24_deb_pkg_gov/sample_good_subset.py
2024-10-24 15:44:23 -04:00

22 lines
583 B
Python

import csv
import os
import pandas as pd
def for_readme_files():
ld_csv_path = "final_data/deb_readme_did.csv"
ta_csv_path = "d_readability_readme.csv"
topic_csv_path = "text_analysis/readme_file_topic_distributions.csv"
# criteria for good readme
# longer than half of a pageview
def for_contributing_files():
ld_csv_path = "final_data/deb_contrib_did.csv"
ta_csv_path = "d_readability_contrib.csv"
topic_csv_path = "text_analysis/contrib_file_topic_distributions.csv"
# criteria for good contributing
# longer than half of a pageview