Pandas Fundamentals in 40 Minutes

import pandas as pd # 1. Load df = pd.read_csv('data.csv') # 2. Peek df.head() df.info() df.describe() # 3. Select columns df['age'] # one column (Series) df[['age', 'income']] # multiple columns (DataFrame) # 4. Filter rows df[df['age'] > 18] df[(df['age'] > 18) & (df['country'] == 'US')] # 5. Sort df.sort_values('income', ascending=False) # 6. Create columns df['income_per_age'] = df['income'] / df['age'] # 7. Group and aggregate df.groupby('country')['income'].mean() df.groupby(['country', 'gender']).agg({ 'income': ['mean', 'median'], 'age': 'mean' }) # 8. Join tables merged = pd.merge(df, other_df, on='user_id', how='left') # 9. Pivot pd.pivot_table(df, index='country', columns='year', values='income') # 10. Save df.to_csv('clean.csv', index=False) df.to_parquet('clean.parquet')

# .loc uses labels df.loc[5] # row with index label 5 df.loc[df['age'] > 18, 'name'] # name column, filtered rows # .iloc uses positions df.iloc[5] # 6th row regardless of index label df.iloc[:10, :3] # first 10 rows, first 3 cols # Chained assignment is a trap # df[df.age > 18]['score'] = 100 # DO NOT DO THIS df.loc[df.age > 18, 'score'] = 100 # CORRECT

# Top N per group top3 = df.groupby('country').apply( lambda g: g.nlargest(3, 'income') ).reset_index(drop=True) # Rolling stats df['7d_avg'] = df['sales'].rolling(window=7).mean() # Replace based on mapping df['country'] = df['country'].replace({'USA': 'US', 'U.S.A.': 'US'}) # One-hot encoding df_encoded = pd.get_dummies(df, columns=['color']) # Handle dates df['date'] = pd.to_datetime(df['date']) df['day_of_week'] = df['date'].dt.day_name()