Pandas - How to compare 2 CSV files and output changes

CSV generally doesn't support different fonts, but here's a solution that uses bold and colors output to the console (note: I only tested on Mac). If you're using Python 3.7+ (dictionaries sorted by insertion order), then the dictionary ordering and columns list shouldn't be necessary.

from collections import OrderedDict from csv import DictReader class Color(object): GREEN = '\033[92m' RED = '\033[91m' BOLD = '\033[1m' END = '\033[0m' def load_csv(file): # Index by ID in order, and keep track of the original column order with open(file, 'r') as fp: reader = DictReader(fp, delimiter=',') rows = OrderedDict((r['ID'], r) for r in reader) return rows, reader.fieldnames def print_row(row, cols, color, prefix): print(Color.BOLD + color + prefix + ','.join(row[c] for c in cols) + Color.END) def print_diff(row1, row2, cols): row = [] for col in cols: value1 = row1[col] if row2[col] != value1: row.append(Color.BOLD + Color.GREEN + value1 + Color.END) else: row.append(value1) print(','.join(row)) def diff_csv(file1, file2): rows1, cols = load_csv(file1) rows2, _ = load_csv(file2) for row_id, row1 in rows1.items(): # Pop the matching ID row row2 = rows2.pop(row_id, None) # If not in file2, then it was added if not row2: print_row(row1, cols, Color.GREEN, '+') # In both files, print the diff else: print_diff(row1, row2, cols) # Anything remaining from file2 was removed in file1 for row in rows2.values(): print_row(row, cols, Color.RED, '-') 

This can be done simply by using python's built in CSV library. If you also care about the order of your entries, you can use an OrderedDict to maintain the original file order.

import csv f = [] f3 = file('results.csv', 'w') with open('file1.csv', 'rb') as f1, open('file2.csv', 'rb') as f2: reader1 = csv.reader(f1, delimiter=",") reader2 = csv.reader(f2, delimiter=",") for line in enumerate(reader1): f.append(line) #For the first file, add them all for line in enumerate(reader2): if not any(e[0] == line[0] for e in f): #For the second file, only add them if there is not an entry with the same name already f.append(line) for e in f: if e[0] == line[0]: changedindexes = i != j for i, j in zip(e[0], line[0]) for val in changedindexes: e[val] = e[val] + 'c' c3 = csv.writer(f3, , quoting=csv.QUOTE_ALL) for line in f: #Write the new merged files into another csv c3.writerow(line) #Then find the differences between the two orderedDicts 

As for bolding, there is no way to do that in CSV, as csv files contain data, not any formatting information.

A second way:

# get indices of differences difference_locations = np.where(df1 != df2) #define reference changed_from = df1.values[difference_locations] changed_to = df2.values[difference_locations] df_differences = pd.DataFrame({'from': changed_from, 'to': changed_to}, index=changed.index)