-
Notifications
You must be signed in to change notification settings - Fork 0
/
K-Fold Accuracy.py
87 lines (72 loc) · 2.95 KB
/
K-Fold Accuracy.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
# -*- coding: utf-8 -*-
"""
Created on Mon Mar 12 20:37:20 2018
@author: Shobhit Sabharwal
"""
# -*- coding: utf-8 -*-
#Classification
#Support vector Machine (SVM)
#Kernal : Gaussian rbf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
#Import Database
dataset = pd.read_csv("Social_Network_Ads.csv")
x = dataset.iloc[:,[2,3]].values
y = dataset.iloc[:,4].values
#spliting dataset into training and test set
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)
#Scalling the datatset
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
x_train = sc.fit_transform(x_train)
x_test = sc.transform(x_test)
#fitting the model
from sklearn.svm import SVC
classifier = SVC(kernel= 'rbf', random_state = 0)
classifier.fit(x_train, y_train)
#Predicting the test set result
y_pred = classifier.predict(x_test)
#Making confusion matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
#Appplying k-fold accuracy
from sklearn.model_selection import cross_val_score
accuracies = cross_val_score(estimator= classifier, X = x_train, y = y_train,
cv = 10)
accuracies.mean()
accuracies.std()
# Visualising the Training set results
from matplotlib.colors import ListedColormap
X_set, y_set = x_train, y_train
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 (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()
# 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()