SVM_CLAASIFIER.py

# -*- coding: utf-8 -*-
"""SVM_Classifier

Original file is located at
    https://colab.research.google.com/drive/133lwaWfMa-vdbMfWz8-mV2aQw0CyrbKg
"""

import numpy as nm
import matplotlib.pyplot as mtp
import pandas as pd

df= pd.read_csv('/content/framingham.csv')
df

x= df.iloc[:, [3,9]].values
y= df.iloc[:, 15].values
#Extracting Independent and dependent Variable

missing_val=["totChol","currentSmoker"]
for i in missing_val:
  mean_val=df[i].mean()
  df[i].fillna(mean_val,inplace=True)

# Splitting the dataset into 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)
#feature Scaling
from sklearn.preprocessing import StandardScaler
st_x= StandardScaler()
x_train= st_x.fit_transform(x_train)
x_test= st_x.transform(x_test)

from sklearn.svm import SVC # "Support vector classifier"
classifier = SVC(kernel='linear', random_state=0)
classifier.fit(x_train, y_train)

y_pred= classifier.predict(x_test)

from sklearn.metrics import confusion_matrix
cm= confusion_matrix(y_test, y_pred)

cm

from matplotlib.colors import ListedColormap
x_set, y_set = x_train, y_train
x1, x2 = nm.meshgrid(nm.arange(start = x_set[:, 0].min() - 1, stop = x_set[:, 0].max() + 1, step  =0.01),
nm.arange(start = x_set[:, 1].min() - 1, stop = x_set[:, 1].max() + 1, step = 0.01))
mtp.contourf(x1, x2, classifier.predict(nm.array([x1.ravel(), x2.ravel()]).T).reshape(x1.shape),
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
mtp.xlim(x1.min(), x1.max())
mtp.ylim(x2.min(), x2.max())
for i, j in enumerate(nm.unique(y_set)):
    mtp.scatter(x_set[y_set == j, 0], x_set[y_set == j, 1],
        c = ListedColormap(('red', 'green'))(i), label = j)
mtp.title('SVM classifier (Training set)')
mtp.xlabel('Age')
mtp.ylabel('Estimated Salary')
mtp.legend()
mtp.show()