# Eenvoudige line plot
x = [1, 2, 3, 4, 5]
y = [2, 4, 6, 8, 10]

plt.figure(figsize=(10, 6))  # Figuur grootte
plt.plot(x, y, label='Line 1', color='blue', linewidth=2, marker='o')

# Labels en titel
plt.xlabel('X As Label', fontsize=12)
plt.ylabel('Y As Label', fontsize=12)
plt.title('Eenvoudige Line Plot', fontsize=14, fontweight='bold')

# Legend en grid
plt.legend()
plt.grid(True, alpha=0.3)

# Opslaan en tonen
plt.savefig('line_plot.png', dpi=300, bbox_inches='tight')
plt.show()

# Data voorbereiden
np.random.seed(42)
x = np.arange(0, 10, 0.1)
y1 = np.sin(x)
y2 = np.cos(x)
y3 = np.sin(x) * np.cos(x)

# Subplots (2 rijen, 2 kolommen)
fig, axes = plt.subplots(2, 2, figsize=(12, 8))

# Plot 1: Line plot
axes[0, 0].plot(x, y1, color='red', label='sin(x)')
axes[0, 0].set_title('Sine Wave')
axes[0, 0].legend()
axes[0, 0].grid(True, alpha=0.3)

# Plot 2: Scatter plot
axes[0, 1].scatter(x, y2, color='green', alpha=0.6, label='cos(x)')
axes[0, 1].set_title('Cosine Scatter')
axes[0, 1].legend()

# Plot 3: Bar plot
axes[1, 0].bar(x[::10], y3[::10], color='blue', alpha=0.7)
axes[1, 0].set_title('Bar Chart')
axes[1, 0].set_xlabel('X values')

# Plot 4: Histogram
axes[1, 1].hist(y3, bins=30, color='purple', alpha=0.7, edgecolor='black')
axes[1, 1].set_title('Histogram')
axes[1, 1].set_xlabel('Value')
axes[1, 1].set_ylabel('Frequency')

# Algemene titel en layout optimaliseren
plt.suptitle('Verschillende Plot Types', fontsize=16, fontweight='bold')
plt.tight_layout()
plt.show()

# Professionele plot met uitgebreide customizatie
fig, ax = plt.subplots(figsize=(12, 7))

# Data
months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun']
sales_2023 = [120, 135, 150, 165, 180, 210]
sales_2024 = [130, 140, 160, 175, 195, 225]

# Plot lines met styling
line1 = ax.plot(months, sales_2023, label='2023 Sales', 
                color='#3498db', linewidth=3, marker='o', 
                markersize=8, markerfacecolor='white', 
                markeredgewidth=2, markeredgecolor='#3498db')

line2 = ax.plot(months, sales_2024, label='2024 Sales', 
                color='#e74c3c', linewidth=3, marker='s', 
                markersize=8, markerfacecolor='white', 
                markeredgewidth=2, markeredgecolor='#e74c3c')

# Fill between (area onder de lijn)
ax.fill_between(months, sales_2023, sales_2024, 
                where=(np.array(sales_2024) > np.array(sales_2023)), 
                color='green', alpha=0.2, label='Growth')

# Labels en titel
ax.set_xlabel('Month', fontsize=12, fontweight='bold')
ax.set_ylabel('Sales (€1000)', fontsize=12, fontweight='bold')
ax.set_title('Monthly Sales Comparison: 2023 vs 2024', 
             fontsize=14, fontweight='bold', pad=20)

# Grid en spines
ax.grid(True, which='both', linestyle='--', linewidth=0.5, alpha=0.7)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

# Legend
ax.legend(loc='upper left', frameon=True, fancybox=True, 
          shadow=True, fontsize=10)

# Annotaties
for i, (v1, v2) in enumerate(zip(sales_2023, sales_2024)):
    growth = ((v2 - v1) / v1) * 100
    if growth > 0:
        ax.annotate(f'+{growth:.1f}%', 
                    xy=(i, v2), 
                    xytext=(0, 10), 
                    textcoords='offset points',
                    ha='center', 
                    color='green',
                    fontweight='bold')

# Y-lim instellen
ax.set_ylim(100, 250)

# Tight layout en opslaan
plt.tight_layout()
plt.savefig('professional_sales_plot.png', dpi=300, 
            bbox_inches='tight', transparent=False)
plt.show()

