5505-public/dima
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add property to extracted dataset as dataframe. Now time column is of datetime type to facilitate downstream procesing.

Browse Source
This commit is contained in:
florez_j
2025-02-04 17:23:32 +01:00
parent 6fae139360
commit 5d0ab4603f
1 changed files with 9 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/hdf5_ops.py
View File

@ -116,7 +116,7 @@ class HDF5DataOpsManager():
return None return None, None
@ -128,6 +128,8 @@ class HDF5DataOpsManager():
raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file_obj' method before attempting to extract datasets.") raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file_obj' method before attempting to extract datasets.")
dataset_obj = self.file_obj[dataset_name] dataset_obj = self.file_obj[dataset_name]
datetime_var, datetime_format = self.infer_datetime_variable(dataset_name)
# Read dataset content from dataset obj # Read dataset content from dataset obj
data = dataset_obj[...] data = dataset_obj[...]
# The above statement can be understood as follows: # The above statement can be understood as follows:
@ -136,6 +138,12 @@ class HDF5DataOpsManager():
# dataset_obj.read_direct(data) # dataset_obj.read_direct(data)
try: try:
data = pd.DataFrame(data)
if datetime_var in data.columns:
data[datetime_var] = data[datetime_var].apply(lambda x : x.decode())
data[datetime_var] = pd.to_datetime(data[datetime_var],format=datetime_format,errors='coerce')
return pd.DataFrame(data) return pd.DataFrame(data)
except ValueError as e: except ValueError as e:
logging.error(f"Failed to convert dataset '{dataset_name}' to DataFrame: {e}. Instead, dataset will be returned as Numpy array.") logging.error(f"Failed to convert dataset '{dataset_name}' to DataFrame: {e}. Instead, dataset will be returned as Numpy array.")