Update app.py

app.py

@@ -1,208 +1,111 @@
 import streamlit as st
 import pandas as pd
-import numpy as np
+import geopandas as gpd
 import ee
 import geemap
-import geopandas as gpd
-from datetime import datetime, timedelta
 import folium
 from streamlit_folium import folium_static
-import plotly.express as px
-import io
-import requests
+import matplotlib.pyplot as plt
+import numpy as np
+from datetime import datetime, timedelta
 
 # Initialize Earth Engine
-def initialize_ee():
-    try:
-        service_account = 'esmaeil-kiani1387-gmail-com@ee-esmaeilkiani13877.iam.gserviceaccount.com'
-        credentials = ee.ServiceAccountCredentials(service_account, 'ee-esmaeilkiani13877-9a054809a4bb.json')
-        ee.Initialize(credentials)
-        return True
-    except Exception as e:
-        st.error(f"خطا در راه‌اندازی Earth Engine: {str(e)}")
-        return False
-
-# Set page config
-st.set_page_config(
-    page_title="تحلیل پوشش گیاهی مزارع",
-    layout="wide",
-    initial_sidebar_state="expanded"
-)
-
-# Custom styling
-st.markdown("""
-<style>
-    .main {
-        background-color: #f5f5f5;
-    }
-    .stButton>button {
-        background-color: #2E4057;
-        color: white;
-        border-radius: 8px;
-        padding: 0.75rem 1.5rem;
-        font-weight: 600;
-    }
-    .stSelectbox {
-        background-color: white;
-        border-radius: 8px;
-    }
-    .plot-container {
-        background-color: white;
-        border-radius: 15px;
-        padding: 1rem;
-        box-shadow: 0 4px 6px rgba(0,0,0,0.1);
-    }
-    body {
-        direction: rtl;
-        font-family: 'Vazirmatn', sans-serif;
-    }
-</style>
-""", unsafe_allow_html=True)
-
-# Constants
-DEFAULT_LOCATION = {
-    "latitude": 31.534442,
-    "longitude": 48.724416,
-    "name": "شرکت کشت و صنعت نیشکر دهخدا"
-}
-
-NDVI_PALETTE = [
-    '#d73027', '#f46d43', '#fdae61', '#fee08b', '#ffffbf',
-    '#d9ef8b', '#a6d96a', '#66bd63', '#1a9850'
-]
+service_account = 'esmaeil-kiani1387-gmail-com@ee-esmaeilkiani13877.iam.gserviceaccount.com'
+credentials = ee.ServiceAccountCredentials(service_account, 'ee-esmaeilkiani13877-9a054809a4bb.json')
+ee.Initialize(credentials)
 
+# Load farm data
 @st.cache_data
-def load_farm_data():
-    try:
-        CSV_URL = "https://hebbkx1anhila5yf.public.blob.vercel-storage.com/tableConvert.com_wftamx-1UC3HLMMTZ9WN2ePEhHQLU2Knn0ACl.csv"
-        response = requests.get(CSV_URL)
-        response.raise_for_status()
-        csv_content = response.content.decode('utf-8')
-        df = pd.read_csv(io.StringIO(csv_content))
-        return df
-    except Exception as e:
-        st.error(f"خطا در بارگیری داده‌های مزارع: {str(e)}")
-        return None
-
-def calculate_ndvi(image):
-    ndvi = image.normalizedDifference(['B8', 'B4']).rename('NDVI')
-    return image.addBands(ndvi)
+def load_data():
+    df = pd.read_csv('tableConvert.com_wftamx (1).csv')
+    return df
 
-def get_sentinel_collection(start_date, end_date, geometry):
+# Calculate vegetation indices
+def calculate_indices(image):
+    ndvi = image.normalizedDifference(['B8', 'B4']).rename('NDVI')
+    evi2 = image.expression(
+        '2.5 * ((NIR - RED) / (NIR + 2.4 * RED + 1))',
+        {'NIR': image.select('B8'), 'RED': image.select('B4')}
+    ).rename('EVI2')
+    lai = image.expression(
+        '3.618 * EVI - 0.118',
+        {'EVI': image.select('EVI2')}
+    ).rename('LAI')
+    return image.addBands([ndvi, evi2, lai])
+
+# Get Sentinel-2 imagery
+def get_sentinel_imagery(geometry, start_date, end_date):
     return (ee.ImageCollection('COPERNICUS/S2_SR')
-            .filterDate(start_date, end_date)
             .filterBounds(geometry)
-            .map(calculate_ndvi)
-            .select('NDVI'))
-
-def create_ndvi_visualization(start_date, end_date, wheat_only=False):
-    try:
-        # Create geometry from default location
-        point = ee.Geometry.Point([DEFAULT_LOCATION['longitude'], DEFAULT_LOCATION['latitude']])
-        region = point.buffer(5000)  # 5km buffer
+            .filterDate(start_date, end_date)
+            .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 20))
+            .map(calculate_indices)
+            .median())
 
