How do you detect and remove duplicate rows in a Pandas DataFrame?

import pandas as pd

df = pd.DataFrame({
    'order_id': [1, 2, 2, 3, 4, 4],
    'product':  ['A', 'B', 'B', 'C', 'D', 'D'],
    'amount':   [100, 200, 200, 150, 80, 90],   # last pair differs!
})

# --- Detecting duplicates ---
df.duplicated()               # True for all duplicates (keeps first)
df.duplicated(keep='last')    # True for all duplicates (keeps last)
df.duplicated(keep=False)     # True for ALL occurrences

print(df.duplicated().sum())  # count of duplicate rows

# Duplicate check on a subset of columns only
df.duplicated(subset=['order_id', 'product'])
# True where order_id AND product are repeated (ignores amount diff)

# --- Removing duplicates ---
df.drop_duplicates()          # removes all but first occurrence
df.drop_duplicates(keep='last')  # keeps last occurrence
df.drop_duplicates(keep=False)   # removes all occurrences of any duplicate

# Subset-based deduplication — keep first by order_id
df.drop_duplicates(subset=['order_id'], keep='first')

# Sort before deduplicating to control which row is 'first'
# (e.g., keep the highest amount per order)
df.sort_values('amount', ascending=False).drop_duplicates(subset=['order_id'])