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-string-ops/code/generate_data.py

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

"""Generate synthetic messy text data for string operations."""

import os
import numpy as np
import pandas as pd

SEED = 42
N_ROWS = 30_000


def generate():
    if os.path.exists("raw_contacts.csv"):
        return

    rng = np.random.default_rng(SEED)

    first_names = ["Alice", "Bob", "  Charlie", "Diana ", " Eve", "FRANK",
                   "grace", " HANK ", "Ivy", "  jack"]
    last_names = ["Smith", " JONES", "Williams ", "  BROWN", "davis",
                  " Miller", "WILSON ", "moore", " Taylor", "Anderson"]
    domains = ["gmail.com", "yahoo.com", "outlook.com", "company.org", "example.net"]

    phones_raw = []
    emails_raw = []
    addresses_raw = []

    for _ in range(N_ROWS):
        # messy phone: mix of formats
        area = rng.integers(200, 999)
        mid = rng.integers(100, 999)
        last4 = rng.integers(1000, 9999)
        fmt = rng.choice(["paren", "dash", "dot", "plain", "intl"])
        if fmt == "paren":
            phones_raw.append(f"({area}) {mid}-{last4}")
        elif fmt == "dash":
            phones_raw.append(f"{area}-{mid}-{last4}")
        elif fmt == "dot":
            phones_raw.append(f"{area}.{mid}.{last4}")
        elif fmt == "plain":
            phones_raw.append(f"{area}{mid}{last4}")
        else:
            phones_raw.append(f"+1-{area}-{mid}-{last4}")

        fn = rng.choice(first_names)
        ln = rng.choice(last_names)
        dom = rng.choice(domains)
        emails_raw.append(f"  {fn.strip().lower()}.{ln.strip().lower()}@{dom}  ")

        num = rng.integers(1, 9999)
        street = rng.choice(["Main St", "Oak Ave", "1st Blvd", "Elm Dr", "Pine Ln"])
        state = rng.choice(["CA", "NY", "TX", "FL", "WA", "IL"])
        zipcode = rng.integers(10000, 99999)
        addresses_raw.append(f" {num} {street}, {state} {zipcode} ")

    df = pd.DataFrame({
        "first_name": rng.choice(first_names, N_ROWS),
        "last_name": rng.choice(last_names, N_ROWS),
        "email": emails_raw,
        "phone": phones_raw,
        "address": addresses_raw,
        "notes": rng.choice([
            "VIP customer - priority support",
            "CALLED 2024-01-15: billing issue",
            "Ref#12345 - pending review",
            "  no notes  ",
            "email BOUNCED on 2024-03-01",
            "Discount: 20% off next order",
            "REF#99887 follow-up required",
            "",
        ], N_ROWS),
    })

    df.to_csv("raw_contacts.csv", index=False)
    print(f"Generated {len(df)} messy contact rows -> raw_contacts.csv")


if __name__ == "__main__":
    generate()
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