认识数据

# -*- coding: utf-8 -*-

def get_feature_names(df):
    '''
    input:df(DataFrame):输入数据
    output:feature_names
    '''
    #*********Begin*********#
    feature_names = df.keys()
    #********** End **********#
    return feature_names

第2关：数据预处理

# -*- coding: utf-8 -*-
from sklearn.preprocessing import Imputer,MinMaxScaler

def data_preprocessing(data):
    '''
    input:data(ndarray):待处理数据
    output:preprocessing_data(ndarray):预处理后数据
    '''
    #*********Begin*********#
    imp = Imputer(missing_values='NaN', strategy='mean', axis=0) 
    data = imp.fit_transform(data) 
    min_max_scaler =MinMaxScaler()
    preprocessing_data = min_max_scaler.fit_transform(data)
    #********** End **********#
    return preprocessing_data

第3关：数学成绩预测

# -*- coding: utf-8 -*-
from sklearn.linear_model import LinearRegression

def lr(train_data,train_label,test_data):
    '''
    input:train_data(ndarray):训练数据
          train_label(ndarray):训练标签
          test_data(ndarray):测试数据
    output:predict(ndarray):测试数据预测标签
    '''
    #********* Begin *********#
    lr = LinearRegression()
    lr.fit(train_data,train_label) 
    predict= lr.predict(test_data)
    #********** End **********#
    return predict