The PDF analysis has been done for the Data Camp teaches by Thierno Diallo.
As principal-developer we have Arsene BAKANDAKAN BOKONDO, as Scrum Master we have Essaid BENAMAR and finaly, Jonah JAUBERT is the Product Owner
Use the package manager pip to install librairies.
Then, install nltk to analyse data
pip install nltkYou need seaborn to vizualise data
pip install seabornThe wordcloud lib produce nice viz as cloud of words
pip install wordcloudFor sentiment analysis, we use textblob
pip install textblobWe are using machine-learning algorithm to predict with sklearn
pip install sklearnYou have 2 types of analysis:
- Google News
##Credit