklearn.metrics import classification_report from sklearn.externals import joblib##Read configuration parameterstrain_file="train.csv" MODEL_PATH="./" test_file="test.csv" SUBMISSION_PATH="./" seed= 0print(train_file,seed)# 輸出得分 def report(grid_scores, n_top=3):top_scores = sorted(grid_scores, key=itemgetter(1), reverse=True)[:n_top]for i, score in enumerate(top_scores):print("Model with rank: {0}".format(i + 1))print("Mean validation score: {0:.3f} (std: {1:.3f})".format(score.mean_validation_score,np.std(score.cv_validation_scores)))print("Parameters: {0}".format(score.parameters))print("")#清理和處理數(shù)據(jù) def substrings_in_string(big_string, substrings):for substring in substrings:if string.find(big_string, substring) != -1:return substringprint(big_string)return np.nanle = preprocessing.LabelEncoder() enc=preprocessing.OneHotEncoder()def clean_and_munge_data(df):#處理缺省值df.Fare = df.Fare.map(lambda x: np.nan if x==0 else x)#處理一下名字，生成Title字段title_list=['Mrs', 'Mr', 'Master', 'Miss', 'Major', 'Rev','Dr', 'Ms', 'Mlle','Col', 'Capt', 'Mme', 'Countess','Don', 'Jonkheer']df['Title']=df['Name'].map(lambda x: substrings_in_string(x, title_list))#處理特殊的稱呼，全處理成mr, mrs, miss, masterdef replace_titles(x):title=x['Title']if title in ['Mr','Don', 'Major', 'Capt', 'Jonkheer', 'Rev', 'Col']:return 'Mr'elif title in ['Master']:return 'Master'elif title in ['Countess', 'Mme','Mrs']:return 'Mrs'elif title in ['Mlle', 'Ms','Miss']:return 'Miss'elif title =='Dr':if x['Sex']=='Male':return 'Mr'else:return 'Mrs'elif title =='':if x['Sex']=='Male':return 'Master'else:return 'Miss'else:return titledf['Title']=df.apply(replace_titles, axis=1)#看看家族是否夠大，咳咳df['Family_Size']=df['SibSp']+df['Parch']df['Family']=df['SibSp']*df['Parch']df.loc[ (df.Fare.isnull())&(df.Pclass==1),'Fare'] =np.median(df[df['Pclass'] == 1]['Fare'].dropna())df.loc[ (df.Fare.isnull())&(df.Pclass==2),'Fare'] =np.median( df[df['Pclass'] == 2]['Fare'].dropna())df.loc[ (df.Fare.isnull())&(df.Pclass==3),'Fare'] = np.median(df[df['Pclass'] == 3]['Fare'].dropna())df['Gender'] = df['Sex'].map( {'female': 0, 'male': 1} ).astype(int)df['AgeFill']=df['Age']mean_ages = np.zeros(4)mean_ages[0]=np.average(df[df['Title'] == 'Miss']['Age'].dropna())mean_ages[1]=np.average(df[df['Title'] == 'Mrs']['Age'].dropna())mean_ages[2]=np.average(df[df['Title'] == 'Mr']['Age'].dropna())mean_ages[3]=np.average(df[df['Title'] == 'Master']['Age'].dropna())df.loc[ (df.Age.isnull()) & (df.Title == 'Miss') ,'AgeFill'] = mean_ages[0]df.loc[ (df.Age.isnull()) & (df.Title == 'Mrs') ,'AgeFill'] = mean_ages[1]df.loc[ (df.Age.isnull()) & (df.Title == 'Mr') ,'AgeFill'] = mean_ages[2]df.loc[ (df.Age.isnull()) & (df.Title == 'Master') ,'AgeFill'] = mean_ages[3]df['AgeCat']=df['AgeFill']df.loc[ (df.AgeFill<=10) ,'AgeCat'] = 'child'df.loc[ (df.AgeFill>60),'AgeCat'] = 'aged'df.loc[ (df.AgeFill>10) & (df.AgeFill <=30) ,'AgeCat'] = 'adult'df.loc[ (df.AgeFill>30) & (df.AgeFill <=60) ,'AgeCat'] = 'senior'df.Embarked = df.Embarked.fillna('S')df.loc[ df.Cabin.isnull()==True,'Cabin'] = 0.5df.loc[ df.Cabin.isnull()==False,'Cabin'] = 1.5df['Fare_Per_Person']=df['Fare']/(df['Family_Size']+1)#Age times classdf['AgeClass']=df['AgeFill']*df['Pclass']df['ClassFare']=df['Pclass']*df['Fare_Per_Person']df['HighLow']=df['Pclass']df.loc[ (df.Fare_Per_Person<8) ,'HighLow'] = 'Low'df.loc[ (df.Fare_Per_Person>=8) ,'HighLow'] = 'High'le.fit(df['Sex'] )x_sex=le.transform(df['Sex'])df['Sex']=x_sex.astype(np.float)le.fit( df['Ticket'])x_Ticket=le.transform( df['Ticket'])df['Ticket']=x_Ticket.astype(np.float)le.fit(df['Title'])x_title=le.transform(df['Title'])df['Title'] =x_title.astype(np.float)le.fit(df['HighLow'])x_hl=le.transform(df['HighLow'])df['HighLow']=x_hl.astype(np.float)le.fit(df['AgeCat'])x_age=le.transform(df['AgeCat'])df['AgeCat'] =x_age.astype(np.float)le.fit(df['Embarked'])x_emb=le.transform(df['Embarked'])df['Embarked']=x_emb.astype(np.float)df = df.drop(['PassengerId','Name','Age','Cabin'], axis=1) #remove Name,Age and PassengerIdreturn df#讀取數(shù)據(jù) traindf=pd.read_csv(train_file) ##清洗數(shù)據(jù) df=clean_and_munge_data(traindf) ########################################formula################################formula_ml='Survived~Pclass+C(Title)+Sex+C(AgeCat)+Fare_Per_Person+Fare+Family_Size' y_train, x_train = dmatrices(formula_ml, data=df, return_type='dataframe') y_train = np.asarray(y_train).ravel() print(y_train.shape,x_train.shape)##選擇訓(xùn)練和測試集 X_train, X_test, Y_train, Y_test = train_test_split(x_train, y_train, test_size=0.2,random_state=seed) #初始化分類器 clf=RandomForestClassifier(n_estimators=500, criterion='entropy', max_depth=5, min_samples_split=1,min_samples_leaf=1, max_features='auto', bootstrap=False, oob_score=False, n_jobs=1, random_state=seed,verbose=0)###grid search找到最好的參數(shù) param_grid = dict( ) ##創(chuàng)建分類pipeline pipeline=Pipeline([ ('clf',clf) ]) grid_search = GridSearchCV(pipeline, param_grid=param_grid, verbose=3,scoring='accuracy',\ cv=StratifiedShuffleSplit(Y_train, n_iter=10, test_size=0.2, train_size=None, indices=None, \ random_state=seed, n_iterations=None)).fit(X_train, Y_train) # 對結(jié)果打分 print("Best score: %0.3f" % grid_search.best_score_) print(grid_search.best_estimator_) report(grid_search.grid_scores_)print('-----grid search end------------') print ('on all train set') scores = cross_val_score(grid_search.best_estimator_, x_train, y_train,cv=3,scoring='accuracy') print(scores.mean(),scores) print ('on test set') scores = cross_val_score(grid_search.best_estimator_, X_test, Y_test,cv=3,scoring='accuracy') print(scores.mean(),scores)# 對結(jié)果打分print(classification_report(Y_train, grid_search.best_estimator_.predict(X_train) )) print('test data') print(classification_report(Y_test, grid_search.best_estimator_.predict(X_test) ))model_file=MODEL_PATH+'model-rf.pkl' joblib.dump(grid_search.best_estimator_, model_file)

?

?

總結(jié)

以上是生活随笔為你收集整理的ML之RF：kaggle比赛之利用泰坦尼克号数据集建立RF模型对每个人进行获救是否预测的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。