SVM - Classification ( linear ) in practice

 Problem statement:

To predict whether a bank currency note is authentic or not based upon four attributes of the note ??

It is a binary classification problem, here we use SVM to classify currency.

import numpy as np

import pandas as pd

Import data set :

df=pd.read_csv("D:\\Raj_DataScience\\Documents\\bill_authentication.csv")

print(df.head())

   Variance  Skewness  Curtosis  Entropy  Class
0   3.62160    8.6661   -2.8073 -0.44699      0
1   4.54590    8.1674   -2.4586 -1.46210      0
2   3.86600   -2.6383    1.9242  0.10645      0
3   3.45660    9.5228   -4.0112 -3.59440      0
4   0.32924   -4.4552    4.5718 -0.98880      0

df.shape

( 1372, 5 )

Attributes & Labels :

x= df.drop('Class',axis=1)

y= df['Class']

Split the data into Train and Test :

from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=51)

Implementing SVM Classifier :

Since, we are going to perform classification task, we will use support vector classifier class, which is written as SVC, and here we are using linear kernel.

from sklearn.svm import SVC

svcclassifier=SVC(kernel='linear')

svcclassifier.fit(x_train,y_train)

y_pred=svcclassifier.predict(x_test)

Model Evaluation :

from sklearn.metrics import classification_report,confusion_matrix,accuracy_score

print(confusion_matrix(y_pred,y_test))

print(classification_report(y_pred,y_test))

print(accuracy_score(y_pred,y_test))

[[159   2]
 [  1 113]]
             precision    recall  f1-score   support

          0       0.99      0.99      0.99       161
          1       0.98      0.99      0.99       114

avg / total       0.99      0.99      0.99       275

0.9890909090909091