VisualML: Visualization of Multi-Dimensional Machine Learning Models
Project description
Visual ML is a library for visualizing the decision boundary of
machine learning models from Sklearn using 2D projections of pairs
of features. Here's an example:
```
>>> import visualml as vml
>>> import pandas as pd
>>> from sklearn.datasets import make_classification
>>> from sklearn.ensemble import RandomForestClassifier as RF
>>> # Create a toy classification dataset
>>> feature_names = ['A','B','C','D']
>>> X, y = make_classification(n_features=4, random_state=42)
>>> # The visualization is only supported if X is a pandas df
>>> X = pd.DataFrame(X, columns=feature_names)
>>> # Train a classifier
>>> clf = RF(random_state=42).fit(X,y)
>>> # Plot decision boundary grid
>>> vml.decision_boundary_grid(clf, X, y)
```
machine learning models from Sklearn using 2D projections of pairs
of features. Here's an example:
```
>>> import visualml as vml
>>> import pandas as pd
>>> from sklearn.datasets import make_classification
>>> from sklearn.ensemble import RandomForestClassifier as RF
>>> # Create a toy classification dataset
>>> feature_names = ['A','B','C','D']
>>> X, y = make_classification(n_features=4, random_state=42)
>>> # The visualization is only supported if X is a pandas df
>>> X = pd.DataFrame(X, columns=feature_names)
>>> # Train a classifier
>>> clf = RF(random_state=42).fit(X,y)
>>> # Plot decision boundary grid
>>> vml.decision_boundary_grid(clf, X, y)
```
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
easycolab-0.1b18.tar.gz
(2.5 kB
view hashes)
Built Distribution
Close
Hashes for easycolab-0.1b18-py2-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2c6e8b42a965989cbeb63aebc905678b565ddd2bef6cc1575935b75fcf121220 |
|
MD5 | af4fbd7976d0feffd119147dffd31a8a |
|
BLAKE2b-256 | 3483d3ccabab5f5bef9b062dd5eac3ea85c46b9ade6ba525ee9fefd292413841 |