Pandas function to generate unique hash for each row

pandas_hash.py

import hashlib
# Function to generate hash for each row
def generate_hash(row):
    hash_object = hashlib.sha256()
    # Convert each element in the row to a string and update the hash object
    for value in row.values:
        hash_object.update(str(value).encode('utf-8'))
    # Return the hexadecimal representation of the hash
    return hash_object.hexdigest()[:30]

# Apply the function to each row and create a new column 'hash'
df['hash'] = df.apply(generate_hash, axis=1)
df

# Useful: check duplicate rows 
df[df.duplicated(keep="first")]

# Keep only first duplicate
df.drop_duplicates("OI",keep="first").reset_index(drop=True)