Skip to main content

unzip compressed files that contain plant images, and covert the images into numpy arrays

Project description

GreenhouseEI Documentation

SD2019-Plant Phenotyping

Dependencies

  • numpy
  • opencv

Functionality

  1. info(plant_ID, date, path)
  • input: plant_ID, date, path
  • output: print types of images that are available
  • example: tools.info("JS39-65", "2018-04-11", "/Users/john/PycharmProjects/Library_SD/output")
  1. unzip(plant_ID, date, image_type, path):
  • input: plant_ID, date, image_type, path
  • output: the folder of images that match plant ID, date, and image type.
  • example: tools.unzip("JS39-65", "2018-04-11", "Nir", "/Users/john/PycharmProjects/Library_SD/output")
  1. preprocess(plant_ID, date, path):
  • input: plant_ID, date, path
  • output: numpy arrays of Hyperspectral images
  • example: tools.preprocess("JS39-65", "2018-04-11", "/Users/john/PycharmProjects/Library_SD/output")
  1. zip2np(plant_ID, date, path)
  • input: plant_ID, date, path
  • output: numpy arrays of Hyperspectral images from zip files.
  • example: tools.zip2np("JS39-65", "2018-04-11", "/Users/john/PycharmProjects/Library_SD/output")

Running the library

  1. Warnings
  • There are two types of dataset.
    1. The folder name of the old dataset contains "Schnable", such as "4-9-18_Schnable_49-281-JS39-65_2018-04-11_12-09-35_9968800.zip". The plant_ID of the old dataset should be in a format like "JS39-65", and the date should be in a format like "2018-04-11".
    2. The folder name of the new dataset is like "71-001-Sesame-D-1.zip". The plant_ID of the new dataset should be in a format like "71-001-Sesame-D-1", and the date should be in a format like "2019-07-03".
  • the possible image types are Hyp, Nir, Vis, Fluo, IR
  • Hyperspectral images should be reconstructed first, before running the "preprocess" to produce the numpy array
  1. import the module as a Python package
  • from greenhouseEI import tools
  • tools.info([plant_ID], [date], [path])
  • tools.unzip([plant name], [date], [image type], [path])
  • tools.preprocess([plant name], [date], [path])
  • tools.zip2np([plant name], [date], [path])
  1. running the module in terminal
  • python3 -m greenhouseEI.tools info -n JS39-65 -d 2018-04-11 -p /Users/john/PycharmProjects/Library_SD/output
  • python3 -m greenhouseEI.tools unzip -n JS39-65 -d 2018-04-11 -t Hyp -p /Users/john/PycharmProjects/Library_SD/output
  • python3 -m greenhouseEI.tools preprocess -n JS39-65 -d 2018-04-11 -p /Users/john/PycharmProjects/Library_SD
  • python3 -m greenhouseEI.tools zip2np -n JS39-65 -d 2018-04-11 -p /Users/john/PycharmProjects/Library_SD/output

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

GreenHouseEI-1.4.tar.gz (3.9 kB view details)

Uploaded Source

File details

Details for the file GreenHouseEI-1.4.tar.gz.

File metadata

  • Download URL: GreenHouseEI-1.4.tar.gz
  • Upload date:
  • Size: 3.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/45.2.0 requests-toolbelt/0.9.1 tqdm/4.42.1 CPython/3.6.4

File hashes

Hashes for GreenHouseEI-1.4.tar.gz
Algorithm Hash digest
SHA256 e0e6f43d5c3b4b5bf74e171b955bec5fdf4f2c08ea4d2f225dee8e943a6c44b0
MD5 f28803d6b75cf3677a5522453ccc6a29
BLAKE2b-256 756ca3c1fb462d4263c8d492a7441c7184ac10d2606459dbc7a0557226799859

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page