# Data voorbereiden
np.random.seed(42)
data = pd.DataFrame({
    'Category': np.repeat(['A', 'B', 'C'], 100),
    'Value': np.concatenate([
        np.random.normal(50, 10, 100),
        np.random.normal(60, 15, 100),
        np.random.normal(55, 12, 100)
    ])
})

# Subplot grid
fig, axes = plt.subplots(2, 2, figsize=(14, 10))

# 1. Histogram met KDE
sns.histplot(data=data, x='Value', kde=True, ax=axes[0, 0])
axes[0, 0].set_title('Histogram met KDE')

# 2. Box plot
sns.boxplot(data=data, x='Category', y='Value', ax=axes[0, 1])
axes[0, 1].set_title('Box Plot per Categorie')

# 3. Violin plot
sns.violinplot(data=data, x='Category', y='Value', ax=axes[1, 0])
axes[1, 0].set_title('Violin Plot')

# 4. ECDF plot
sns.ecdfplot(data=data, x='Value', hue='Category', ax=axes[1, 1])
axes[1, 1].set_title('Empirical CDF')

plt.suptitle('Distribution Analysis met Seaborn', fontsize=16, fontweight='bold')
plt.tight_layout()
plt.show()

# Complexe dataset
tips = sns.load_dataset("tips")  # Ingebouwd Seaborn dataset

# Subplots
fig, axes = plt.subplots(2, 2, figsize=(14, 10))

# 1. Scatter plot met regressie
sns.regplot(data=tips, x='total_bill', y='tip', ax=axes[0, 0])
axes[0, 0].set_title('Scatter met Linear Regressie')

# 2. Categorical bar plot
sns.barplot(data=tips, x='day', y='total_bill', hue='sex', 
            errorbar='sd', ax=axes[0, 1])
axes[0, 1].set_title('Bar Plot met Error Bars')

# 3. Heatmap (correlatie matrix)
numeric_cols = tips.select_dtypes(include=[np.number]).columns
corr_matrix = tips[numeric_cols].corr()
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', 
            center=0, ax=axes[1, 0])
axes[1, 0].set_title('Correlatie Heatmap')

# 4. Pair plot (scatter matrix)
// Pair plot werkt niet goed in subplots, dus apart tonen
pair_plot = sns.pairplot(tips, hue='sex', diag_kind='kde')
pair_plot.fig.suptitle('Pair Plot van Tips Dataset', y=1.02)

plt.tight_layout()
plt.show()

# Maak een complexe dataset
np.random.seed(42)
n_samples = 500
complex_data = pd.DataFrame({
    'x': np.random.randn(n_samples),
    'y': np.random.randn(n_samples) * 2 + 1,
    'category': np.random.choice(['A', 'B', 'C'], n_samples),
    'size': np.random.uniform(10, 200, n_samples),
    'value': np.random.exponential(2, n_samples)
})

# FacetGrid: Meerdere subplots gebaseerd op categorische variabelen
g = sns.FacetGrid(complex_data, col='category', height=4, aspect=1.2)
g.map(sns.scatterplot, 'x', 'y', s='size', alpha=0.6)
g.set_titles("{col_name}")
g.set_axis_labels("X Waarde", "Y Waarde")
plt.suptitle('FacetGrid: Scatter Plots per Categorie', y=1.02)
plt.show()

# Joint plot: scatter met marginale distributies
joint = sns.jointplot(data=complex_data, x='x', y='y', 
                      hue='category', kind='scatter',
                      height=7, ratio=5, space=0.2)
joint.fig.suptitle('Joint Plot: Scatter met Marginale Distributies', y=1.02)

# Relational plot met meerdere variabelen
fig, ax = plt.subplots(figsize=(10, 6))
scatter = sns.scatterplot(data=complex_data, x='x', y='y',
                          hue='category', size='size',
                          sizes=(20, 200), alpha=0.7,
                          palette='viridis')

# Legenda aanpassen
scatter.legend(loc='upper left', bbox_to_anchor=(1, 1))
plt.title('Multi-variable Scatter Plot', fontsize=14, fontweight='bold')
plt.tight_layout()
plt.show()

import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots

# Sample data
df = px.data.gapminder().query("year == 2007")

# 1. Scatter plot met Plotly Express (simpele syntax)
fig1 = px.scatter(df, x="gdpPercap", y="lifeExp",
                 size="pop", color="continent",
                 hover_name="country",
                 size_max=60,
                 title="GDP per Capita vs Life Expectancy (2007)")
fig1.show()

