Python での大規模データ処理の最適化: CSV 操作の並列化ガイド

import os

def split_csv(file_path, lines_per_chunk=1000000):
    with open(file_path, 'r') as file:
        header = file.readline()
        file_count = 0
        output_file = None
        for i, line in enumerate(file):
            if i % lines_per_chunk == 0:
                if output_file:
                    output_file.close()
                file_count += 1
                output_file = open(f'chunk_{file_count}.csv', 'w')
                output_file.write(header)
            output_file.write(line)
        if output_file:
            output_file.close()
    print(f"Split into {file_count} files.")

import dask.dataframe as dd

# Load the dataset as a Dask DataFrame
df = dd.read_csv('large_file.csv')

# Perform parallel operations
result = df[df['column_name'] > 100].groupby('another_column').mean()

# Save the result
result.to_csv('output_*.csv', single_file=True)

import polars as pl

# Read CSV using Polars
df = pl.read_csv('large_file.csv')

# Filter and aggregate data
filtered_df = df.filter(pl.col('column_name') > 100).groupby('another_column').mean()

# Write to CSV
filtered_df.write_csv('output.csv')

from multiprocessing import Pool
import pandas as pd

def process_chunk(file_path):
    df = pd.read_csv(file_path)
    # Perform operations
    filtered_df = df[df['column_name'] > 100]
    return filtered_df

if __name__ == '__main__':
    chunk_files = [f'chunk_{i}.csv' for i in range(1, 6)]
    with Pool(processes=4) as pool:
        results = pool.map(process_chunk, chunk_files)

    # Combine results
    combined_df = pd.concat(results)
    combined_df.to_csv('final_output.csv', index=False)