-        # Get Sentinel-2 collection
-        collection = get_sentinel_collection(start_date, end_date, region)
-        
-        # Calculate mean NDVI
-        ndvi = collection.mean()
-
-        # Visualization parameters
-        vis_params = {
-            'min': -1,
-            'max': 1,
-            'palette': NDVI_PALETTE
-        }
-
-        if wheat_only:
-            # Load wheat farm locations
-            farms_df = load_farm_data()
-            wheat_farms = farms_df[farms_df['crop_type'] == 'wheat']
-            
-            # Create mask for wheat farms
-            wheat_mask = ee.FeatureCollection(
-                wheat_farms.apply(
-                    lambda x: ee.Feature(
-                        ee.Geometry.Point([x['longitude'], x['latitude']])
-                    ),
-                    axis=1
-                ).tolist()
-            ).geometry().buffer(100)  # 100m buffer around wheat farms
-            
-            # Apply mask
-            ndvi = ndvi.updateMask(wheat_mask)
-
-        # Create the map
-        Map = geemap.Map(center=[DEFAULT_LOCATION['latitude'], DEFAULT_LOCATION['longitude']], zoom=12)
-        Map.add_layer(ndvi, vis_params, 'NDVI')
-        
-        # Add legend
-        Map.add_legend(title="NDVI Values", colors=NDVI_PALETTE,
-                      labels=[f"{i:.1f}" for i in np.linspace(-1, 1, len(NDVI_PALETTE))])
-        
-        return Map
+# Main app
+def main():
+    st.title('Sugarcane Farm Analysis')
 
-    except Exception as e:
-        st.error(f"خطا در محاسبه NDVI: {str(e)}")
-        return None
+    # Load data
+    df = load_data()
 
-def main():
-    # Initialize Earth Engine
-    if not initialize_ee():
-        return
+    # Sidebar
+    st.sidebar.title('Farm Selection')
+    selected_farm = st.sidebar.selectbox('Select a farm', df['name'])
 
-    st.title("تحلیل شاخص NDVI مزارع")
+    # Main content
+    col1, col2 = st.columns([1, 2])
 
-    # Date selection
-    col1, col2 = st.columns(2)
     with col1:
-        start_date = st.date_input(
-            "تاریخ شروع",
-            datetime.now() - timedelta(days=30),
-            help="تاریخ شروع برای محاسبه NDVI"
-        )
+        st.subheader('Farm Information')
+        farm_data = df[df['name'] == selected_farm].iloc[0]
+        st.write(f"Age: {farm_data['age']}")
+        st.write(f"Variety: {farm_data['variety']}")
+
     with col2:
-        end_date = st.date_input(
-            "تاریخ پایان",
-            datetime.now(),
-            help="تاریخ پایان برای محاسبه NDVI"
-        )
-
-    # Wheat farms filter
-    wheat_only = st.checkbox("نمایش فقط مزارع گندم", help="فیلتر کردن نقشه برای نمایش فقط مزارع گندم")
-
-    if st.button("محاسبه NDVI"):
-        with st.spinner("در حال محاسبه NDVI..."):
-            start_time = datetime.now()
-            
-            # Create NDVI visualization
-            Map = create_ndvi_visualization(
-                start_date.strftime("%Y-%m-%d"),
-                end_date.strftime("%Y-%m-%d"),
-                wheat_only
-            )
-            
-            if Map:
-                # Display the map
-                Map.to_streamlit(height=600)
-                
-                # Display processing time
-                end_time = datetime.now()
-                processing_time = (end_time - start_time).total_seconds()
-                st.info(f"زمان پردازش: {processing_time:.2f} ثانیه")
-                
-                # Display NDVI information
-                st.markdown("""
-                <div class="plot-container">
-                    <h3>راهنمای تفسیر NDVI</h3>
-                    <ul>
-                        <li>مقادیر نزدیک به 1 (سبز تیره): پوشش گیاهی متراکم</li>
-                        <li>مقادیر متوسط (زرد تا سبز روشن): پوشش گیاهی متوسط</li>
-                        <li>مقادیر نزدیک به 0 (نارنجی): پوشش گیاهی کم یا خاک لخت</li>
-                        <li>مقادیر منفی (قرمز): آب یا ابر</li>
-                    </ul>
-                </div>
-                """, unsafe_allow_html=True)
-
-if __name__ == "__main__":
-    main()
+        st.subheader('Farm Location')
+        m = folium.Map(location=[farm_data['latitude'], farm_data['longitude']], zoom_start=12)
+        folium.Marker(
+            [farm_data['latitude'], farm_data['longitude']],
+            popup=farm_data['name']
+        ).add_to(m)
+        folium_static(m)
+
+    # Vegetation indices analysis
+    st.subheader('Vegetation Indices Analysis')
+    
+    # Date range selection
+    today = datetime.now()
+    start_date = st.date_input('Start date', today - timedelta(days=30))
+    end_date = st.date_input('End date', today)
+
+    if start_date and end_date:
+        geometry = ee.Geometry.Point([farm_data['longitude'], farm_data['latitude']])
+        image = get_sentinel_imagery(geometry, start_date.strftime('%Y-%m-%d'), end_date.strftime('%Y-%m-%d'))
+
+        # Display NDVI map
+        ndvi_map = geemap.Map(center=[farm_data['latitude'], farm_data['longitude']], zoom=14)
+        ndvi_map.add_layer(image.select('NDVI'), {'min': 0, 'max': 1, 'palette': ['red', 'yellow', 'green']}, 'NDVI')
+        ndvi_map.add_child(folium.LayerControl())
+        folium_static(ndvi_map)
+
+        # Plot time series of indices
+        indices = ['NDVI', 'EVI2', 'LAI']
+        fig, ax = plt.subplots(figsize=(10, 6))
+        
+        for index in indices:
+            values = image.select(index).reduceRegion(
+                reducer=ee.Reducer.mean(),
+                geometry=geometry,
+                scale=10
+            ).getInfo()[index]
+            ax.plot([start_date, end_date], [values, values], label=index)
+
+        ax.set_xlabel('Date')
+        ax.set_ylabel('Index Value')
+        ax.legend()
+        st.pyplot(fig)
+
+if __name__ == '__main__':
+    main()
+