Replaced read_dataset_from_hdf5file(hdf5_file_path, dataset_path) with HDF5DataOpsManager.extract_dataset_as_dataframe(self,dataset_name)

src/hdf5_ops.py

@@ -22,9 +22,11 @@ import copy
 class HDF5DataOpsManager():
 
     """
-    A class to handle HDF5 file operations.
+    A class to handle HDF5 fundamental middle level file operations to power data updates, metadata revision, and data analysis
+    with hdf5 files encoding multi-instrument experimental campaign data.
 
     Parameters:
+    -----------
         path_to_file : str
             path/to/hdf5file.
         mode : str
@@ -85,7 +87,6 @@ class HDF5DataOpsManager():
 
 
     
-    
     def extract_dataset_as_dataframe(self,dataset_name):
         """ 
         returns a copy of the dataset content in the form of dataframe when possible or numpy array 
@@ -423,29 +424,6 @@ class HDF5DataOpsManager():
 
         
 
-        
-
-
-
-
-
-def read_dataset_from_hdf5file(hdf5_file_path, dataset_path):
-    # Open the HDF5 file
-    with h5py.File(hdf5_file_path, 'r') as hdf:
-        # Load the dataset
-        dataset = hdf[dataset_path]
-        data = np.empty(dataset.shape, dtype=dataset.dtype)
-        dataset.read_direct(data)
-        df = pd.DataFrame(data)
-        
-        for col_name in df.select_dtypes(exclude='number'):
-            df[col_name] = df[col_name].str.decode('utf-8') #apply(lambda x: x.decode('utf-8') if isinstance(x,bytes) else x)
-        ## Extract metadata (attributes) and convert to a dictionary
-        #metadata = hdf5_vis.construct_attributes_dict(hdf[dataset_name].attrs)
-        ## Create a one-row DataFrame with the metadata
-        #metadata_df = pd.DataFrame.from_dict(data, orient='columns')        
-    return df
-
 def get_parent_child_relationships(file: h5py.File):
 
     nodes = ['/']