pandas से गड़बड़ डेटा साफ़ करना

import pandas as pd

# A made-up table with typical problems.
df = pd.DataFrame({
    "village": ["Rampur", "rampur ", "Sonpur", "Sonpur", "Kalyani"],
    "wells":   ["4", "4", "N/A", "N/A", "7"],
    "people":  ["1,250", "1,250", "980", "980", ""],
})
print(df)
print()
print(df.dtypes)             # "object" or "str" means text: the numbers are stored as text
print()
df["village"] = df["village"].str.strip().str.title()
df["wells"] = pd.to_numeric(df["wells"], errors="coerce")        # "N/A" becomes NaN
df["people"] = pd.to_numeric(df["people"].str.replace(",", ""), errors="coerce")
print(df)
print()
print("Missing per column:")
print(df.isna().sum())
print("Duplicate rows:", df.duplicated().sum())
print(df.drop_duplicates())