Pandas vs. Polars: 구문, 속도 및 메모리 사용량 완벽 비교

import pandas as pd
import polars as pl
import time

# pandas: Read CSV
start = time.time()
df_pandas = pd.read_csv('large_dataset.csv')
pandas_time = time.time() - start

# Polars: Read CSV
start = time.time()
df_polars = pl.read_csv('large_dataset.csv')
polars_time = time.time() - start

print(f"Pandas read time: {pandas_time:.2f} seconds")
print(f"Polars read time: {polars_time:.2f} seconds")

import polars as pl

# Read in lazy mode
df_lazy = pl.scan_csv('large_dataset.csv')

# Build a complex query
result = (
    df_lazy
    .filter(pl.col('age') > 30)
    .group_by('department')
    .agg([
        pl.col('salary').mean().alias('avg_salary'),
        pl.len().alias('employee_count')
    ])
    .collect() # This runs the query
)