Welcome to the Data-Driven ML Insights repository!
This repository contains a collection of machine learning models and data analysis tasks that derive insights from various datasets. The projects explore diverse aspects of data-driven decision-making using machine learning techniques, primarily focusing on extensive data exploration. Each project is assigned to a separate respository which contains even more information of the project.
- Project Highlights
- Usage
- Feedback
- Projects
- Technologies Used
- Installation
- Contributing
- License
- Contact
- Machine Learning Models: Explore a variety of machine learning models implemented for different tasks.
- Data Analysis Tasks: Dive into projects that extract meaningful insights from datasets.
Feel free to explore the projects based on your interests. Each branch represents a different project or task, providing a modular and organized structure.
If you have any suggestions, find issues, or want to contribute, please open an issue or a pull request. Your feedback is highly valued!
Happy exploration and coding!
-
This project performs the regression analysis of the Wages of the employees all around US considering different features like the employee industry, area, state, ... etc to find out how the wages are being affected with different features. Which are most critical factors contributing to the variation in wages are also studied.
-
The core purpose of this study is to find the impact of Sentiment Analysis in predicting customer churn for the e-commerce industry by employing different predictive models. Furthermore, the study is also focused on observing which model is best in a more accurate prediction for determining the churn rate of customers.
-
Clustering is performed for different Starbucks beverages based on their calories using DBSCAN and K-Means.
-
Recommending different TV shows that are similar to the one that the user is interested in.
-
Clustering is performed for different Nike Inc. products (shoes) based on Customers' sentiments, ratings, discounts, and other important features. LLaMa2 has been utilized to extract the sentiments.
-
Developing a Classification Model for Predicting whether a product is good or bad for the organization in the long run.
-
Dashboard and appropriate relationships between different variables for the Netflix data to interpret and gain data-driven insights.
-
Image classification for various animals using EfficientNetB7 (CNN).
-- More Projects are yet to be added. Will be attaching more projects soon --
- Python
- Pandas
- Scikit-learn
- TensorFlow/Keras
- Matplotlib
- Seaborn
- SQL
- Tableau
- Power BI
- DBSCAN
- K-Means
- EfficientNetB7
- LLaMa2
- Clone the repository:
git clone https://github.com/yourusername/Data_Driven-ML_Insights.git
- Navigate to the project directory:
cd Data_Driven-ML_Insights - Install the required packages:
pip install -r requirements.txt
Contributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Distributed under the MIT License. See LICENSE for more information.
Ganesh Kota