Quick and easy way to deploy your Numerai models
Project description
compute-lite
build and release
pip install -r requirements.txt
# modify pyproject.toml version
python -m build # this will generate dist dir
python -m twine upload dist/* # upload to pypi
usage
import json
import os
import pandas as pd
import numerai_compute_lite as ncl
from numerapi import NumerAPI
from lightgbm import LGBMRegressor
import dotenv
dotenv.load_dotenv() # loads API secrets from .env file
napi = NumerAPI()
napi.download_dataset("v4/train.parquet")
napi.download_dataset("v4/features.json")
training_data = pd.read_parquet('v4/train.parquet')
feature_set = []
with open("v4/features.json", "r") as f:
feature_metadata = json.load(f)
features = feature_metadata["feature_sets"]["small"]
model = LGBMRegressor()
model.fit(
training_data[features],
training_data['target']
)
targets = training_data.columns.str.startswith('target')
model_id = '08e77bbf-036c-4216-b2f7-f8ed4beb88e9'
ncl.deploy(model_id, model, features, 'requirements.txt')
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
numerai-compute-lite-0.0.2.tar.gz
(11.9 kB
view hashes)
Built Distribution
Close
Hashes for numerai-compute-lite-0.0.2.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5db0f408325b9583853d903b6c19480a1aa5c06f6e793d6fb28306d8b068c580 |
|
MD5 | cccb49b0b1a3f4707fe86d89bc79b910 |
|
BLAKE2b-256 | f2e4b1766ee51b82e9915c7f3c6280924ad2190691f53365188794d9b08518de |
Close
Hashes for numerai_compute_lite-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5e008908f2ee69efc7b403f717029f0801d1829468197f36837ae458726d7ec5 |
|
MD5 | e3a6cf521b746ddfd0b1f043e307d74d |
|
BLAKE2b-256 | 06603288b250f76ea9a65880ef76485a76074f6e7fc31b3c5ea1ea34a1a45ad6 |