24_deb_pkg_gov/sample_good_subset.py

import csv
import os
import pandas as pd


def for_readme_files():
    ld_csv_path = "final_data/deb_readme_did.csv"
    ta_csv_path = "text_analysis/d_readability_readme.csv"
    topic_csv_path = "text_analysis/readme_file_topic_distributions.csv"
    # criteria for good readme
    # mean of three examples listed on the contributing page
    # https://github.com/rails/rails/blob/main/README.md (71s)
    # https://github.com/github/docs/blob/main/README.md (48s)
    # https://github.com/opengovernment/opengovernment/blob/master/README.md (14s)
    # Median 48s
    readme_ta_df = pd.read_csv(ta_csv_path)
    threshold_count = readme_ta_df[readme_ta_df['reading_time'] >= 48].shape[0]
    print(threshold_count)
    # R8 > 0.125
    readme_topic_df = pd.read_csv(topic_csv_path)

def for_contributing_files():
    ld_csv_path = "final_data/deb_contrib_did.csv"
    ta_csv_path = "text_analysis/d_readability_contributing.csv"
    topic_csv_path = "text_analysis/contrib_file_topic_distributions.csv"
    # criteria for good contributing 
    # mean of three examples listed on https://docs.github.com/en/communities/setting-up-your-project-for-healthy-contributions/setting-guidelines-for-repository-contributors
    # https://github.com/rails/rails/blob/main/CONTRIBUTING.md (116s)
    # https://github.com/github/docs/blob/main/.github/CONTRIBUTING.md (59s)
    # https://github.com/opengovernment/opengovernment/blob/master/CONTRIBUTING.md (45s)
    # Median 59s
    contributing_ta_df = pd.read_csv(ta_csv_path)
    threshold_count = contributing_ta_df[contributing_ta_df['reading_time'] >= 59].shape[0]
    print(threshold_count)
    # and then making sure they're on topic, C4 > 0.25
    contributing_ta_df = pd.read_csv(topic_csv_path)

if __name__ == "__main__":
    for_contributing_files()
    for_readme_files()