Lopullinen visualisointi ja raportin vienti

import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec

plt.style.use('seaborn-v0_8-whitegrid')

# 2x2 layout with custom row heights
fig = plt.figure(figsize=(16, 12))
gs = gridspec.GridSpec(2, 2,
                       height_ratios=[1, 1.2],
                       hspace=0.4, wspace=0.35)

ax_trend   = fig.add_subplot(gs[0, :])   # full width top row
ax_heatmap = fig.add_subplot(gs[1, 0])   # bottom left
ax_bar     = fig.add_subplot(gs[1, 1])   # bottom right

print('Figure with 3 panels created.')

import pandas as pd
import matplotlib.pyplot as plt

monthly = pd.read_parquet('output/kpi_monthly_category_revenue.parquet')
monthly_total = monthly.sum(axis=1)

ax = plt.gca()
ax.plot(monthly_total.index, monthly_total.values,
        marker='o', linewidth=2, color='#2196F3', label='Monthly Revenue')
ax.plot(monthly_total.index,
        monthly_total.rolling(3, min_periods=1).mean().values,
        linewidth=2, linestyle='--', color='#FF5722', label='3-Month Avg')
ax.fill_between(monthly_total.index, monthly_total.values, alpha=0.1, color='#2196F3')

# Annotate peak
peak_idx = monthly_total.idxmax()
ax.annotate(f'Peak: ${monthly_total[peak_idx]/1e3:.0f}K',
            xy=(peak_idx, monthly_total[peak_idx]),
            xytext=(0, 20), textcoords='offset points',
            arrowprops=dict(arrowstyle='->', color='#E91E63'),
            color='#E91E63', fontsize=10)
ax.set_title('Monthly Revenue Trend', fontsize=14, fontweight='bold')
ax.legend()
plt.show()

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

retention = pd.read_parquet('output/kpi_cohort_retention.parquet')

fig, ax = plt.subplots(figsize=(10, 6))

sns.heatmap(
    retention,
    annot=True,
    fmt='.0%',
    cmap='YlOrRd_r',
    mask=retention.isna(),
    linewidths=0.5,
    ax=ax,
    cbar_kws={'label': 'Retention Rate'}
)
ax.set_title('Cohort Retention Matrix', fontsize=14, fontweight='bold')
ax.set_xlabel('Months After First Purchase')
ax.set_ylabel('Cohort Month')
plt.tight_layout()
plt.show()

import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.cm as cm
import numpy as np

region_kpi = pd.read_parquet('output/kpi_region_summary.parquet')
top5 = region_kpi.head(5).sort_values('total_revenue')

fig, ax = plt.subplots(figsize=(8, 5))
colors = cm.Blues(np.linspace(0.4, 0.9, len(top5)))

bars = ax.barh(top5['region'], top5['total_revenue'], color=colors)
for bar, val in zip(bars, top5['total_revenue']):
    ax.text(bar.get_width() * 1.01, bar.get_y() + bar.get_height()/2,
            f'${val/1e3:.0f}K', va='center', fontsize=9)

ax.set_title('Top 5 Regions by Revenue', fontsize=13, fontweight='bold')
ax.set_xlabel('Total Revenue ($)')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt

# After assembling all panels in the figure
fig.suptitle('2024 Sales Performance Report', fontsize=16,
             fontweight='bold', y=1.02)

# Save as PNG (for web/presentations)
fig.savefig('output/report_figure.png',
            dpi=150,
            bbox_inches='tight',
            facecolor='white')

# Save as PDF (for print)
fig.savefig('output/report_figure.pdf',
            bbox_inches='tight',
            facecolor='white')

print('Figures saved:')
print('  output/report_figure.png')
print('  output/report_figure.pdf')

import pandas as pd
from datetime import datetime

df = pd.read_parquet('output/analysis_ready.parquet')
region_kpi = pd.read_parquet('output/kpi_region_summary.parquet')
retention = pd.read_parquet('output/kpi_cohort_retention.parquet')

report = f'''
# 2024 Sales Performance Report

Generated: {datetime.now().strftime('%Y-%m-%d %H:%M')}

## Executive Summary

- **Total Revenue**: ${df['revenue'].sum():,.0f}
- **Total Orders**: {df['order_id'].nunique():,}
- **Unique Customers**: {df['customer_id'].nunique():,}
- **Top Region**: {region_kpi.iloc[0]['region']} (${region_kpi.iloc[0]['total_revenue']:,.0f})
- **Average Month-3 Retention**: {retention.get(3, pd.Series([0])).mean():.1%}

## Key Findings

1. Revenue grew steadily through the year with a peak in October.
2. The top region accounts for {region_kpi.iloc[0]['revenue_share']:.0%} of total revenue.
3. Month-3 cohort retention averages {retention.get(3, pd.Series([0])).mean():.1%}.

## Figures

![Revenue Trends](report_figure.png)
'''
with open('output/report.md', 'w') as f:
    f.write(report)
print('Report written to output/report.md')

import matplotlib.pyplot as plt
import matplotlib.ticker as mticker
import pandas as pd

monthly_total = pd.read_parquet('output/kpi_monthly_category_revenue.parquet').sum(axis=1)

fig, ax = plt.subplots(figsize=(12, 5))
ax.plot(monthly_total.index, monthly_total.values, linewidth=2.5, color='#1565C0')

# Format y-axis as $K
ax.yaxis.set_major_formatter(
    mticker.FuncFormatter(lambda x, _: f'${x/1e3:.0f}K')
)

# Mark a hypothetical event
ax.axvline(x='2024-06', color='red', linestyle=':', alpha=0.6)
ax.text('2024-06', monthly_total.max() * 0.95,
        ' Campaign\n Launch', color='red', fontsize=9)

ax.set_title('Monthly Revenue 2024', fontsize=14, fontweight='bold')
ax.set_xlabel('Month')
ax.set_ylabel('Revenue')
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

import pandas as pd

region_kpi = pd.read_parquet('output/kpi_region_summary.parquet')
retention = pd.read_parquet('output/kpi_cohort_retention.parquet')
product_rank = pd.read_parquet('output/kpi_product_ranking.parquet')

with pd.ExcelWriter('output/sales_report_2024.xlsx', engine='openpyxl') as writer:
    region_kpi.to_excel(writer, sheet_name='Region KPIs', index=False)
    retention.to_excel(writer, sheet_name='Cohort Retention')
    product_rank.head(50).to_excel(writer, sheet_name='Top 50 Products', index=False)

print('Excel workbook written: output/sales_report_2024.xlsx')

import logging
import time
from datetime import datetime

logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s [%(levelname)s] %(message)s'
)

def main():
    start = time.time()
    logging.info('Pipeline started')

    logging.info('Step 1: Data ingestion')
    # load_and_merge()  # returns df

    logging.info('Step 2: Data cleaning')
    # clean(df)  # returns df_clean

    logging.info('Step 3: KPI computation')
    # compute_kpis(df_clean)  # saves parquet files

    logging.info('Step 4: Visualisation and report export')
    # build_report()  # saves PNG, PDF, markdown, Excel

    elapsed = time.time() - start
    logging.info(f'Pipeline complete in {elapsed:.1f}s')

if __name__ == '__main__':
    main()