Gaussian Mixtures

Load Iris dataset and create clusters.

from __future__ import annotations

from gemseo import configure_logger
from gemseo import create_benchmark_dataset
from gemseo.datasets.dataset import Dataset
from gemseo.mlearning import create_clustering_model
from gemseo.post.dataset.scatter_plot_matrix import ScatterMatrix
from numpy import array

configure_logger()

<RootLogger root (INFO)>

Create dataset

We import the Iris benchmark dataset through the API.

iris = create_benchmark_dataset("IrisDataset")

# Extract inputs as a new dataset
data = iris.get_view(group_names=iris.PARAMETER_GROUP).to_numpy()
variables = iris.get_variable_names(iris.PARAMETER_GROUP)
print(variables)

dataset = Dataset.from_array(data, variables)

['petal_length', 'petal_width', 'sepal_length', 'sepal_width']

Create clustering model

We know that there are three classes of Iris plants. We will thus try to identify three clusters.

model = create_clustering_model("GaussianMixture", data=dataset, n_components=3)
model.learn()
print(model)

GaussianMixture(n_components=3, var_names=None)
   based on the scikit-learn library
   built from 150 learning samples

Predict output

Once it is built, we can use it for prediction.

input_value = {
    "sepal_length": array([4.5]),
    "sepal_width": array([3.0]),
    "petal_length": array([1.0]),
    "petal_width": array([0.2]),
}
output_value = model.predict(input_value)
print(output_value)

2

Plot clusters

Show cluster labels

dataset.add_variable("gm_specy", model.labels.reshape((-1, 1)), "labels")
ScatterMatrix(dataset, kde=True, classifier="gm_specy").execute(save=False, show=True)

/home/docs/checkouts/readthedocs.org/user_builds/gemseo/envs/5.0.1/lib/python3.9/site-packages/gemseo/post/dataset/scatter_plot_matrix.py:137: UserWarning: To output multiple subplots, the figure containing the passed axes is being cleared.
  sub_axes = scatter_matrix(

[<Figure size 640x480 with 16 Axes>]