How do you build an end-to-end data cleaning and visualisation pipeline with NumPy, Pandas, and Seaborn?

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt

sns.set_theme(style='whitegrid', context='notebook')

# --- 1. Load ---
df = pd.read_csv('customer_orders.csv', parse_dates=['order_date'])

# --- 2. Audit ---
print(df.info())
print(df.isnull().sum())
print(df.describe())

# --- 3. Clean ---
df = (
    df
    .drop_duplicates(subset=['order_id'])
    .dropna(subset=['customer_id', 'amount'])
    .assign(
        amount=lambda d: pd.to_numeric(d['amount'], errors='coerce'),
        category=lambda d: d['category'].str.strip().str.title().astype('category'),
        year=lambda d: d['order_date'].dt.year,
        month=lambda d: d['order_date'].dt.month,
    )
    .dropna(subset=['amount'])
    .query('amount > 0')
)

# --- 4. Feature engineering (NumPy) ---
amounts = df['amount'].to_numpy()
df['log_amount']  = np.log1p(amounts)       # log1p avoids log(0)
df['amount_zscore'] = (amounts - amounts.mean()) / amounts.std()

# --- 5. Aggregate ---
monthly = (
    df.groupby(['year', 'month', 'category'])
    .agg(total=('amount', 'sum'), orders=('order_id', 'count'))
    .reset_index()
)

# --- 6. Visualise ---
fig, axes = plt.subplots(1, 2, figsize=(14, 5))

# Revenue distribution by category
sns.boxplot(data=df, x='category', y='log_amount', ax=axes[0])
axes[0].set(title='Log Revenue by Category', xlabel='', ylabel='log(1+amount)')

# Monthly trend
df['period'] = df['order_date'].dt.to_period('M').astype(str)
trend = df.groupby('period')['amount'].sum().reset_index()
axes[1].plot(trend['period'], trend['amount'], marker='o', linewidth=2)
axes[1].tick_params(axis='x', rotation=45)
axes[1].set(title='Monthly Revenue Trend', xlabel='Month', ylabel='Revenue')

plt.tight_layout()
plt.savefig('dashboard.png', dpi=150, bbox_inches='tight')
plt.show()