Developed a class to manage data operations on a given hdf5 file

src/hdf5_data_extraction.py

@@ -3,6 +3,66 @@ import pandas as pd
 import numpy as np
 import os
 import src.hdf5_vis as hdf5_vis
+import logging
+
+class HDF5DataOpsManager():
+    def __init__(self, file_path, mode = 'r+') -> None:
+
+        if mode in ['r','r+']:
+            self.mode = mode
+        self.file_path = file_path        
+        self.file_obj = None
+        self._open_file()
+
+    # Define private methods
+    
+    def _open_file(self): 
+        if self.file_obj is None:
+            self.file_obj = h5py.File(self.file_path, self.mode)
+
+    def _collect_dataset_names(self, name, obj, list_of_datasets):
+        if isinstance(obj, h5py.Dataset):
+            list_of_datasets.append(name)
+
+    # Define public methods
+
+    def close_file(self):
+        if self.file_obj:
+            self.file_obj.flush()  # Ensure all data is written to disk
+            self.file_obj.close()
+            self.file_obj = None
+
+    def retrieve_dataframe_of_dataset_names(self):
+        list_of_datasets = []
+        self.file_obj.visititems(lambda name, obj: self._collect_dataset_names(name, obj, list_of_datasets))
+
+        dataset_df = pd.DataFrame({'dataset_name': list_of_datasets})
+        dataset_df['parent_instrument'] = dataset_df['dataset_name'].apply(lambda x: x.split('/')[-3])
+        dataset_df['parent_file'] = dataset_df['dataset_name'].apply(lambda x: x.split('/')[-2])
+
+        return dataset_df
+    
+    def read_dataset_as_dataframe(self,dataset_name):
+        """ 
+        returns a copy of the dataset content in the form of dataframe when possible or numpy array 
+        """
+        if self.file_obj is None:
+            self.open_file()
+
+        dataset_obj = self.file_obj()[dataset_name]
+        # Read dataset content from dataset obj
+        data = dataset_obj[...] 
+        # The above statement can be understood as follows: 
+        # data = np.empty(shape=dataset_obj.shape, 
+        #                 dtype=dataset_obj.dtype)
+        # dataset_obj.read_direct(data)
+
+        try:
+            return pd.DataFrame(data)
+        except ValueError as exp:
+            logging.error(f"Failed to convert dataset '{dataset_name}' to DataFrame: {exp}")
+            return data  # 'data' is a NumPy array here
+
 
 
 def read_dataset_from_hdf5file(hdf5_file_path, dataset_path):