How To See The Progress Bar Of Read_csv

I'm trying to read 100GB size of csv file I want to see the profess bar when they reading file file = pd.read_csv('../code/csv/file.csv') like =====> 30% is there way to se

Solution 1:

import os
import sys
from tqdm import tqdm

temp = pd.read_csv(INPUT_FILENAME, nrows=20)
N = len(temp.to_csv(index=False))
df = [temp[:0]]
t = int(os.path.getsize(fn)/N*20/10**5) + 1with tqdm(total = t, file = sys.stdout) as pbar:
    for i,chunk inenumerate(pd.read_csv(fn, chunksize=10**5, low_memory=False)):
        df.append(chunk)
        pbar.set_description('Importing: %d' % (1 + i))
        pbar.update(1)

data = temp[:0].append(df)
del df            

Solution 2:

A fancy output with typer module, which I have tested in Jupyter Notebook with a massive delimited text file having 618k rows.

from pathlib import Path
import pandas as pd
import tqdm
import typer

txt = Path("<path-to-massive-delimited-txt-file>").resolve()

# read number of rows quickly
length = sum(1for row inopen(txt, 'r'))

# define a chunksize
chunksize = 5000# initiate a blank dataframe
df = pd.DataFrame()

# fancy logging with typer
typer.secho(f"Reading file: {txt}", fg="red", bold=True)
typer.secho(f"total rows: {length}", fg="green", bold=True)

# tqdm contextwith tqdm.auto.tqdm(total=length, desc="chunks read: ") as bar:
    # enumerate chunks read without low_memory (it is massive for pandas to precisely assign dtypes)for i, chunk inenumerate(pd.read_csv(txt, chunksize=chunksize, low_memory=False)):
        
        # print the chunk numberprint(i)
        
        # append it to df
        df = df.append(other=chunk)
        
        # update tqdm progress bar
        bar.update(chunksize)
        
        # 6 chunks are enough to testif i==5:
            break# finally inform with a friendly message
typer.secho("end of reading chunks...", fg=typer.colors.BRIGHT_RED)
typer.secho(f"Dataframe length:{len(df)}", fg="green", bold=True)
    

Jupyter Notebook Output - png