diff --git a/src/process/twitter_process.py b/src/process/twitter_process.py index 1cf6282..5178c98 100644 --- a/src/process/twitter_process.py +++ b/src/process/twitter_process.py @@ -1,9 +1,11 @@ -import os +""" +TODO: Module Docstring +""" import random -from dataclasses import dataclass from typing import NamedTuple +from dataclasses import dataclass -from py7zr import py7zr, SevenZipFile +from py7zr import SevenZipFile from utils import * @@ -101,6 +103,9 @@ def get_user_popularity_ranking(user: str, user_dir: str = './data/twitter/user/ @dataclass() class Sample: + """ + This is a data class storing our different samples. + """ most_popular: list[ProcessedUser] random: list[ProcessedUser] @@ -165,7 +170,8 @@ def load_user_sample(user_dir: str = './data/twitter/user/') -> Sample: class Posting(NamedTuple): """ - Posting data (whether or not a posting is covid-related) + Posting data stores the processed tweets data, and it contains info such as whether or not a + tweet is covid-related """ # Full text of the post's content covid_related: bool diff --git a/src/process/twitter_visualization.py b/src/process/twitter_visualization.py index 3b048e0..7427228 100644 --- a/src/process/twitter_visualization.py +++ b/src/process/twitter_visualization.py @@ -1,3 +1,6 @@ +""" +TODO: Module Docstring +""" from matplotlib import pyplot as plt from tabulate import tabulate