1 # -*- coding: utf-8 -*-
2 """
3 Created on Thu Jan 4 19:52:03 2018
4
5 @author: markli
6 """
7 import numpy as np;
8 import pandas as pd;
9 from sklearn import linear_model;
10 from sklearn.externals import joblib;
11 import sys;
12
13 sys.path.append('../');
14 path = 'DeliverIncludeClass.csv';
15 #names=['Miles','NumberDeliveries','TravelTime'];
16 reader = pd.read_csv(path,header=0,names=['Number','Miles','NumberDeliveries','Car','TravelTime']);
17
18 #print(reader);
19 X = np.array(reader[['Miles','NumberDeliveries']]);
20 Y = np.array(reader['TravelTime']);
21 Car = np.array(reader['Car']); #将为类别属性的数据列单独读出来
22 #print(X);
23 #print(Y);
24 car_feature = list(set(Car));
25 VectoreCar = np.zeros((len(Car),len(car_feature)));
26 #本例中Car属性为类别属性，将其向量化
27 for i in range(len(Car)):
28 VectoreCar[i][Car[i]]=1;
29
30 print(VectoreCar);
31 print(Car);
32
33 #将向量化的类别属性值与其他数据合并
34 X = np.hstack((X,VectoreCar));
35 print(X);
36
37
38 reg = linear_model.LinearRegression();
39 reg.fit(X,Y);
40 joblib.dump(reg,'IncludeClassAttrRegression.pkl');
41 print("系数 %s " %(reg.coef_));
42 print("常系数 %s" %(reg.intercept_) );
43 #
44 x_test = [[80,5,0,1,0]];
45 y_predict = reg.predict(x_test);
46 print(y_predict);
DeliverIncludeClass.csv 文件格式
