Skip to content

souch19/Some_ML_Projects

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 

Repository files navigation

Some_ML_Projects

1-----Predicting Flight Prices-----

This repository contains a Jupyter notebook with a machine learning model for predicting flight prices. The project uses Python and several popular machine learning libraries, including pandas, numpy, scikit-learn, and matplotlib.

Getting Started

To run this project, you will need to have Jupyter Notebook installed on your machine. You can download and install it from the official website: https://jupyter.org/install.

You will also need to install the following libraries using pip:

pandas, numpy, scikit-learn, matplotlib, seaborn. Once you have installed these dependencies, you can open the Predicting_Flights_Prices.ipynb file in Jupyter Notebook and run the cells to reproduce the analysis.

Data

The data for this project was obtained from Kaggle's "Predicting Flight Prices" competition. The dataset contains information on flight routes, airlines, and prices for flights departing from major Indian cities.

Analysis

The notebook walks through the entire machine learning pipeline, including data cleaning, exploratory data analysis, feature engineering, model selection, and model evaluation. The final model is a Random Forest Regressor, which achieved an R2 score of 0.8 on the test set.

The notebook also includes visualizations of the data and model performance, as well as explanations of the thought process behind feature selection and engineering.

Conclusion

This project demonstrates how machine learning can be used to predict flight prices, which can be useful for both consumers and airlines. The notebook provides a detailed walkthrough of the machine learning pipeline and can be a helpful resource for anyone looking to improve their skills in data analysis and modeling.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published