Delete streamlit.py

streamlit.py

@@ -1,412 +0,0 @@
-import streamlit as st
-import ee
-import geemap.foliumap as geemap
-import folium
-import pandas as pd
-import numpy as np
-import plotly.express as px
-import plotly.graph_objects as go
-from datetime import datetime, date
-import json
-
-# Configure Streamlit page
-st.set_page_config(
-    page_title="Interactive Landsat 9 Analysis",
-    page_icon="🛰️",
-    layout="wide",
-    initial_sidebar_state="expanded"
-)
-
-# Initialize Earth Engine function
-@st.cache_resource
-def init_ee_with_project(project_id=None):
-    try:
-        if project_id:
-            ee.Initialize(project=project_id)
-        else:
-            ee.Initialize()
-        return True, None
-    except Exception as e:
-        return False, str(e)
-
-# Main title and description
-st.title("🛰️ Interactive Landsat 9 OLI/TIRS Analysis")
-st.markdown("""
-This interactive application allows you to analyze Landsat 9 satellite imagery with various spectral indices 
-and visualizations. Customize your analysis parameters using the sidebar controls.
-""")
-
-# Earth Engine initialization with project handling
-ee_initialized = False
-
-# Try to initialize without project first
-success, error = init_ee_with_project()
-
-if not success:
-    st.warning("Earth Engine initialization failed. Please provide your Google Cloud Project ID.")
-    st.info("""
-    **To get your Project ID:**
-    1. Go to https://console.cloud.google.com/
-    2. Create a new project or select an existing one
-    3. Enable the Earth Engine API for your project
-    4. Copy the Project ID from the project selector
-    """)
-    
-    project_id = st.text_input(
-        "Enter your Google Cloud Project ID:",
-        help="Find this in your Google Cloud Console dashboard"
-    )
-    
-    if project_id:
-        success, error = init_ee_with_project(project_id)
-        if success:
-            st.success(f"Successfully initialized Earth Engine with project: {project_id}")
-            ee_initialized = True
-        else:
-            st.error(f"Failed to initialize with project {project_id}: {error}")
-    
-    if not ee_initialized:
-        st.stop()
-else:
-    ee_initialized = True
-    st.success("Earth Engine initialized successfully!")
-
-# Sidebar controls
-st.sidebar.header("🎛️ Analysis Parameters")
-
-# Location settings
-st.sidebar.subheader("📍 Location Settings")
-center_lat = st.sidebar.number_input("Center Latitude", value=34.741, format="%.3f")
-center_lon = st.sidebar.number_input("Center Longitude", value=71.878, format="%.3f")
-buffer_size = st.sidebar.slider("Buffer Size (km)", min_value=10, max_value=100, value=50)
-
-# Date range settings
-st.sidebar.subheader("📅 Date Range")
-start_date = st.sidebar.date_input("Start Date", value=date(2022, 1, 1))
-end_date = st.sidebar.date_input("End Date", value=date(2022, 12, 31))
-
-# Cloud cover filter
-cloud_cover = st.sidebar.slider("Maximum Cloud Cover (%)", min_value=0, max_value=100, value=20)
-
-# Visualization options
-st.sidebar.subheader("🎨 Visualization Options")
-vis_options = {
-    "True Color (432)": {"bands": ["B4", "B3", "B2"], "min": 8000, "max": 18000},
-    "False Color (543)": {"bands": ["B5", "B4", "B3"], "min": 8000, "max": 20000},
-    "Agriculture (654)": {"bands": ["B6", "B5", "B4"], "min": 8000, "max": 20000},
-    "Geology (764)": {"bands": ["B7", "B6", "B4"], "min": 8000, "max": 20000},
-    "Bathymetric (431)": {"bands": ["B4", "B3", "B1"], "min": 8000, "max": 18000}
-}
-
-selected_vis = st.sidebar.selectbox("Select Band Combination", list(vis_options.keys()))
-
-# Index calculations
-st.sidebar.subheader("📊 Spectral Indices")
-show_indices = st.sidebar.multiselect(
-    "Select Indices to Display",
-    ["NDVI", "EVI", "SAVI", "NDWI", "MNDWI", "NDBI", "NBR", "NDSI"],
-    default=["NDVI", "NDWI"]
-)
-
-# Analysis function
-@st.cache_data
-def perform_analysis(lat, lon, buffer_km, start_dt, end_dt, max_cloud):
-    # Define area of interest
-    aoi = ee.Geometry.Point([lon, lat]).buffer(buffer_km * 1000)
-    
-    # Load Landsat 9 dataset
-    dataset = ee.ImageCollection('LANDSAT/LC09/C02/T1') \
-                .filterDate(start_dt.strftime('%Y-%m-%d'), end_dt.strftime('%Y-%m-%d')) \
-                .filterBounds(aoi) \
-                .filter(ee.Filter.lt('CLOUD_COVER', max_cloud)) \
-                .sort('CLOUD_COVER')
-    
-    # Get dataset info
-    size = dataset.size().getInfo()
-    
-    if size == 0:
-        return None, None, "No images found for the specified criteria."
