1 from sklearn.externals import joblib
 2 from sklearn.model_selection import train_test_split
 3 from sklearn.datasets import load_boston
 4 from sklearn.preprocessing import StandardScaler
 5 from sklearn.linear_model import LinearRegression
 6 from sklearn.metrics import r2_score
 7 from sklearn import neighbors
 8 import pandas as pd
 9 import numpy as np
10 import seaborn as sns
11 import matplotlib.pyplot as plt
12 import sklearn.preprocessing as sp
13 import sklearn.pipeline as pl

1 # np.column_stack：取行排列数组
2 # np.vstack：取列排列数组
3 # a = np.array([1,2])
4 # b = np.array([3,4])
5 # print(np.vstack((a,b)))
6 # array([[1, 2],[3, 4]])
7 # print(np.column_stack((a,b)))
8 # array([[1, 3],[2, 4]])

1 # 获取波士顿房价数据
2 lb = load_boston()
3 # 将房价数据转换为每行包括影响因素和房价的DataFrame
4 df = pd.DataFrame(np.column_stack((lb.data, lb.target)),
5                   columns=[‘CRIM‘, ‘ZN‘, ‘INDUS‘, ‘CHAS‘, ‘NOX‘, ‘RM‘, ‘AGE‘, ‘DIS‘, ‘RAD‘,
6                            ‘TAX‘, ‘PTRATIO‘, ‘B‘, ‘LSTAT‘, ‘MEDV‘])
7 cols = [‘LSTAT‘, ‘INDUS‘, ‘NOX‘, ‘RM‘, ‘MEDV‘]
8 print(df)
9 print(df[cols])

 1 def pairplot_analyse():
 2     ‘‘‘
 3     style:whitegrid-白色网格图   darkgrid-黑色网格图  ticks-散点图   dark white
 4     context：notebook    paper   talk    poster      # size: paper < talk < poster < notebook
 5     palette：调色板
 6     kind：使用回归
 7     diag_kind：改变对角图
 8     markers：改变点形状
 9     :return:
10     ‘‘‘
11     sns.set(style=‘dark‘, context=‘notebook‘)
12     sns.pairplot(df[cols], height=2, palette=‘husl‘, kind=‘reg‘, diag_kind=‘kde‘, markers=‘+‘)
13     plt.tight_layout()
14     plt.show()

 1 def heatmap_analyse():
 2     ‘‘‘
 3     cbar：柱子
 4     annot：标记
 5     square：方形
 6     fmt：数据格式
 7     yticklabels：y轴标签
 8     xticklabels：x轴标签
 9     :return:
10     ‘‘‘
11     # 计算皮尔逊相关系数
12     corr = np.corrcoef(df[cols].values.T)
13     # 生成热点图
14     hm = sns.heatmap(corr, cbar=True, annot=True, square=True, fmt=‘.2f‘, annot_kws={‘size‘: 15}, yticklabels=cols,
15                      xticklabels=cols)
16     plt.show()

 1 def bostn_linear():
 2     ‘‘‘
 3     线性回归直接预测房子价格
 4     :return:
 5     ‘‘‘
 6 
 7     # 获取数据
 8     lb = load_boston()
 9 
10     # 分割数据集为训练集和测试集 test_size:分割比例
11     x_train, x_test, y_train, y_test = train_test_split(lb.data, lb.target, test_size=0.25)
12 
13     # print(y_train, y_test)
14     # 特征值和目标值是都必须进行标准化处理，实例化两个标准化API
15     std_x = StandardScaler()
16 
17     x_train = std_x.fit_transform(x_train)
18     # 用转化训练集的标准归一化测试集：上是fit_transform,下是transform
19     x_test = std_x.transform(x_test)
20 
21     # 目标值
22     std_y = StandardScaler()
23     # -1表示自动识别行数
24     y_train = std_y.fit_transform(y_train.reshape(-1, 1))
25     y_test = std_y.transform(y_test.reshape(-1, 1))
26 
27     # estimator
28     # 正规方程求解方式预测结果
29     # 创建线性回归对象
30     lr = LinearRegression()
31     # 训练数据
32     lr.fit(x_train, y_train)
33     print(lr.coef_)  # 权值
34 
35     # 保存训练好的模型
36     joblib.dump(lr, ‘./test.pkl‘)
37 
38     # 预测测试集的房子价格
39     # y_lr_predict = std_y.inverse_transform(lr.predict(x_test))
40     orgin = std_y.inverse_transform(y_test[3])  # 转换成原格式
41     print(‘orgin value is:::::‘, orgin)
42     y_lr_predict = std_y.inverse_transform(lr.predict(np.array([x_test[3]])))  # predict参数是二维数组
43 
44     print(‘正规方程测试集里面每个房子的预测价格：‘, y_lr_predict)
45     # print(‘正规方程R2评分：‘, r2_score(std_y.inverse_transform(y_test), y_lr_predict))
46     # print(‘正规方程R2评分：‘, r2_score(orgin, y_lr_predict))     #r2_score，参数1：原测试数据，参数2：预测数据

