UMAP

Testing iris dataset: https://umap-learn.readthedocs.io/en/latest/basic_usage.html#iris-data

Kernel: Python 3 (Ubuntu Linux)

In [1]:

import numpy as np
from sklearn.datasets import load_iris, load_digits
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
sns.set(style='white', context='notebook', rc={'figure.figsize':(14,10)})

In [4]:

iris = load_iris()
iris_df = pd.DataFrame(iris.data, columns=iris.feature_names)
iris_df['species'] = pd.Series(iris.target).map(dict(zip(range(3),iris.target_names)))
sns.pairplot(iris_df, hue='species')

In [5]:

import umap
reducer = umap.UMAP()

In [6]:

embedding = reducer.fit_transform(iris.data)
embedding.shape

/usr/local/lib/python3.6/dist-packages/umap/spectral.py:229: UserWarning: Embedding a total of 2 separate connected components using meta-embedding (experimental)
  n_components

(150, 2)

In [7]:

plt.scatter(
    embedding[:, 0],
    embedding[:, 1],
    c=[sns.color_palette()[x] for x in iris.target])
plt.gca().set_aspect('equal', 'datalim')
plt.title('UMAP projection of the Iris dataset', fontsize=24)

Text(0.5,1,'UMAP projection of the Iris dataset')

In [0]:

CoCalc provides the best real-time collaborative environment for Jupyter Notebooks, LaTeX documents, and SageMath, scalable from individual use to large groups and classes! Also, H100 GPUs starting at $2/hour.

UMAP

Product

Resources

Company