Logistic Regression in Python – Step 7.) Visualize Results with Logistic Regression Model

with No Comments

#Import Libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

#Import Dataset
dataset = pd.read_csv(‘Social_Network_Ads.csv’)
x = dataset.iloc[:,[2,3]].values
y =dataset.iloc[:,4].values

#Split Training Set and Testing 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)

#Feature Scaling
from sklearn.preprocessing import StandardScaler
sc_X=StandardScaler()
x_train=sc_X.fit_transform(x_train)
x_test=sc_X.transform(x_test)

#Training the Logistic Model
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression()
classifier.fit(x_train, y_train)

#Predicting the Test Set Result
y_pred = classifier.predict(x_test)

#Create Confusion Matrix for Evaluation
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)

#Visualize 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(x1.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(‘Logistic Regression (Training set)’)
plt.xlabel(‘Age’)
plt.ylabel(‘Estimated Salary’)
plt.show()

#Visualize 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(x1.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(‘Logistic Regression (Testing set)’)
plt.xlabel(‘Age’)
plt.ylabel(‘Estimated Salary’)
plt.show()

Leave a Reply