Added output_files' folder, environment.yml file, and jupyter notebook demo on how to create and visualize hdf5 files.

This commit is contained in:
2023-11-02 15:49:35 +01:00
parent 25c0f07cc3
commit bf4d03f369
2 changed files with 126 additions and 0 deletions

View File

@ -0,0 +1,113 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import hdf5_lib as h5lib\n",
"import os\n",
"\n",
"# define input file directory\n",
"\n",
"input_file_path = './input_files\\\\BeamTimeMetaData.h5'\n",
"output_dir_path = './output_files'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Read the above specified input_file_path as a dataframe. \n",
"\n",
"Since we know this file was created from a Thorsten Table's format, we can use h5lib.read_mtable_as_dataframe() to read it.\n",
"\n",
"Then, we rename the name column as filename, as this is the column's name use to idenfify files in subsequent functions.\n",
"Also, we add to the dataframe a few categorical columns to be used as grouping variables when creating the hdf5 file's group hierarchy. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Read BeamTimeMetaData.h5, containing Thorsten's Matlab Table\n",
"input_data_df = h5lib.read_mtable_as_dataframe(input_file_path)\n",
"\n",
"# Preprocess Thorsten's input_data dataframe so that i can be used to create a newer .h5 file\n",
"# under certain grouping specificiations.\n",
"input_data_df = input_data_df.rename(columns = {'name':'filename'})\n",
"input_data_df = h5lib.augment_with_filenumber(input_data_df)\n",
"input_data_df = h5lib.augment_with_filetype(input_data_df)\n",
"input_data_df = h5lib.split_sample_col_into_sample_and_data_quality_cols(input_data_df)\n",
"input_data_df['lastModifiedDatestr'] = input_data_df['lastModifiedDatestr'].astype('datetime64[s]')\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Define grouping functions to be passed into create_hdf5_file function. These can also be set\n",
"# as strings refering to categorical columns in input_data_df.\n",
"\n",
"test_grouping_funcs = True\n",
"if test_grouping_funcs:\n",
" group_by_sample = lambda x : h5lib.group_by_df_column(x,'sample')\n",
" group_by_type = lambda x : h5lib.group_by_df_column(x,'filetype')\n",
" group_by_filenumber = lambda x : h5lib.group_by_df_column(x,'filenumber')\n",
"else:\n",
" group_by_sample = 'sample'\n",
" group_by_type = 'filetype'\n",
" group_by_filenumber = 'filenumber'\n",
"\n",
"output_filename = 'test.h5'\n",
"\n",
"h5lib.create_hdf5_file(os.path.join(output_dir_path,output_filename),\n",
" input_data_df, 'top-down', \n",
" group_by_funcs = [group_by_sample, group_by_type, group_by_filenumber]\n",
" )\n",
"\n",
"annotation_dict = {'Campaign name': 'SLS-Campaign-2023',\n",
" 'Users':'Thorsten, Luca, Zoe',\n",
" 'Startdate': str(input_data_df['lastModifiedDatestr'].min()),\n",
" 'Enddate': str(input_data_df['lastModifiedDatestr'].max())\n",
" }\n",
"h5lib.annotate_root_dir('test.h5',annotation_dict)\n",
"\n",
"h5lib.display_group_hierarchy_on_a_treemap('test.h5')\n",
"\n",
"print(':)')\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "test_atmos_chem_env",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

13
environment.yml Normal file
View File

@ -0,0 +1,13 @@
name: test_atmos_chem_env
channels:
- conda-forge
- defaults
dependencies:
- python=3.11
- jupyter
- numpy
- pandas
- matplotlib
- plotly=5.18
- h5py=3.10
- pybis=1.35