Rohan Kadakia's repositories
anomaly-detection
Anomaly detection using ML approaches such as isolation forests and one-class SVM
kidney-disease-xgboost
Predicting chronic kidney disease using xgboost
API-practice
Interacting with various APIs and parsing the results
caption-maker
Image captioning by transfer learning, with a CNN (VGG) as encoder and LSTM as decoder
caption_app
Repository for my web application
finch-beaks
Statistical analysis of beak measurements for two species of finches
global-bokeh-heroku
Version 2 of my bokeh app
rohanapp
Flask application
Summer-Olympics
Examining data on Olympic medals dating back to 1896
Census
An analysis of census data using SQLAlchemy
deeper-learning
Wage prediction (regression) and digit recognition (classification) in Keras
Euler
Solutions to a few Project Euler problems
fake-news-and-more
Fake news classifier, as well as lots of NLP practice
flight-delays-Dask
Analysis of flight delays due to weather using Dask
fracking-and-parkfield
Statistical analysis of seismicity and earthquake frequency
gapminder-bokeh-heroku
Files needed for heroku deployment of a server-based bokeh app
Insight
Where have Insight data science fellows started their careers?
Kaggle
Solutions to Kaggle competitions
Life-Expectancy
Analyzing life expectancy data while demonstrating data cleaning skills
many_xml_to_df
The goal is to extract data out of many XML files, and into rows of a dataframe
mord
Ordinal regression algorithms
multi-armed-bandits
Introduction to multi-armed bandits, including implementation of an epsilon-greedy algorithm
PySpark_SQL_ML
Running SQL Queries on Spark tables and dataframes, and building PySpark ML pipelines
python-getting-started
Getting Started with Python on Heroku.
recommender-systems
Content-based filtering, collaborative filtering, and an attempt at using LightFM
time-series-intro
Covers basic concepts in time series analysis using real data
Weather
Exploratory data analysis on weather data for Austin, Texas
wiki-cluster
Wikipedia articles, clustering and NMF