Pandas Basics

import pandas as pd

# Create DataFrame from dictionary
df = pd.DataFrame({
    'name': ['Alice', 'Bob'],
    'age': [25, 30]
})

# Read from CSV file
df = pd.read_csv('data.csv')  # load CSV file
df = pd.read_excel('data.xlsx')  # load Excel file

df.head(5)  # first 5 rows
df.tail(3)  # last 3 rows
df.info()  # data types and non-null counts
df.describe()  # statistical summary
df.shape  # (rows, columns)
df.columns  # column names

# Select single column
df['name']  # returns Series
df[['name', 'age']]  # multiple columns, returns DataFrame

# Select rows
df.loc[0]  # by label/index
df.iloc[0]  # by integer position
df.loc[0:2]  # slice by label

# Filter rows
df[df['age'] > 25]  # filter by condition

# Add column
df['new_col'] = 0  # add with constant value
df['total'] = df['a'] + df['b']  # calculated column

# Drop column
df.drop('name', axis=1)  # axis=1 for columns
df.drop(['a', 'b'], axis=1)  # drop multiple

# Sort
df.sort_values('age')  # ascending
df.sort_values('age', ascending=False)  # descending

# Group by
df.groupby('name').mean()  # average by group