!python -V #%% import pandas as pd import pickle from sklearn.metrics import root_mean_squared_error from sklearn.feature_extraction import DictVectorizer import mlflow def read_dataframe1(filename): df = pd.read_parquet(filename) df['duration'] = df.tpep_dropoff_datetime - df.tpep_pickup_datetime df.duration = df.duration.apply(lambda td: td.total_seconds()/60) df = df[df.duration >= 1] & (df.duration <= 60) categorical = ['PULocationID', 'DOLocationID'] df[categorical] = df[categorical].astype(str) return df #%% train_df = read_dataframe1("https://d37ci6vzurychx.cloudfront.net/trip-data/yellow_tripdata_2023-01.parquet") When I run the last line for loading the parquet file with the function read_dataframe1, it does not load even after waiting over 30 minutes and the cell keeps running What can be the reason? Continue reading...
