Pandas Cheat Sheet

All Essential Functions in One Place

■ Your go-to reference for data analysis

Sections:

1. Importing & Creating Data

2. Viewing & Exploring Data

3. Selecting & Filtering

4. Data Cleaning

5. Data Manipulation

6. Grouping & Aggregating

7. Merging & Joining

8. Date & Time

9. Exporting Data
1. Importing & Creating Data

Import pandas
import pandas as pd
import numpy as np

Reading Files
# CSV
df = pd.read_csv('[Link]')
df = pd.read_csv('[Link]', encoding='utf-8', sep=',')

# Excel
df = pd.read_excel('[Link]')
df = pd.read_excel('[Link]', sheet_name='Sheet1')

# JSON
df = pd.read_json('[Link]')

# From URL
df = pd.read_csv('[Link]

# SQL
import sqlite3
conn = [Link]('[Link]')
df = pd.read_sql('SELECT * FROM table', conn)

Creating DataFrames
# From dictionary
df = [Link]({
'name': ['Rahul', 'Priya', 'Amit'],
'age': [25, 30, 28],
'city': ['Mumbai', 'Delhi', 'Pune']
})

# From list of lists

df = [Link](
[['Rahul', 25], ['Priya', 30]],
columns=['name', 'age']
)

# Empty DataFrame
df = [Link]()

2. Viewing & Exploring Data

[Link]() # First 5 rows
[Link](10) # First 10 rows
[Link]() # Last 5 rows
[Link](5) # Random 5 rows

[Link] # (rows, columns)

[Link]() # Data types, non-null counts
[Link]() # Statistics for numeric columns
[Link] # Data type of each column

[Link] # Column names

[Link] # Row index
[Link] # Data as numpy array

len(df) # Number of rows

[Link] # Total elements (rows × cols)
df.memory_usage() # Memory used by each column
3. Selecting & Filtering

Selecting Columns
df['name'] # Single column (Series)
df[['name', 'age']] # Multiple columns (DataFrame)
[Link] # Dot notation (avoid if spaces)

[Link]() # List all columns

[Link](columns=['col1']) # Remove column

Selecting Rows
[Link][0] # First row by position
[Link][0:5] # Rows 0-4
[Link][-1] # Last row

[Link][0] # Row with index 0

[Link][0:5] # Rows with index 0-5 (inclusive!)

[Link][0:5, 0:3] # Rows 0-4, Columns 0-2

[Link][0:5, ['name', 'age']] # Rows 0-5, specific columns

Filtering (Super Important!)

# Single condition
df[df['age'] > 25]
df[df['city'] == 'Mumbai']
df[df['salary'] >= 50000]

# Multiple conditions (AND)

df[(df['age'] > 25) & (df['city'] == 'Mumbai')]

# Multiple conditions (OR)

df[(df['city'] == 'Mumbai') | (df['city'] == 'Delhi')]

# isin - multiple values

df[df['city'].isin(['Mumbai', 'Delhi', 'Pune'])]

# String contains
df[df['name'].[Link]('Kumar', case=False)]

# Starts with / Ends with

df[df['name'].[Link]('R')]
df[df['name'].[Link]('a')]

# Between
df[df['age'].between(25, 35)]

# Null / Not Null

df[df['email'].isnull()]
df[df['email'].notnull()]

# Query method (cleaner syntax)

[Link]('age > 25 and city == "Mumbai"')
4. Data Cleaning

Missing Values
# Check missing
[Link]().sum() # Count nulls per column
[Link]().sum().sum() # Total nulls
[Link]().any() # Any nulls per column?

# Drop missing
[Link]() # Drop rows with any null
[Link](subset=['email']) # Drop if email is null
[Link](how='all') # Drop only if ALL values null

# Fill missing
df['col'].fillna(0) # Fill with 0
df['col'].fillna(df['col'].mean()) # Fill with mean
df['col'].fillna(df['col'].median()) # Fill with median
df['col'].fillna('Unknown') # Fill with text
[Link](method='ffill') # Forward fill
[Link](method='bfill') # Backward fill

Duplicates
[Link]().sum() # Count duplicates
df[[Link]()] # View duplicates
df.drop_duplicates() # Remove duplicates
df.drop_duplicates(subset=['email']) # Based on column
df.drop_duplicates(keep='last') # Keep last occurrence

Data Types
df['col'].astype(int) # Convert to integer
df['col'].astype(float) # Convert to float
df['col'].astype(str) # Convert to string
df['col'].astype('category') # Convert to category

pd.to_numeric(df['col'], errors='coerce') # To numeric (errors → NaN)

pd.to_datetime(df['date']) # To datetime

Renaming & Formatting

# Rename columns
[Link](columns={'old': 'new'})
[Link](columns={'name': 'full_name', 'age': 'years'})

# Clean column names

[Link] = [Link]()
[Link] = [Link](' ', '_')
[Link] = [Link]()

# String operations
df['name'] = df['name'].[Link]() # Remove whitespace
df['name'] = df['name'].[Link]() # Uppercase
df['name'] = df['name'].[Link]() # Lowercase
df['name'] = df['name'].[Link]() # Title Case
df['name'] = df['name'].[Link]('old', 'new')
5. Data Manipulation

