import sys
import os
import pandas as pd

source_path = sys.argv[1]
file_name = os.path.splitext(os.path.basename(source_path))[0]
directory = os.path.dirname(os.path.abspath(source_path))
column = sys.argv[2]

# 1. Read CSV
df = pd.read_csv(source_path, low_memory=False)

# 2(a). For complete row duplicate
# pd.drop_duplicates(inplace=True)

# 2(b). For partials
# df.drop_duplicates(subset=['email'], inplace=True)

df=df[df[column].isnull() | ~df[df[column].notnull()].duplicated(subset=column,keep='first')]

# 3. Save then
save_path = os.path.normpath(directory + '/' + file_name + "-without-dups.csv")
df.to_csv(save_path, index=False)