Untitled
import pandas as pd # Read the dataframe from URL url = input() df = pd.read_csv(url) # Delete rows with more than 50% missing values df = df.dropna(thresh=len(df.columns) / 2) # Remove character from the 'Date' column df['Date'] = df['Date'].str.replace('é', '') # Round off all float columns to two decimal places float_columns = df.select_dtypes(include=['float']).columns df[float_columns] = df[float_columns].round(2) # Print number of rows and columns in the final dataframe print(len(df)) print(len(df.columns)) # Print first 10 values of the 'Date' column print(df['Date'].head(10).tolist()) # Print first 5 rows with only the float columns print(df.select_dtypes(include=['float']).head())
Leave a Comment