基于线性回归的学生成绩预测

参考学生成绩预测_Mr_Bo_的博客-CSDN博客_学生成绩预测，使用了Anaconda3下的Spyder工具进行代码撰写、测试，最后附上数据文件以供下载。

 

代码（直接粘贴运行）

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""

import pandas as pd
import numpy as np
import json

data_features = pd.read_csv('SP_train.csv',
                usecols=['gender','race/ethnicity',
                         'parental level of education',
                         'lunch','test preparation course' ])
from sklearn.preprocessing import OneHotEncoder
encoder = OneHotEncoder(sparse = False)
data_features = encoder.fit_transform(data_features)

data=pd.DataFrame(data_features,
                  columns=['gender_1','gender_2',
                           'race_1','race_2',
                           'race_3','race_4',
                           'race_5','edu_1',
                           'edu_2','edu_3',
                           'edu_4','edu_5',
                           'edu_6','lunch_1',
                           'lunch_2','test_1',
                           'test_2'
                           ],dtype=float)
x=data[['gender_1','gender_2','race_1','race_2',
        'race_3','race_4','race_5','edu_1',
        'edu_2','edu_3','edu_4','edu_5',
        'edu_6','lunch_1','lunch_2','test_1',
                          'test_2']]

y=pd.read_csv('SP_train.csv',
                usecols=['math score','reading score','writing score'])

from sklearn import linear_model
regr=linear_model.LinearRegression()
regr.fit(x,y)
coef = regr.coef_
intercept = regr.intercept_
R2 = regr.score(x,y)
print(regr.coef_)
#打印常数
print(regr.intercept_)

#预测单个学生成绩
z=regr.predict([[1,0,0,0,1,
                0,0,0,0,0,
                 0,0,1,0,1,
                1,0]])
print('score:' + str(z))



#处理测试集
data_test_features=pd.read_csv('SP_test.csv',
                 usecols=['gender', 'race/ethnicity','parental level of education','lunch','test preparation course'])
data_test_features=encoder.fit_transform(data_test_features)
data_test=pd.DataFrame(data_test_features,
                  columns=['gender_1','gender_2',
                          'race_1','race_2',
                          'race_3','race_4',
                          'race_5','edu_1',
                          'edu_2','edu_3',
                          'edu_4','edu_5',
                          'edu_6','lunch_1',
                          'lunch_2','test_1',
                          'test_2'],dtype=float)
x_test=data_test[['gender_1','gender_2',
                          'race_1','race_2',
                          'race_3','race_4',
                          'race_5','edu_1',
                          'edu_2','edu_3',
                          'edu_4','edu_5',
                          'edu_6','lunch_1',
                          'lunch_2','test_1',
                          'test_2']]

#预测测试集中学生成绩
y_test_pre=regr.predict(x_test)
y_test_pre=np.round(y_test_pre)
#y_test_pre=np.array(y_test_pre,dtype=np.int32)
#print (y_test_pre)
#print(type(y_test_pre))

list=[]
for i in range(1000):
    list.append(str(i))
#print(list)
#生成字典
dict1={}
dict1=dict(zip(list,y_test_pre))

#重写json类
class NumpyEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, (np.int_, np.intc, np.intp, np.int8,
            np.int16, np.int32, np.int64, np.uint8,
            np.uint16, np.uint32, np.uint64)):
            return int(obj)
        elif isinstance(obj, (np.float_, np.float16, np.float32,
            np.float64)):
            return float(obj)
        elif isinstance(obj,(np.ndarray,)): #### This is the fix
            return obj.tolist()
        return json.JSONEncoder.default(self, obj)

submission1=json.dumps(dict1,cls=NumpyEncoder)

预测结果：

测试数据下载：

 基于线性回归的学生成绩预测_测试数据文件-机器学习文档类资源-CSDN下载