AssignemtTask.txt

ASSIGNNMENT 1:-
1) Take sample dataset of IMDB,
2) Remove special chracters and hyperlinks from text.
3) Using Spacy Find the user names,City mentioned in the top 5000 records and store in list and add another column to list called Entity like if name is name of
person then new column should contain "Person" if name is name of City then new column should be "City"
4) Store above data in DataFrame and convert  it to JSON and  return that JSON from function.
5) Create web app through Flask and create POST API and post API will take Name(text) as input parameter and should ruturn is it City or Person.

Dataset for this question.
https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews#IMDB%20Dataset.csv


Assignment 2:-

In attached SpeechToText.json file there are two josn object. One contains the time stamp of each spoken word and another contains the speakers lable with from time and to time. Now we want to combine these 2 objects and get the each sentence seperated with speaker wise. 
Like Speaker1:so thank you very much for coming David it's g..
Speaker2: good as my pleasure Michael glad to be with you
Spearker1: how real is artificial intelligence
Speaker2: the question of how real is artificial intelli...
.
.
.
like this.


Deliverables:
Share python code files with dataset attached and add comments to each sections.