-    
-    # Create composite
-    composite = dataset.median().clip(aoi)
-    
-    # Calculate indices
-    indices = {}
-    
-    # Vegetation indices
-    indices['NDVI'] = composite.normalizedDifference(['B5', 'B4']).rename('NDVI')
-    indices['EVI'] = composite.expression(
-        '2.5 * ((NIR - RED) / (NIR + 6 * RED - 7.5 * BLUE + 1))', {
-            'NIR': composite.select('B5'),
-            'RED': composite.select('B4'),
-            'BLUE': composite.select('B2')
-        }).rename('EVI')
-    indices['SAVI'] = composite.expression(
-        '((NIR - RED) / (NIR + RED + 0.5)) * (1 + 0.5)', {
-            'NIR': composite.select('B5'),
-            'RED': composite.select('B4')
-        }).rename('SAVI')
-    
-    # Water indices
-    indices['NDWI'] = composite.normalizedDifference(['B3', 'B5']).rename('NDWI')
-    indices['MNDWI'] = composite.normalizedDifference(['B3', 'B6']).rename('MNDWI')
-    
-    # Urban indices
-    indices['NDBI'] = composite.normalizedDifference(['B6', 'B5']).rename('NDBI')
-    
-    # Burn index
-    indices['NBR'] = composite.normalizedDifference(['B5', 'B7']).rename('NBR')
-    
-    # Snow index
-    indices['NDSI'] = composite.normalizedDifference(['B3', 'B6']).rename('NDSI')
-    
-    # Calculate statistics
-    stats = {}
-    for name, index in indices.items():
-        stat = index.reduceRegion(
-            reducer=ee.Reducer.mean().combine(ee.Reducer.stdDev(), sharedInputs=True),
-            geometry=aoi,
-            scale=30,
-            maxPixels=1e9
-        ).getInfo()
-        stats[name] = stat
-    
-    return composite, indices, stats, aoi, size
-
-# Run analysis button
-if st.sidebar.button("🚀 Run Analysis", type="primary"):
-    with st.spinner("Analyzing Landsat 9 imagery..."):
-        try:
-            result = perform_analysis(
-                center_lat, center_lon, buffer_size, 
-                start_date, end_date, cloud_cover
-            )
-            
-            if result[0] is None:
-                st.error(result[2])
-            else:
-                composite, indices, stats, aoi, image_count = result
-                st.success(f"Analysis complete! Found {image_count} images.")
