移动 案例到 docs/examples 目录下

auto_examples/Linear-Models/plot_ols.md

-
-# 线性回归
-
->翻译者:[@Loopy](https://github.com/loopyme)        
->校验者:[@barrycg](https://github.com/barrycg)
-
-本例仅使用`糖尿病数据集`的第一个特征，来展示线性回归在二维空间上的表现。下图中的直线, 即是线性回归所确定的一个界限，其目标是使得数据集中的实际值与线性回归所得的预测值之间的残差平方和最小。
-
-同时也计算了回归系数、残差平方和以及解释方差得分，来判断该线性回归模型的质量。
-> *原文解释和代码不符合*:
->>实际上计算了回归系数, 均方误差（MSE）,判定系数(r2_score)
->>>判定系数和解释方差得分并不绝对相等，当实际值和预测值之间的误差均值为0时，两者相同，否则数值上有着略微误差。均方误差和残差平方和虽然都是定义预测值和实际值的偏离关系，但是数值大小的差距较大。
->>>> 解释方差得分函数: explained_variance_score()。
-
-
-```python
-import matplotlib.pyplot as plt
-import numpy as np
-from sklearn import datasets, linear_model
-from sklearn.metrics import mean_squared_error, r2_score, explained_variance_score
-```
-
-
-```python
-# 加载糖尿病数据集
-diabetes = datasets.load_diabetes()
-```
-
-
-```python
-# 只使用1个特征
-diabetes_X = diabetes.data[:, np.newaxis, 2]
-```
-
-
-```python
-# 划分训练,测试集
-diabetes_X_train = diabetes_X[:-20]
-diabetes_X_test = diabetes_X[-20:]
-
-diabetes_y_train = diabetes.target[:-20]
-diabetes_y_test = diabetes.target[-20:]
-```
-
-
-```python
-# 创建线性回归模型
-regr = linear_model.LinearRegression()
-
-# 训练这个模型
-regr.fit(diabetes_X_train, diabetes_y_train)
-
-# 使用模型做预测
-diabetes_y_pred = regr.predict(diabetes_X_test)
-```
-
-
-```python
-# 评价预测结果
-print('回归系数(coef_):', regr.coef_)
-print("均方误差(MSE): %.2f"% mean_squared_error(diabetes_y_test, diabetes_y_pred))
-print('判断系数(r2_score): %.2f' % r2_score(diabetes_y_test, diabetes_y_pred))
-# 额外增加
-print('解释方差得分(explained_variance_score): %.2f' % explained_variance_score(diabetes_y_test, diabetes_y_pred))
-```
-
-    回归系数(coef_): [938.23786125]
-    均方误差(MSE): 2548.07
-    判断系数(r2_score): 0.47
-    解释方差得分(explained_variance_score): 0.53
-
-
-```python
-# 绘制输出
-plt.scatter(diabetes_X_test, diabetes_y_test,  color='black')
-plt.plot(diabetes_X_test, diabetes_y_pred, color='blue', linewidth=3)
-
-plt.xticks(())
-plt.yticks(())
-
-plt.show()
-```
-
-
-![png](data:image/png;base64,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)