-
Notifications
You must be signed in to change notification settings - Fork 0
/
5. SupportVector.py
64 lines (51 loc) · 2 KB
/
5. SupportVector.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
# -*- coding: utf-8 -*-
"""
Created on Sat Feb 22 12:30:41 2020
@author: DELL
"""
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
#importing dataset
dataset = pd.read_csv('Social_Network_Ads.csv')
X=dataset.iloc[:,[2,3]].values
y=dataset.iloc[:,4].values
#Spliting the data based on Training and Test set
from sklearn.model_selection 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 400 dataset, 100 (0.25) will be test size and other 300 will be trainning set
#Feature Scaling
from sklearn.preprocessing import StandardScaler
sc=StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
#Create the MODEL for SVM
from sklearn.svm import SVC
classifier = SVC(kernel='linear', random_state=0)
classifier.fit(X_train,y_train)
#Predict the test set results
y_pred = classifier.predict(X_test)
#Making the confusion matrix
from sklearn.metrics import confusion_matrix
cm=confusion_matrix(y_test,y_pred)
#from this we can see our model predicted 90 correct data out of 100 test set
'''array([[66, 2],
[ 8, 24]], dtype=int64)
'''
# Visualising the Test set results
from matplotlib.colors import ListedColormap
X_set, y_set = X_test, y_test
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('SVM (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()