forked from veraposeidon/Insect_Identification
-
Notifications
You must be signed in to change notification settings - Fork 0
/
LinearRegression.py
42 lines (29 loc) · 1.41 KB
/
LinearRegression.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
# coding=utf-8
import pandas as pd
# 创建特征列表
column_names = ['P_rect', 'P_extend', 'P_spherical', 'P_leaf', 'P_circle', 'Species']
# column_names = ['P_rect', 'P_extend', 'P_spherical', 'P_leaf', 'P_circle','P_complecate', 'Species']
data = pd.read_csv('data/data.csv', names=column_names)
# print data.shape
# 这个功能快要被抛弃了,分割训练和测试集
from sklearn.cross_validation import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(data[column_names[0:5]], data[column_names[5]], test_size=0.25,
random_state=33)
# print Y_train.value_counts()
# print Y_test.value_counts()
# 数据整理,但是整形的,需要注意
# from sklearn.preprocessing import StandardScaler
# ss = StandardScaler()
# X_train = ss.fit_transform(X_train)
# X_test = ss.transform(X_test)
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression()
lr.fit(X_train, Y_train)
lr_y_predict = lr.predict(X_test)
from sklearn.metrics import classification_report
print "LR 精确度:" + str(lr.score(X_test, Y_test))
# print classification_report(Y_test, lr_y_predict, target_names=['fly','wo','jingui','zhang'])
print classification_report(Y_test, lr_y_predict, target_names=['fly','wo','jingui','zhang','zhizhu'])
# 保存训练结果,供后面直接使用
from sklearn.externals import joblib
joblib.dump(lr,'model/lr.model')