https://github.com/simonblanke/progressboard
Add on for Hyperactive package to visualize progress of optimization run.
https://github.com/simonblanke/progressboard
dashboard hyperactive hyperparameter-optimization panel visualization
Last synced: 4 months ago
JSON representation
Add on for Hyperactive package to visualize progress of optimization run.
- Host: GitHub
- URL: https://github.com/simonblanke/progressboard
- Owner: SimonBlanke
- License: mit
- Created: 2021-09-14T10:04:20.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2022-08-30T07:41:40.000Z (over 3 years ago)
- Last Synced: 2025-01-12T19:21:20.239Z (about 1 year ago)
- Topics: dashboard, hyperactive, hyperparameter-optimization, panel, visualization
- Language: Python
- Homepage:
- Size: 2.88 MB
- Stars: 3
- Watchers: 3
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Progress Board
An addon for the Hyperactive package to visualize the progress of optimization runs.
The Progress Board is a dashboard (opens in webbrowser) that provides visualization of live-updated data from Hyperactive. It integrates seamlessly with Hyperactive (v4) and opens up the optimization run with useful information. It also supports multiprocessing and multiple searches at the same time without any added complexity or work for the user.
The Progress Board should be used for computationally expensive objective functions (like machine-/deep-learning models).
The Progress Board is tested in Ubuntu, but Windows support maybe added in the future.
## State of project
### This project is in an early development stage. If you encounter a problem it would be very helpful to open an issue and describe it in detail.
## Installation
```console
pip install hyperactive-progress-board
```
## Example
```python
from sklearn.model_selection import cross_val_score
from sklearn.tree import DecisionTreeRegressor
from sklearn.datasets import fetch_california_housing
from hyperactive import Hyperactive
from hyperactive_progress_board import ProgressBoard # import progress board
data = fetch_california_housing()
X, y = data.data, data.target
progress = ProgressBoard() # init progress board
@progress.update # add decorator
def dtr_model(opt):
dtr = DecisionTreeRegressor(
min_samples_split=opt["min_samples_split"],
)
scores = cross_val_score(dtr, X, y, cv=5)
return scores.mean()
search_space = {
"max_depth": list(range(2, 50)),
"min_samples_split": list(range(2, 50)),
"min_samples_leaf": list(range(1, 50)),
}
progress.open() # open progress board before run begins
hyper = Hyperactive()
hyper.add_search(dtr_model, search_space, n_iter=1000)
hyper.run()
```
## FAQ
Command line opens and closes immediately
This happens because of the command line of a previous run of the progress-board is still running. Close the command-line from the previous run to start a new one.