# 2. Bar plot
fig2 = px.bar(df, x="continent", y="pop",
             color="continent",
             title="Population per Continent (2007)")
fig2.update_layout(xaxis_title="Continent", 
                  yaxis_title="Population")
fig2.show()

# 3. Animated plot (over tijd)
df_all = px.data.gapminder()
fig3 = px.scatter(df_all, x="gdpPercap", y="lifeExp",
                 animation_frame="year",
                 animation_group="country",
                 size="pop", color="continent",
                 hover_name="country",
                 size_max=45,
                 range_x=[100, 100000], 
                 range_y=[25, 90],
                 title="Life Expectancy vs GDP Over Time")
fig3.show()

# Complexe visualisatie met Graph Objects
fig = make_subplots(
    rows=2, cols=2,
    subplot_titles=('Line Plot', 'Bar Plot', 'Scatter Plot', '3D Surface'),
    specs=[[{"type": "xy"}, {"type": "xy"}],
           [{"type": "xy"}, {"type": "scene"}]]
)

# Data
x = np.linspace(0, 10, 100)
y1 = np.sin(x)
y2 = np.cos(x)

# 1. Line plot
fig.add_trace(
    go.Scatter(x=x, y=y1, mode='lines', name='sin(x)',
               line=dict(color='blue', width=2)),
    row=1, col=1
)

# 2. Bar plot
fig.add_trace(
    go.Bar(x=['A', 'B', 'C', 'D'], 
           y=[10, 20, 15, 25],
           name='Bar Data',
           marker_color=['red', 'green', 'blue', 'orange']),
    row=1, col=2
)

# 3. Scatter plot
fig.add_trace(
    go.Scatter(x=x, y=y2, mode='markers', name='cos(x)',
               marker=dict(size=8, color='green', 
                          line=dict(width=1, color='darkgreen'))),
    row=2, col=1
)

# 4. 3D Surface plot
X = np.linspace(-5, 5, 50)
Y = np.linspace(-5, 5, 50)
X, Y = np.meshgrid(X, Y)
Z = np.sin(np.sqrt(X**2 + Y**2))

fig.add_trace(
    go.Surface(z=Z, x=X, y=Y, colorscale='Viridis'),
    row=2, col=2
)

# Layout aanpassen
fig.update_layout(
    title_text="Interactive Dashboard met Plotly",
    height=800,
    showlegend=True,
    hovermode='closest'
)

# Update axes labels
fig.update_xaxes(title_text="X Values", row=1, col=1)
fig.update_yaxes(title_text="sin(x)", row=1, col=1)
fig.update_xaxes(title_text="Categories", row=1, col=2)
fig.update_yaxes(title_text="Values", row=1, col=2)

fig.show()

# Opslaan als HTML (interactief in browser)
fig.write_html("interactive_dashboard.html")

# app.py
import dash
from dash import dcc, html
from dash.dependencies import Input, Output
import plotly.express as px
import pandas as pd
import numpy as np

# Sample data
np.random.seed(42)
n_samples = 1000
df = pd.DataFrame({
    'Date': pd.date_range(start='2024-01-01', periods=n_samples, freq='D'),
    'Sales': np.random.randn(n_samples).cumsum() + 100,
    'Region': np.random.choice(['North', 'South', 'East', 'West'], n_samples),
    'Product': np.random.choice(['A', 'B', 'C'], n_samples),
    'Profit': np.random.uniform(10, 100, n_samples)
})

# Initialize Dash app
app = dash.Dash(__name__)

# App layout
app.layout = html.Div([
    # Header
    html.H1('Sales Dashboard', style={'textAlign': 'center', 'color': '#2c3e50'}),
    
