| |
| import pandas as pd |
|
|
| |
| file_path = '<YOUR_DATA_PATH>/' |
| input_file_path = file_path + 'data_for_model_e_columns/' |
|
|
|
|
| def read_data(file): |
| """ |
| Read in data source |
| -------- |
| :param file: string filename |
| :return: dataframe |
| """ |
| df = pd.read_csv(file) |
| return df |
|
|
|
|
| def format_data(data, IDs, onboard): |
| """ |
| Convert datetime columns to datetime format, filter to only include RECEIVER and scale up IDs, |
| and join oboarding dates |
| -------- |
| :param data: NIV dataframe |
| :param IDs: dataframe containing Study IDs |
| :param onboard: dataframe containing onboarding dates |
| :return: formatted dataframe |
| """ |
| data = data[['Study_ID', 'ie_ratio_value_50', 'ie_ratio_value_95', |
| 'ie_ratio_maximum_value', 'resp_events_AHI', |
| 'resp_events_HI', 'Stop_time', 'Start_time']] |
| data['Stop_time'] = pd.to_datetime(data['Stop_time']) |
| onboard['OB_date'] = pd.to_datetime(onboard['OB_date']) |
| onboard['yearcensor'] = onboard['OB_date'] + pd.offsets.DateOffset(days=365) |
| data = pd.merge(IDs, data, on="Study_ID", how="left") |
| data = pd.merge(data, onboard, on="Study_ID", how="left") |
| return data |
|
|
|
|
| def filter_study_censor(data): |
| """ |
| Filter the dataframe to only contain data obtained before the study censor date |
| -------- |
| :param data: dataframe |
| :return: dataframe containing data obtained before the study censor date |
| """ |
| return data[data['Stop_time'] < '2021-09-01'] |
|
|
|
|
| def filter_first_year(data): |
| """ |
| Filter the dataframe to only contain data obtained in the first year post-onboarding |
| -------- |
| :param data: dataframe |
| :return: dataframe containing only data obtained in the first year post-onboarding |
| """ |
| return data[data['yearcensor'] >= data['Stop_time']] |
|
|
|
|
| def mean_max_summary(data, col): |
| """ |
| Create a dataframe showing mean and max values per group |
| -------- |
| :param data: dataframe |
| :param col: parameter to group on |
| :return: summary dataframe showing mean and max scores for each study ID |
| """ |
| summary_metrics = ['mean', 'max', 'count'] |
| return data.groupby(col).agg( |
| {'ie_ratio_value_50': summary_metrics, |
| 'ie_ratio_value_95': summary_metrics, |
| 'ie_ratio_maximum_value': summary_metrics, |
| 'resp_events_AHI': summary_metrics, |
| 'resp_events_HI': summary_metrics}) |
|
|
|
|
| def calculate_summary_data(data): |
| """ |
| Calculate the average NIV parameters up to the study censor date and a year |
| after onboarding for each study ID and save the resulting summary |
| dataframe as a csv file |
| -------- |
| :param data: dataframe |
| :param typ: string value to be input into file name showing what is summarised |
| """ |
| data_filter_censor = filter_study_censor(data) |
| summary_censor = mean_max_summary(data_filter_censor, 'Study_ID') |
|
|
| data_year_censor = filter_first_year(data) |
| summary_year = mean_max_summary(data_year_censor, 'Study_ID') |
| |
| output_file_path = file_path + 'NIV_ Average_parameters_to_' |
| summary_censor.to_csv(output_file_path + 'censor.csv') |
| summary_year.to_csv(output_file_path + 'year.csv') |
|
|
|
|
| def main(): |
| |
| NIV_data_file = input_file_path + "NIV_data_wrangled.csv" |
| onboard_file = input_file_path + "onboarding_dates.csv" |
| RC_SU1_IDs_file = input_file_path + "RC_SU1_IDs.csv" |
|
|
| NIV_data = read_data(NIV_data_file) |
| onboard = read_data(onboard_file) |
| RC_SU1_IDs = read_data(RC_SU1_IDs_file) |
|
|
| |
| NIV_data = format_data(NIV_data, RC_SU1_IDs, onboard) |
|
|
| |
| calculate_summary_data(NIV_data) |
|
|
|
|
| main() |
