Skip to main content

A quantum & classical reservoir handler for Temporal Series Prediction

Project description

NAREF

Neutral Atom Renewable Energy Forecasting

This file showcases quantum and classical reservoirs in a simple example.

import naref
from naref.classical.hyper import HyperC
from naref.quantum.hyper import HyperQ
from naref.quantum import QRC
from naref.classical import CRC
from naref import data
qrc = QRC(
    sample_len=8,
    nb_atoms=9,
    N_samples=1024,
    inp_duration=1000,
    reset_rate=0,
    geometry="grid_lattice_centred",
    atom_distance=15,
    input_type="mackey",
    test_len=data.real_test_len,
    train_len=data.real_train_len,
    verbose=True)

qrc.build_model(data.mackey[:250], data.mackey[250:280])
qrc.show_test_prediction()
qrc.show_train_prediction()

qrc.get_error_train()
qrc.get_error_test()
Building Quantum Reservoir...
10 training steps finished, training time : 24.890s
20 training steps finished, training time : 24.411s
30 training steps finished, training time : 24.441s
40 training steps finished, training time : 25.471s
50 training steps finished, training time : 25.757s
60 training steps finished, training time : 25.194s
70 training steps finished, training time : 24.324s
80 training steps finished, training time : 24.378s
90 training steps finished, training time : 31.824s
100 training steps finished, training time : 29.980s
110 training steps finished, training time : 28.739s
120 training steps finished, training time : 27.935s
130 training steps finished, training time : 30.140s
140 training steps finished, training time : 31.482s
150 training steps finished, training time : 33.550s
160 training steps finished, training time : 33.109s
170 training steps finished, training time : 31.198s
180 training steps finished, training time : 32.346s
190 training steps finished, training time : 34.320s
200 training steps finished, training time : 37.271s
210 training steps finished, training time : 37.513s
220 training steps finished, training time : 33.800s
230 training steps finished, training time : 35.306s
240 training steps finished, training time : 34.594s
Training finished. Total training time: 731.384s
Train error (Mean absolute error regression loss):  5.165748453421183e-15
10 testing steps finished, testing time : 36.515s
20 testing steps finished, testing time : 34.390s
Test error (Mean absolute error regression loss):  0.014927562760331666

png

png

0.014927562760331666
crc = CRC(
    sample_len=8,
    nb_neurons=9)
crc.build_model(data.mackey[:250], data.mackey[250:280])
crc.show_test_prediction()
crc.show_train_prediction()
crc.get_error_test()
Building Classical Reservoir...

png

png

0.047504000683266046
crc.get_error_train()
0.05308248069948858
crc = CRC(
    sample_len=8,
    nb_neurons=15)
crc.build_model(data.mackey[:500], data.mackey[500:530])
crc.show_test_prediction()
crc.show_train_prediction()
crc.get_error_test()
Building Classical Reservoir...

png

png

0.009784391178625047
crc.get_error_train()
0.008250889994704327


          

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

naref-0.0.4.tar.gz (18.3 kB view details)

Uploaded Source

Built Distribution

naref-0.0.4-py3-none-any.whl (21.4 kB view details)

Uploaded Python 3

File details

Details for the file naref-0.0.4.tar.gz.

File metadata

  • Download URL: naref-0.0.4.tar.gz
  • Upload date:
  • Size: 18.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.13

File hashes

Hashes for naref-0.0.4.tar.gz
Algorithm Hash digest
SHA256 6441ad7e25e6acfbb2420bcc190f0501db1261406f754fac94d9be4e168d511e
MD5 c4a96e4b99b92145a2d4e3f75d2b1450
BLAKE2b-256 8a26882490ee65995a5844ec38fb51176430b9ffcceaf8c5f156b7643d2761ac

See more details on using hashes here.

File details

Details for the file naref-0.0.4-py3-none-any.whl.

File metadata

  • Download URL: naref-0.0.4-py3-none-any.whl
  • Upload date:
  • Size: 21.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.13

File hashes

Hashes for naref-0.0.4-py3-none-any.whl
Algorithm Hash digest
SHA256 d8928d68d114d4003100af4203eaad78e0ac8659d065300167d518bf71fe14f4
MD5 b5dd222aebf3551e09b724c1798fc554
BLAKE2b-256 0a585c36827298e5769bfeed9b003fc986ed7cafd65daad15c52a88cf70795fd

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