    # Filters
    html.Div([
        html.Label('Select Region:'),
        dcc.Dropdown(
            id='region-dropdown',
            options=[{'label': region, 'value': region} 
                     for region in df['Region'].unique()],
            value=['North', 'South'],
            multi=True
        ),
        
        html.Label('Date Range:', style={'marginTop': '20px'}),
        dcc.DatePickerRange(
            id='date-picker',
            min_date_allowed=df['Date'].min(),
            max_date_allowed=df['Date'].max(),
            start_date=df['Date'].min(),
            end_date=df['Date'].max()
        ),
        
        html.Label('Sales Threshold:', style={'marginTop': '20px'}),
        dcc.Slider(
            id='sales-slider',
            min=0,
            max=200,
            value=50,
            marks={0: '0', 50: '50', 100: '100', 150: '150', 200: '200'}
        )
    ], style={'width': '20%', 'display': 'inline-block', 'verticalAlign': 'top', 'padding': '20px'}),
    
    # Graphs
    html.Div([
        # Row 1
        html.Div([
            dcc.Graph(id='sales-time-series'),
            dcc.Graph(id='region-bar-chart')
        ], style={'display': 'flex', 'justifyContent': 'space-between'}),
        
        # Row 2
        html.Div([
            dcc.Graph(id='product-pie-chart'),
            dcc.Graph(id='profit-scatter')
        ], style={'display': 'flex', 'justifyContent': 'space-between', 'marginTop': '20px'})
    ], style={'width': '75%', 'display': 'inline-block'}),
    
    # Summary statistics
    html.Div(id='summary-stats', style={'marginTop': '30px', 'padding': '20px', 'backgroundColor': '#f8f9fa'})
])

# Callbacks voor interactiviteit
@app.callback(
    [Output('sales-time-series', 'figure'),
     Output('region-bar-chart', 'figure'),
     Output('product-pie-chart', 'figure'),
     Output('profit-scatter', 'figure'),
     Output('summary-stats', 'children')],
    [Input('region-dropdown', 'value'),
     Input('date-picker', 'start_date'),
     Input('date-picker', 'end_date'),
     Input('sales-slider', 'value')]
)
def update_dashboard(selected_regions, start_date, end_date, sales_threshold):
    # Filter data
    filtered_df = df[
        (df['Region'].isin(selected_regions)) & 
        (df['Date'] >= start_date) & 
        (df['Date'] <= end_date) &
        (df['Sales'] >= sales_threshold)
    ]
    
    # 1. Time series plot
    time_series = px.line(filtered_df, x='Date', y='Sales',
                         title='Sales Over Time')
    
    # 2. Bar chart by region
    region_sales = filtered_df.groupby('Region')['Sales'].sum().reset_index()
    bar_chart = px.bar(region_sales, x='Region', y='Sales',
                      title='Total Sales by Region',
                      color='Region')
    
    # 3. Pie chart by product
    product_sales = filtered_df.groupby('Product')['Sales'].sum().reset_index()
    pie_chart = px.pie(product_sales, values='Sales', names='Product',
                      title='Sales Distribution by Product')
    
    # 4. Scatter plot
    scatter = px.scatter(filtered_df, x='Sales', y='Profit',
                        color='Product', size='Sales',
                        title='Sales vs Profit')
    
    # 5. Summary statistics
    total_sales = filtered_df['Sales'].sum()
    avg_profit = filtered_df['Profit'].mean()
    total_orders = len(filtered_df)
    
    summary = html.Div([
        html.H3('Summary Statistics'),
        html.P(f"Total Sales: €{total_sales:,.2f}"),
        html.P(f"Average Profit: €{avg_profit:.2f}"),
        html.P(f"Total Orders: {total_orders:,}"),
        html.P(f"Date Range: {start_date} to {end_date}")
    ])
    
    return time_series, bar_chart, pie_chart, scatter, summary

if __name__ == '__main__':
    app.run_server(debug=True, port=8050)

import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import matplotlib.pyplot as plt
import seaborn as sns

# 1. Data simulatie
np.random.seed(42)
n_customers = 1000
n_days = 365

# Customer data
customer_data = pd.DataFrame({
    'customer_id': range(1, n_customers + 1),
    'region': np.random.choice(['North', 'South', 'East', 'West'], n_customers),
    'customer_type': np.random.choice(['Retail', 'Business', 'Wholesale'], n_customers, p=[0.6, 0.3, 0.1]),
    'signup_date': pd.to_datetime('2023-01-01') + pd.to_timedelta(np.random.randint(0, n_days, n_customers), unit='D')
})

