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

Moved read_mtable_as_dataframe(filename) to src/hdf5_ops.py

Browse Source
This commit is contained in:
florez_j
2024-11-24 11:03:44 +01:00
parent 3122c4482f
commit 0330773f08
1 changed files with 1 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
src/hdf5_lib_part2.py
View File

@ -12,65 +12,7 @@ import utils.g5505_utils as utils
import instruments.readers.filereader_registry as filereader_registry
import src.hdf5_ops as hdf5_ops
def read_mtable_as_dataframe(filename):
""" Reconstruct a Matlab Table encoded in a .h5 file as a Pandas DataFrame. The input .h5 file
contains as many groups as rows in the Matlab Table, and each group stores dataset-like variables in the Table as
Datasets while categorical and numerical variables in the table are represented as attributes of each group.
Note: DataFrame is constructed columnwise to ensure homogenous data columns.
Parameters:
filename (str): .h5 file's name. It may include location-path information.
Returns:
output_dataframe (pd.DataFrame): Matlab's Table 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
def create_group_hierarchy(obj, df, columns):
"""