Data Analytics Learning Path

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

def select_chart(data, chart_type, **kwargs):
    """
    Helper functie voor chart selectie
    Parameters:
    - data: DataFrame of array
    - chart_type: 'bar', 'line', 'scatter', 'histogram', 'pie', 'box'
    - kwargs: extra parameters voor styling
    """
    
    fig, ax = plt.subplots(figsize=(10, 6))
    
    if chart_type == 'bar':
        # Voor categorische vergelijkingen
        ax.bar(data.index, data.values, **kwargs)
        ax.set_xlabel('Categories')
        ax.set_ylabel('Values')
        ax.set_title('Bar Chart - Category Comparison')
        
    elif chart_type == 'line':
        # Voor trends over tijd
        ax.plot(data.index, data.values, marker='o', **kwargs)
        ax.set_xlabel('Time')
        ax.set_ylabel('Metric')
        ax.set_title('Line Chart - Trend Analysis')
        
    elif chart_type == 'scatter':
        # Voor correlatie analyse
        x = data['x']
        y = data['y']
        ax.scatter(x, y, **kwargs)
        
        # Trendlijn toevoegen
        z = np.polyfit(x, y, 1)
        p = np.poly1d(z)
        ax.plot(x, p(x), "r--", alpha=0.7)
        
        ax.set_xlabel('X Variable')
        ax.set_ylabel('Y Variable')
        ax.set_title('Scatter Plot with Trendline')
        
    elif chart_type == 'histogram':
        # Voor distributie analyse
        ax.hist(data, bins=30, edgecolor='black', **kwargs)
        ax.set_xlabel('Value')
        ax.set_ylabel('Frequency')
        ax.set_title('Histogram - Distribution Analysis')
        
    plt.tight_layout()
    return fig, ax

# Gebruiksvoorbeeld:
# sales_data = pd.Series([120, 150, 90, 200, 180], index=['Jan', 'Feb', 'Mar', 'Apr', 'May'])
# fig, ax = select_chart(sales_data, 'bar', color='skyblue')
# plt.show()