Umap Learn

pip install umap-learn

# For Parametric UMAP (neural network variant)
pip install umap-learn[parametric_umap]  # requires TensorFlow 2.x

import umap
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import load_digits

# Load and scale data
X, y = load_digits(return_X_y=True)
X_scaled = StandardScaler().fit_transform(X)

# Fit and transform
embedding = umap.UMAP(random_state=42).fit_transform(X_scaled)
print(f"Input: {X_scaled.shape}, Output: {embedding.shape}")
# Input: (1797, 64), Output: (1797, 2)

import umap
from sklearn.preprocessing import StandardScaler

X_scaled = StandardScaler().fit_transform(data)

# Method 1: fit_transform (single step)
embedding = umap.UMAP(
    n_neighbors=15,     # local neighborhood size (2-200)
    min_dist=0.1,       # min distance between embedded points (0.0-0.99)
    n_components=2,     # output dimensions
    metric='euclidean', # distance metric
    random_state=42,    # reproducibility
).fit_transform(X_scaled)
print(f"Embedding shape: {embedding.shape}")

# Method 2: fit + access (for reuse)
reducer = umap.UMAP(random_state=42)
reducer.fit(X_scaled)
embedding = reducer.embedding_  # trained embedding
graph = reducer.graph_          # fuzzy simplicial set (sparse matrix)

# Visualization
import matplotlib.pyplot as plt

plt.figure(figsize=(8, 6))
plt.scatter(embedding[:, 0], embedding[:, 1], c=labels, cmap='Spectral', s=5)
plt.colorbar()
plt.title('UMAP Embedding')
plt.tight_layout()
plt.savefig('umap_embedding.png', dpi=150)

import umap

# Supervised — all labels known
embedding = umap.UMAP(random_state=42).fit_transform(X_scaled, y=labels)

# Semi-supervised — partial labels (mark unlabeled as -1)
semi_labels = labels.copy()
semi_labels[unlabeled_indices] = -1
embedding = umap.UMAP(random_state=42).fit_transform(X_scaled, y=semi_labels)

# Control label influence with target_weight (0.0=unsupervised, 1.0=fully supervised)
reducer = umap.UMAP(
    target_weight=0.7,               # emphasize labels
    target_metric='categorical',     # for classification; use distance metric for regression
    random_state=42
)
embedding = reducer.fit_transform(X_scaled, y=labels)
print(f"Supervised embedding: {embedding.shape}")

import umap
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Fit on training data
reducer = umap.UMAP(n_components=10, random_state=42)
X_train_emb = reducer.fit_transform(X_train_scaled)

# Transform test data
X_test_emb = reducer.transform(X_test_scaled)
print(f"Train: {X_train_emb.shape}, Test: {X_test_emb.shape}")

# Works in sklearn Pipelines
from sklearn.pipeline import Pipeline
from sklearn.svm import SVC

pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('umap', umap.UMAP(n_components=10, random_state=42)),
    ('classifier', SVC())
])
pipeline.fit(X_train, y_train)
accuracy = pipeline.score(X_test, y_test)
print(f"Pipeline accuracy: {accuracy:.3f}")

from umap.parametric_umap import ParametricUMAP

# Default architecture (3-layer, 100-neuron FC network)
embedder = ParametricUMAP(n_components=2, random_state=42)
embedding = embedder.fit_transform(X_scaled)
new_emb = embedder.transform(new_data)  # fast neural network inference
print(f"Parametric embedding: {embedding.shape}")

import tensorflow as tf
from umap.parametric_umap import ParametricUMAP

# Custom encoder/decoder for autoencoder mode
input_dim = X_scaled.shape[1]
encoder = tf.keras.Sequential([
    tf.keras.layers.InputLayer(input_shape=(input_dim,)),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(2),
])
decoder = tf.keras.Sequential([
    tf.keras.layers.InputLayer(input_shape=(2,)),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(input_dim),
])

embedder = ParametricUMAP(
    encoder=encoder, decoder=decoder, dims=(input_dim,),
    parametric_reconstruction=True, autoencoder_loss=True,
    n_training_epochs=10, batch_size=128,
    n_neighbors=15, min_dist=0.1, random_state=42
)
embedding = embedder.fit_transform(X_scaled)
reconstructed = embedder.inverse_transform(embedding)
print(f"Reconstruction error: {np.mean((X_scaled - reconstructed)**2):.4f}")

import umap

reducer = umap.UMAP(
    densmap=True,          # enable DensMAP
    dens_lambda=2.0,       # density preservation weight
    dens_frac=0.3,         # fraction for density estimation
    output_dens=True,      # output density estimates
    n_neighbors=15,
    min_dist=0.1,
    random_state=42
)
embedding = reducer.fit_transform(X_scaled)

# Access density estimates
original_density = reducer.rad_orig_  # density in original space
embedded_density = reducer.rad_emb_   # density in embedded space
print(f"DensMAP embedding: {embedding.shape}")
print(f"Density correlation: {np.corrcoef(original_density, embedded_density)[0,1]:.3f}")

from umap import AlignedUMAP

# Multiple related datasets
datasets = [day1_data, day2_data, day3_data]

mapper = AlignedUMAP(
    n_neighbors=15,
    alignment_regularisation=1e-2,  # alignment strength
    alignment_window_size=2,        # align with N adjacent datasets
    n_components=2,
    random_state=42
)
mapper.fit(datasets)

aligned_embeddings = mapper.embeddings_  # list of aligned embedding arrays
print(f"Aligned {len(aligned_embeddings)} datasets")
for i, emb in enumerate(aligned_embeddings):
    print(f"  Dataset {i}: {emb.shape}")

import umap
import hdbscan
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import adjusted_rand_score

# Step 1: Preprocess
X_scaled = StandardScaler().fit_transform(data)
print(f"Input shape: {X_scaled.shape}")

# Step 2: UMAP for clustering (NOT visualization parameters)
reducer = umap.UMAP(
    n_neighbors=30,     # more global structure for clustering
    min_dist=0.0,       # allow tight packing
    n_components=10,    # higher dims preserve density better than 2D
    metric='euclidean',
    random_state=42
)
embedding = reducer.fit_transform(X_scaled)

# Step 3: HDBSCAN clustering
clusterer = hdbscan.HDBSCAN(min_cluster_size=15, min_samples=5)
cluster_labels = clusterer.fit_predict(embedding)

n_clusters = len(set(cluster_labels)) - (1 if -1 in cluster_labels else 0)
noise = sum(cluster_labels == -1)
print(f"Clusters: {n_clusters}, Noise: {noise}")

# Step 4: Separate 2D embedding for visualization
vis_emb = umap.UMAP(n_neighbors=15, min_dist=0.1, random_state=42).fit_transform(X_scaled)
plt.scatter(vis_emb[:, 0], vis_emb[:, 1], c=cluster_labels, cmap='Spectral', s=5)
plt.colorbar()
plt.title(f'HDBSCAN Clusters (n={n_clusters})')
plt.tight_layout()
plt.savefig('umap_clusters.png', dpi=150)

import umap
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.metrics import classification_report

# Split and scale
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
scaler = StandardScaler()
X_train_s = scaler.fit_transform(X_train)
X_test_s = scaler.transform(X_test)

# Supervised UMAP for feature engineering
reducer = umap.UMAP(n_components=10, random_state=42)
X_train_emb = reducer.fit_transform(X_train_s, y=y_train)
X_test_emb = reducer.transform(X_test_s)

# Downstream classifier
clf = SVC(kernel='rbf')
clf.fit(X_train_emb, y_train)
y_pred = clf.predict(X_test_emb)

print(classification_report(y_test, y_pred))