app/dashboard.py

###____________ Chart selection logic and dashboard generation___________


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

class DashboardGenerator:
    def __init__(self, df, schema):
        self.df = df
        self.schema = schema
        self.charts = []
        
    def generate_all_charts(self):
        """
        Generate appropriate charts for each column type
        """
        print(" Generating charts...")
        
        #numeric columns - Histograms
        for col in self.schema['numeric'][:5]:  # Limit to 5 charts
            fig = self.create_histogram(col)
            self.charts.append({
                'title': f'Distribution of {col}',
                'figure': fig,
                'type': 'histogram'
            })
        
        # categorical columns - Bar charts (top 10)
        for col in self.schema['categorical'][:3]:
            fig = self.create_bar_chart(col)
            self.charts.append({
                'title': f'Top values in {col}',
                'figure': fig,
                'type': 'bar'
            })
        
        # time series - Line charts
        for date_col in self.schema['datetime']:
            for num_col in self.schema['numeric'][:2]:
                fig = self.create_time_series(date_col, num_col)
                self.charts.append({
                    'title': f'{num_col} over time',
                    'figure': fig,
                    'type': 'line'
                })
        
        # correlation heatmap
        if len(self.schema['numeric']) >= 2:
            fig = self.create_correlation_heatmap()
            self.charts.append({
                'title': 'Correlation Heatmap',
                'figure': fig,
                'type': 'heatmap'
            })
        
        return self.charts
    
    def create_histogram(self, column):
        """Create histogram for numeric column"""
        fig = px.histogram(
            self.df, 
            x=column,
            title=f'Distribution of {column}',
            color_discrete_sequence=['#2E86AB'],
            nbins=30
        )
        fig.update_layout(
            showlegend=False,
            height=400,
            template='plotly_white'
        )
        return fig
    
    def create_bar_chart(self, column):
        """Create bar chart for categorical column"""
        value_counts = self.df[column].value_counts().head(10)
        
        fig = px.bar(
            x=value_counts.values,
            y=value_counts.index,
            orientation='h',
            title=f'Top 10 values in {column}',
            color=value_counts.values,
            color_continuous_scale='Blues'
        )
        fig.update_layout(
            xaxis_title='Count',
            yaxis_title=column,
            height=400,
            template='plotly_white'
        )
        return fig
    
    def create_time_series(self, date_col, value_col):
        """Create time series line chart"""
        # group by date
        time_data = self.df.groupby(pd.Grouper(key=date_col, freq='D'))[value_col].mean().reset_index()
        
        fig = px.line(
            time_data,
            x=date_col,
            y=value_col,
            title=f'{value_col} over time',
            markers=True
        )
        fig.update_layout(
            xaxis_title='Date',
            yaxis_title=value_col,
            height=400,
            template='plotly_white'
        )
        return fig
    
    def create_correlation_heatmap(self):
        """Create correlation heatmap"""
        corr_matrix = self.df[self.schema['numeric']].corr()
        
        fig = px.imshow(
            corr_matrix,
            text_auto='.2f',
            aspect='auto',
            color_continuous_scale='RdBu',
            title='Correlation Heatmap'
        )
        fig.update_layout(
            height=500,
            template='plotly_white'
        )
        return fig
    
    def create_key_metrics(self):
        """Create KPI cards for important metrics"""
        metrics = []
        
        for col in self.schema['numeric'][:4]:  # Top 4 numeric columns
            mean_val = self.df[col].mean()
            std_val = self.df[col].std()
            min_val = self.df[col].min()
            max_val = self.df[col].max()
            
            metrics.append({
                'name': col.upper(),
                'value': f"{mean_val:,.0f}",
                'change': f"±{std_val:,.0f}",
                'min': f"{min_val:,.0f}",
                'max': f"{max_val:,.0f}",
                'type': 'average'
            })
        
        return metrics
    
    def create_summary_table(self):
        """Create summary statistics table"""
        summary = []
        for col in self.schema['numeric']:
            summary.append({
                'Column': col,
                'Mean': round(self.df[col].mean(), 2),
                'Median': round(self.df[col].median(), 2),
                'Std Dev': round(self.df[col].std(), 2),
                'Min': round(self.df[col].min(), 2),
                'Max': round(self.df[col].max(), 2)
            })
        
        return pd.DataFrame(summary)