# 1.4 创建线性回归器
import sys
import numpy as np
from sklearn import linear_modelfilename = sys.argv[1]
X = []
y = []with open(filename, 'r') as f:
for line in f.readlines():
xt, yt = [float(i) for i in line.split(',')]
X.append(xt)
y.append(yt)
## 读取训练数据~~~
num_training = int(0.8 * len(X))
num_test = len(X) - num_training# 训练数据
X_train = np.array(X[:num_training]).reshape((num_training,1 ))
y_train = np.array(y[:num_training])
# 测试数据
X_test = np.array(X[num_training:]).reshape((num_test,1 ))
y_test = np.array(y[num_training:])# ~~~3回归器 进行运算
# 创建线性回归对象
linear_regressor = linear_model.LinearRegression()
# 用训练数据集训练模型
linear_regressor.fit(X_train, y_train)
##~~~ 4 展示
import matplotlib.pyplot as plt
y_train_pred = linear_regressor.predict(X_train)
plt.figure()
plt.scatter(X_train, y_train, color='green')
plt.plot(X_train, y_train_pred, color='black', linewidth=4)
plt.title('Training data')
plt.show()
# ~~ 5 预测-画出预测图
y_test_pred = linear_regressor.predict(X_test)
plt.scatter(X_test, y_test, color='green')
plt.plot(X_test, y_test_pred, color='black', linewidth=4)
plt.title('Test data')
plt.show()# 6 评价计算结果
# 平均绝对误差
print("Mean absolute error =",round(sm.mean_absolute_error(y_test, y_test_pred),2))
# 均方误差
print("Mean squared error =",round(sm.mean_squared_error(y_test, y_test_pred), 2))
# 中位数绝对误差
print("Median absolute error =",round(sm.median_absolute_error(y_test, y_test_pred),2))
# 解释方差分
print("Explained variance score =",round(sm.explained_variance_score(y_test,y_test_pred),2))
# R方得分
print("R2 score =",round(sm.r2_score(y_test, y_test_pred), 2))结果
python regressor.py data_singlevar.txt
Mean absolute error = 1.95
Mean squared error = 3.86
Median absolute error = 1.95
Explained variance score = 0.98
R2 score = -0.72
