Skip to main content

JAX/Flax implementation of AbstractCosmologicalEmulators.jl interface

Project description

jaxace

Tests Documentation Documentation codecov

JAX/Flax implementation of cosmological emulators with automatic JIT compilation.

Installation

pip install -e .

Usage

import jaxace
import jax.numpy as jnp

# Cosmology
cosmo = jaxace.W0WaCDMCosmology(
    ln10As=3.044, ns=0.9649, h=0.6736,
    omega_b=0.02237, omega_c=0.1200,
    m_nu=0.06, w0=-1.0, wa=0.0
)

# Background functions
z = jnp.array([0.0, 0.5, 1.0])
growth = jaxace.D_z_from_cosmo(z, cosmo)
distance = jaxace.r_z_from_cosmo(z, cosmo)

# Neural network emulator
emulator = jaxace.init_emulator(nn_dict, weights, jaxace.FlaxEmulator)
output = emulator(input_data)  # Auto-JIT + batch detection

Features

  • Background cosmology (growth, distances, Hubble)
  • Neural network emulators with auto-JIT
  • Massive neutrinos and dark energy support
  • Full JAX integration (grad, vmap, jit)

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

jaxace-0.1.0.tar.gz (15.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

jaxace-0.1.0-py3-none-any.whl (17.6 kB view details)

Uploaded Python 3

File details

Details for the file jaxace-0.1.0.tar.gz.

File metadata

  • Download URL: jaxace-0.1.0.tar.gz
  • Upload date:
  • Size: 15.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for jaxace-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a9bd0ed6cc545beddacfadcd1e05df09d9b4d3fd01e4299b95fd395a1e447e99
MD5 a09d73dcaa04997599d5aacc57be8109
BLAKE2b-256 a20f6c6fb79fa7e7d805331f4af3a00367503bdffd245cb10a510e1836840701

See more details on using hashes here.

Provenance

The following attestation bundles were made for jaxace-0.1.0.tar.gz:

Publisher: publish.yml on CosmologicalEmulators/jaxace

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file jaxace-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: jaxace-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 17.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for jaxace-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9e37bd15fa25a703eb17fa057f1f7e28bbe1b6386e40163bea70e1d29f7955b1
MD5 309bd4046765a0928ab960bb9d21c069
BLAKE2b-256 308efdd8ad413a1b178e5e05a732f5ffbec90e6e1a781589d80cc4be7be36d25

See more details on using hashes here.

Provenance

The following attestation bundles were made for jaxace-0.1.0-py3-none-any.whl:

Publisher: publish.yml on CosmologicalEmulators/jaxace

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

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