Machine Learning

Original Source Here

Linear Regression vs. Logistic Regression

Diving into a comparison of the supervised machine learning algorithm

A photo by Author

I am writing this article to make a deep understanding of the similarity and differences between Linear and Logistic regression algorithm and their working with help of their code.

Linear regression

As we know that Linear Regression is a supervised Machine Learning algorithm, is a statistical method which is used to study of relationships between two continuous variables i.e. dependent and independent variable. It also predicts continuous values and finds the best fitting line that describes variables.

Mathematically Linear Regression

Image Source

Image Source

Image Source

Image Source

One of the classification models, the linear model i.e. Logistic Regression is used to predict categorical data.

Logistic regression

It is an another supervised machine learning algorithm used statistically analyzing a dataset in which there are one or more independent variables that determine an outcome. The outcome is measured with a dichotomous variable (two possible outcomes i.e.1 (TRUE, success, pregnant, etc.) or 0 (FALSE, failure, non-pregnant, etc.).

Also, it uses the concept of probability which is the likelihood or chance of an event occurring.

Logistic Regression Vs Linear Regression

The concept of probability and sigmoid modify the linear regression into the Logistic regression.

Image Source

Image Source

Logistic Regression working with the help of probability

Let us have an example of a dataset having age and old-age benefits. Those who have age 35 or more than 35 then are given old-age benefit and those who are below 35 they cannot have given old-age benefit.

We set a threshold value of 0.5 for understanding the working, in given below figure more than 0.5 values have higher chances to given benefit according to the probability values.

Image Source

Linear Regression and Logistic Regression are similar in the following ways.

• Both are supervised Machine Learning algorithms.
• Both the models are parametric regression means both the models use linear equations for predictions.

Differences

• The continuous values in the target variable are handled by Linear Regression whereas the binary classes in the target column are handled by Logistic regression.
• Linear Regression finds the best-fitted line while Logistic regression is fitting the line values to the sigmoid curve.
• Loss function in linear regression can be calculated by the mean square error method while logistic regression used maximum likelihood estimation.

Code for Linear Regression

#import librariesimport numpy as np
import pandas as pd
import matplotlib.pyplot as pltdatafile=pd.read_csv("salaryData.csv")
print(datafile)

A photo by Author

#visualisation usingh scatter plotx=datafile['YearsExperience']
y=datafile['Salary']plt.xlabel('YearsExperience')
plt.ylabel('Salary')
plt.scatter(x,y,color='red',marker='+')
plt.show()

A photo by Author

#Splitting of data set in to testing and trainingx=datafile.iloc[:,:-1].values
y=datafile.iloc[:,1].valuesprint(x)

A photo by Author

import sklearnfrom sklearn.model_selection import train_test_splitxtrain,xtest,ytrain,ytest=train_test_split(x,y,test_size=1/3,random_state=1)#creating simple linear modelx=datafile.iloc[:,:-1].valuesy=datafile.iloc[:,1].valuesfrom sklearn.linear_model import LinearRegressionmodel=LinearRegression()   #y=ax+b
model.fit(xtrain,ytrain)LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)#predictiony_pred=model.predict(xtest)
y_pred

A photo by Author

#plotting linear regressionplt.scatter(xtrain,ytrain,color='red')
plt.plot(xtrain,model.predict(xtrain))
plt.show()

A photo by Author

Code for Logistic Regression

# Importing Libraries and data setimport numpy as np
import pandas as pd
import matplotlib.pyplot as pltdatafile=pd.read_csv(‘LR.csv’)
datafile

A photo by Author

X=datafile.iloc[:,[0,1]].valuesY=datafile.iloc[:,2].values#training and testing datafrom sklearn.model_selection import train_test_splitX_train,X_test,Y_train,Y_test=train_test_split(X,Y,test_size=0.25,random_state=0)from sklearn.preprocessing import StandardScalersc=StandardScaler()X_train=sc.fit_transform(X_train)X_test =sc.transform(X_test)

Logistic Regression applying on our training part of data set.

from sklearn.linear_model import LogisticRegressionclassifer=LogisticRegression(random_state=0)classifer.fit(X_train,Y_train)

Predicted value execution

Y_pred=classifer.predict(X_test)# Confusion matrix.from sklearn.metrics import confusion_matrixcm=confusion_matrix(Y_test,Y_pred)cm#output:
array([[65,  3],
      [ 8, 24]])

Accuracy

from sklearn.metrics import accuracy_scoreaccuracy_score(Y_test,Y_pred)#output:
0.89

I hope you like the article. Reach me on my LinkedIn and twitter.

Recommended Articles

1. NLP — Zero to Hero with Python
2. Python Data Structures Data-types and Objects
3. Exception Handling Concepts in Python
4. Why LSTM more useful than RNN in Deep Learning?
5. Neural Networks: The Rise of Recurrent Neural Networks
6. Fully Explained Linear Regression with Python
7. Fully Explained Logistic Regression with Python
8. Differences Between concat(), merge() and join() with Python
9. Data Wrangling With Python — Part 1
10. Confusion Matrix in Machine Learning

AI/ML

Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot

via WordPress https://ramseyelbasheer.io/2021/07/01/machine-learning-6/