-                
-                # Store results in session state
-                st.session_state.composite = composite
-                st.session_state.indices = indices
-                st.session_state.stats = stats
-                st.session_state.aoi = aoi
-                st.session_state.analysis_params = {
-                    'lat': center_lat, 'lon': center_lon, 'buffer': buffer_size
-                }
-                
-        except Exception as e:
-            st.error(f"Analysis failed: {str(e)}")
-
-# Display results if analysis has been run
-if 'composite' in st.session_state:
-    # Create tabs for different views
-    tab1, tab2, tab3, tab4 = st.tabs(["🗺️ Interactive Map", "📊 Statistics", "📈 Charts", "📋 Data Export"])
-    
-    with tab1:
-        st.subheader("Interactive Satellite Imagery Map")
-        
-        # Create the map
-        Map = geemap.Map(center=[st.session_state.analysis_params['lat'], 
-                                st.session_state.analysis_params['lon']], zoom=12)
-        
-        # Add selected visualization
-        vis_params = vis_options[selected_vis]
-        Map.addLayer(
-            st.session_state.composite.select(vis_params['bands']),
-            {
-                'min': vis_params['min'],
-                'max': vis_params['max'],
-                'bands': vis_params['bands']
-            },
-            selected_vis
-        )
-        
-        # Add selected indices
-        index_vis_params = {
-            'NDVI': {'min': -0.5, 'max': 0.8, 'palette': ['red', 'yellow', 'green']},
-            'EVI': {'min': -0.5, 'max': 0.8, 'palette': ['red', 'yellow', 'green']},
-            'SAVI': {'min': -0.5, 'max': 0.8, 'palette': ['red', 'yellow', 'green']},
-            'NDWI': {'min': -0.5, 'max': 0.5, 'palette': ['white', 'blue']},
-            'MNDWI': {'min': -0.5, 'max': 0.5, 'palette': ['white', 'blue']},
-            'NDBI': {'min': -0.5, 'max': 0.5, 'palette': ['blue', 'white', 'red']},
-            'NBR': {'min': -0.5, 'max': 0.5, 'palette': ['green', 'yellow', 'red']},
-            'NDSI': {'min': 0, 'max': 0.8, 'palette': ['red', 'yellow', 'white']}
-        }
-        
-        for index_name in show_indices:
-            if index_name in st.session_state.indices:
-                Map.addLayer(
-                    st.session_state.indices[index_name].selfMask(),
-                    index_vis_params[index_name],
-                    index_name,
-                    False  # Start with layer hidden
-                )
-        
-        # Add AOI boundary
-        Map.addLayer(st.session_state.aoi, {'color': 'yellow'}, 'Area of Interest')
-        
-        # Display the map
-        Map.to_streamlit(height=600)
-    
-    with tab2:
-        st.subheader("📊 Spectral Index Statistics")
-        
-        # Create statistics dataframe
-        stats_data = []
-        for index_name, stat_dict in st.session_state.stats.items():
-            if index_name in show_indices:
-                mean_key = f"{index_name}_mean"
-                std_key = f"{index_name}_stdDev"
-                
-                mean_val = stat_dict.get(mean_key, 0)
-                std_val = stat_dict.get(std_key, 0)
-                
-                stats_data.append({
-                    'Index': index_name,
-                    'Mean': round(mean_val, 4) if mean_val else 0,
-                    'Standard Deviation': round(std_val, 4) if std_val else 0,
-                    'Range': f"{round(mean_val - std_val, 4)} to {round(mean_val + std_val, 4)}" if mean_val and std_val else "N/A"
-                })
-        
-        if stats_data:
-            df_stats = pd.DataFrame(stats_data)
-            st.dataframe(df_stats, use_container_width=True)
-            
-            # Create bar chart of mean values
-            fig_bar = px.bar(
-                df_stats, 
-                x='Index', 
-                y='Mean', 
-                title='Mean Values of Spectral Indices',
-                color='Mean',
-                color_continuous_scale='viridis'
-            )
-            fig_bar.update_layout(height=400)
-            st.plotly_chart(fig_bar, use_container_width=True)
-    
-    with tab3:
-        st.subheader("📈 Data Visualization")
-        
-        # Index interpretation guide
-        with st.expander("📖 Index Interpretation Guide"):
-            st.markdown("""
-            **Vegetation Indices:**
-            - **NDVI**: -1 to 1 (higher = more vegetation)
-            - **EVI**: -1 to 1 (enhanced vegetation, reduces atmospheric effects)
-            - **SAVI**: -1 to 1 (soil-adjusted vegetation index)