 1 def log_fit():
 2     x = np.linspace(0, 20, 50)
 3     y = x ** 3 + np.random.random(50, ) * 100
 4     # pf = sp.PolynomialFeatures(3)
 5 
 6     lr = LinearRegression()
 7     # modle = pl.make_pipeline(pf,lr)
 8     lr.fit(x.reshape(-1, 1), y)
 9     x_predict = lr.predict(x.reshape(-1, 1))
10     print(x_predict)
11 
12     plt.scatter(x, y)  # 曲线：原曲线
13     plt.scatter(x, x_predict, c=‘r‘)  # 直线：预测曲线
14     plt.show()

 1 def test_fj():
 2     X = np.array([[500, 3, 0.3], [1000, 1, 0.6], [750, 2, 0.3], [600, 5, 0.2], [1200, 1, 0.6]], dtype=float)
 3     Y = np.array([10000, 9000, 8000, 12000, 8500], dtype=float)
 4 
 5     x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.25)
 6     print(x_train, x_test)
 7     print(‘===================================================‘)
 8     print(y_train, y_test)
 9 
10     std_x = StandardScaler()
11     x_train = std_x.fit_transform(x_train)
12     x_test = std_x.transform(x_test)
13 
14     std_y = StandardScaler()
15     y_train = std_y.fit_transform(y_train.reshape(-1, 1))
16     y_test = std_y.transform(y_test.reshape(-1, 1))
17 
18     lr = LinearRegression()
19     lr.fit(x_train, y_train)
20     print(lr.coef_)
21 
22     # orign = std_y.inverse_transform(y_test[1])
23     # print(‘orign is value:::::‘,orign)
24     # y_lr_predict = std_y.inverse_transform(lr.predict(np.array([x_test[1]])))
25     y_lr_predict = std_y.inverse_transform(lr.predict(x_test))
26 
27     print(‘房价：‘, y_lr_predict)
28     print(‘评分：‘, r2_score(std_y.inverse_transform(y_test), y_lr_predict))
29 
30 
31 def price_predict():
32     # 数据有三个特征：距离地铁距离、附近小学、小区绿化率
33     X = np.array([[500, 3, 0.3], [1000, 1, 0.6], [750, 2, 0.3], [600, 5, 0.2], [1200, 1, 0.6]], dtype=float)
34     # 具有三个特征的房屋对应的房价
35     Y = np.array([10000, 9000, 8000, 12000, 8500], dtype=float)
36 
37     std_x = StandardScaler()
38     x_train = std_x.fit_transform(X)
39 
40     std_y = StandardScaler()
41     y_train = std_y.fit_transform(Y.reshape(-1, 1))
42     # 构建线性预测模型
43     lr = LinearRegression()
44     # 模型在历史数据上进行训练，Y.reshape(-1,1)将Y变为二维数组，fit函数参数要求是二维数组
45     lr.fit(x_train, y_train.reshape(-1, 1))
46     # 使用训练模型预测新房屋价格
47     distance = input(‘请输入新房屋距离地铁的距离：‘)
48     school = input(‘请输入附近小学数量：‘)
49     green = input(‘请输入小区绿化率：‘)
50     x_predict = std_x.transform(np.array([[distance, school, green]], dtype=float))
51     print(std_y.inverse_transform(lr.predict(x_predict)))
52     # print(lr.predict(np.array([[distance, school, green]], dtype=float)))
53     # print(lr.predict(np.array([[1300, 3, 0.4]])))
54 
55 
56 if __name__ == ‘__main__‘:
57     pairplot_analyse()
58     # heatmap_analyse()
59     # bostn_linear()
60     # log_fit()
61     # test_fj()
62     # price_predict()
63     pass