jfk.yaml

# Copyright 2021 The MLX Contributors
#
# SPDX-License-Identifier: Apache-2.0
id: noaa-weather-data-jfk-airport
name: NOAA Weather Data - JFK Airport
description: Local climatological data originally collected at JFK airport.
version: 1.1.4
created: 2019-07-19
updated: 2020-07-19
format:
  - type: CSV
    url: https://en.wikipedia.org/wiki/Comma-separated_values
domain: Time Series

# Information about the entity that makes the data set available
provider:
  name: Data Asset eXchange
  url: https://developer.ibm.com/exchanges/data/all/jfk-weather-data/

# REQUIRED; identifies where the data set is stored and how it is stored
repository:
  type: HTTP
  url: https://dax-cdn.cdn.appdomain.cloud/dax-noaa-weather-data-jfk-airport/1.1.4/noaa-weather-data-jfk-airport.tar.gz
  mime_type: application/x-tar
  sha_512:  e3f27a8fcc0db5289df356e3f48aef6df56236798d5b3ae3889d358489ec6609d2d797e4c4932b86016d2ce4a379ac0a0749b6fb2c293ebae4e585ea1c8422ac
  size: 3.5M

# REQUIRED; data set license information
license:
  commercial: false
  name: CDLA-Sharing
  url: https://cdla.io/sharing-1-0/

# REQUIRED; describes relevant files in the data set archive
content:
  - pattern: noaa-weather-data-jfk-airport/jfk_weather.csv
    description: Raw data file
    records: 114546
    size: 30M
    format: CSV
    mime_type: text/csv
    type: file
  - pattern: noaa-weather-data-jfk-airport/jfk_weather_cleaned.csv
    description: jfk_weather.csv cleaned-up using noaa-weather-data-jfk-airport/clean_data.py
    records: 75125
    size: 6M
    format: CSV
    mime_type: text/csv
    type: file

# OPTIONAL; Identifies where the data set was obtained from
source:
  name: National Oceanic and Atmospheric Administration
  url: https://www.ncdc.noaa.gov/

# OPTIONAL; but recommended
seo_tags:
  - weather
  - time series

# OPTIONAL; assets that complement this data set, e.g. notebooks
related_assets:
  - name: Explore the data
    description: Data preview and glossary
    url: https://dax-cdn.cdn.appdomain.cloud/dax-noaa-weather-data-jfk-airport/1.1.4/data-preview/index.html
  - name: DAX Weather project
    description: Watson Studio Gallery project for the NOAA data set
    mime_type: text/html
    url: https://dataplatform.cloud.ibm.com/exchange/public/entry/view/a7432f0c29c5bda2fb42749f363bd9ff
  - name: Effective Farming - Monitor Crop Growth
    description: Accelerator for Cloud Pak for Data
    mime_type: text/html
    url: https://community.ibm.com/community/user/cloudpakfordata/viewdocument/effective-farming-monitor-crop-gr
  - name: Elyra pipeline
    description: Elyra example pipeline
    mime_type: text/html
    url: https://github.com/elyra-ai/examples/tree/master/pipelines/dax_noaa_weather_data
  - name: MLX notebook
    description: Machine Learning Exchange example notebook with data mount
    mime_type: application/x-ipynb+json
    url: https://github.com/machine-learning-exchange/mlx/blob/main/notebooks/dlf-notebooks/JFK_Data.ipynb
    application:
      name: MLX
      asset_id: notebooks/jfk-airport-analysis

# OPTIONAL; url for the markdown file which describes the asset
readme_url: https://raw.githubusercontent.com/machine-learning-exchange/katalog/main/dataset-samples/jfk/jfk.md