notes.py

x.py

from collections import defaultdict
import csv
csv.field_size_limit(999999999)


def get_csv(filename):
    # get data from csv
    # don't use built ins, like input, as variable names
    with open('filename', 'r') as file_handle:
        reader = csv.reader(file_handle, delimiter='|')
        return [row for row in reader]


def get_targets(filename):
    # read in filename and return a set of each master key
    return set([row[0] for row in get_csv(filename)])


def get_keepers(filename):
    # read in filename and return a set with each report_key with filter 'M' in third column
    keepers = set()
    # let's recycle our get_csv function here
    rows = get_csv(filename)
    for row in rows:
        if row[2] == 'M':
        keepers.add(row[0])
    # this should work, but add a print statement to make sure as you debug
    print(keepers)
    # this could also be:
    keepers = set(r[0] for r in rows if r[2] == 'M')
    print(keepers)
    return keepers


def gather(keepers, data_file):
    '''
    This returns a dictionary of report_key: [list of data_points]
    '''
    found = defaultdict(list)
    # remember we need to reuse our read_csv function
    for key, point in read_csv(data_file):
        if key in keepers:
            found[key].append(point)

    
    return found


def save_csv(found):
    with open('outputCSV.txt', 'w', newline='') as output:
        writer = csv.writer(output, delimiter='|')
        # since the dictionary is set up like report_key:[list of data], we
        # need both the key and value, so use the items() method to get both
        for report_key, data_points in found.items():
            # now build the new_row to look like:
            # [report_key, data, data, ...]
            new_row = [report_key] + data_points
            # just to make sure, print during debugging
            print(new_row)
            writer.writerow(new_row)


def main():
    targets = get_targets('masterkeyCSV.txt')
    keepers = get_keepers('CSVwithFILTER.txt')

    keepers = targets & keepers

    found = gather(keepers, 'CSVwithDATAPOINT.txt')
    save_csv(found)