# Sales transactions
n_transactions = 5000
transactions = pd.DataFrame({
    'transaction_id': range(1, n_transactions + 1),
    'customer_id': np.random.choice(customer_data['customer_id'], n_transactions),
    'date': pd.to_datetime('2024-01-01') + pd.to_timedelta(np.random.randint(0, n_days, n_transactions), unit='D'),
    'product_category': np.random.choice(['Electronics', 'Clothing', 'Home', 'Books'], n_transactions),
    'amount': np.random.exponential(100, n_transactions),
    'quantity': np.random.randint(1, 10, n_transactions)
})

# Merge data
sales_data = pd.merge(transactions, customer_data, on='customer_id')

# 2. Data aggregaties voor visualisatie
# Daily sales
daily_sales = sales_data.groupby('date').agg({
    'amount': 'sum',
    'transaction_id': 'count'
}).reset_index()
daily_sales.columns = ['date', 'daily_revenue', 'daily_transactions']

# Monthly sales
sales_data['month'] = sales_data['date'].dt.to_period('M').astype(str)
monthly_sales = sales_data.groupby('month').agg({
    'amount': 'sum',
    'transaction_id': 'count',
    'customer_id': 'nunique'
}).reset_index()
monthly_sales.columns = ['month', 'monthly_revenue', 'monthly_transactions', 'unique_customers']

# 3. Matplotlib/Seaborn static analysis
fig, axes = plt.subplots(2, 2, figsize=(14, 10))

# Revenue trend
axes[0, 0].plot(daily_sales['date'], daily_sales['daily_revenue'                 ], color='#3498db', linewidth=2)
axes[0, 0].set_title('Daily Revenue Trend', fontweight='bold')
axes[0, 0].set_xlabel('Date')
axes[0, 0].set_ylabel('Revenue (€)')
axes[0, 0].grid(True, alpha=0.3)

# Revenue by region
region_revenue = sales_data.groupby('region')['amount'].sum().sort_values()
axes[0, 1].bar(region_revenue.index, region_revenue.values, color=['#1abc9c', '#3498db', '#9b59b6', '#e74c3c'])
axes[0, 1].set_title('Revenue by Region', fontweight='bold')
axes[0, 1].set_xlabel('Region')
axes[0, 1].set_ylabel('Total Revenue (€)')
for i, v in enumerate(region_revenue.values):
    axes[0, 1].text(i, v + max(region_revenue.values)*0.01, f'€{v:,.0f}', 
                    ha='center', fontweight='bold')

# Product category distribution
category_sales = sales_data.groupby('product_category')['amount'].sum()
axes[1, 0].pie(category_sales.values, labels=category_sales.index, 
               autopct='%1.1f%%', colors=['#1abc9c', '#3498db', '#9b59b6', '#e74c3c'])
axes[1, 0].set_title('Revenue by Product Category', fontweight='bold')

# Customer type analysis
customer_revenue = sales_data.groupby('customer_type')['amount'].sum()
axes[1, 1].barh(customer_revenue.index, customer_revenue.values, 
                color=['#1abc9c', '#3498db', '#9b59b6'])
axes[1, 1].set_title('Revenue by Customer Type', fontweight='bold')
axes[1, 1].set_xlabel('Total Revenue (€)')

plt.suptitle('Sales Performance Analysis Dashboard', fontsize=16, fontweight='bold')
plt.tight_layout()
plt.savefig('sales_dashboard_static.png', dpi=300, bbox_inches='tight')
plt.show()

# 4. Plotly interactive dashboard
fig = make_subplots(
    rows=3, cols=3,
    subplot_titles=('Monthly Revenue Trend', 'Revenue by Region', 'Revenue by Product',
                    'Customer Distribution', 'Transaction Distribution', 'Revenue Heatmap',
                    'Customer Type Revenue', 'Monthly Growth', 'Top Customers'),
    specs=[[{'type': 'scatter'}, {'type': 'bar'}, {'type': 'pie'}],
           [{'type': 'histogram'}, {'type': 'box'}, {'type': 'heatmap'}],
           [{'type': 'bar'}, {'type': 'scatter'}, {'type': 'bar'}]],
    vertical_spacing=0.08,
    horizontal_spacing=0.08
)

# 1. Monthly Revenue Trend
fig.add_trace(
    go.Scatter(x=monthly_sales['month'], y=monthly_sales['monthly_revenue'],
               mode='lines+markers', name='Revenue',
               line=dict(color='#3498db', width=3)),
    row=1, col=1
)

