We have implemented the cosine text similarity task in three different methods:
- Using count vector method
- Using sklearn's TfidfVectorizer
- Using word2vec model from genism
All the details of these methods are documented in the notebook's markdown cells.
This project is situated in ./Task_One/TextSimilarity/TextSimilarityCosine.ipynb
We have implemented the sentiment analysis task in two different methods:
- Using Naïve Bayes Classifier
- Using textblob library
All the details of these methods are documented in the notebook's markdown cells.
This project is situated in ./Task_One/SentimentAnalysis/TwitterSentiment.ipynb
We have split task two into two parts:
- Data Cleaning /Non Visual Analytics
- Data Visualization / Visual Analytics.
All the details and logic for this are documented in the notebook's markdown cells.
This project is situated in ./Task_Two/DataVisualization.ipynb