dashboard.py

import streamlit as st
import pandas as pd
from datetime import datetime
import plotly.express as px
import plotly.graph_objects as go

# Set page config
st.set_page_config(
    page_title="License Plate Detection Results",
    page_icon="🚗",
    layout="wide"
)

# Custom CSS
st.markdown("""
<style>
    .metric-container {
        background-color: #f0f2f6;
        border-radius: 10px;
        padding: 15px;
        margin: 10px 0;
    }
    .stMetric {
        background-color: white !important;
        border-radius: 5px;
        padding: 10px;
        box-shadow: 0 2px 4px rgba(0,0,0,0.1);
    }
</style>
""", unsafe_allow_html=True)

# Title and description
st.title("📊 License Plate Detection Dashboard")
st.markdown("""
This dashboard shows the results of license plate detections from video surveillance.
""")

# Load and process data
@st.cache_data
def load_data():
    try:
        df = pd.read_csv("car_plate_data_stored.csv")
        
        # Handle different column names
        if 'NumberPlate' in df.columns:
            df = df.rename(columns={'NumberPlate': 'ID'})
        elif 'ImageFile' in df.columns:
            df = df.rename(columns={'ImageFile': 'ID'})
            
        # Ensure we have all required columns
        if 'Confidence' not in df.columns:
            df['Confidence'] = 'N/A'
            
        # Convert dates
        df['DateTime'] = pd.to_datetime(df['Date'] + ' ' + df['Time'], 
                                      format='%d-%m-%Y %H:%M:%S', 
                                      dayfirst=True)
        
        return df
    except Exception as e:
        st.error(f"Error loading data: {str(e)}")
        return pd.DataFrame(columns=['ID', 'Date', 'Time', 'Confidence', 'DateTime'])

# Load data
df = load_data()

# Dashboard layout
col1, col2 = st.columns([2, 1])

with col1:
    # Statistics cards in a grid
    st.markdown('<div class="metric-container">', unsafe_allow_html=True)
    stat_col1, stat_col2, stat_col3 = st.columns(3)
    
    with stat_col1:
        st.metric("Total Detections", len(df))
    
    with stat_col2:
        if not df.empty:
            numeric_conf = pd.to_numeric(df['Confidence'].replace('N/A', float('nan')), errors='coerce')
            avg_confidence = numeric_conf.mean()
            if pd.notnull(avg_confidence):
                st.metric("Average Confidence", f"{avg_confidence:.2f}%")
            else:
                st.metric("Average Confidence", "N/A")
    
    with stat_col3:
        if not df.empty:
            today = datetime.now().date()
            today_detections = df[pd.to_datetime(df['Date']).dt.date == today].shape[0]
            st.metric("Today's Detections", today_detections)
    st.markdown('</div>', unsafe_allow_html=True)
    
    # Timeline chart
    if not df.empty:
        st.subheader("Detection Timeline")
        detections_by_time = df.groupby(df['DateTime'].dt.floor('H')).size().reset_index(name='count')
        
        fig = go.Figure()
        fig.add_trace(go.Scatter(
            x=detections_by_time['DateTime'],
            y=detections_by_time['count'],
            mode='lines+markers',
            line=dict(color='#1f77b4', width=2),
            marker=dict(size=6),
            name='Detections'
        ))
        
        fig.update_layout(
            title="Detections Over Time",
            xaxis_title="Time",
            yaxis_title="Number of Detections",
            height=400,
            hovermode='x unified',
            plot_bgcolor='white',
            paper_bgcolor='white',
            xaxis=dict(
                showgrid=True,
                gridcolor='#f0f0f0',
            ),
            yaxis=dict(
                showgrid=True,
                gridcolor='#f0f0f0',
            )
        )
        st.plotly_chart(fig, use_container_width=True)

with col2:
    st.subheader("Recent Detections")
    if not df.empty:
        recent = df.tail(5)
        for _, row in recent.iterrows():
            with st.container():
                st.markdown(f"""
                <div style="padding: 10px; background-color: #f0f2f6; border-radius: 5px; margin: 5px 0;">
                    <p><strong>ID:</strong> {row['ID']}</p>
                    <p><strong>Time:</strong> {row['Time']}</p>
                    <p><strong>Confidence:</strong> {row['Confidence'] if row['Confidence'] != 'N/A' else 'N/A'}</p>
                </div>
                """, unsafe_allow_html=True)

# Data table with filters
st.subheader("Detection Records")
if not df.empty:
    col1, col2 = st.columns([1, 2])
    
    with col1:
        date_filter = st.date_input(
            "Filter by date",
            pd.to_datetime(df['Date']).min()
        )
    
    with col2:
        confidence_filter = st.slider(
            "Minimum confidence",
            0.0, 100.0, 0.0,
            help="Filter detections by minimum confidence score"
        )
    
    # Apply filters
    filtered_df = df[df['DateTime'].dt.date == date_filter]
    if confidence_filter > 0:
        numeric_conf = pd.to_numeric(filtered_df['Confidence'].replace('N/A', -1), errors='coerce')
        filtered_df = filtered_df[numeric_conf >= confidence_filter]
    
    # Display the filtered dataframe
    st.dataframe(
        filtered_df[['ID', 'Date', 'Time', 'Confidence']].style.format({
            'Confidence': lambda x: f"{x:.2f}%" if isinstance(x, (int, float)) else x
        }),
        use_container_width=True
    )

# Add summary statistics
if not df.empty:
    st.subheader("Detection Statistics")
    col1, col2 = st.columns(2)
    
    with col1:
        # Detections by hour
        hourly_stats = df.groupby(df['DateTime'].dt.hour).size()
        fig = px.bar(
            x=hourly_stats.index,
            y=hourly_stats.values,
            labels={'x': 'Hour of Day', 'y': 'Number of Detections'},
            title='Detections by Hour of Day'
        )
        fig.update_layout(bargap=0.2)
        st.plotly_chart(fig, use_container_width=True)
    
    with col2:
        # Confidence distribution
        confidence_values = pd.to_numeric(df['Confidence'].replace('N/A', float('nan')), errors='coerce')
        confidence_values = confidence_values.dropna()
        
        if not confidence_values.empty:
            fig = px.histogram(
                confidence_values,
                nbins=20,
                labels={'value': 'Confidence Score', 'count': 'Number of Detections'},
                title='Distribution of Confidence Scores'
            )
            fig.update_layout(bargap=0.2)
            st.plotly_chart(fig, use_container_width=True)