INNER CODE UNIT · Python
prep_kaggle_data_on_tfl_trips
aeturrell/coding-for-economists · data_set_prep.py:179
def prep_kaggle_data_on_tfl_trips():
"""Prep a sliver of Kaggle data on tfl trips for the tables page.
Note that this uses data from this url: https://www.kaggle.com/code/benivitai/tfl-oyster-card-journeys-analysis
This function expects that the csv file, Nov09JnyExport.csv, has been extracted and downloaded
to data/data_not_stored/
"""
tfl = pd.read_csv(Path("data/data_not_stored/Nov09JnyExport.csv"))
tfl = clean_columns(tfl)
# cast columns
data_type_dict = {
"downo": "int",
"daytype": "category",
"sub_system": "category",
"start_stn": "category",
"end_station": "category",
"ent_time": "int",
"ex_time": "int",