Auchinto Chatterjee


Data Scientist

Looking forward to solve interesting problems...

Portfolio

Personal Lab

Forest Cover Prediction

Multi-Class Classification
Python • Flask • Matplotlib • Pandas • Scikit-Learn • Imblean • XgBoost • Sqlite3

Predicting Type of Forest Cover given features based on data collected as part of previous year surveys. This is a multi-class classification problem.

Market Analysis - Data Science Jobs

Exploratory Data Analysis
Python • NLTK • Beautiful Soup • Matplotlib • Seaborn • Pandas • Scikit-Learn

Acquisition of data using web-scraping, and optimizing the job application process. Analyze job openings, the key requirements and paygrade trends across industries.

Text to Image Converter

Generative Adversarial Networks
Python • Google Colab • Tensorflow • Keras • NLTK • Scikit-Learn

Create an image, given a textual description using a model of Stacked - Generative Adversarial Networks (Stack - GANs). Deploy the trained model using Flask on Heroku.

Podcast Transcript Analysis

Natural Language Processing
Python • NLTK • Beautiful Soup • Matplotlib • Seaborn • Pandas • WordCloud

Analyze the transcripts of podcasts from a particular domain, such as Data Science, thus summarize the content to derive consolidated meaning.

Sales Insights - Power BI

Data Visualization
SQL ♦ Data Engineering ♦ Data Visualization

Create a Power BI dashboard showcasing insights derived from the sales dump, after transformations, available as a MySQL Data Source.

Stock Price Prediction

Time-Series Analysis
Python • YFinance • Matplotlib • Seaborn • Numpy • Pandas • Scikit-Learn

Predicting stock price using various machine learning models.

Self Driving Car Simulation (2D)

Reinforcement Learning
Javascript

Developing a simulation of self driving car that evolves through generations to navigate better through coming traffic using Deep Learning.

Cotton Leaf Disease Detection

Image Classification
Python • Keras • Matplotlib • Numpy • Pandas

Detect whether a cotton leaf or a cotton plant is affected by the disease by analysing the image of the cotton plant and it's leaves.

Simpson Character Identification

Image Classification
Python • OpenCV • Keras • Matplotlib • Numpy

Recognize the various characters in Simpsons in the given images.

Penguin Species

Classification
Python • Streamlit • Pandas • Scikit-Learn

Implement a Dashboard to identify the penguin species given features like island, sex, bill - length & depth, flipper length and body mass.

Iris Flower Species

Classification
Python • Streamlit • Pandas • Scikit-Learn

Implement a Dashboard to identify the Iris flower species based on features sepal length & width, petal length & width.

Boston House Price Prediction

Regression
Python • Streamlit • Beautiful Soup • Pandas • Scikit-Learn

Implement a Dashboard to predict the house prices in Boston using Random Forest Regression

Vehicle Price Prediction

Regression
Python • Flask • Numpy • Matplotlib • Seaborn • Pandas • Scikit-Learn

Implement a Dashboard to predict the vehicle price using Random Forest Regression.

Crypto-Currency Value

Exploratory Data Analysis
Python • Streamlit • Beautiful Soup • Matplotlib • Pandas

Implement a dashboard showcasing analysis of 100 Crypto-Currencies.

S&P500 Stock Closing Price

Exploratory Data Analysis
Python • Streamlit • YFinance • Matplotlib • Pandas

Implement a dashboard showcasing analysis of S&P500 Equity Index.

Football Player Stats

Exploratory Data Analysis
Python • Streamlit • Matplotlib • Pandas

Implement a dashboard showcasing analysis of Pro-Football Player Statistics.

NBA Basketball Player Stats

Exploratory Data Analysis
Python • Streamlit • Matplotlib • Pandas

Implement a dashboard showcasing analysis of NBA Basketball Player Statistics.