mgaughan/24_deb_pkg_gov
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

subsetting data set for stuff

Browse Source
This commit is contained in:
mgaughan 2024-10-26 16:31:43 -05:00
parent 5bc4003a99
commit 456b6e85cf
1 changed files with 25 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
sample_good_subset.py
View File

@ -5,17 +5,36 @@ import pandas as pd
def for_readme_files(): def for_readme_files():
ld_csv_path = "final_data/deb_readme_did.csv" ld_csv_path = "final_data/deb_readme_did.csv"
ta_csv_path = "d_readability_readme.csv" ta_csv_path = "text_analysis/d_readability_readme.csv"
topic_csv_path = "text_analysis/readme_file_topic_distributions.csv" topic_csv_path = "text_analysis/readme_file_topic_distributions.csv"
# criteria for good readme # criteria for good readme
# longer than half of a pageview # 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(): def for_contributing_files():
ld_csv_path = "final_data/deb_contrib_did.csv" ld_csv_path = "final_data/deb_contrib_did.csv"
ta_csv_path = "d_readability_contrib.csv" ta_csv_path = "text_analysis/d_readability_contributing.csv"
topic_csv_path = "text_analysis/contrib_file_topic_distributions.csv" topic_csv_path = "text_analysis/contrib_file_topic_distributions.csv"
# criteria for good contributing # criteria for good contributing
# longer than half of a pageview # 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()