Compare two data frames by column values

compare.py

import numpy as np
import pandas as pd

# content from '1.csv'
#
# a,b,c,d
# 1,0.1,"a-10","hello"
# 2,0.2,"a-11","hola"
# 3,0.3,"a-12","hallo"
# 4,0.5,"a-13","hello"

# content from '2.csv'
# other,other_c
# 3.1,"a-99"
# 4.2,"a-10"
# 6.3,"a-22"
# 1.5,"a-11"

df_a = pd.read_csv("1.csv")
df_b = pd.read_csv("2.csv")

a = df_a[['a', 'b', 'c']]
b = df_b[['other', 'other_c']]

print(a)
print(b)
print("-"*10)


print("values from `1.csv` that are in `2.csv` based on column `c`")
contains = a[b['other_c'].apply(lambda x: x in a['c'].values)]
print(contains)
print("-"*10)

print("values from `1.csv` that are NOT in `2.csv` based on column `c`")
diff = a[b['other_c'].apply(lambda x: x not in a['c'].values)]
print(diff)

# Output
#
#    a    b     c
# 0  1  0.1  a-10
# 1  2  0.2  a-11
# 2  3  0.3  a-12
# 3  4  0.5  a-13
#    other other_c
# 0    3.1    a-99
# 1    4.2    a-10
# 2    6.3    a-22
# 3    1.5    a-11
# ----------
# values from `1.csv` that are in `2.csv` based on column `c`
#    a    b     c
# 1  2  0.2  a-11
# 3  4  0.5  a-13
# ----------
# values from `1.csv` that are NOT in `2.csv` based on column `c`
#    a    b     c
# 0  1  0.1  a-10
# 2  3  0.3  a-12
#