Clean up excel data
Jump to navigation
Jump to search
import pandas as pd excel_file = 'docs/baddata.xlsx' df = pd.read_excel(excel_file) #print(df.head(2)) #test on one column #df['Name'] = df['Name'].str.replace(r'\W',"") # r means regular expression \w (opposite of w) selects everything that is not a number and not a letter, replace with blank #apply to entire sheet for column in df.columns: df[column] = df[column].str.replace(r'\W',"") print(df) df.to_excel("docs/cleaned.xlsx")