-
- Take sample dataset of IMDB,
-
- Remove special chracters and hyperlinks from text.
-
- 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"
-
- Store above data in DataFrame and convert it to JSON and return that JSON from function.
-
- 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
this work done by Ahmed Salama at Aug-2022