Easy Pandas Tutorial Cheat Code

1. Import Pandas

import pandas as pd

2. Create a DataFrame

data = {'Name': ['Alice', 'Bob'], 'Age': [25, 30]}
df = pd.DataFrame(data)
print(df)

3. Read and Write CSV Files

# Read CSV
df = pd.read_csv('file.csv')

# Write to CSV
df.to_csv('output.csv', index=False)

4. Inspect Data

print(df.head())   # First 5 rows
print(df.info())  # Data types and summary

5. Select Columns

age_column = df['Age']
subset = df[['Name', 'Age']]

6. Filter Rows

filtered = df[df['Age'] > 25]

7. Add and Remove Columns

# Add a column
df['Salary'] = [50000, 60000]

# Drop a column
df = df.drop(columns=['Salary'])

8. Sorting

# Sort by age
df_sorted = df.sort_values(by='Age', ascending=False)

9. GroupBy and Aggregation

# Group by and calculate mean
grouped = df.groupby('Age').mean()

10. Handle Missing Data

# Fill missing values
df['Age'] = df['Age'].fillna(0)

# Drop rows with missing values
df = df.dropna()

11. Merge and Join

# Merge two DataFrames
df1 = pd.DataFrame({'ID': [1, 2], 'Name': ['Alice', 'Bob']})
df2 = pd.DataFrame({'ID': [1, 2], 'Score': [90, 80]})
merged = pd.merge(df1, df2, on='ID')

12. Concatenate DataFrames

concat = pd.concat([df1, df2], axis=0)

13. Apply Functions

# Apply a custom function
df['AgeSquared'] = df['Age'].apply(lambda x: x ** 2)

14. Pivot Table

# Create a pivot table
pivot = df.pivot_table(values='Score', index='Name', aggfunc='mean')

15. Iterating Over Rows

for index, row in df.iterrows():
    print(row['Name'], row['Age'])

16. Reset Index

df = df.reset_index(drop=True)

17. Set Index

df = df.set_index('Name')

18. String Operations

# Convert names to lowercase
df['Name'] = df['Name'].str.lower()

19. Convert Data Types

# Convert Age to float
df['Age'] = df['Age'].astype(float)

20. Save to Excel

df.to_excel('output.xlsx', index=False)

21. Load Excel File

df = pd.read_excel('file.xlsx')

22. Handle Duplicate Rows

# Drop duplicates
df = df.drop_duplicates()

23. Rename Columns

df = df.rename(columns={'Name': 'FullName'})

24. Check for Null Values

null_check = df.isnull().sum()

25. Get Column Statistics

mean_age = df['Age'].mean()
sum_age = df['Age'].sum()