#1 Polar vs Pandas

Simple Program to explain the speed, Memory Usage  using polar > pandas.

import pandas as pd

import polars as pl

import numpy as np

import time, psutil

# Create sample data

n = 100_000_000

data = {"A": np.random.rand(n), "B": np.random.rand(n)}

# --- Pandas ---

start = time.time()

pdf = pd.DataFrame(data)

print("Pandas creation time:", round(time.time() - start, 3), "s")

#Pandas creation time: 0.475 s

# --- Polars ---

start = time.time()

pldf = pl.DataFrame(data)

print("Polars creation time:", round(time.time() - start, 3), "s")

#Polars creation time: 0.001 s

# To check the memory image comparison

import sys

print("Pandas Memory (MB):", round(pdf.memory_usage(deep=True).sum() / 1024**2, 2))

#Pandas Memory (MB): 1525.88

print("Polars Memory (MB):", round(pldf.estimated_size() / 1024**2, 2))

#Polars Memory (MB): _______ (find out yourself)👈👈👈👈

# Benchmark Evaluation

import matplotlib.pyplot as plt

sizes = [10_000, 100_000, 1_000_000, 5_000_000]

pandas_times, polars_times = [], []

for n in sizes:

    data = {"A": np.random.rand(n), "B": np.random.rand(n)}

    start = time.time()

    pd.DataFrame(data)["A"].sum()

    pandas_times.append(time.time() - start)

    start = time.time()

    pl.DataFrame(data)["A"].sum()

    polars_times.append(time.time() - start)

plt.plot(sizes, pandas_times, label="Pandas")

plt.plot(sizes, polars_times, label="Polars")

plt.xlabel("Rows")

plt.ylabel("Time (s)")

plt.legend()

plt.title("Polars vs Pandas Performance")

plt.show()

Response:

n-joy 😄😄😄