Welcome to my GitHub repository showcasing the projects I completed during my Internshala Data Science Course. This repository is organized into four modules, each focusing on different aspects of data science, and a final project that demonstrates the culmination of my learning journey.
Introduction to Python for Data Science In this module, I honed my Python skills by completing coding challenges that involved implementing functions to perform specific tasks. These challenges aimed to build a strong foundation in Python programming for data science.
Projects:
Function Implementation Challenges
- Description: Implementation of functions to perform specific tasks using Python.
- Key Concepts: Python programming, functions, data manipulation.
This module centered around performing bivariate analysis on the Titanic dataset, encompassing both continuous and categorical variables. The analysis aimed to uncover insights and relationships within the data.
Projects:
Continuous Bivariate Analysis on Titanic Data
- Description: Exploring relationships between continuous variables in the Titanic dataset.
- Key Techniques: Correlation analysis, scatter plots.
Categorical Bivariate Analysis on Titanic Data
- Description: Analyzing interactions between categorical variables in the Titanic dataset.
- Key Techniques: Cross-tabulation, stacked bar plots.
In this module, I tackled statistical coding challenges that involved performing various statistical operations on provided data. The challenges aimed to strengthen my understanding of statistical concepts and their practical implementation.
Projects:
Statistical Operations Coding Challenge
- Description: Implementing statistical operations such as mean, median, and t-test on given data.
- Key Techniques: Descriptive statistics, hypothesis testing.
Module 4 focused on regression techniques and their application in solving real-world problems. The main project involved predicting hourly bike rental demand by combining historical usage patterns with weather data.
Projects:
Bike Rental Demand Forecasting
- Description: Utilizing regression techniques to predict hourly bike rental demand based on historical and weather data.
- Key Techniques: Linear regression, feature engineering, time series analysis.
The final project challenged me with a classification task where the task was to predict whether a client would subscribe to a term deposit based on a combination of client information and call details.
Project Details:
- Description: Predicting client subscription to term deposit using classification techniques.
- Key Techniques: Feature engineering, classification algorithms, model evaluation.
- Results: Various ML models were tested out of which Random Forest Classifier had the highest accuracy of 90%.
Feel free to explore each module's directory for detailed information and code related to the projects. I hope you find my journey through the Internshala Data Science Course both informative and inspiring!
For inquiries or collaborations, please contact me at abhaynagendrapancholi@gmail.com