24_deb_pkg_gov/text_analysis/qual_sampling.py

import csv
import io 
import shutil 
import os 
from random import sample

readme_wd = "/data/users/mgaughan/kkex/time_specific_files/dwo_partitioned_readme"
contributing_wd = "/data/users/mgaughan/kkex/time_specific_files/dwo_partitioned_contributing"


def sample_from_doc(sample_k, doc_directory):
    subdirs = os.listdir(doc_directory)
    for dir in subdirs: 
        print(dir)
        files = os.listdir(doc_directory + "/" + dir)
        final_sampled = []
        while len(final_sampled) < sample_k:
            trial_sample = sample(files, 1)[0]
            with open(doc_directory + "/" + dir + "/" + trial_sample,"r") as f:
                file_length = len(f.readlines())
                if file_length >= 10:
                    final_sampled.append([trial_sample, file_length])
        print(final_sampled)

if __name__ == "__main__":
    sample_from_doc(3, contributing_wd)