Skip to main content

casPYan

A Python implementation of the Caspian SNN processor simulator.

Installation

pip install caspyan

Usage

import casPYan

Loading a Caspian network

# load a network from a json file
import json
with open("network.json") as f:
    network = json.load(f)

# Create a processor and load the network into it
processor = casPYan.Processor()
processor.load_network(network)

Setting up Encoders and Decoders

import casPYan.ende.rate as ende

# Create encoder and decoder arrays
encoders = [
    ende.RateEncoder(interval=10, domain=[0.0, 1.0])
    for _ in processor.inputs
]
decoders = [
    ende.RateDecoder(interval=10, domain=[0.0, 1.0])
    for _ in processor.outputs
]

Running a Caspian processor

input_vector = [0.5, 1.0]

# encode to spikes
spikes = [enc.get_spikes(x) for enc, x in zip(encoders, input_vector)]

# apply spikes
processor.apply_spikes(spikes)
# run processor for 10 ticks
processor.run(10)

# decode spikes to floats
data = [dec.decode(node.history) for dec, node in zip(decoders, processor.outputs)]

Saving a Caspian network

network = processor.to_tennlab()
with open("network.json", "w") as f:
    json.dump(network, f)

Creating a Caspian network from scratch

The low-level representation of a Caspian network is a list of nodes, along with a list of inputs and outputs that reference those nodes.

nodes = []

nodes.append(casPYan.Node(threshold=0.5, delay=0.0, leak=0.0))
nodes.append(casPYan.Node(threshold=1.0, delay=0.0, leak=0.0))

inputs = [nodes[0]]
outputs = [nodes[1]]

casPYan.connect(nodes[0], nodes[1], weight=0.5, delay=0)

casPYan.run(nodes, 10)

spikes = [node.history for node in outputs]

# saving and loading node representations
json_dict = casPYan.to_tennlab(nodes, inputs, outputs)
# json_dict is a Python dict that can be saved to a json file
# It is similar to what is loaded by casPYan.network_from_json
nodes, inputs, outputs = casPYan.network_from_json(json_dict)

See the following files for more low-level functions:

  • casPYan/node.py
  • casPYan/edge.py
  • casPYan/network.py

Disclaimer

This software does not guarantee the correctness of the simulation in relation to the original Caspian SNN simulator, Caspian processors, or any other software.

casPYan is not a substitute for the original software, and it is not supported by the original authors.

It should not be thought of as a port.

Metadata

Release files for caspyan 0.2.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for caspyan 0.2.2
File Size Uploaded
caspyan-0.2.2.tar.gz 11.9 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for caspyan 0.2.2
File Interpreter ABI Platform
caspyan-0.2.2-py3-none-any.whl Python 3 none any Details

Total release size: 24.1 kB

Release files / caspyan-0.2.2.tar.gz

Download URL caspyan-0.2.2.tar.gz
Size 11.9 kB
Tags Source
SHA-256 checksum
How to use checksums
b48150f891b2edf1266420c11de7ee3b6204fd2f1a998aeef9bafd9fe88a668c
BLAKE2b-256 checksum
How to use checksums
f11923ef2bccf2ee83e0b56244d09dbfda8c4f953709c7197fe4b738a111c7d7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on May 27, 2026.

Transparency log

Release files / caspyan-0.2.2-py3-none-any.whl

Download URL caspyan-0.2.2-py3-none-any.whl
Size 12.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
ba4d2529003b528383a876ec917abf9d47f7e53a79d831c595838c55ba8bbefb
BLAKE2b-256 checksum
How to use checksums
54a26bd05dd808acfcd9fdd1f5a8dc25ef2cc8a55478cc86fcb43c7a3d1471ad
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on May 27, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.2.2 This release

2 release files

0.2.1

2 release files

0.2.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page