import data_preprocessing

# Example usage:
# combined_df = process_stepcount_files(
#     input_folders=[
#         '/content/drive/My Drive/Data/iOS',
#         '/content/drive/My Drive/Data/Watch'
#     ],
#     output_folder='/content/drive/My Drive/Data/Results',
#     files_to_skip={
#         'StepCount06.csv', 'StepCount10.csv', 'StepCount12.csv',
#         'StepCount13.csv', 'StepCount15.csv', 'StepCount17.csv',
#         'StepCount18.csv', 'StepCount20.csv', 'StepCount24.csv',
#         'StepCount27.csv', 'StepCount31.csv', 'StepCount32.csv',
#         'StepCount42.csv', 'StepCount46.csv'
#     },
#     interval='15T',     # or '1H'
#     threshold=25        # or None
# )

input_folders=[
         'Step_Data_Project_India/Europe/Europe',
         'Step_Data_Project_India/Rest_of_the_World'
]
output_folder='Step_Data_Project_India/Preprocessing_Results'
files_to_skip={
         'StepCount06.csv', 'StepCount10.csv', 'StepCount12.csv',
         'StepCount13.csv', 'StepCount15.csv', 'StepCount17.csv',
         'StepCount18.csv', 'StepCount20.csv', 'StepCount24.csv',
         'StepCount27.csv', 'StepCount31.csv', 'StepCount32.csv',
         'StepCount42.csv', 'StepCount46.csv'
}
interval='15T'    
threshold=25 

combined_df = data_preprocessing.process_stepcount_files(input_folders, output_folder, files_to_skip, interval, threshold)