top of page

PROJECTS

Click on "Read More" to know more at the end of the description of each project.

tf.png

TENSORFLOW

APRIL 2018-JUNE 2018

This project is a great example of how I keep my knowledge on TensorFlow updated. I started with the very basics of TensorFlow. I built a a simple neural network of 4 hidden layers for the handwritten character recognition, the famous MNIST Dataset. I have also demonstrated the use of Tensorboard. Then after, I demonstrated the processing of the text data and the wrangling required for sentiment analysis using TensorFlow. I am continuing to add more and more content to this repository on Github

github-logo.png

OPEN SOURCE PROJECT: ANALYSIS OF GITHUB PROFILES RELATED TO DEEP LEARNING COMMUNITY.

JAN 2018-MAY 2018

Data integrated and gathered from Github API. Sample data has been collected of the primary members and contributors of primary open source deep learning frameworks: TensorFlow, PyTorch, Caffe2, Theano, Keras. Hypothesis formulation and testing, interaction effects, drawing inferences and recommendations for upcoming deep learning contributors and developers.

Language: Python 3 and R. Libraries: Pandas, Scikit-Learn, Statsmodel.  IDE: Jupyter Notebook(Anaconda), R-Studio

Churn Rate Prediction: Statistical Modelling and Economic Interpretation of the Model..Read More

​

Screen Shot 2018-06-03 at 3.04.06 PM.png

ENERGY CONSUMPTION PREDICTION

JAN 2018-MAY 2018

This project aims at analyzing the data in hand and use it to forecast the total energy consumption of electric appliances that are installed in a building using various data mining methods like regression and time series analysis. See the code here.  This project provides a hands-on experience of using the various data mining methods to analyze a data set for practical applications from the inference obtained after data analysis..Read More

Screen Shot 2018-06-03 at 3.25.19 PM.png

DETAILED ANALYSIS OF CUSTOMER CHURN IN TELCO

DEC 2017-FEB 2018

In this project, we have explored the rate of loss of customers (also known as churn rate) of a telecommunications corporation, TELCO. The data can be acquired from the following link:

Link : https://www.ibm.com/communities/analytics/watson-analytics-blog/predictive-insights-in-the-telco-customer-churn-data-set/

This data set provides info to help you predict behavior to retain customers..Read More

Hurricane_NOAA1.jpg

WEATHER EXPLORATORY DATA ANALYTICS

NOV 2017

It was a good exploratory data analysis project.

This project is built on numpy and matplotlib.

PROJECT GOALS:

1. Load NOAA Station and temperature data from text files. 2. Integrate, smooth and plot data.

3. Compute Daily Records.

4. Comparing warmest year of a cold location with the coldest year of warmest location..Read More

  • LinkedIn
  • Facebook
  • YouTube
  • Twitter

©2018 by Tanay Karmarkar

bottom of page