Learning-Data-Science

Bio: Supratim Haldar

Collection of my practice and project work in Data Science and Machine Learning. The repository is organized as follows:

• statistics: Implementations of core concepts of statistics using Python 3.

• machine-learning: My implementations of core machine learning algorithms using only Python 3 and Numpy.

• ml-using-libraries: Understanding of core machine learning algorithms using standard libraries, such as scikit-learn, nltk etc.

• deep-learning: My implementations of deep neural networks using only Python 3 and Numpy.

• project-playground: Solutions to real world use cases using data collected from public repositories.

• web-scraping: Projects to collect data from web using scraping methods.

Quick link to few interesting projects:

• An analysis of traffic and accidents on roads of Bangalore
• An analysis of customer churn in the telco industry
• Analysis of chances of survival of passengers on board Titanic ship and prediction of chances of survival of the passengers
• Detecting hate comments in Tweets
• Anomaly Detection: An implementation (from scratch) to detect server hardware performance anomalies
• Movie Recommender System using Collaborative Filtering from scratch: recommend movies to user based on taste of other similar users
• Movie Recommender System using Content-Based Filtering from scratch: recommend movies based on plot, cast and crew, genres and keywords