Program to compute histogram bins of code line counts by project folder using line counts from cloc.

aggregate_by_folder.py

#!/usr/bin/env python
# A solution to
# https://stackoverflow.com/questions/70182311/is-there-a-tool-that-shows-a-distribution-of-lines-of-code-per-file-of-a-folder
import sys
import os.path
import pandas as pd
def add_folder(df):
    """
    Return a Pandas dataframe with an additional 'folder' column
    containing each file's parent directory
    """
    header = 'github.com/AlDanial/cloc'
    df = df.drop(df.columns[df.columns.str.contains(header)], axis=1)
    df['folder'] = df['filename'].dropna().apply(os.path.dirname)
    return df

def bin_by_folder(df):
    bins = list(range(0,1000,50))
    return df.groupby('folder')['code'].value_counts(bins=bins).sort_index()

def file_count_by_folder(df):
    df_files = pd.pivot_table(df, index=['folder'], aggfunc='count')
    file_counts = df_files.rename(columns={'blank':'file count'})
    return file_counts[['file count']]

def main():
    if len(sys.argv) != 2:
        print(f"Usage:  {sys.argv[0]} data.csv")
        print("     where the .csv file is created with")
        print("       cloc --by-file --csv --out data.csv my_code_base")
        raise SystemExit
    pd.set_option('display.max_rows', None)
    pd.set_option('display.width', None)
    pd.set_option('display.max_colwidth', None)
    df = add_folder(pd.read_csv(sys.argv[1]))
    print(pd.pivot_table(df, index=['folder'], aggfunc='sum'))
    print('-' * 50)
    print(file_count_by_folder(df))
    print('-' * 50)
    print(bin_by_folder(df))

if __name__ == "__main__": main()