Creating New Columns

# Simple calculation
df['total'] = df['quantity'] * df['price']
df['profit'] = df['revenue'] - df['cost']

# Conditional column
df['status'] = [Link](df['score'] >= 50, 'Pass', 'Fail')

# Multiple conditions
df['grade'] = [Link](
[df['score'] >= 90, df['score'] >= 80, df['score'] >= 70],
['A', 'B', 'C'],
default='F'
)

# Using apply
df['new_col'] = df['col'].apply(lambda x: x * 2)
df['new_col'] = [Link](lambda row: row['a'] + row['b'], axis=1)

# Using map (for mapping values)

df['region_name'] = df['region_code'].map({'N': 'North', 'S': 'South'})

Sorting
df.sort_values('column') # Ascending
df.sort_values('column', ascending=False) # Descending
df.sort_values(['col1', 'col2']) # Multiple columns
df.sort_index() # Sort by index

[Link](10, 'sales') # Top 10 by sales

[Link](10, 'price') # Bottom 10 by price

Modifying Data
# Replace values
df['col'].replace('old', 'new')
df['col'].replace({'old1': 'new1', 'old2': 'new2'})

# Drop columns/rows
[Link](columns=['col1', 'col2'])
[Link](index=[0, 1, 2])

# Reset index
df.reset_index(drop=True)

# Set column as index

df.set_index('id')

# Binning (create categories from numbers)

df['age_group'] = [Link](df['age'], bins=[0, 18, 35, 50, 100],
labels=['Child', 'Young', 'Middle', 'Senior'])
6. Grouping & Aggregating
# Basic groupby
[Link]('category')['sales'].sum()
[Link]('category')['sales'].mean()
[Link]('category')['sales'].count()

# Multiple aggregations
[Link]('category')['sales'].agg(['sum', 'mean', 'count', 'min', 'max'])

# Group by multiple columns

[Link](['region', 'category'])['sales'].sum()

# Different agg for different columns

[Link]('category').agg({
'sales': 'sum',
'quantity': 'mean',
'customer_id': 'nunique'
})

# Named aggregations
[Link]('category').agg(
total_sales=('sales', 'sum'),
avg_sales=('sales', 'mean'),
unique_customers=('customer_id', 'nunique')
)

# Reset index after groupby

[Link]('category')['sales'].sum().reset_index()

# Value counts (frequency)

df['category'].value_counts()
df['category'].value_counts(normalize=True) # Percentages

# Unique values
df['category'].unique()
df['category'].nunique()

■ Always use reset_index() after groupby if you want a DataFrame back.

7. Merging & Joining
# Inner join (only matching)
[Link](df1, df2, on='customer_id')
[Link](df1, df2, on='customer_id', how='inner')

# Left join (all from left)

[Link](df1, df2, on='customer_id', how='left')

# Right join (all from right)

[Link](df1, df2, on='customer_id', how='right')

# Outer join (all from both)

[Link](df1, df2, on='customer_id', how='outer')

# Join on different column names

[Link](df1, df2, left_on='cust_id', right_on='customer_id')

# Join on multiple columns

[Link](df1, df2, on=['customer_id', 'product_id'])

# Concatenate (stack vertically)

[Link]([df1, df2])
[Link]([df1, df2], ignore_index=True)

# Concatenate horizontally
[Link]([df1, df2], axis=1)

8. Date & Time

# Convert to datetime
df['date'] = pd.to_datetime(df['date'])
df['date'] = pd.to_datetime(df['date'], format='%Y-%m-%d')

# Extract components
df['year'] = df['date'].[Link]
df['month'] = df['date'].[Link]
df['day'] = df['date'].[Link]
df['weekday'] = df['date'].[Link] # 0=Monday
df['day_name'] = df['date'].dt.day_name() # Monday, Tuesday...
df['month_name'] = df['date'].dt.month_name()
df['quarter'] = df['date'].[Link]
df['week'] = df['date'].[Link]().week

# Date calculations
df['days_since'] = ([Link]() - df['date']).[Link]

# Filter by date
df[df['date'] >= '2024-01-01']
df[df['date'].between('2024-01-01', '2024-12-31')]

# Resample (time series)

df.set_index('date').resample('M').sum() # Monthly
df.set_index('date').resample('W').mean() # Weekly

9. Exporting Data
# CSV
df.to_csv('[Link]', index=False)

# Excel
df.to_excel('[Link]', index=False, sheet_name='Data')

# Multiple sheets
with [Link]('[Link]') as writer:
df1.to_excel(writer, sheet_name='Sheet1', index=False)
df2.to_excel(writer, sheet_name='Sheet2', index=False)

# JSON
df.to_json('[Link]', orient='records')

# Clipboard (for quick paste)

df.to_clipboard()
Quick Reference

Task Code

Load CSV pd.read_csv('[Link]')

First 5 rows [Link]()

Shape [Link]

Info [Link]()

Stats [Link]()

Select column df['col']

Filter df[df['col'] > value]

Multiple filters df[(cond1) & (cond2)]

Null count [Link]().sum()

Drop nulls [Link]()

Fill nulls df['col'].fillna(value)

Remove duplicates df.drop_duplicates()

Sort df.sort_values('col')

Group & sum [Link]('col')['val'].sum()

Merge [Link](df1, df2, on='col')

New column df['new'] = df['a'] + df['b']

To datetime pd.to_datetime(df['date'])

Save CSV df.to_csv('[Link]', index=False)

Keep this handy. Practice daily. You'll master pandas in no time! ■■