solution.py 文件源码

def optimize_logisticRegression():
    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 = fe_preprocessData(train_data,'process_train_data')  # ????????????
    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 = linear_model.LogisticRegression(C=1.0,tol=1e-6).fit(X_train,y_train)
    model = linear_model.LogisticRegression(C=1.0,tol=1e-6).fit(X,y)
    print pd.DataFrame({"columns":list(train_data.columns)[1:],"coef_":list(model.coef_.T)})

    '''??????'''
    test_data = pd.read_csv(r"data/test.csv")
    process_test_data = fe_preprocessData(test_data,'process_test_data')  # ?????
    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'optimize_logisticRegression_result/prediction.csv',index=False)
    #clf = linear_model.LogisticRegression(C=1.0,tol=1e-6)
    #print cross_validation.cross_val_score(clf, X,y,cv=5)    
## ????????