SAHIL JAIN
Started with "Hello World" and now I'm here.
Python, Web Scraping, SQL, Machine Learning, NLP, Plotly Dash, Power BI, Excel.
Hello! I am Sahil Jain, a Data Analyst currently working at Wizikey. I believe in God for miracles but for everything else, I believe there is Data. My work revolves around crunching insights from Raw Data and solving business problems. I specialize mostly in Natural Language Processing tasks and I make data easier to understand through various Visualization techniques.
Apart from coding, you can find me posting memes on twitter when I'm bored or playing chess/badminton/table-tennis or video games. You can contact me through Email or Twitter if you would like to collaborate on Kaggle Competitions or even if you need help with anything related to Data Analytics. I'm happy to help.
This will extract all the similar tweets which might have been tweeted before for a particular user.
This is a web scraping project where I used the snscrape library and analytics to find similar tweets. It uses nltk for data cleaning and finds the last most similar tweet for a given tweet.
This will convert Google News to a CSV Format
The following Dashboard is build using Dash Plotly and Deployed in Heroku Platform. The code uses Google News RSS Feed to extract real time news from Google. The News Extracted can be downloaded as a CSV File.
This model will categorize article into various categories.
This is a multi-label classification problem which has been build using a Maching Learning model. It can automatically categorize an article into multiple categories depending on the news.
This model will estimate the reading time of an Article.
This model is build using Flask and Deployed in Heroku Platform. The code uses various NLP techniques to tokenize the texts and predicts the estimated reading time based on the average human reading time per word and sentences.
Data Analytics
Business Strategy and Analytics
Actuarial Underwriting and Data Analytics