Skip to content

MichelRojo86WPP/copilot-config / skills/accelerated-computing-cudf

accelerated-computing-cudf

Verified

Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.

FileKindSize
BENCHMARK.mdmarkdown4.2 KB
SKILL.mdskill md9.2 KB
evals/evals.jsonconfig15.8 KB
evals/files/cudf-apply-udf/code/generate_data.pyscript1.5 KB
evals/files/cudf-apply-udf/code/udf_pipeline.pyscript5.3 KB
evals/files/cudf-csv-etl/code/etl_pipeline.pyscript2.6 KB
evals/files/cudf-csv-etl/code/generate_data.pyscript1.2 KB
evals/files/cudf-groupby-agg/code/generate_data.pyscript1.4 KB
evals/files/cudf-groupby-agg/code/groupby_analysis.pyscript4.3 KB
evals/files/cudf-multi-join/code/generate_data.pyscript2.0 KB
evals/files/cudf-multi-join/code/multi_join.pyscript3.6 KB
evals/files/cudf-native-stream-handoff-boundary/NOTICE.mdmarkdown344 B
evals/files/cudf-native-stream-handoff-boundary/code/run_smoke.shscript464 B
evals/files/cudf-native-stream-handoff-boundary/code/threaded_handoff.cuother3.9 KB
evals/files/cudf-null-handling/code/generate_data.pyscript2.1 KB
evals/files/cudf-null-handling/code/null_pipeline.pyscript4.7 KB
evals/files/cudf-parquet-io/code/generate_data.pyscript2.0 KB
evals/files/cudf-parquet-io/code/parquet_pipeline.pyscript4.3 KB
evals/files/cudf-pivot-melt/code/generate_data.pyscript1.4 KB
evals/files/cudf-pivot-melt/code/reshape_analysis.pyscript4.6 KB
evals/files/cudf-string-ops/code/clean_contacts.pyscript3.4 KB
evals/files/cudf-string-ops/code/generate_data.pyscript2.7 KB
evals/files/cudf-timeseries-resample/code/generate_data.pyscript1.5 KB
evals/files/cudf-timeseries-resample/code/timeseries_analysis.pyscript4.1 KB
evals/files/cudf-window-functions/code/generate_data.pyscript1.4 KB
evals/files/cudf-window-functions/code/window_analysis.pyscript5.1 KB
evals/files/negative-deep-learning-training/code/train.pyscript1.4 KB
evals/files/source-cudf-null-fillna-semantics/NOTICE.mdmarkdown342 B
evals/files/source-cudf-null-fillna-semantics/code/null_cleanup.pyscript1.4 KB
references/api-patterns.mdmarkdown6.9 KB
references/cudf-pandas-accelerator.mdmarkdown3.6 KB
references/dask-cudf-patterns.mdmarkdown7.0 KB
skill-card.mdmarkdown4.0 KB
skill.oms.sigother12.2 KB

evals/files/cudf-parquet-io/code/parquet_pipeline.py

View on GitHub
# SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

"""Parquet I/O pipeline: read multiple files, concatenate, filter, write partitioned.

Reads log data from multiple parquet files, concatenates them, applies
filters and transformations, then writes partitioned parquet output.
"""

import os
import numpy as np
import pandas as pd
from pathlib import Path

from generate_data import generate


def load_all_parquet(input_dir):
    """Read all parquet files from a directory and concatenate."""
    generate()
    parquet_files = sorted(Path(input_dir).glob("*.parquet"))
    print(f"Found {len(parquet_files)} parquet files in {input_dir}")

    frames = []
    for f in parquet_files:
        df = pd.read_parquet(f)
        df["source_file"] = f.stem
        frames.append(df)

    combined = pd.concat(frames, ignore_index=True)
    print(f"Combined: {len(combined)} rows, {combined.columns.tolist()}")
    return combined


def filter_and_transform(df):
    """Apply filters and add computed columns."""
    # Filter out health check endpoints
    df = df[df["endpoint"] != "/api/health"].copy()
    print(f"After filtering health checks: {len(df)} rows")

    # Categorize status codes
    df["status_category"] = pd.cut(
        df["status_code"],
        bins=[0, 199, 299, 399, 499, 599],
        labels=["1xx", "2xx", "3xx", "4xx", "5xx"],
    )

    # Performance buckets
    df["is_slow"] = (df["response_time_ms"] > 500).astype(int)
    df["perf_bucket"] = pd.cut(
        df["response_time_ms"],
        bins=[0, 50, 200, 500, 1000, float("inf")],
        labels=["fast", "normal", "slow", "very_slow", "timeout"],
    )

    # Extract hour from timestamp
    df["hour"] = df["timestamp"].dt.hour
    df["day_of_week"] = df["timestamp"].dt.dayofweek

    return df


def compute_summaries(df):
    """Compute endpoint and region summaries."""
    endpoint_summary = df.groupby("endpoint").agg(
        request_count=("user_id", "count"),
        unique_users=("user_id", "nunique"),
        avg_response_ms=("response_time_ms", "mean"),
        p95_response_ms=("response_time_ms", lambda x: x.quantile(0.95)),
        error_count=("is_slow", "sum"),
        total_bytes=("bytes_sent", "sum"),
    ).reset_index()

    region_summary = df.groupby("region").agg(
        request_count=("user_id", "count"),
        avg_response_ms=("response_time_ms", "mean"),
        cache_hit_rate=("is_cached", "mean"),
    ).reset_index()

    print(f"Endpoint summary:\n{endpoint_summary.to_string(index=False)}")
    print(f"\nRegion summary:\n{region_summary.to_string(index=False)}")

    return endpoint_summary, region_summary


def write_partitioned(df, output_dir):
    """Write partitioned parquet output by region."""
    output_path = Path(output_dir)
    if output_path.exists():
        import shutil
        shutil.rmtree(output_path)
    output_path.mkdir(parents=True)

    # Convert categoricals to string for parquet compatibility
    for col in df.select_dtypes(include=["category"]).columns:
        df[col] = df[col].astype(str)

    for region, group in df.groupby("region"):
        region_dir = output_path / f"region={region}"
        region_dir.mkdir(exist_ok=True)
        out_file = region_dir / "data.parquet"
        group.to_parquet(out_file, index=False)
        print(f"Wrote {out_file} ({len(group)} rows)")


def write_summaries(endpoint_summary, region_summary, output_dir):
    """Write summary tables as parquet."""
    output_path = Path(output_dir)
    output_path.mkdir(parents=True, exist_ok=True)
    endpoint_summary.to_parquet(output_path / "endpoint_summary.parquet", index=False)
    region_summary.to_parquet(output_path / "region_summary.parquet", index=False)
    print(f"Wrote summary parquets to {output_path}")


def main():
    df = load_all_parquet("raw_logs")
    df = filter_and_transform(df)
    endpoint_summary, region_summary = compute_summaries(df)
    write_partitioned(df, "processed_logs")
    write_summaries(endpoint_summary, region_summary, "processed_logs/summaries")

    # Verify round-trip by reading back
    read_back = pd.read_parquet("processed_logs/summaries/endpoint_summary.parquet")
    print(f"\nRound-trip verification: {len(read_back)} endpoint summary rows read back")


if __name__ == "__main__":
    main()
deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall