solution.py 文件源码

def baseline_randomForest():
    train_data = pd.read_csv(r"data/train.csv")
    print u"?????\n",train_data.info()
    print u'?????\n',train_data.describe()  
    #display_data(train_data)  # ????????
    #display_with_process(train_data) # ??????????????????,????
    process_data = pre_processData(train_data,'process_train_data',optimize=False)  # ????????????
    train_data = process_data.filter(regex='Survived|Age|SibSp|Parch|Fare|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')  # ???????????
    train_np = train_data.as_matrix()  # ????

    '''??model'''
    X = train_np[:,1:]
    y = train_np[:,0] 
    X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2)

    model = RandomForestClassifier(n_estimators=100).fit(X,y)
    #predictions = model.predict(X_test)
    #print np.float32(np.sum(predictions == y_test))/np.float32(predictions.shape[0])
    '''??'''
    test_data = pd.read_csv(r"data/test.csv")
    process_test_data = pre_processData(test_data,'process_test_data',optimize=False)  # ?????
    test_data = process_test_data.filter(regex='Age|SibSp|Parch|Fare|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
    test_np = test_data.as_matrix()
    predict = model.predict(test_np)
    result = pd.DataFrame(data={'PassengerId':process_test_data['PassengerId'].as_matrix(),'Survived':predict.astype(np.int32)})
    result.to_csv(r'baseline_randomForest_result/prediction.csv',index=False)   
# baseline crossValidate?SVM??———???????