/
Naive Bayes Classification.py
51 lines (51 loc) · 2.26 KB
/
Naive Bayes Classification.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
#Naive Bayes Classification
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
dataset=pd.read_csv('Social_Network_Ads.csv')
x=dataset.iloc[:,[2,3]].values
y=dataset.iloc[:,4].values
from sklearn.model_selection import train_test_split as tts
xTrain,xTest,yTrain,yTest=tts(x,y,test_size=0.25,random_state=0)
from sklearn.preprocessing import StandardScaler as ss
scale=ss()
xTrain=scale.fit_transform(xTrain)
xTest=scale.transform(xTest)
from sklearn.naive_bayes import GaussianNB as nb
classifier=nb()
classifier.fit(xTrain,yTrain)
yPred=classifier.predict(xTest)
from sklearn.metrics import confusion_matrix as cm
cm=cm(yTest,yPred)
from matplotlib.colors import ListedColormap
X_set, y_set = xTrain, yTrain
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('Naive Bayes Classification (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()
from matplotlib.colors import ListedColormap
X_set, y_set = xTest, yTest
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('Naive Bayes Classification (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()