openeuler/distroless-pip-cc repository overview

# Base image with minimal Python pip runtime and libstdc++
FROM openeuler/distroless-pip-cc:23.3.1-cc12.3.1-oe2403lts

# Update CA certificates for SSL verification
RUN update-ca-trust

# Install Python packages with libstdc++ dependencies, pyarrow requires libstdc++ runtime
RUN pip install pyarrow pandas

COPY app.py /app/

CMD ["python3", "/app/app.py"]

import pyarrow as pa
import pyarrow.parquet as pq
import pandas as pd
from datetime import datetime

def process_data():
    """Demonstrates PyArrow's core features with Arrow Tables and Parquet I/O"""
    
    data = {
        "timestamp": [datetime(2023, 1, 1), datetime(2023, 1, 2)],
        "temperature": [22.5, 23.1],
        "sensor_id": ["A001", "A002"]
    }
    table = pa.Table.from_pydict(data)
    
    df = table.to_pandas()
    print("Pandas DataFrame:")
    print(df)
    
    pq.write_table(table, "/app/data.parquet", compression='SNAPPY')
    reloaded = pq.read_table("/app/data.parquet")
    
    mean_temp = pa.compute.mean(reloaded["temperature"])
    print(f"\nMean temperature: {mean_temp.as_py():.2f}°C")

if __name__ == "__main__":
    print(f"PyArrow version: {pa.__version__}")
    print(f"Running with {pa.cpu_count()} CPU cores")
    process_data()