cuml-machine-learning

cuML Machine Learning Skill

GPU-accelerated machine learning using NVIDIA RAPIDS cuML. cuML provides a scikit-learn-compatible API that runs on NVIDIA GPUs, enabling massive speedups on large datasets.

When to Use This Skill

Use this skill when:

• Training classification models (predict categories, detect fraud, classify text)
• Training regression models (forecast values, predict prices, estimate quantities)
• Clustering data (segment customers, group documents, find patterns)
• Dimensionality reduction (visualize high-dimensional data, compress features)
• Preprocessing and feature engineering on large datasets
• Any ML task on datasets with 10K+ rows where GPU acceleration helps

Initialization (REQUIRED)

Always start every script with this boilerplate. It tests actual GPU ML operations.

import pandas as pd
import numpy as np

try:
    import cudf
    import cuml
    # Smoke-test: verify GPU ML works end-to-end
    _test_data = cudf.DataFrame({'a': [1.0, 2.0, 3.0, 4.0], 'b': [5.0, 6.0, 7.0, 8.0]})
    _km = cuml.cluster.KMeans(n_clusters=2, n_init=1, random_state=42)
    _km.fit(_test_data)
    assert len(_km.labels_) == 4
    GPU = True
except Exception as e:
    print(f"[GPU] cuml unavailable, falling back to scikit-learn: {e}")
    GPU = False

def read_csv(path):
    return cudf.read_csv(path) if GPU else pd.read_csv(path)

def to_pd(df):
    """Convert cuML/cuDF output to pandas. Use this instead of .to_pandas() directly."""
    if not GPU:
        return df
    try:
        return df.to_pandas()
    except Exception as e:
        print(f"[GPU] .to_pandas() failed, using Arrow fallback: {e}")
        return df.to_arrow().to_pandas()

Import Patterns

# GPU mode
if GPU:
    from cuml.cluster import KMeans, DBSCAN, HDBSCAN
    from cuml.ensemble import RandomForestClassifier, RandomForestRegressor
    from cuml.linear_model import LinearRegression, Ridge, Lasso, LogisticRegression
    from cuml.neighbors import KNeighborsClassifier, KNeighborsRegressor
    from cuml.svm import SVC, SVR
    from cuml.decomposition import PCA, TruncatedSVD
    from cuml.manifold import UMAP, TSNE
    from cuml.preprocessing import StandardScaler, MinMaxScaler, LabelEncoder
    from cuml.model_selection import train_test_split
    from cuml.metrics import accuracy_score, r2_score, mean_squared_error
# CPU fallback
else:
    from sklearn.cluster import KMeans, DBSCAN, HDBSCAN
    from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
    from sklearn.linear_model import LinearRegression, Ridge, Lasso, LogisticRegression
    from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor
    from sklearn.svm import SVC, SVR
    from sklearn.decomposition import PCA, TruncatedSVD
    from sklearn.manifold import TSNE
    from sklearn.preprocessing import StandardScaler, MinMaxScaler, LabelEncoder
    from sklearn.model_selection import train_test_split
    from sklearn.metrics import accuracy_score, r2_score, mean_squared_error
    # UMAP not in sklearn — skip or pip install umap-learn