sklearn的数据训练和评估3

gzj137070928

sklearn的数据训练和评估3

import matplotlib.pyplot as plt
import pandas as pd
from collections import OrderedDict
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split

examDict = {'学习时间':[0.5,0.75,1,1.25,1.5,1.75,1.75,2,2.25,2.5,2.75,3,
                    3.25,3.5,4,4.25,4.5,4.75,5,5.0], 
            '分数':[10,22,13,43,20,22,33,50,62,48,55,75,62,
                  73,81,76,64,82,90,93]
            }
examOrderedDict = OrderedDict(examDict)
examDf = pd.DataFrame(examOrderedDict)
# examDf.head()
exam_X = examDf.loc[:,'学习时间']
exam_y = examDf.loc[:,'分数']
plt.scatter(exam_X,exam_y,color='b',label='exam data')
plt.legend(loc=2)
plt.xlabel('Hours')
plt.ylabel('Score')
plt.show()
# 下面建立训练数据和测试数据
X_train,X_test,y_train,y_test = train_test_split(exam_X,exam_y,train_size=0.8)
print('X的原始数据特征：',exam_X.shape)
print('X的训练数据特征：',X_train.shape)
print('X的测试数据特征：',X_test.shape)
plt.scatter(X_train,y_train,color='b',label='train data')
plt.scatter(X_test,y_test,color='r',label='test data')
plt.legend(loc='best')
plt.show()
# 下面是训练模型
X_train_t = X_train.values.reshape(-1,1)  # 转换成二维数组**行1列
y_train_t = y_train.values.reshape(-1,1)
model = LinearRegression()
model.fit(X_train_t,y_train_t)
# 建立最佳拟合线：z= a + b*X
a = model.intercept_
b = model.coef_
print('最佳拟合线的截距a=',a,'回归系数b=',b)
# 绘制最佳拟合线
plt.scatter(X_train,y_train,color='b',label='train data')
y_train_pre = model.predict(X_train)  # 训练数据的预测
plt.plot(X_train,y_train_pre,color='black',linewidth=3,label='best line')
plt.legend(loc=3)
plt.xlabel('Hours')
plt.ylabel('Score')
plt.show()
# 评估模型的决定系数R^2
rDf = examDf.coor()
print('相关系数矩阵：',rDf)
model.score('决定系数：',X_train_t,y_train_t)