APOG_public/acsm-fairifier
0
0
Fork 0
mirror of https://gitea.psi.ch/APOG/acsm-fairifier.git synced 2025-07-10 01:48:00 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fix duplicate time stamp problems and added code to check for NaTs before ebas submission files.)

Browse Source
This commit is contained in:
florez_j
2025-03-04 09:02:37 +01:00
parent 9a23744f63
commit f035afbf3b
3 changed files with 75 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
pipelines/steps/prepare_ebas_submission.py
View File

@ -39,7 +39,8 @@ def join_tables(csv_files: list):
raise RuntimeError("Parameter csv_files contains either an unreachable/broken path or a non-CSV file.")
acum_df = pd.read_csv(csv_files[0])
left_datetime_var = get_metadata(csv_files[0]).get('datetime_var', None)
left_datetime_var = get_metadata(csv_files[0]).get('datetime_var', None)
acum_df = acum_df.drop_duplicates(subset=[left_datetime_var])
if left_datetime_var is None:
raise ValueError(f"Missing datetime_var metadata in {csv_files[0]}")
@ -51,7 +52,8 @@ def join_tables(csv_files: list):
if right_datetime_var is None:
raise ValueError(f"Missing datetime_var metadata in {csv_files[idx]}")
acum_df = acum_df.merge(append_df, left_on=left_datetime_var, right_on=right_datetime_var, how='inner')
append_df = append_df.drop_duplicates(subset=[right_datetime_var])
acum_df = acum_df.merge(append_df, left_on=left_datetime_var, right_on=right_datetime_var, how='left')
return acum_df
@ -87,36 +89,21 @@ if __name__ == "__main__":
#print("Renaming map keys:", acsm_to_ebas['renaming_map'].keys())
acum_df = acum_df.rename(columns=acsm_to_ebas['renaming_map'])
acum_df['ACSM_time'] = pd.to_datetime(acum_df['ACSM_time'])
reduced_set_of_vars = [key for key in acum_df.columns if 'factor' not in key]
print(reduced_set_of_vars)
acum_df.loc[:,reduced_set_of_vars].to_csv('data/JFJ_ACSM-017_2024.txt',sep='\t',index=None, date_format="%Y/%m/%d %H:%M:%S")
#print(reduced_set_of_vars)
flags_acum_df = join_tables([path3])
flags_acum_df = flags_acum_df.rename(columns=acsm_to_ebas['renaming_map'])
# Count the number of NaT (null) values
num_nats = acum_df['ACSM_time'].isna().sum()
# Get the total number of rows
total_rows = len(acum_df)
# Calculate the percentage of NaT values
percentage_nats = (num_nats / total_rows) * 100
print(f"Total rows: {total_rows}")
print(f"NaT (missing) values: {num_nats}")
print(f"Percentage of data loss: {percentage_nats:.2f}%")
acum_df = join_tables([path3])
acum_df = acum_df.rename(columns=acsm_to_ebas['renaming_map'])
# Ensure time columns are datetime
acum_df['ACSM_time'] = pd.to_datetime(acum_df['ACSM_time'])
flags_acum_df['ACSM_time'] = pd.to_datetime(acum_df['ACSM_time'])
# Count the number of NaT (null) values
num_nats = acum_df['ACSM_time'].isna().sum()
# Get the total number of rows
total_rows = len(acum_df)
# Calculate the percentage of NaT values
percentage_nats = (num_nats / total_rows) * 100
@ -124,4 +111,48 @@ if __name__ == "__main__":
print(f"NaT (missing) values: {num_nats}")
print(f"Percentage of data loss: {percentage_nats:.2f}%")
acum_df.to_csv('data/JFJ_ACSM-017_FLAGS_2024.txt',sep='\t',index=None, date_format="%Y/%m/%d %H:%M:%S")
# Count the number of NaT (null) values
num_nats = flags_acum_df['ACSM_time'].isna().sum()
# Get the total number of rows
total_rows = len(flags_acum_df)
# Calculate the percentage of NaT values
percentage_nats = (num_nats / total_rows) * 100
print(f"Total rows: {total_rows}")
print(f"NaT (missing) values: {num_nats}")
print(f"Percentage of data loss: {percentage_nats:.2f}%")
nat_acum = acum_df['ACSM_time'].isna()
nat_flags = flags_acum_df['ACSM_time'].isna()
valid_rows = ~(nat_acum | nat_flags) # Compute valid rows in one step
acum_df.loc[valid_rows.to_numpy(),reduced_set_of_vars].to_csv('data/JFJ_ACSM-017_2024.txt',sep='\t',index=None, date_format="%Y/%m/%d %H:%M:%S")
flags_acum_df.loc[valid_rows.to_numpy(),:].to_csv('data/JFJ_ACSM-017_FLAGS_2024.txt',sep='\t',index=None, date_format="%Y/%m/%d %H:%M:%S")
#acum_df['ACSM_time'] = pd.to_datetime(acum_df['ACSM_time'])
#flags_acum_df['ACSM_time'] = pd.to_datetime(flags_acum_df['ACSM_time'])
# Set datetime as index
#acum_df.set_index('ACSM_time', inplace=True)
#flags_acum_df.set_index('ACSM_time', inplace=True)
#nat_acum = acum_df['ACSM_time'].isna()
#nat_flags = flags_acum_df['ACSM_time'].isna()
#valid_rows = ~(nat_acum | nat_flags) # Compute valid rows in one step
#acum_df_filtered = acum_df.loc[valid_rows.to_numpy(),:]
#flags_acum_df_filtered = flags_acum_df[valid_rows.to_numpy(),:]
# Step 4: Apply the valid mask to both dataframes
#acum_df_filtered = acum_df[valid_rows]
#flags_acum_df_filtered = flags_acum_df[valid_rows]
# Display results
#print(acum_df_filtered)
#print(flags_acum_df_filtered)