# 2. Revenue by Region
fig.add_trace(
    go.Bar(x=region_revenue.index, y=region_revenue.values,
           marker_color=['#1abc9c', '#3498db', '#9b59b6', '#e74c3c'],
           name='Region Revenue'),
    row=1, col=2
)

# 3. Revenue by Product Category
fig.add_trace(
    go.Pie(labels=category_sales.index, values=category_sales.values,
           hole=0.3, marker_colors=['#1abc9c', '#3498db', '#9b59b6', '#e74c3c']),
    row=1, col=3
)

# 4. Customer Distribution by Region
region_customers = sales_data.groupby('region')['customer_id'].nunique()
fig.add_trace(
    go.Histogram(x=sales_data['region'], nbinsx=4,
                 marker_color=['#1abc9c', '#3498db', '#9b59b6', '#e74c3c'],
                 name='Customers by Region'),
    row=2, col=1
)

# 5. Transaction Amount Distribution
fig.add_trace(
    go.Box(y=sales_data['amount'], name='Transaction Amount',
           boxpoints='outliers', marker_color='#3498db'),
    row=2, col=2
)

# 6. Revenue Heatmap (Day of Week vs Hour)
sales_data['day_of_week'] = sales_data['date'].dt.day_name()
sales_data['hour'] = sales_data['date'].dt.hour
heatmap_data = sales_data.pivot_table(values='amount', 
                                       index='day_of_week', 
                                       columns='hour', 
                                       aggfunc='sum').fillna(0)

fig.add_trace(
    go.Heatmap(z=heatmap_data.values,
               x=heatmap_data.columns,
               y=heatmap_data.index,
               colorscale='Viridis',
               name='Revenue Heatmap'),
    row=2, col=3
)

# 7. Revenue by Customer Type
fig.add_trace(
    go.Bar(x=customer_revenue.index, y=customer_revenue.values,
           marker_color=['#1abc9c', '#3498db', '#9b59b6'],
           name='Customer Type Revenue'),
    row=3, col=1
)

# 8. Monthly Growth
monthly_sales['growth'] = monthly_sales['monthly_revenue'].pct_change() * 100
fig.add_trace(
    go.Scatter(x=monthly_sales['month'], y=monthly_sales['growth'],
               mode='lines+markers', name='Growth %',
               line=dict(color='#27ae60', width=3),
               fill='tozeroy'),
    row=3, col=2
)

# 9. Top 10 Customers
top_customers = sales_data.groupby('customer_id')['amount'].sum().nlargest(10)
fig.add_trace(
    go.Bar(x=[f'Customer {i}' for i in top_customers.index], 
           y=top_customers.values,
           marker_color='#e74c3c',
           name='Top Customers'),
    row=3, col=3
)

# Update layout
fig.update_layout(
    title_text='Interactive Sales Dashboard - Complete Analysis',
    height=1200,
    showlegend=False,
    title_font_size=20,
    title_font_color='#2c3e50'
)

# Update axes
fig.update_xaxes(tickangle=45)
fig.update_yaxes(title_text="Revenue (€)", row=1, col=1)
fig.update_yaxes(title_text="Revenue (€)", row=1, col=2)
fig.update_yaxes(title_text="Count", row=2, col=1)
fig.update_yaxes(title_text="Amount (€)", row=2, col=2)
fig.update_yaxes(title_text="Growth %", row=3, col=2)
fig.update_yaxes(title_text="Revenue (€)", row=3, col=3)

# Save interactive dashboard
fig.write_html("interactive_sales_dashboard.html")

print("✅ Dashboard created successfully!")
print("📊 Static dashboard saved as: sales_dashboard_static.png")
print("🖱️ Interactive dashboard saved as: interactive_sales_dashboard.html")
print("📈 Summary statistics:")
print(f"   • Total Revenue: €{sales_data['amount'].sum():,.2f}")
print(f"   • Total Transactions: {len(sales_data):,}")
print(f"   • Unique Customers: {sales_data['customer_id'].nunique():,}")
print(f"   • Average Transaction: €{sales_data['amount'].mean():.2f}")
print(f"   • Date Range: {sales_data['date'].min().date()} to {sales_data['date'].max().date()}")