solution.py 文件源码

def pre_processData(train_data,file_path):
    train_data.loc[(train_data.Age.isnull()), 'Age' ] = np.mean(train_data.Age)  # ???????????
    train_data.loc[(train_data.Cabin.notnull(),'Cabin')] = 'yes' # Cabin??????yes
    train_data.loc[(train_data.Cabin.isnull(),'Cabin')] = 'no'    
    '''0/1????'''
    dummies_cabin = pd.get_dummies(train_data['Cabin'],prefix='Cabin')  # get_dummies?????0/1??????????????prefix???Cabin
    dummies_Embarked = pd.get_dummies(train_data['Embarked'], prefix='Embarked')
    dummies_Sex = pd.get_dummies(train_data['Sex'], prefix='Sex')
    dummies_Pclass = pd.get_dummies(train_data['Pclass'],prefix='Pclass')
    train_data = pd.concat([train_data,dummies_cabin,dummies_Embarked,dummies_Pclass,dummies_Sex], axis=1)  # ??dataframe,axis=1??
    train_data.drop(['Pclass','Name','Sex','Embarked','Cabin','Ticket'],axis=1,inplace=True)   # ????????????            
    header_string = ','.join(train_data.columns.tolist())  # ?????string???????
    np.savetxt(file_path+r'/pre_processData1.csv', train_data, delimiter=',',header=header_string)  # ?????????????    
    '''???????(Age?Fare)'''
    scaler = StandardScaler()
    age_scaler = scaler.fit(train_data['Age'])
    train_data['Age'] = age_scaler.fit_transform(train_data['Age'])
    if np.sum(train_data.Fare.isnull()):  # ??Fare???????????
        train_data.loc[(train_data.Fare.isnull(),'Fare')]=np.mean(train_data.Fare)
    fare_scaler = scaler.fit(train_data['Fare'])
    train_data['Fare'] = fare_scaler.transform(train_data['Fare'])
    header_string = ','.join(train_data.columns.tolist())  # ?????string???????
    np.savetxt(file_path+r'/pre_processData_scaled.csv', train_data, delimiter=',',header=header_string)  # ?????????????    
    return train_data






## feature engineering?????-?????