Skip to content

Commit 84c711d

Browse files
authored
Merge pull request #7 from maxmekiska/development
feat!: imbrium 2.0.0
2 parents b267ad9 + ea1f5d6 commit 84c711d

32 files changed

+4308
-24280
lines changed

.github/workflows/main.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ jobs:
88
runs-on: windows-latest
99
strategy:
1010
matrix:
11-
python: ["3.7", "3.8", "3.9", "3.10"]
11+
python: ["3.8", "3.9", "3.10", "3.11"]
1212

1313
steps:
1414
- uses: actions/checkout@v3

CHANGELOG.md

Lines changed: 9 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -80,4 +80,12 @@ activation function type
8080

8181
- added depth parameter to architectures
8282
- added optimizer configuration support
83-
- added optimizer configuration to seeker
83+
- added optimizer configuration to seeker
84+
85+
### 2.0.0
86+
87+
- adapted `keras_core`
88+
- removed internal hyperparameter tuning
89+
- removed encoder-decoder architectures
90+
- improved layer configuration via dictionary input
91+
- split data argument into target and feature numpy arrays

README.md

Lines changed: 24 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# imbrium [![Downloads](https://pepy.tech/badge/imbrium)](https://pepy.tech/project/imbrium) [![PyPi](https://img.shields.io/pypi/v/imbrium.svg?color=blue)](https://pypi.org/project/imbrium/) [![GitHub license](https://img.shields.io/github/license/maxmekiska/Imbrium?color=black)](https://github.com/maxmekiska/Imbrium/blob/main/LICENSE) [![PyPI pyversions](https://img.shields.io/pypi/pyversions/imbrium.svg)](https://pypi.python.org/project/imbrium/) [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/maxmekiska/ImbriumTesting-Demo/main?labpath=TestImbrium.ipynb)
1+
# imbrium [![Downloads](https://pepy.tech/badge/imbrium)](https://pepy.tech/project/imbrium) [![PyPi](https://img.shields.io/pypi/v/imbrium.svg?color=blue)](https://pypi.org/project/imbrium/) [![GitHub license](https://img.shields.io/github/license/maxmekiska/Imbrium?color=black)](https://github.com/maxmekiska/Imbrium/blob/main/LICENSE) [![PyPI pyversions](https://img.shields.io/pypi/pyversions/imbrium.svg)](https://pypi.python.org/project/imbrium/)
22

33
## Status
44

@@ -25,20 +25,33 @@ Time Series Forecasting.
2525
╚═╝╚═╝░░░░░╚═╝╚═════╝░╚═╝░░╚═╝╚═╝░╚═════╝░╚═╝░░░░░╚═╝
2626

2727

28-
## Introduction to Imbrium
28+
## Introduction to imbrium
2929

30-
Imbrium is a deep learning library that specializes in time series forecasting. Its primary objective is to provide a user-friendly repository of deep learning architectures for this purpose. The focus is on simplifying the process of creating and applying these architectures, with the goal of allowing users to create complex architectures without having to build them from scratch. Instead, the emphasis shifts to high-level configuration of the architectures.
30+
imbrium is a deep learning library that specializes in time series forecasting. Its primary objective is to provide a user-friendly repository of deep learning architectures for this purpose. The focus is on simplifying the process of creating and applying these architectures, with the goal of allowing users to create complex architectures without having to build them from scratch. Instead, the emphasis shifts to high-level configuration of the architectures.
3131

32-
## Contributions
3332

34-
The development and improvement of Imbrium is an ongoing process, and contributions from the community are greatly appreciated. New architectures, in particular, can help Imbrium achieve its goals more quickly. While Imbrium is currently based on Keras, it is open to being extended to other machine learning frameworks such as Pytorch.
33+
## imbrium Summary
3534

36-
Recent research in the field of time series forecasting has shown the potential of graph-based neural networks. If you have experience in this area and would like to contribute architectures to Imbrium, your contributions would be most welcomed.
35+
imbrium is designed to simplify the application of deep learning models for time series forecasting. The library offers a variety of pre-built architectures. The user retains full control over the configuration of each layer, including the number of neurons, the type of activation function, loss function, optimizer, and metrics applied. This allows for the flexibility to adapt the architecture to the specific needs of the forecast task at hand. Imbrium also offers a user-friendly interface for training and evaluating these models, making it easy to quickly iterate and test different configurations.
3736

38-
## imbrium Summary
37+
## imbrium 2.0.0
38+
39+
- adapting `keras_core`
40+
- removing internal hyperparameter tuning
41+
- removing encoder-decoder architectures
42+
- improve layer configuration
43+
- split input data into target and feature numpy arrays
44+
- overall lighten the library
3945

40-
Imbrium is designed to simplify the application of deep learning models for time series forecasting. The library offers a variety of pre-built architectures, each with a fixed number of layers. However, the user retains full control over the configuration of each layer, including the number of neurons, the type of activation function, loss function, optimizer, and metrics applied. This allows for the flexibility to adapt the architecture to the specific needs of the forecast task at hand. Imbrium also offers a user-friendly interface for training and evaluating these models, making it easy to quickly iterate and test different configurations.
46+
### Examples
4147

48+
Notebook showing how to use the library:
49+
- https://github.com/maxmekiska/ImbriumTesting-Demo
50+
51+
## LEGACY: imbrium versions <= v.1.3.0
52+
<details>
53+
<summary>Expand</summary>
54+
<br>
4255

4356
The library differentiates between two
4457
modes:
@@ -1250,4 +1263,7 @@ Brwonlee, J., 2018c. How to develop multilayer perceptron models for time series
12501263
https://machinelearningmastery.com/how-to-develop-multilayer-
12511264
perceptron-models-for-time-series-forecasting/.
12521265

1266+
</details>
1267+
1268+
12531269
</details>

imbrium/__init__.py

Lines changed: 5 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,6 @@
1-
__version__ = "1.3.0"
1+
__version__ = "2.0.0"
22

3-
from imbrium import architectures, blueprints, predictors, utils
3+
from imbrium.predictors.multivarhybrid import HybridMulti
4+
from imbrium.predictors.multivarpure import PureMulti
5+
from imbrium.predictors.univarhybrid import HybridUni
6+
from imbrium.predictors.univarpure import PureUni

imbrium/architectures/__init__.py

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +0,0 @@
1-
from imbrium.architectures.models import *

0 commit comments

Comments
 (0)