-
Notifications
You must be signed in to change notification settings - Fork 110
/
logistic_regression.py
97 lines (69 loc) · 2.45 KB
/
logistic_regression.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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat Aug 11 20:32:57 2018
@author: liuchuang
"""
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib.colors import ListedColormap
dataset = pd.read_csv('Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values
y = dataset.iloc[:, 4].values
"""
plt.scatter(X[:,0],X[:,1],color='blue', marker='x', label='dataset')
plt.xlabel('Age')
plt.ylabel('salary')
plt.legend(loc=2)
plt.show()
"""
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
from sklearn.linear_model import LogisticRegression
cl = LogisticRegression()
cl.fit(X_train, y_train)
y_pred = cl.predict(X_test)
def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
# setup marker generator and color map
markers = ('s', 'x', 'o', '^', 'v')
colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
cmap = ListedColormap(colors[:len(np.unique(y))])
# plot the decision surface
x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution), np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
# plot class samples
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1],alpha=0.8, c=cmap(idx),marker=markers[idx], label=cl)
# highlight test samples
if test_idx:
X_test, y_test = X[test_idx, :], y[test_idx]
plt.scatter(X_test[:, 0], X_test[:, 1], c='', alpha=1.0, linewidth=1, marker='o', s=55, label='test set')
plot_decision_regions(X_test, y_pred, classifier=cl)
plt.xlabel('age')
plt.ylabel('salary')
plt.legend(loc='upper left')
plt.title("Test set")
plt.show()
"""
plot_decision_regions(X_train, y_train, classifier=cl)
plt.xlabel('age')
plt.ylabel('salary')
plt.legend(loc='upper left')
plt.title("Training set")
plt.show()
"""
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
plt.matshow(cm,cmap=plt.cm.gray)
print(cm)