Untitled
import pandas as pd def combine_csv_remove_duplicates(file1, file2, output_file): """ Combines two CSV files, removes duplicate rows, and writes the result to a new file. :param file1: Path to the first CSV file. :param file2: Path to the second CSV file. :param output_file: Path to the output CSV file. """ # Load both CSV files into dataframes df1 = pd.read_csv(file1) df2 = pd.read_csv(file2) # Concatenate the dataframes combined_df = pd.concat([df1, df2], ignore_index=True) # Remove duplicates based on all columns combined_df = combined_df.drop_duplicates() # Write to output CSV combined_df.to_csv(output_file, index=False) # Example usage file1 = 'file1.csv' file2 = 'file2.csv' output_file = 'combined_output.csv' combine_csv_remove_duplicates(file1, file2, output_file)
Leave a Comment