Time series models

Description

Time series neural network models for Time series predictor

Installation

pip install time-series-models

Usage example

from time_series_models import BenchmarkLSTM
from skorch.callbacks import EarlyStopping
from skorch.dataset import CVSplit
from torch.optim import Adam
from flights_time_series_dataset import FlightSeriesDataset
from time_series_predictor import TimeSeriesPredictor

tsp = TimeSeriesPredictor(
    BenchmarkLSTM(),
    lr = 1e-3,
    lambda1=1e-8,
    optimizer__weight_decay=1e-8,
    iterator_train__shuffle=True,
    early_stopping=EarlyStopping(patience=50),
    max_epochs=250,
    train_split=CVSplit(10),
    optimizer=Adam
)

past_pattern_length = 24
future_pattern_length = 12
pattern_length = past_pattern_length + future_pattern_length
fsd = FlightSeriesDataset(pattern_length, past_pattern_length, pattern_length, stride=1)
tsp.fit(fsd)
mean_r2_score = tsp.score(tsp.dataset)
print(f"Achieved R2 score: {mean_r2_score}")
assert mean_r2_score > -20

Oze dataset history

Metadata

Release files for time-series-models 0.3.9

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

Source distribution (sdist)

Source distribution for time-series-models 0.3.9
File	Size	Uploaded
time-series-models-0.3.9.tar.gz	5.0 kB	Oct 7, 2021	Details

Built distribution (wheel)

Table of built distributions (wheels) for time-series-models 0.3.9
File	Interpreter	ABI	Platform	Reset
time_series_models-0.3.9-py3-none-any.whl 6.2 kB Oct 7, 2021	Python 3	none	any	Details

Total release size: 11.2 kB

Release files / time-series-models-0.3.9.tar.gz

Download URL	time-series-models-0.3.9.tar.gz
Size	5.0 kB
Tags	Source
SHA-256 checksum How to use checksums	`6eff8b88685f12c19e07c198573ef7e50a70e880fbc3109478d9104e0a0d576e`
BLAKE2b-256 checksum How to use checksums	`c486f58cf7567f92254cf7f3a375eee75e34146b091366b436d9b206ad4de464`
Upload date	Oct 7, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.2`

Release files / time_series_models-0.3.9-py3-none-any.whl

Download URL	time_series_models-0.3.9-py3-none-any.whl
Size	6.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`7642eaf800e44b9aa0587b7a48b418fe29622e9047e5ae7be6f632bc9fa5464e`
BLAKE2b-256 checksum How to use checksums	`93ff09b5d663399a4551bc4c51585c7c78174d284fbd819e1be2cee7bac2d723`
Upload date	Oct 7, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.2`