Skip to content

Machine Learning Project - Linear_regression πŸš€

Notifications You must be signed in to change notification settings

amish027/Machine_Learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

3 Commits
Β 
Β 
Β 
Β 

Repository files navigation

Machine_Learning

Built Machine learning models : Linear_reg, Multiple_reg, Logistic_reg, etc

1. Project Overview

This project involved building a machine learning model to predict target variables using a dataset. The process included importing necessary libraries, data preprocessing, exploratory data analysis (EDA), and visualizations such as line charts, bar plots, scatter plots, heatmaps, and correlation matrices. A simple linear regression model was built, and the dataset was split into training and testing sets. The model achieved an accuracy of 81% upon validation.

2. Tools and Methodology

  • Libraries Used: Pandas, Seaborn, Matplotlib, Sklearn for data manipulation, visualization, and modeling.
  • Data Transformation: Cleaned and transformed the dataset to handle missing values and standardize features.
  • Exploratory Data Analysis (EDA): Generated line charts, bar plots, scatter plots, heatmaps, and correlation matrices.
  • Model Building: Developed a simple linear regression model to understand relationships between variables.
  • Model Validation: Split the dataset, trained the model, tested it, and validated with an accuracy of 81%.

3. Machine Learning Life Cycle

  • Problem Definition: Identified the problem and defined objectives for predicting target variables using machine learning.
  • Data Collection: Gathered and imported the dataset required for analysis and model building.
  • Data Preprocessing: Cleaned, transformed, and prepared the data for exploratory analysis and modeling.
  • Model Building and Training: Developed and trained the linear regression model using the training dataset.
  • Model Evaluation and Validation: Tested the model with the testing dataset, validated results, and evaluated accuracy (81%).

Releases

No releases published

Packages

No packages published