Document Similarity ( NLP)

Technology Used

• Mongo Db
• Pyhton 3.6 version (Flask)

Requirements

• Python version 3.5 or greater

• pip to install packages

• Mongo Db

• Pycharm (Not Essential - could run code using commmand Line)

• pip install flask

• pip install pymongo

• pip install numpy

• pip install scipy

• pip install –U nltk

• import nlkt on python shell

• first write nltk.dowload(‘punkt’)

• Second write nltk.download(‘averaged_perceptron_tagger’)

• pip install – U gensim

Procedure To Run The Code

• Clone the repository
• Install all the things mentioned in the Requirements Section
• Run mongo db using the command "mongod" on command line (Make sure the mongoDb run on port 27017)
• Open the cloned Directory
• Run "python connection.py" on command line
• Finally open the link on the browser (http://127.0.0.1:5000)

Screen Shots

• Running Mongodb

• Running connection.py

• Opening Browser / Home Page (http://127.0.0.1:5000)

• Counting_words

• Total /Merging counts of words of all books

• Counting Verbs_Nouns

• Total /Merging counts of verbs/Nouns of all books

• Top 10 unique and similar Sentence

• User Input for Sentence Similarity