(決策樹)泰坦尼克號生還者簡單預測
阿新 • • 發佈:2018-11-02
import pandas as pd titanic=pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt') X=titanic[['pclass','age','sex']] y=titanic['survived'] X['age'].fillna(X['age'].mean(),inplace=True) from sklearn.cross_validation import train_test_split X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=33) from sklearn.feature_extraction import DictVectorizer vec=DictVectorizer(sparse=False) X_train=vec.fit_transform(X_train.to_dict(orient='record')) #print vec.feature_names_ X_test=vec.transform(X_test.to_dict(orient='record')) from sklearn.tree import DecisionTreeClassifier dtc=DecisionTreeClassifier() dtc.fit(X_train,y_train) y_predict=dtc.predict(X_test) from sklearn.metrics import classification_report print dtc.score(X_test,y_test) print classification_report(y_predict,y_test,target_names=['died','survived']) #視覺化決策樹,還差一步 from sklearn.tree import export_graphviz with open("tree.dot", 'w') as f: f = export_graphviz(dtc.fit(X_train,y_train), out_file = f)