jlaehne / pooch Goto Github PK

import pooch
import pandas as pd

# Download a file and save it locally, returning the path to it.
# Running this again will not cause a download. Pooch will check the hash
# (checksum) of the downloaded file against the given value to make sure
# it's the right file (not corrupted or outdated).
fname_bathymetry = pooch.retrieve(
    url="https://github.com/fatiando-data/caribbean-bathymetry/releases/download/v1/caribbean-bathymetry.csv.xz",
    known_hash="md5:a7332aa6e69c77d49d7fb54b764caa82",
)

# Pooch can also download based on a DOI from certain providers.
fname_gravity = pooch.retrieve(
    url="doi:10.5281/zenodo.5882430/southern-africa-gravity.csv.xz",
    known_hash="md5:1dee324a14e647855366d6eb01a1ef35",
)

# Load the data with Pandas
data_bathymetry = pd.read_csv(fname_bathymetry)
data_gravity = pd.read_csv(fname_gravity)

"""
Module mypackage/datasets.py
"""
import pkg_resources
import pandas
import pooch

# Get the version string from your project. You have one of these, right?
from . import version

# Create a new friend to manage your sample data storage
GOODBOY = pooch.create(
    # Folder where the data will be stored. For a sensible default, use the
    # default cache folder for your OS.
    path=pooch.os_cache("mypackage"),
    # Base URL of the remote data store. Will call .format on this string
    # to insert the version (see below).
    base_url="https://github.com/myproject/mypackage/raw/{version}/data/",
    # Pooches are versioned so that you can use multiple versions of a
    # package simultaneously. Use PEP440 compliant version number. The
    # version will be appended to the path.
    version=version,
    # If a version as a "+XX.XXXXX" suffix, we'll assume that this is a dev
    # version and replace the version with this string.
    version_dev="main",
    # An environment variable that overwrites the path.
    env="MYPACKAGE_DATA_DIR",
    # The cache file registry. A dictionary with all files managed by this
    # pooch. Keys are the file names (relative to *base_url*) and values
    # are their respective SHA256 hashes. Files will be downloaded
    # automatically when needed (see fetch_gravity_data).
    registry={"gravity-data.csv": "89y10phsdwhs09whljwc09whcowsdhcwodcydw"}
)
# You can also load the registry from a file. Each line contains a file
# name and it's sha256 hash separated by a space. This makes it easier to
# manage large numbers of data files. The registry file should be packaged
# and distributed with your software.
GOODBOY.load_registry(
    pkg_resources.resource_stream("mypackage", "registry.txt")
)

# Define functions that your users can call to get back the data in memory
def fetch_gravity_data():
    """
    Load some sample gravity data to use in your docs.
    """
    # Fetch the path to a file in the local storage. If it's not there,
    # we'll download it.
    fname = GOODBOY.fetch("gravity-data.csv")
    # Load it with numpy/pandas/etc
    data = pandas.read_csv(fname)
    return data