Pandas Setup

python --version
# or
python3 --version

brew install python@3.11

sudo apt update
sudo apt install python3.11 python3.11-venv python3-pip

# Create virtual environment
python -m venv cookbook-env
 
# Activate virtual environment
# macOS/Linux
source cookbook-env/bin/activate
 
# Windows
cookbook-env\Scripts\activate

# Create environment
conda create -n cookbook python=3.11
 
# Activate environment
conda activate cookbook

pip install pandas numpy matplotlib seaborn jupyter

# Data visualization
pip install plotly altair
 
# Statistical analysis
pip install scipy statsmodels scikit-learn
 
# Time series analysis
pip install prophet
 
# BigQuery integration (optional)
pip install google-cloud-bigquery db-dtypes

pandas>=2.0.0
numpy>=1.24.0
matplotlib>=3.7.0
seaborn>=0.12.0
jupyter>=1.0.0
plotly>=5.15.0
scipy>=1.10.0
statsmodels>=0.14.0
scikit-learn>=1.3.0

pip install -r requirements.txt

cookbook-data/
├── src_orders.csv
├── src_order_items.csv
├── src_products.csv
├── src_users.csv
├── src_events.csv
├── events_augmented.csv
├── cs_tickets_dummy.csv
└── mkt_campaigns_dummy.csv

from google.cloud import bigquery
import pandas as pd
 
client = bigquery.Client(project='your-project-id')
 
tables = [
    'src_orders', 'src_order_items', 'src_products',
    'src_users', 'src_events', 'events_augmented',
    'cs_tickets_dummy', 'mkt_campaigns_dummy'
]
 
for table in tables:
    query = f"SELECT * FROM `your-project-id.retail_analytics.{table}`"
    df = client.query(query).to_dataframe()
    df.to_csv(f'cookbook-data/{table}.csv', index=False)
    print(f"✅ {table}.csv saved ({len(df):,} rows)")

jupyter notebook
# or
jupyter lab

# Import basic libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime, timedelta
import warnings
warnings.filterwarnings('ignore')
 
# Set visualization style
plt.style.use('seaborn-v0_8-whitegrid')
sns.set_palette("husl")
plt.rcParams['figure.figsize'] = (12, 6)
plt.rcParams['font.size'] = 10
 
# Korean font settings (optional)
# macOS
# plt.rcParams['font.family'] = 'AppleGothic'
# Windows
# plt.rcParams['font.family'] = 'Malgun Gothic'
# Linux
# plt.rcParams['font.family'] = 'NanumGothic'
 
plt.rcParams['axes.unicode_minus'] = False
 
# Pandas display options
pd.set_option('display.max_columns', 50)
pd.set_option('display.max_rows', 100)
pd.set_option('display.width', 200)
pd.set_option('display.float_format', '{:.2f}'.format)
 
# Set data path
DATA_PATH = './cookbook-data/'
 
print("✅ Environment setup complete!")

def load_data(table_name):
    """Load data and perform basic preprocessing"""
    df = pd.read_csv(f'{DATA_PATH}{table_name}.csv')
 
    # Auto-convert date columns
    date_columns = [col for col in df.columns if 'date' in col.lower() or 'at' in col.lower()]
    for col in date_columns:
        try:
            df[col] = pd.to_datetime(df[col])
        except:
            pass
 
    return df
 
# Usage example
orders = load_data('src_orders')
print(f"Orders data: {len(orders):,} rows x {len(orders.columns)} columns")

import sys
import importlib
 
def check_environment():
    print("=" * 50)
    print("Environment Setup Check")
    print("=" * 50)
 
    # Python version
    print(f"\n🐍 Python version: {sys.version}")
 
    # Check required packages
    packages = [
        'pandas', 'numpy', 'matplotlib', 'seaborn',
        'scipy', 'sklearn', 'plotly'
    ]
 
    print("\n📦 Package versions:")
    for pkg in packages:
        try:
            module = importlib.import_module(pkg)
            version = getattr(module, '__version__', 'N/A')
            print(f"   ✅ {pkg}: {version}")
        except ImportError:
            print(f"   ❌ {pkg}: not installed")
 
    # Check data files
    import os
    data_path = './cookbook-data/'
 
    print(f"\n📁 Data files ({data_path}):")
    if os.path.exists(data_path):
        files = os.listdir(data_path)
        csv_files = [f for f in files if f.endswith('.csv')]
        for f in csv_files:
            size = os.path.getsize(os.path.join(data_path, f)) / 1024 / 1024
            print(f"   ✅ {f} ({size:.2f} MB)")
        if not csv_files:
            print("   ⚠️ No CSV files found.")
    else:
        print(f"   ❌ Folder does not exist: {data_path}")
 
    print("\n" + "=" * 50)
    print("🎉 Environment setup check complete!")
    print("=" * 50)
 
check_environment()

==================================================
Environment Setup Check
==================================================

🐍 Python version: 3.11.0 (...)

📦 Package versions:
   ✅ pandas: 2.0.3
   ✅ numpy: 1.24.3
   ✅ matplotlib: 3.7.2
   ✅ seaborn: 0.12.2
   ✅ scipy: 1.11.1
   ✅ sklearn: 1.3.0
   ✅ plotly: 5.15.0

📁 Data files (./cookbook-data/):
   ✅ src_orders.csv (5.23 MB)
   ✅ src_order_items.csv (8.45 MB)
   ✅ src_products.csv (1.12 MB)
   ✅ src_users.csv (3.67 MB)
   ✅ src_events.csv (12.34 MB)

==================================================
🎉 Environment setup check complete!
==================================================

{
    "python.defaultInterpreterPath": "./cookbook-env/bin/python",
    "jupyter.notebookFileRoot": "${workspaceFolder}",
    "python.analysis.typeCheckingMode": "basic"
}