def make_df_results():
"""
Creates two dataframes, one containing all speed data and one containing all strokes data
"""
file_name_results = '../data/Racedata/total_file_results.csv'
time = datetime.now().strftime('%d-%m %H:%M:%S')
print("[%s: Loading results feature file...]" % time)
# If both total files are present no new files are created, but the df's are taken directly form the csv files
# (Saves time)
if os.path.isfile(file_name_results) and os.path.isfile(file_name_results):
df_results = pd.read_csv(file_name_results, index_col=0)
# If the file is missing, create a new one from the files in the results folders
else:
print('Could not find results file')
all_results_files_dict = {}
# loop through all available years (Hardcoded limited from 2013 to 2016) If one wants to include 2017 change 7 into 8
for i in range(3, 7):
path_results = '../data/Racedata/201' + str(i) + '/Results/'
# All files are retrieved from the specified speeds folder and added to the all_speeds_files_dict
file_retriever_results = rf.retrieve_files(path_results)
results_files_dict = file_retriever_results.get_csv_files()
all_results_files_dict = merge_two_dicts(all_results_files_dict, results_files_dict)
# preproces results data to a total df
data_preparator_results = ppr.preprocess_race(all_results_files_dict)
df_results = data_preparator_results.read_csv_results()
# Is returned to main
return df_results
def make_data_results(file_dict_results):
"""
:param: file_dict_results
:return: Nothing, just places parsed files in the folder Results. These folders are in each year containing
the parsed files for that year
"""
prep_results = ppr.preprocess_race(file_dict_results)
prep_results.read_raw_results()
def make_data_GPS(file_dict_GPS):
"""
:param: file_dict_GPS
:return: Nothing, just places parsed files in the folders Speeds and Strokes. These folders are in each year containing
the parsed files for that year
"""
prep_GPS = ppr.preprocess_race(file_dict_GPS)
prep_GPS.read_raw_GPS()