Update README.md campaign descriptor template and docker environment

This commit is contained in:
2025-06-18 16:33:17 +02:00
parent f9b9e1226b
commit 490a542126
4 changed files with 161 additions and 4 deletions

67
campaignDescriptor.yaml Normal file
View File

@ -0,0 +1,67 @@
# ------------------------------------------------------------------------------
# Configuration for FAIR Data Integration Pipeline
# ------------------------------------------------------------------------------
# INPUT DATA DIRECTORY
# Can be a local or network path. Examples:
# - Local: '../data/data_folder/' # manually create data_folder/ with instrument folders
# - Network: /mnt/network_drive/data_folder (Docker)
input_file_directory: '/mnt/network_drive/Data'
# OUTPUT DATA DIRECTORY
# Always relative to notebook location. If run from `notebooks/`,
# output will be saved in `../data/`.
# Do not modify unless you're running from the project root.
output_file_directory: '../data/'
# ------------------------------------------------------------------------------
# Project Metadata
# ------------------------------------------------------------------------------
project: 'Insert project title here'
contact: 'Your Name or Team'
group_id: '0000' # Optional internal group or project ID
# Type of experiment (e.g., campaign, flow_tube_study, smog_chamber, lab_study)
experiment: 'experiment_type'
# Dataset coverage range (optional but recommended)
dataset_startdate: 'YYYY-MM-DD'
dataset_enddate: 'YYYY-MM-DD'
# Data processing level (typically '0', '1', or '2'; follows ACTRIS or custom standards)
actris_level: '1'
# ------------------------------------------------------------------------------
# Output File Naming Convention (Optional)
# ------------------------------------------------------------------------------
# Year of observation
year: 'YYYY'
# Format string used to define output filenames.
# You may use any field from this config as a part, comma-separated.
# Example: 'experiment, year' → experiment_year.h5
filename_format: 'experiment, year'
# ------------------------------------------------------------------------------
# Instrument Data Source
# ------------------------------------------------------------------------------
# Relative subdirectories inside the input directory that contain instrument data.
# Use one or more folder paths as needed.
instrument_datafolder:
- 'instFolder1/subfolder/'
- 'instFolder2'
# ------------------------------------------------------------------------------
# Data Integration Options
# ------------------------------------------------------------------------------
# Integration mode: 'collection' or 'single_experiment'.
integration_mode: 'collection'
# Optional: list of timestamps marking experimental phases or steps.
# Format each entry as: 'YYYY-MM-DD HH:MM:SS'
datetime_steps: []