kavin525zhang/llm_reasoning_framework/cudf-analytics

import pandas as pd
try:
    import cudf
    # Smoke-test: verify GPU compute AND host transfer both work
    _test = cudf.Series([1, 2, 3])
    assert _test.sum() == 6
    assert _test.to_pandas().tolist() == [1, 2, 3]
    GPU = True
except Exception as e:
    print(f"[GPU] cudf unavailable, falling back to pandas: {e}")
    GPU = False
def read_csv(path):
    return cudf.read_csv(path) if GPU else pd.read_csv(path)
def to_pd(df):
    """Convert cuDF DataFrame/Series 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()

df = read_csv("data.csv")

# Use to_pd() when you need pandas output
summary = to_pd(df[["value", "score"]].describe())
# Scalar values work directly with float()
mean_val = float(df["value"].mean())
q1 = float(df["value"].quantile(0.25))
# Correlation
corr = float(df["value"].corr(df["score"]))

result = df.groupby("category").agg({
    "revenue": ["sum", "mean", "count"],
    "quantity": ["sum", "mean"],
})
result_pd = to_pd(result)

col = "value"
Q1 = float(df[col].quantile(0.25))
Q3 = float(df[col].quantile(0.75))
IQR = Q3 - Q1
lower = Q1 - 1.5 * IQR
upper = Q3 + 1.5 * IQR
outliers = to_pd(df[(df[col] < lower) | (df[col] > upper)])

mean = float(df[col].mean())
std = float(df[col].std())
df["z_score"] = (df[col] - mean) / std
anomalies = to_pd(df[df["z_score"].abs() > 3])

# Filter rows
filtered = df[df["status"] == "active"]
# Select columns
subset = df[["name", "revenue", "date"]]
# Sort
sorted_df = df.sort_values("revenue", ascending=False)
# Convert to pandas for final output / iteration
result_pd = to_pd(sorted_df)