-            
-            **Water Indices:**
-            - **NDWI**: -1 to 1 (higher = more water)
-            - **MNDWI**: -1 to 1 (modified NDWI, better for water detection)
-            
-            **Urban/Built-up:**
-            - **NDBI**: -1 to 1 (higher = more built-up areas)
-            
-            **Environmental:**
-            - **NBR**: -1 to 1 (normalized burn ratio for fire detection)
-            - **NDSI**: 0 to 1 (normalized difference snow index)
-            """)
-        
-        # Create comparison chart if multiple indices selected
-        if len(show_indices) > 1:
-            comparison_data = []
-            for index_name in show_indices:
-                if index_name in st.session_state.stats:
-                    stat_dict = st.session_state.stats[index_name]
-                    mean_key = f"{index_name}_mean"
-                    mean_val = stat_dict.get(mean_key, 0)
-                    comparison_data.append({'Index': index_name, 'Mean Value': mean_val})
-            
-            if comparison_data:
-                df_comparison = pd.DataFrame(comparison_data)
-                fig_comparison = px.bar(
-                    df_comparison,
-                    x='Index',
-                    y='Mean Value',
-                    title='Spectral Index Comparison',
-                    color='Mean Value',
-                    color_continuous_scale='RdYlGn'
-                )
-                fig_comparison.update_layout(height=400)
-                st.plotly_chart(fig_comparison, use_container_width=True)
-    
-    with tab4:
-        st.subheader("📋 Data Export Options")
-        
-        col1, col2 = st.columns(2)
-        
-        with col1:
-            st.markdown("**📊 Statistics Export**")
-            if st.button("Download Statistics as CSV"):
-                if 'stats' in st.session_state:
-                    stats_data = []
-                    for index_name, stat_dict in st.session_state.stats.items():
-                        mean_key = f"{index_name}_mean"
-                        std_key = f"{index_name}_stdDev"
-                        stats_data.append({
-                            'Index': index_name,
-                            'Mean': stat_dict.get(mean_key, 0),
-                            'Standard_Deviation': stat_dict.get(std_key, 0)
-                        })
-                    
-                    df_export = pd.DataFrame(stats_data)
-                    csv = df_export.to_csv(index=False)
-                    st.download_button(
-                        label="📥 Download CSV",
-                        data=csv,
-                        file_name=f"landsat9_analysis_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv",
-                        mime="text/csv"
-                    )
-        
-        with col2:
-            st.markdown("**🗺️ Map Export**")
-            st.info("Use the map's built-in export tools to save visualizations as images.")
-        
-        # Analysis summary
-        st.markdown("**📋 Analysis Summary**")
-        summary_info = f"""
-        - **Location**: {st.session_state.analysis_params['lat']:.3f}°N, {st.session_state.analysis_params['lon']:.3f}°E
-        - **Buffer Size**: {st.session_state.analysis_params['buffer']} km
-        - **Date Range**: {start_date} to {end_date}
-        - **Cloud Cover**: ≤ {cloud_cover}%
-        - **Selected Visualization**: {selected_vis}
-        - **Active Indices**: {', '.join(show_indices)}
-        """
-        st.markdown(summary_info)
-
-else:
-    # Instructions when no analysis has been run
-    st.info("👈 Configure your analysis parameters in the sidebar and click 'Run Analysis' to get started!")
-    
-    # Feature overview
-    st.markdown("""
-    ## 🌟 Features
-    
-    **🛰️ Satellite Data Analysis**
-    - Landsat 9 OLI/TIRS imagery (30m resolution)
-    - Customizable date ranges and cloud cover filtering
-    - Multiple band combinations for different applications
-    
-    **📊 Spectral Indices**
-    - Vegetation: NDVI, EVI, SAVI
-    - Water: NDWI, MNDWI  
-    - Urban: NDBI
-    - Environmental: NBR (burn), NDSI (snow)
-    
-    **🎨 Interactive Visualizations**
-    - True color, false color, and specialized composites
-    - Statistical analysis and charting
-    - Export capabilities for further analysis
-    
-    **🗺️ Interactive Mapping**
-    - Zoom, pan, and layer control
-    - Real-time visualization switching
-    - Area of interest boundary display
-    """)
-
-# Footer
-st.markdown("---")
-st.markdown("Built with ❤️ using Streamlit, Google Earth Engine, and geemap")