Data Cleaning with Pandas

Data cleaning is the process of fixing or removing incorrect, incomplete, or duplicate data before analysis or machine learning.

1. Import Pandas

import pandas as pd

2. Load Data

df = pd.read_csv("data.csv")

Common Data Cleaning Tasks

3. Check Data Overview

df.head()
df.info()
df.describe()
df.shape

4. Handling Missing Values (NaN)

✔ Check missing values

df.isnull().sum()

✔ Remove rows with missing values

df.dropna(inplace=True)

✔ Fill missing values

df['age'].fillna(df['age'].mean(), inplace=True)   # numerical
df['city'].fillna(df['city'].mode()[0], inplace=True)  # categorical

✔ Replace missing values with custom value

df.fillna("Unknown", inplace=True)

5. Handling Duplicates

✔ Find duplicates

df.duplicated().sum()

✔ Remove duplicates

df.drop_duplicates(inplace=True)

6. Fixing Incorrect Data

✔ Replace wrong values

df['gender'].replace({'M':'Male', 'F':'Female'}, inplace=True)

✔ Correct text cases

df['city'] = df['city'].str.title()

✔ Remove extra spaces

df['name'] = df['name'].str.strip()

7. Handling Outliers

✔ Using IQR

Q1 = df['price'].quantile(0.25)
Q3 = df['price'].quantile(0.75)
IQR = Q3 - Q1

df = df[(df['price'] >= Q1 - 1.5*IQR) & (df['price'] <= Q3 + 1.5*IQR)]

✔ Capping outliers

df['price'] = df['price'].clip(lower=df['price'].quantile(0.05),
                               upper=df['price'].quantile(0.95))

8. Converting Data Types

✔ Check data types

df.dtypes

✔ Convert column type

df['age'] = df['age'].astype(int)
df['amount'] = df['amount'].astype(float)
df['date'] = pd.to_datetime(df['date'])

9. Standardizing Text

df['product'] = df['product'].str.lower()
df['phone'] = df['phone'].str.replace('-', '')

10. Renaming Columns

df.rename(columns={'oldName':'newName'}, inplace=True)

11. Handling Inconsistent Categories

Example: “Delhi”, “delhi “, “DELHI”

df['city'] = df['city'].str.strip().str.lower()

12. Dropping Unwanted Columns

df.drop(['temp_column', 'unnecessary'], axis=1, inplace=True)

13. Replace Null-like strings ("N/A", "-", "none")

df.replace(['N/A', 'NA', '-', 'None'], pd.NA, inplace=True)

Final Data Cleaning Workflow Example

df = pd.read_csv("data.csv")

# Missing Values
df['age'].fillna(df['age'].mean(), inplace=True)

# Remove Duplicates
df.drop_duplicates(inplace=True)

# Fix Text
df['name'] = df['name'].str.strip().str.title()

# Correct Data Types
df['date'] = pd.to_datetime(df['date'])

# Fix categories
df['city'] = df['city'].str.strip().str.lower()