josejimenezluna / Nnet Ts
Licence: other
Neural network architecture for time series forecasting.
Stars: ✭ 103
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Nnet Ts
Tsrepr
TSrepr: R package for time series representations
Stars: ✭ 75 (-27.18%)
Mutual labels: time-series
Marketstore
DataFrame Server for Financial Timeseries Data
Stars: ✭ 1,290 (+1152.43%)
Mutual labels: time-series
Deeptemporalclustering
📈 Keras implementation of the Deep Temporal Clustering (DTC) model
Stars: ✭ 96 (-6.8%)
Mutual labels: time-series
Sdtw pytorch
Implementation of soft dynamic time warping in pytorch
Stars: ✭ 79 (-23.3%)
Mutual labels: time-series
Cnn For Stock Market Prediction Pytorch
CNN for stock market prediction using raw data & candlestick graph.
Stars: ✭ 86 (-16.5%)
Mutual labels: time-series
Covid19
JSON time-series of coronavirus cases (confirmed, deaths and recovered) per country - updated daily
Stars: ✭ 1,177 (+1042.72%)
Mutual labels: time-series
Btctrading
Time Series Forecast with Bitcoin value, to detect upward/down trends with Machine Learning Algorithms
Stars: ✭ 99 (-3.88%)
Mutual labels: time-series
Filodb
Distributed Prometheus time series database
Stars: ✭ 1,286 (+1148.54%)
Mutual labels: time-series
Online Recurrent Extreme Learning Machine
Online-Recurrent-Extreme-Learning-Machine (OR-ELM) for time-series prediction, implemented in python
Stars: ✭ 95 (-7.77%)
Mutual labels: time-series
Awesome time series in python
This curated list contains python packages for time series analysis
Stars: ✭ 1,245 (+1108.74%)
Mutual labels: time-series
Timbala
Durable time-series database that's API-compatible with Prometheus.
Stars: ✭ 85 (-17.48%)
Mutual labels: time-series
Brein Time Utilities
Library which contains several time-dependent data and index structures (e.g., IntervalTree, BucketTimeSeries), as well as algorithms.
Stars: ✭ 94 (-8.74%)
Mutual labels: time-series
Stl Decomp 4j
Java implementation of Seasonal-Trend-Loess time-series decomposition algorithm.
Stars: ✭ 75 (-27.18%)
Mutual labels: time-series
Doppelganger
[IMC 2020 (Best Paper Finalist)] Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
Stars: ✭ 97 (-5.83%)
Mutual labels: time-series
Systemicrisk
A framework for systemic risk valuation and analysis.
Stars: ✭ 72 (-30.1%)
Mutual labels: time-series
Forecastml
An R package with Python support for multi-step-ahead forecasting with machine learning and deep learning algorithms
Stars: ✭ 101 (-1.94%)
Mutual labels: time-series
Diamondb
[WIP] DiamonDB: Rebuild of time series database on AWS.
Stars: ✭ 98 (-4.85%)
Mutual labels: time-series
Stingray
Anything can happen in the next half hour (including spectral timing made easy)!
Stars: ✭ 94 (-8.74%)
Mutual labels: time-series
nnet-ts
Neural network architecture for time series forecasting.
Requirements and installation
This packages relies heavily on numpy
, scipy
, pandas
, theano
and keras
. Check on their repositories how to install them first.
Then, simply fetch the package from PyPI.
sudo pip install nnet-ts
Usage
Using Box & Jenkins classical air passenger data.
from nnet_ts import *
time_series = np.array(pd.read_csv("AirPassengers.csv")["x"])
Create a TimeSeriesNnet
object and specify each layer size and activation function.
neural_net = TimeSeriesNnet(hidden_layers = [20, 15, 5], activation_functions = ['sigmoid', 'sigmoid', 'sigmoid'])
Then just fit the data and predict values:
neural_net.fit(time_series, lag = 40, epochs = 10000)
neural_net.predict_ahead(n_ahead = 30)
Did we get it right? Let's check
import matplotlib.pyplot as plt
plt.plot(range(len(neural_net.timeseries)), neural_net.timeseries, '-r', label='Predictions', linewidth=1)
plt.plot(range(len(time_series)), time_series, '-g', label='Original series')
plt.title("Box & Jenkins AirPassenger data")
plt.xlabel("Observation ordered index")
plt.ylabel("No. of passengers")
plt.legend()
plt.show()
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].