It works with chats between two people or group chats. It will display the results in terminal as well as write it to a file (stats.txt).
This script requires the TextBlob package to be installed.
The main script. This script does all the processing of the history file.
python whatsapp_stats.py <filename> [<stopwords_filename>]
Where <filename> is the whatsapp chat history file e.g. WhatsApp Chat with XYZ.txt
You do not have to specify the stopwords file, it will then just use the default file stopwords.txt.
Contains a list of words that you wish to exclude from the most common words count. Contains words like a, an, the, I etc.
Please raise issues with any difficulties you find.
For the sentiment analysis I'm using TextBlob.
For the stopwords list I extended the English Google stopwords list found at https://code.google.com/p/stop-words/.
A script that processes the history file to build a database of the most used words in a chat, along with the sentement of each word.