SVM Model Application (2) Comparison of Logistic Regression and SVC Model through Pima Indian Diabetes Prediction Problem

import numpy as np
from sklearn import svm
from sklearn.linear_model import LogisticRegression

my_matrix=np.loadtxt("E:\\pima-indians-diabetes.txt",delimiter=",",skiprows=0) 

lenth_x=len(my_matrix[0])

data_y=my_matrix[:,lenth_x-1]

data_x=my_matrix[:,0:lenth_x-1]
print(data_x[0],len(data_x[0]),len(data_x))

(array([   6.   ,  148.   ,   72.   ,   35.   ,    0.   ,   33.6  ,
          0.627,   50.   ]), 8, 768)

n_train=int(len(data_y)*0.7)

X_train=data_x[:n_train]
y_train=data_y[:n_train]
X_test=data_x[n_train:]
y_test=data_y[n_train:]

clf1=svm.SVC()
clf1.fit(X_train,y_train)
clf2=LogisticRegression()
clf2.fit(X_train,y_train)

LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False)

y_predictions1=clf1.predict(X_test)
y_predictions2=clf2.predict(X_test)

print(y_predictions1)

[ 0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.]

print(y_predictions2)

[ 0.  0.  0.  0.  0.  0.  0.  0.  1.  1.  0.  0.  1.  0.  0.  0.  0.  0.
  0.  0.  0.  1.  0.  0.  1.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  1.  0.  0.  0.  0.  0.  0.  1.  0.  1.  0.  1.
  0.  0.  0.  0.  1.  0.  0.  1.  0.  0.  0.  0.  1.  1.  0.  1.  0.  0.
  0.  0.  1.  1.  0.  1.  0.  0.  0.  0.  0.  0.  0.  1.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  1.  0.  0.  0.  0.  0.  0.  0.  1.  0.  0.  0.  0.  1.  1.  1.
  1.  0.  0.  0.  0.  0.  1.  1.  0.  0.  1.  0.  1.  0.  0.  0.  0.  0.
  1.  0.  0.  0.  0.  0.  0.  0.  0.  0.  1.  0.  1.  0.  0.  1.  0.  0.
  1.  0.  0.  1.  1.  0.  0.  0.  0.  1.  0.  0.  0.  1.  0.  0.  1.  1.
  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  1.  0.  0.
  0.  0.  0.  0.  0.  1.  0.  0.  1.  1.  0.  1.  0.  1.  1.  1.  0.  0.
  1.  1.  0.  0.  0.  0.  1.  0.  1.  0.  0.  0.  0.  0.  0.]

print(y_test)

[ 0.  0.  1.  1.  1.  1.  0.  0.  1.  1.  0.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  0.  0.  1.  1.  0.  0.  0.  0.  0.  0.  0.  1.  0.  0.  0.
  0.  0.  0.  0.  1.  0.  1.  1.  0.  0.  0.  1.  0.  1.  0.  1.  0.  1.
  0.  1.  0.  0.  1.  0.  0.  1.  0.  0.  0.  0.  1.  1.  0.  1.  0.  0.
  0.  0.  1.  1.  0.  1.  0.  0.  0.  1.  1.  0.  0.  0.  0.  0.  0.  0.
  0.  0.  0.  1.  0.  0.  0.  0.  1.  0.  0.  1.  0.  0.  0.  1.  0.  0.
  0.  1.  1.  1.  0.  0.  0.  0.  0.  0.  1.  0.  0.  0.  1.  0.  1.  1.
  1.  1.  0.  1.  1.  0.  0.  0.  0.  0.  0.  0.  1.  1.  0.  1.  0.  0.
  1.  0.  1.  0.  0.  0.  0.  0.  1.  0.  1.  0.  1.  0.  1.  1.  0.  0.
  0.  0.  1.  1.  0.  0.  0.  1.  0.  1.  1.  0.  0.  1.  0.  0.  1.  1.
  0.  0.  1.  0.  0.  1.  0.  0.  0.  0.  0.  0.  0.  1.  1.  1.  0.  0.
  0.  0.  0.  0.  1.  1.  0.  0.  1.  0.  0.  1.  0.  1.  1.  1.  0.  0.
  1.  1.  1.  0.  1.  0.  1.  0.  1.  0.  0.  0.  0.  1.  0.]

k,h=0,0
for i in range(len(y_test)):
    if y_predictions1[i]==y_test[i]:
        k+=1
for i in range(len(y_test)):
    if y_predictions2[i]==y_test[i]:
        h+=1        
print(k,h)

(152, 183)

Since the SVM uses the classic model and the parameters are not adjusted, the prediction results are all 0. The SVM model will be studied in depth later, and the parameters will be adjusted to improve the effect of the model.