Skip to main content

AutoML time series forecasting

Project description

Auto Forecast

AutoML library for time series forecasting

Quick start

Upgrade pip

$ pip install pip --upgrade

Install autoforecast

$ pip install autoforecast

Try it out with your own dataset

  1. Preprocessing
from Autoforecast.preprocessing import preprocessing

X_train, y_train, X_test, y_test = preprocessing(
    df=df,
    target_name=['sales'],
    categoricals=['store_id', 'dpt_id', 'holiday', 'zipcode', ...],
    numericals=['employee_num', 'store_surface', ...],
    date_col=['date'],
    train_size=0.8,
    engineering=True,
    selection=True
)
  1. Fitting and predicting
from autoforecast.automl import AutoForecast


model = AutoForecast()

print('Autoforecast() model fitting...')
model.fit(X_train=X_train, y_train=y_train)

print('Autoforecast() model predicting...')

y_pred = model.predict(X_test=X_test)
print(f'y_pred={y_pred})

Run the example function

from autoforecast.examples import autoforecast_bitcoin


autoforecast_bitcoin.run()

Fetch historical cryptocurrency data

This function is a wrapper of https://developers.coinbase.com/api/v2#prices

  • n: integer, number of days we want since today
  • type: str, ['buy', 'sell', 'spot']
  • currency_pair: str, crypto & currency
from autoforecast.datasets.import_bitcoin_price import get_price_for_last_n_days


crypto_df = get_price_for_last_n_days(
    n=1, type='spot', currency_pair='BTC-USD')
)

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

autoforecast-0.0.9.tar.gz (15.3 kB view details)

Uploaded Source

Built Distribution

autoforecast-0.0.9-py3-none-any.whl (25.6 kB view details)

Uploaded Python 3

File details

Details for the file autoforecast-0.0.9.tar.gz.

File metadata

  • Download URL: autoforecast-0.0.9.tar.gz
  • Upload date:
  • Size: 15.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/4.6.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.1 CPython/3.9.5

File hashes

Hashes for autoforecast-0.0.9.tar.gz
Algorithm Hash digest
SHA256 fa51de563c61db1490891cb84364c5ddf5f44309478e01388d93625888089d09
MD5 5963982f2e723e30bb8c28f2707a265a
BLAKE2b-256 56d9a1b1a272f74b27dc22438a3cc5503dd428924a0dc00298a802589e896989

See more details on using hashes here.

File details

Details for the file autoforecast-0.0.9-py3-none-any.whl.

File metadata

  • Download URL: autoforecast-0.0.9-py3-none-any.whl
  • Upload date:
  • Size: 25.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/4.6.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.1 CPython/3.9.5

File hashes

Hashes for autoforecast-0.0.9-py3-none-any.whl
Algorithm Hash digest
SHA256 5bb9c5a52ab4c22e57590c6267e171195fba225c7f6497dae6461996198594af
MD5 c319712f9c33ec67f01bf5d8b128dd01
BLAKE2b-256 781597cd75a536a22ad34cae27a1fe276012f3aa9652a9fbeac5705deaf4852a

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