geovisualisierung/projects/project-3/openapi/read_csv.py

import csv
import os


def read_files(base_dir, max_num=2):
    data = []
    for file in os.listdir(base_dir):
        if max_num == 0:
            break
        print(f'reading file \'{file}\'')
        with open(os.path.join(base_dir, file), 'r', newline='') as input_file:
            data.extend(list(csv.DictReader(input_file)))
        max_num -= 1
    return data


def get_key_counts(data):
    all_key_sets = [e.keys() for e in data]
    key_counts = {}
    for key_set in all_key_sets:
        for key in key_set:
            try:
                key_counts[key] += 1
            except KeyError:
                key_counts[key] = 1
    return key_counts


def main():
    data = read_files('data/usage-stats', max_num=10)
    print("Sorting")
    data = sorted(data, key=lambda entry: int(entry['Rental Id']))
    print(f'final length of data {len(data)}')

    # counts = get_key_counts(data)
    # for count, val in counts.items():
    #     if val != len(data):
    #         print(count, val)
    # print(counts)
    with open('test.csv', 'w', newline='') as out_file:
        writer = csv.DictWriter(out_file, data[0].keys(), extrasaction='ignore')
        writer.writeheader()
        writer.writerows(data)


if __name__ == '__main__':
    main()


#
# with open('test.csv') as again_in:
#     reader2 = csv.DictReader(again_in)
#     data2 = list(reader2)
#
# print(data2[0])
#
# print(f"Is same? {data[0] == data2[0]}")