Added read_mtable_as_dataframe(filename) back so that jupyter notebook can use it to demonstrate some functionality

src/hdf5_ops.py

@@ -572,6 +572,70 @@ def get_groups_at_a_level(file: h5py.File, level: str):
     #file.visititems()
     return groups
 
+def read_mtable_as_dataframe(filename):
+
+    """
+    Reconstruct a MATLAB Table encoded in a .h5 file as a Pandas DataFrame.
+
+    This function reads a .h5 file containing a MATLAB Table and reconstructs it as a Pandas DataFrame. 
+    The input .h5 file contains one group per row of the MATLAB Table. Each group stores the table's 
+    dataset-like variables as Datasets, while categorical and numerical variables are represented as 
+    attributes of the respective group.
+
+    To ensure homogeneity of data columns, the DataFrame is constructed column-wise.
+
+    Parameters
+    ----------
+    filename : str
+        The name of the .h5 file. This may include the file's location and path information.
+
+    Returns
+    -------
+    pd.DataFrame
+        The MATLAB Table reconstructed as a Pandas DataFrame.
+    """
+
+    
+    #contructs dataframe by filling out entries columnwise. This way we can ensure homogenous data columns"""
+
+    with h5py.File(filename,'r') as file:
+     
+        # Define group's attributes and datasets. This should hold
+        # for all groups. TODO: implement verification and noncompliance error if needed.
+        group_list = list(file.keys())
+        group_attrs = list(file[group_list[0]].attrs.keys())
+        # 
+        column_attr_names = [item[item.find('_')+1::] for item in group_attrs]
+        column_attr_names_idx = [int(item[4:(item.find('_'))]) for item in group_attrs]
+    
+        group_datasets = list(file[group_list[0]].keys()) if not 'DS_EMPTY' in file[group_list[0]].keys() else []
+        #
+        column_dataset_names = [file[group_list[0]][item].attrs['column_name'] for item in group_datasets]
+        column_dataset_names_idx = [int(item[2:]) for item in group_datasets]
+
+
+        # Define data_frame as group_attrs + group_datasets
+        #pd_series_index = group_attrs + group_datasets
+        pd_series_index = column_attr_names + column_dataset_names
+
+        output_dataframe = pd.DataFrame(columns=pd_series_index,index=group_list)
+
+        tmp_col = []
+
+        for meas_prop in group_attrs + group_datasets:
+            if meas_prop in group_attrs:
+                column_label = meas_prop[meas_prop.find('_')+1:]
+                # Create numerical or categorical column from group's attributes
+                tmp_col = [file[group_key].attrs[meas_prop][()][0] for group_key in group_list]
+            else:
+                # Create dataset column from group's datasets
+                column_label = file[group_list[0] + '/' + meas_prop].attrs['column_name']
+                #tmp_col = [file[group_key + '/' + meas_prop][()][0] for group_key in group_list]
+                tmp_col = [file[group_key + '/' + meas_prop][()] for group_key in group_list]
+            
+            output_dataframe.loc[:,column_label] = tmp_col
+
+    return output_dataframe
 
 if __name__ == "__main__":
     if len(sys.argv) < 4: