Update app.py

app.py

@@ -19,21 +19,13 @@ import altair as alt
 from streamlit_option_menu import option_menu
 from streamlit_lottie import st_lottie
 import requests
-import hydralit_components as hc
-from streamlit_extras.colored_header import colored_header
-from streamlit_extras.metric_cards import style_metric_cards
-from streamlit_extras.chart_container import chart_container
-from streamlit_extras.add_vertical_space import add_vertical_space
-from streamlit_card import card
-import pydeck as pdk
-import math
 from sklearn.ensemble import RandomForestRegressor
 from sklearn.cluster import KMeans
 from tensorflow.keras.models import Sequential
 from tensorflow.keras.layers import LSTM, Dense
 from sklearn.preprocessing import MinMaxScaler
 
-# Page configuration with custom theme
+# --- Configuration ---
 st.set_page_config(
     page_title="سامانه هوشمند پایش مزارع نیشکر دهخدا",
     page_icon="🌿",
@@ -41,125 +33,40 @@ st.set_page_config(
     initial_sidebar_state="expanded"
 )
 
-# Custom CSS with modern design, animations, and theme support
+# --- Custom CSS ---
 st.markdown("""
 <style>
     @import url('https://fonts.googleapis.com/css2?family=Vazirmatn:wght@100;200;300;400;500;600;700;800;900&display=swap');
-    
-    * {
-        font-family: 'Vazirmatn', sans-serif !important;
-        transition: all 0.3s ease;
-    }
-    
-    .main {
-        background: linear-gradient(135deg, #f5f7fa 0%, #e4e9f2 100%);
-    }
-    
-    .dark-theme .main {
-        background: linear-gradient(135deg, #2c3e50 0%, #1a252f 100%);
-        color: #ecf0f1;
-    }
-    
-    .main-header {
-        background: linear-gradient(90deg, #1a8754 0%, #115740 100%);
-        padding: 1.5rem;
-        border-radius: 12px;
-        box-shadow: 0 8px 32px rgba(0, 0, 0, 0.1);
-        margin-bottom: 2rem;
-        position: relative;
-        overflow: hidden;
-        animation: header-glow 3s infinite alternate;
-    }
-    
-    @keyframes header-glow {
-        0% { box-shadow: 0 8px 32px rgba(26, 135, 84, 0.1); }
-        100% { box-shadow: 0 8px 32px rgba(26, 135, 84, 0.3); }
-    }
-    
-    .main-header h1, .main-header p {
-        color: white;
-        z-index: 1;
-        position: relative;
-    }
-    
-    .stcard {
-        border-radius: 12px;
-        box-shadow: 0 4px 20px rgba(0, 0, 0, 0.05);
-        transition: transform 0.3s ease, box-shadow 0.3s ease;
-    }
-    
-    .stcard:hover {
-        transform: translateY(-5px);
-        box-shadow: 0 8px 30px rgba(0, 0, 0, 0.1);
-    }
-    
-    .dark-theme .stcard {
-        background: #34495e;
-        color: #ecf0f1;
-    }
-    
-    .stButton>button {
-        border-radius: 50px;
-        padding: 0.5rem 1.5rem;
-        font-weight: 600;
-        transition: all 0.3s ease;
-    }
-    
-    .primary-btn {
-        background: linear-gradient(90deg, #1a8754 0%, #115740 100%);
-        color: white;
-    }
-    
-    .dark-theme .primary-btn {
-        background: linear-gradient(90deg, #27ae60 0%, #219653 100%);
-    }
-    
-    .metric-card {
-        background: white;
-        border-radius: 12px;
-        padding: 1.5rem;
-        box-shadow: 0 4px 20px rgba(0, 0, 0, 0.05);
-        text-align: center;
-    }
-    
-    .dark-theme .metric-card {
-        background: #34495e;
-        color: #ecf0f1;
-    }
-    
-    .map-container {
-        border-radius: 12px;
-        overflow: hidden;
-        box-shadow: 0 4px 20px rgba(0, 0, 0, 0.05);
-    }
-    
-    .animate-load {
-        animation: fadeIn 0.5s ease forwards;
-    }
-    
-    @keyframes fadeIn {
-        0% { opacity: 0; transform: translateY(20px); }
-        100% { opacity: 1; transform: translateY(0); }
-    }
-    
-    .rtl {
-        direction: rtl;
-        text-align: right;
-    }
+    * { font-family: 'Vazirmatn', sans-serif !important; transition: all 0.3s ease; }
+    .main { background: linear-gradient(135deg, #f5f7fa 0%, #e4e9f2 100%); }
+    .dark-theme .main { background: linear-gradient(135deg, #2c3e50 0%, #1a252f 100%); color: #ecf0f1; }
+    .main-header { background: linear-gradient(90deg, #1a8754 0%, #115740 100%); padding: 1.5rem; border-radius: 12px; box-shadow: 0 8px 32px rgba(0, 0, 0, 0.1); margin-bottom: 2rem; animation: header-glow 3s infinite alternate; }
+    @keyframes header-glow { 0% { box-shadow: 0 8px 32px rgba(26, 135, 84, 0.1); } 100% { box-shadow: 0 8px 32px rgba(26, 135, 84, 0.3); } }
+    .main-header h1, .main-header p { color: white; }
+    .stcard { border-radius: 12px; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.05); transition: transform 0.3s ease, box-shadow 0.3s ease; }
+    .stcard:hover { transform: translateY(-5px); box-shadow: 0 8px 30px rgba(0, 0, 0, 0.1); }
+    .dark-theme .stcard { background: #34495e; color: #ecf0f1; }
+    .stButton>button { border-radius: 50px; padding: 0.5rem 1.5rem; font-weight: 600; transition: all 0.3s ease; }
+    .primary-btn { background: linear-gradient(90deg, #1a8754 0%, #115740 100%); color: white; }
+    .dark-theme .primary-btn { background: linear-gradient(90deg, #27ae60 0%, #219653 100%); }
+    .metric-card { background: white; border-radius: 12px; padding: 1.5rem; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.05); text-align: center; }
+    .dark-theme .metric-card { background: #34495e; color: #ecf0f1; }
+    .map-container { border-radius: 12px; overflow: hidden; box-shadow: 0 4px 20px rgba(0, 0, 0, 0.05); }
+    .animate-load { animation: fadeIn 0.5s ease forwards; }
+    @keyframes fadeIn { 0% { opacity: 0; transform: translateY(20px); } 100% { opacity: 1; transform: translateY(0); } }
+    .rtl { direction: rtl; text-align: right; }
 </style>
 """, unsafe_allow_html=True)
 
-# Theme selection
+# --- Theme Selection ---
 if 'theme' not in st.session_state:
     st.session_state.theme = 'light'
-
 theme = st.sidebar.selectbox("انتخاب تم", ["روشن", "تیره"], index=0 if st.session_state.theme == 'light' else 1)
 st.session_state.theme = 'light' if theme == "روشن" else 'dark'
 theme_class = "dark-theme" if st.session_state.theme == 'dark' else ""
-
 st.markdown(f'<body class="{theme_class}">', unsafe_allow_html=True)
 
-# Earth Engine Initialization
+# --- Utility Functions ---
 @st.cache_resource
 def initialize_earth_engine():
     try:
@@ -177,661 +84,337 @@ def initialize_earth_engine():
             "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/dehkhodamap-e9f0da4ce9f6514021%40ee-esmaeilkiani13877.iam.gserviceaccount.com",
             "universe_domain": "googleapis.com"
         }
-        
-        credentials_file = 'ee-esmaeilkiani13877-cfdea6eaf411.json'
-        with open(credentials_file, 'w') as f:
+        with open('ee_credentials.json', 'w') as f:
             json.dump(credentials_dict, f)
-        
-        credentials = ee.ServiceAccountCredentials(service_account, credentials_file)
+        credentials = ee.ServiceAccountCredentials(service_account, 'ee_credentials.json')
         ee.Initialize(credentials)
-        
-        os.remove(credentials_file)
+        os.remove('ee_credentials.json')
         return True
     except Exception as e:
         st.error(f"خطا در اتصال به Earth Engine: {e}")
         return False
 
-# Load data
 @st.cache_data
-def load_farm_data():
+def load_data(file_name, error_message):
     try:
-        df = pd.read_csv("پایگاه داده (1).csv")
-        return df
+        return pd.read_csv(file_name)
     except Exception as e:
-        st.error(f"خطا در بارگذاری داده‌های مزارع: {e}")
+        st.error(f"{error_message}: {e}")
         return pd.DataFrame()
 
 @st.cache_data
-def load_coordinates_data():
-    try:
-        df = pd.read_csv("farm_coordinates.csv")
-        return df
-    except Exception as e:
-        st.error(f"خطا در بارگذاری داده‌های مختصات: {e}")
-        return pd.DataFrame()
-
-# Load animation JSON
-@st.cache_data
-def load_lottie_url(url: str):
+def load_lottie_url(url):
     r = requests.get(url)
-    if r.status_code != 200:
-        return None
-    return r.json()
+    return r.json() if r.status_code == 200 else None
 
-# Weather data function
-def get_weather_data(lat, lon, api_key):
+def get_weather_data(lat, lon, api_key="ed47316a45379e2221a75f813229fb46"):
     url = f"http://api.openweathermap.org/data/2.5/weather?lat={lat}&lon={lon}&appid={api_key}&units=metric"
     response = requests.get(url)
-    if response.status_code == 200:
-        return response.json()
-    return None
+    return response.json() if response.status_code == 200 else None
 
-# Estimate water requirement
-def estimate_water_requirement(farm_id, date_str):
-    api_key = "ed47316a45379e2221a75f813229fb46"
+def estimate_water_requirement(farm_id, date_str, coordinates_df):
     farm_row = coordinates_df[coordinates_df['مزرعه'] == farm_id].iloc[0]
-    lat, lon = farm_row['عرض جغرافیایی'], farm_row['طول جغرافیایی']
-    weather_data = get_weather_data(lat, lon, api_key)
+    weather_data = get_weather_data(farm_row['عرض جغرافیایی'], farm_row['طول جغرافیایی'])
     if weather_data:
         temperature = weather_data['main']['temp']
         humidity = weather_data['main']['humidity']
-        water_requirement = (temperature - 20) * 0.5 + (100 - humidity) * 0.1
-        return max(0, water_requirement)
+        return max(0, (temperature - 20) * 0.5 + (100 - humidity) * 0.1)
     return None
 
-# Create Earth Engine map with heatmap option
-def create_ee_map(farm_id, date_str, layer_type="NDVI", heatmap=False):
-    try:
-        farm_row = coordinates_df[coordinates_df['مزرعه'] == farm_id].iloc[0]
-        lat, lon = farm_row['عرض جغرافیایی'], farm_row['طول جغرافیایی']
-        
-        m = folium.Map(location=[lat, lon], zoom_start=14, tiles='CartoDB positron')
-        
-        date_obj = datetime.strptime(date_str, '%Y-%m-%d')
-        start_date = (date_obj - timedelta(days=5)).strftime('%Y-%m-%d')
-        end_date = (date_obj + timedelta(days=5)).strftime('%Y-%m-%d')
-        
-        region = ee.Geometry.Point([lon, lat]).buffer(1500)
-        
-        s2 = ee.ImageCollection('COPERNICUS/S2_SR') \
-            .filterDate(start_date, end_date) \
-            .filterBounds(region) \
-            .sort('CLOUDY_PIXEL_PERCENTAGE') \
-            .first()
-        
-        if layer_type == "NDVI":
-            index = s2.normalizedDifference(['B8', 'B4']).rename('NDVI')
-            viz_params = {'min': -0.2, 'max': 0.8, 'palette': ['#ff0000', '#ff4500', '#ffd700', '#32cd32', '#006400']}
-            legend_title = 'شاخص پوشش گیاهی (NDVI)'
-        elif layer_type == "NDMI":
-            index = s2.normalizedDifference(['B8', 'B11']).rename('NDMI')
-            viz_params = {'min': -0.5, 'max': 0.5, 'palette': ['#8b0000', '#ff8c00', '#00ced1', '#00b7eb', '#00008b']}
-            legend_title = 'شاخص رطوبت (NDMI)'
-        elif layer_type == "EVI":
-            nir = s2.select('B8')
-            red = s2.select('B4')
-            blue = s2.select('B2')
-            index = nir.subtract(red).multiply(2.5).divide(nir.add(red.multiply(6)).subtract(blue.multiply(7.5)).add(1)).rename('EVI')
-            viz_params = {'min': 0, 'max': 1, 'palette': ['#d73027', '#f46d43', '#fdae61', '#fee08b', '#4caf50']}
-            legend_title = 'شاخص پیشرفته گیاهی (EVI)'
-        elif layer_type == "NDWI":
-            index = s2.normalizedDifference(['B3', 'B8']).rename('NDWI')
-            viz_params = {'min': -0.5, 'max': 0.5, 'palette': ['#00008b', '#00b7eb', '#add8e6', '#fdae61', '#d73027']}
-            legend_title = 'شاخص آب (NDWI)'
-        elif layer_type == "SoilMoisture":
-            s1 = ee.ImageCollection('COPERNICUS/S1_GRD') \
-                .filterDate(start_date, end_date) \
-                .filterBounds(region) \
-                .sort('system:time_start') \
-                .first()
-            index = s1.select('VV').rename('SoilMoisture')
-            viz_params = {'min': -25, 'max': -5, 'palette': ['#00008b', '#add8e6', '#ffffff']}
-            legend_title = 'رطوبت خاک (Soil Moisture)'
-        
-        if heatmap:
-            map_id_dict = ee.Image(index).getMapId({'min': viz_params['min'], 'max': viz_params['max'], 'palette': viz_params['palette'], 'opacity': 0.7})
-            folium.TileLayer(
-                tiles=map_id_dict['tile_fetcher'].url_format,
-                attr='Google Earth Engine Heatmap',
-                name=f'{layer_type} Heatmap',
-                overlay=True,
-                control=True
-            ).add_to(m)
-        else:
-            map_id_dict = ee.Image(index).getMapId(viz_params)
-            folium.TileLayer(
-                tiles=map_id_dict['tile_fetcher'].url_format,
-                attr='Google Earth Engine',
-                name=layer_type,
-                overlay=True,
-                control=True
-            ).add_to(m)
-        
-        folium.Marker([lat, lon], popup=f'مزرعه {farm_id}', tooltip=f'مزرعه {farm_id}', icon=folium.Icon(color='green', icon='leaf')).add_to(m)
-        folium.Circle([lat, lon], radius=1500, color='green', fill=True, fill_color='green', fill_opacity=0.1).add_to(m)
-        folium.LayerControl().add_to(m)
-        
-        legend_html = f'''
-        <div style="position: fixed; bottom: 50px; right: 50px; border: 2px solid grey; z-index: 9999; background-color: white; padding: 10px; border-radius: 5px; direction: rtl;">
-            <div style="font-size: 14px; font-weight: bold; margin-bottom: 5px;">{legend_title}</div>
-            <div style="display: flex; align-items: center; margin-bottom: 5px;">
-                <div style="background: {viz_params['palette'][0]}; width: 20px; height: 20px; margin-left: 5px;"></div>
-                <span>کم</span>
-            </div>
-            <div style="display: flex; align-items: center; margin-bottom: 5px;">
-                <div style="background: {viz_params['palette'][2]}; width: 20px; height: 20px; margin-left: 5px;"></div>
-                <span>متوسط</span>
-            </div>
-            <div style="display: flex; align-items: center;">
-                <div style="background: {viz_params['palette'][-1]}; width: 20px; height: 20px; margin-left: 5px;"></div>
-                <span>زیاد</span>
-            </div>
-        </div>
-        '''
-        m.get_root().html.add_child(folium.Element(legend_html))
-        
-        return m
-    except Exception as e:
-        st.error(f"خطا در ایجاد نقشه: {e}")
-        return None
+def create_ee_map(farm_id, date_str, coordinates_df, layer_type="NDVI", heatmap=False):
+    farm_row = coordinates_df[coordinates_df['مزرعه'] == farm_id].iloc[0]
+    lat, lon = farm_row['عرض جغرافیایی'], farm_row['طول جغرافیایی']
+    m = folium.Map(location=[lat, lon], zoom_start=14, tiles='CartoDB positron')
+    date_obj = datetime.strptime(date_str, '%Y-%m-%d')
+    start_date = (date_obj - timedelta(days=5)).strftime('%Y-%m-%d')
+    end_date = (date_obj + timedelta(days=5)).strftime('%Y-%m-%d')
+    region = ee.Geometry.Point([lon, lat]).buffer(1500)
+    s2 = ee.ImageCollection('COPERNICUS/S2_SR').filterDate(start_date, end_date).filterBounds(region).sort('CLOUDY_PIXEL_PERCENTAGE').first()
+    
+    layers = {
+        "NDVI": (s2.normalizedDifference(['B8', 'B4']).rename('NDVI'), {'min': -0.2, 'max': 0.8, 'palette': ['#ff0000', '#ff4500', '#ffd700', '#32cd32', '#006400']}, 'شاخص پوشش گیاهی (NDVI)'),
+        "NDMI": (s2.normalizedDifference(['B8', 'B11']).rename('NDMI'), {'min': -0.5, 'max': 0.5, 'palette': ['#8b0000', '#ff8c00', '#00ced1', '#00b7eb', '#00008b']}, 'شاخص رطوبت (NDMI)'),
+        "EVI": (s2.normalizedDifference(['B8', 'B4']).multiply(2.5).divide(s2.select('B8').add(s2.select('B4').multiply(6)).subtract(s2.select('B2').multiply(7.5)).add(1)).rename('EVI'), {'min': 0, 'max': 1, 'palette': ['#d73027', '#f46d43', '#fdae61', '#fee08b', '#4caf50']}, 'شاخص پیشرفته گیاهی (EVI)'),
+        "NDWI": (s2.normalizedDifference(['B3', 'B8']).rename('NDWI'), {'min': -0.5, 'max': 0.5, 'palette': ['#00008b', '#00b7eb', '#add8e6', '#fdae61', '#d73027']}, 'شاخص آب (NDWI)'),
+        "SoilMoisture": (ee.ImageCollection('COPERNICUS/S1_GRD').filterDate(start_date, end_date).filterBounds(region).sort('system:time_start').first().select('VV').rename('SoilMoisture'), {'min': -25, 'max': -5, 'palette': ['#00008b', '#add8e6', '#ffffff']}, 'رطوبت خاک (Soil Moisture)')
+    }
+    
+    index, viz_params, legend_title = layers[layer_type]
+    map_id_dict = ee.Image(index).getMapId(viz_params if not heatmap else {**viz_params, 'opacity': 0.7})
+    folium.TileLayer(tiles=map_id_dict['tile_fetcher'].url_format, attr='Google Earth Engine', name=layer_type, overlay=True, control=True).add_to(m)
+    folium.Marker([lat, lon], popup=f'مزرعه {farm_id}', tooltip=f'مزرعه {farm_id}', icon=folium.Icon(color='green', icon='leaf')).add_to(m)
+    folium.Circle([lat, lon], radius=1500, color='green', fill=True, fill_opacity=0.1).add_to(m)
+    folium.LayerControl().add_to(m)
+    
+    legend_html = f'''
+    <div style="position: fixed; bottom: 50px; right: 50px; border: 2px solid grey; z-index: 9999; background-color: white; padding: 10px; border-radius: 5px; direction: rtl;">
+        <div style="font-size: 14px; font-weight: bold; margin-bottom: 5px;">{legend_title}</div>
+        <div style="display: flex; align-items: center; margin-bottom: 5px;"><div style="background: {viz_params['palette'][0]}; width: 20px; height: 20px; margin-left: 5px;"></div><span>کم</span></div>
+        <div style="display: flex; align-items: center; margin-bottom: 5px;"><div style="background: {viz_params['palette'][2]}; width: 20px; height: 20px; margin-left: 5px;"></div><span>متوسط</span></div>
+        <div style="display: flex; align-items: center;"><div style="background: {viz_params['palette'][-1]}; width: 20px; height: 20px; margin-left: 5px;"></div><span>زیاد</span></div>
+    </div>
+    '''
+    m.get_root().html.add_child(folium.Element(legend_html))
+    return m
 
-# Generate mock growth data
 def generate_mock_growth_data(farm_data, selected_variety="all", selected_age="all"):
     weeks = list(range(1, 23))
-    filtered_farms = farm_data
-    if selected_variety != "all":
-        filtered_farms = filtered_farms[filtered_farms['واریته'] == selected_variety]
-    if selected_age != "all":
-        filtered_farms = filtered_farms[filtered_farms['سن'] == selected_age]
-    
-    farm_growth_data = []
-    for _, farm in filtered_farms.iterrows():
-        base_height = np.random.uniform(50, 100)
-        growth_rate = np.random.uniform(5, 15)
-        growth_data = {
-            'farm_id': farm['مزرعه'],
-            'variety': farm['واریته'],
-            'age': farm['سن'],
-            'weeks': weeks,
-            'heights': [round(base_height + growth_rate * week) for week in weeks]
-        }
-        farm_growth_data.append(growth_data)
-    
-    if farm_growth_data:
-        avg_heights = [round(sum(farm['heights'][week-1] for farm in farm_growth_data) / len(farm_growth_data)) for week in weeks]
-        avg_growth_data = {
-            'farm_id': 'میانگین',
-            'variety': 'همه',
-            'age': 'همه',
-            'weeks': weeks,
-            'heights': avg_heights
-        }
-        return {'individual': farm_growth_data, 'average': avg_growth_data}
-    return {
-        'individual': [],
-        'average': {'farm_id': 'میانگین', 'variety': 'همه', 'age': 'همه', 'weeks': weeks, 'heights': [0] * len(weeks)}
-    }
+    filtered_farms = farm_data[(farm_data['واریته'] == selected_variety) if selected_variety != "all" else farm_data.index] \
+                    [(farm_data['سن'] == selected_age) if selected_age != "all" else farm_data.index]
+    farm_growth_data = [
+        {'farm_id': farm['مزرعه'], 'variety': farm['واریته'], 'age': farm['سن'], 'weeks': weeks,
+         'heights': [round(np.random.uniform(50, 100) + np.random.uniform(5, 15) * week) for week in weeks]}
+        for _, farm in filtered_farms.iterrows()
+    ]
+    avg_heights = [round(np.mean([farm['heights'][week-1] for farm in farm_growth_data])) if farm_growth_data else 0 for week in weeks]
+    return {'individual': farm_growth_data, 'average': {'farm_id': 'میانگین', 'variety': 'همه', 'age': 'همه', 'weeks': weeks, 'heights': avg_heights}}
 
-# Calculate farm statistics and detect stress
 def calculate_farm_stats(farm_id, layer_type="NDVI"):
-    if layer_type == "NDVI":
-        mean = round(np.random.uniform(0.6, 0.8), 2)
-        min_val = round(mean - np.random.uniform(0.2, 0.3), 2)
-        max_val = round(mean + np.random.uniform(0.1, 0.2), 2)
-        std_dev = round(np.random.uniform(0.05, 0.15), 2)
-    elif layer_type == "NDMI":
-        mean = round(np.random.uniform(0.3, 0.5), 2)
-        min_val = round(mean - np.random.uniform(0.2, 0.3), 2)
-        max_val = round(mean + np.random.uniform(0.1, 0.2), 2)
-        std_dev = round(np.random.uniform(0.05, 0.15), 2)
-    elif layer_type == "EVI":
-        mean = round(np.random.uniform(0.4, 0.6), 2)
-        min_val = round(mean - np.random.uniform(0.2, 0.3), 2)
-        max_val = round(mean + np.random.uniform(0.1, 0.2), 2)
-        std_dev = round(np.random.uniform(0.05, 0.15), 2)
-    elif layer_type == "NDWI":
-        mean = round(np.random.uniform(-0.1, 0.1), 2)
-        min_val = round(mean - np.random.uniform(0.2, 0.3), 2)
-        max_val = round(mean + np.random.uniform(0.1, 0.2), 2)
-        std_dev = round(np.random.uniform(0.05, 0.15), 2)
-    elif layer_type == "SoilMoisture":
-        mean = round(np.random.uniform(-20, -10), 2)
-        min_val = round(mean - np.random.uniform(5, 10), 2)
-        max_val = round(mean + np.random.uniform(5, 10), 2)
-        std_dev = round(np.random.uniform(2, 5), 2)
-    
-    hist_data = np.random.normal(mean, std_dev, 1000)
-    hist_data = np.clip(hist_data, min_val, max_val)
-    
-    stress_alerts = []
-    if layer_type == "NDVI" and mean < 0.3:
-        stress_alerts.append("تنش سلامتی: NDVI پایین نشان‌دهنده پوشش گیاهی ضعیف است.")
-    if layer_type == "NDMI" and mean < 0.1:
-        stress_alerts.append("تنش آبی: NDMI پایین نشان‌دهنده کمبود رطوبت است.")
-    if layer_type == "SoilMoisture" and mean < -20:
-        stress_alerts.append("تنش خاک: رطوبت خاک بسیار پایین است.")
-    
-    return {
-        'mean': mean, 'min': min_val, 'max': max_val, 'std_dev': std_dev,
-        'histogram_data': hist_data, 'stress_alerts': stress_alerts
+    stats_ranges = {
+        "NDVI": (0.6, 0.8, 0.2, 0.3, 0.1, 0.2, 0.05, 0.15, 0.3, "تنش سلامتی: NDVI پایین"),
+        "NDMI": (0.3, 0.5, 0.2, 0.3, 0.1, 0.2, 0.05, 0.15, 0.1, "تنش آبی: NDMI پایین"),
+        "EVI": (0.4, 0.6, 0.2, 0.3, 0.1, 0.2, 0.05, 0.15, None, None),
+        "NDWI": (-0.1, 0.1, 0.2, 0.3, 0.1, 0.2, 0.05, 0.15, None, None),
+        "SoilMoisture": (-20, -10, 5, 10, 5, 10, 2, 5, -20, "تنش خاک: رطوبت پایین")
     }
+    mean_range, min_adj1, min_adj2, max_adj1, max_adj2, std_range = stats_ranges[layer_type][:6]
+    mean = round(np.random.uniform(*mean_range), 2)
+    min_val = round(mean - np.random.uniform(min_adj1, min_adj2), 2)
+    max_val = round(mean + np.random.uniform(max_adj1, max_adj2), 2)
+    std_dev = round(np.random.uniform(*std_range), 2)
+    hist_data = np.clip(np.random.normal(mean, std_dev, 1000), min_val, max_val)
+    stress_threshold, stress_message = stats_ranges[layer_type][8:]
+    stress_alerts = [stress_message] if stress_threshold and mean < stress_threshold else []
+    return {'mean': mean, 'min': min_val, 'max': max_val, 'std_dev': std_dev, 'histogram_data': hist_data, 'stress_alerts': stress_alerts}
 
-# Time-series data generation
 def generate_time_series_data(farm_id, layer_type, period="weekly"):
-    dates = pd.date_range(end=datetime.now(), periods=30 if period == "weekly" else 90 if period == "monthly" else 365, freq='W' if period == "weekly" else 'M' if period == "monthly" else 'Q')
-    if layer_type == "NDVI":
-        values = np.random.normal(0.7, 0.1, len(dates))
-    elif layer_type == "NDMI":
-        values = np.random.normal(0.4, 0.1, len(dates))
-    elif layer_type == "EVI":
-        values = np.random.normal(0.5, 0.1, len(dates))
-    elif layer_type == "NDWI":
-        values = np.random.normal(0, 0.1, len(dates))
-    elif layer_type == "SoilMoisture":
-        values = np.random.normal(-15, 5, len(dates))
-    return pd.DataFrame({'Date': dates, layer_type: values})
+    periods = {"weekly": 30, "monthly": 90, "seasonal": 365}
+    freqs = {"weekly": 'W', "monthly": 'M', "seasonal": 'Q'}
+    dates = pd.date_range(end=datetime.now(), periods=periods[period], freq=freqs[period])
+    ranges = {"NDVI": (0.7, 0.1), "NDMI": (0.4, 0.1), "EVI": (0.5, 0.1), "NDWI": (0, 0.1), "SoilMoisture": (-15, 5)}
+    return pd.DataFrame({'Date': dates, layer_type: np.random.normal(*ranges[layer_type], len(dates))})
 
-# Advanced prediction with Random Forest and LSTM
-def predict_growth_advanced(farm_id, historical_data):
+def predict_growth_advanced(historical_data):
     weeks = historical_data['Week'].values.reshape(-1, 1)
     heights = historical_data['Height'].values
-    
-    # Random Forest
-    rf_model = RandomForestRegressor(n_estimators=100, random_state=42)
+    rf_model = RandomForestRegressor(n_estimators=50, random_state=42)  # Reduced trees for speed
     rf_model.fit(weeks, heights)
     future_weeks = np.array(range(16, 23)).reshape(-1, 1)
     rf_predictions = rf_model.predict(future_weeks)
     
-    # LSTM
     scaler = MinMaxScaler()
     scaled_heights = scaler.fit_transform(heights.reshape(-1, 1))
-    X, y = [], []
-    for i in range(3, len(scaled_heights)):
-        X.append(scaled_heights[i-3:i])
-        y.append(scaled_heights[i])
-    X, y = np.array(X), np.array(y)
-    
-    lstm_model = Sequential([
-        LSTM(50, activation='relu', input_shape=(3, 1), return_sequences=True),
-        LSTM(50, activation='relu'),
-        Dense(1)
-    ])
+    X = np.array([scaled_heights[i-3:i] for i in range(3, len(scaled_heights))])
+    y = scaled_heights[3:]
+    lstm_model = Sequential([LSTM(20, activation='relu', input_shape=(3, 1)), Dense(1)])  # Simplified LSTM
     lstm_model.compile(optimizer='adam', loss='mse')
-    lstm_model.fit(X, y, epochs=50, batch_size=1, verbose=0)
-    
+    lstm_model.fit(X, y, epochs=20, batch_size=1, verbose=0)  # Reduced epochs
     lstm_input = scaled_heights[-3:].reshape((1, 3, 1))
-    lstm_predictions = []
-    for _ in range(7):
-        pred = lstm_model.predict(lstm_input, verbose=0)
-        lstm_predictions.append(pred[0, 0])
-        lstm_input = np.append(lstm_input[:, 1:, :], pred.reshape(1, 1, 1), axis=1)
-    lstm_predictions = scaler.inverse_transform(np.array(lstm_predictions).reshape(-1, 1)).flatten()
-    
+    lstm_predictions = [scaler.inverse_transform(lstm_model.predict(lstm_input, verbose=0)).flatten()[0] for _ in range(7)]
     return rf_predictions, lstm_predictions
 
-# Cluster farms
 def cluster_farms(farm_data):
-    features = farm_data[['مساحت', 'سن']].astype(float)
-    kmeans = KMeans(n_clusters=3, random_state=42)
+    # Clean data: Convert to numeric, replace invalid values with NaN, then fill with median
+    features = farm_data[['مساحت', 'سن']].apply(pd.to_numeric, errors='coerce').fillna({'مساحت': farm_data['مساحت'].median(), 'سن': farm_data['سن'].median()})
+    kmeans = KMeans(n_clusters=3, random_state=42, n_init=10)  # Added n_init for explicit control
     farm_data['Cluster'] = kmeans.fit_predict(features)
     return farm_data, kmeans.cluster_centers_
 
-# Initialize Earth Engine
+# --- Initialization ---
 ee_initialized = initialize_earth_engine()
-farm_df = load_farm_data()
-coordinates_df = load_coordinates_data()
-
-# Load animations
+farm_df = load_data("پایگاه داده (1).csv", "خطا در بارگذاری داده‌های مزارع")
+coordinates_df = load_data("farm_coordinates.csv", "خطا در بارگذاری داده‌های مختصات")
 lottie_farm = load_lottie_url('https://assets5.lottiefiles.com/packages/lf20_ystsffqy.json')
 lottie_analysis = load_lottie_url('https://assets3.lottiefiles.com/packages/lf20_qp1q7mct.json')
 lottie_report = load_lottie_url('https://assets9.lottiefiles.com/packages/lf20_vwcugezu.json')
-
-# Session state
 if 'heights_df' not in st.session_state:
     st.session_state.heights_df = pd.DataFrame(columns=['Farm_ID', 'Week', 'Measurement_Date', 'Height', 'Station1', 'Station2', 'Station3', 'Station4', 'Station5', 'Groundwater1', 'Groundwater2', 'Sheath_Moisture', 'Nitrogen', 'Variety', 'Age', 'Area', 'Channel', 'Administration'])
 
-# Main header
-st.markdown('<div class="main-header animate-load">', unsafe_allow_html=True)
-st.markdown('<h1>سامانه هوشمند پایش مزارع نیشکر دهخدا</h1>', unsafe_allow_html=True)
-st.markdown('<p>پلتفرم جامع مدیریت، پایش و تحلیل داده‌های مزارع نیشکر با استفاده از تصاویر ماهواره‌ای و هوش مصنوعی</p>', unsafe_allow_html=True)
-st.markdown('</div>', unsafe_allow_html=True)
-
-# Navigation menu
+# --- Main UI ---
+st.markdown('<div class="main-header animate-load"><h1>سامانه هوشمند پایش مزارع نیشکر دهخدا</h1><p>پلتفرم جامع مدیریت و پایش مزارع نیشکر</p></div>', unsafe_allow_html=True)
 selected = option_menu(
-    menu_title=None,
-    options=["داشبورد", "نقشه مزارع", "ورود اطلاعات", "تحلیل داده‌ها", "گزارش‌گیری", "تنظیمات"],
-    icons=["speedometer2", "map", "pencil-square", "graph-up", "file-earmark-text", "gear"],
-    default_index=0,
-    orientation="horizontal",
-    styles={
-        "container": {"padding": "0!important", "background-color": "transparent", "margin-bottom": "20px"},
-        "icon": {"color": "#1a8754", "font-size": "18px"}, 
-        "nav-link": {"font-size": "16px", "text-align": "center", "margin":"0px", "--hover-color": "#e9f7ef", "border-radius": "10px"},
-        "nav-link-selected": {"background-color": "#1a8754", "color": "white", "font-weight": "600"},
-    }
+    menu_title=None, options=["داشبورد", "نقشه مزارع", "ورود اطلاعات", "تحلیل داده‌ها", "گزارش‌گیری", "تنظیمات"],
+    icons=["speedometer2", "map", "pencil-square", "graph-up", "file-earmark-text", "gear"], default_index=0, orientation="horizontal",
+    styles={"container": {"padding": "0!important", "background-color": "transparent", "margin-bottom": "20px"}, "icon": {"color": "#1a8754", "font-size": "18px"},
+            "nav-link": {"font-size": "16px", "text-align": "center", "margin": "0px", "--hover-color": "#e9f7ef", "border-radius": "10px"}, "nav-link-selected": {"background-color": "#1a8754", "color": "white", "font-weight": "600"}}
 )
 
-# Dashboard
+# --- Dashboard ---
 if selected == "داشبورد":
     st.markdown('<div class="animate-load">', unsafe_allow_html=True)
     col1, col2, col3, col4 = st.columns(4)
+    for col, value, label in [(col1, len(farm_df), "تعداد مزارع"), (col2, int(len(farm_df) * 0.85), "مزارع فعال"), (col3, 175, "میانگین ارتفاع (cm)"), (col4, 68, "میانگین رطوبت (%)")]:
+        col.markdown(f'<div class="metric-card"><div class="metric-value">{value}</div><div class="metric-label">{label}</div></div>', unsafe_allow_html=True)
     
-    with col1:
-        st.markdown('<div class="metric-card">', unsafe_allow_html=True)
-        st.markdown(f'<div class="metric-value">{len(farm_df)}</div>', unsafe_allow_html=True)
-        st.markdown('<div class="metric-label">تعداد مزارع</div>', unsafe_allow_html=True)
-        st.markdown('</div>', unsafe_allow_html=True)
-    
-    with col2:
-        active_farms = int(len(farm_df) * 0.85)
-        st.markdown('<div class="metric-card">', unsafe_allow_html=True)
-        st.markdown(f'<div class="metric-value">{active_farms}</div>', unsafe_allow_html=True)
-        st.markdown('<div class="metric-label">مزارع فعال</div>', unsafe_allow_html=True)
-        st.markdown('</div>', unsafe_allow_html=True)
-    
-    with col3:
-        avg_height = 175
-        st.markdown('<div class="metric-card">', unsafe_allow_html=True)
-        st.markdown(f'<div class="metric-value">{avg_height} cm</div>', unsafe_allow_html=True)
-        st.markdown('<div class="metric-label">میانگین ارتفاع</div>', unsafe_allow_html=True)
-        st.markdown('</div>', unsafe_allow_html=True)
-    
-    with col4:
-        avg_moisture = 68
-        st.markdown('<div class="metric-card">', unsafe_allow_html=True)
-        st.markdown(f'<div class="metric-value">{avg_moisture}%</div>', unsafe_allow_html=True)
-        st.markdown('<div class="metric-label">میانگین رطوبت</div>', unsafe_allow_html=True)
-        st.markdown('</div>', unsafe_allow_html=True)
-    
-    # Interactive Dashboard Filters
-    st.markdown("### فیلترهای داشبورد")
+    st.markdown("### فیلترها")
     col_filter1, col_filter2, col_filter3 = st.columns(3)
-    with col_filter1:
-        variety_filter = st.multiselect("واریته", ["همه"] + list(farm_df['واریته'].unique()), default="همه")
-    with col_filter2:
-        age_filter = st.multiselect("سن", ["همه"] + list(farm_df['سن'].unique()), default="همه")
-    with col_filter3:
-        channel_filter = st.multiselect("کانال", ["همه"] + list(farm_df['کانال'].unique()), default="همه")
-    
-    filtered_df = farm_df
-    if "همه" not in variety_filter:
-        filtered_df = filtered_df[filtered_df['واریته'].isin(variety_filter)]
-    if "همه" not in age_filter:
-        filtered_df = filtered_df[filtered_df['سن'].isin(age_filter)]
-    if "همه" not in channel_filter:
-        filtered_df = filtered_df[filtered_df['کانال'].isin(channel_filter)]
+    filters = [col_filter1.multiselect("واریته", ["همه"] + list(farm_df['واریته'].unique()), default="همه"),
+               col_filter2.multiselect("سن", ["همه"] + list(farm_df['سن'].unique()), default="همه"),
+               col_filter3.multiselect("کانال", ["همه"] + list(farm_df['کانال'].unique()), default="همه")]
+    filtered_df = farm_df[([(v in filters[0]) for v in farm_df['واریته']] if "همه" not in filters[0] else farm_df.index) &
+                         ([(a in filters[1]) for a in farm_df['سن']] if "همه" not in filters[1] else farm_df.index) &
+                         ([(c in filters[2]) for c in farm_df['کانال']] if "همه" not in filters[2] else farm_df.index)]
     
     tab1, tab2, tab3, tab4 = st.tabs(["نمای کلی", "نقشه مزارع", "نمودارها", "داده‌ها"])
-    
     with tab1:
-        st.markdown("### توزیع واریته‌ها و سن محصول")
         col1, col2 = st.columns(2)
-        with col1:
-            variety_counts = filtered_df['واریته'].value_counts().reset_index()
-            variety_counts.columns = ['واریته', 'تعداد']
-            fig = px.pie(variety_counts, values='تعداد', names='واریته', title='توزیع واریته‌ها', color_discrete_sequence=px.colors.sequential.Greens_r)
-            st.plotly_chart(fig, use_container_width=True)
-        with col2:
-            age_counts = filtered_df['سن'].value_counts().reset_index()
-            age_counts.columns = ['سن', 'تعداد']
-            fig = px.pie(age_counts, values='تعداد', names='سن', title='توزیع سن محصول', color_discrete_sequence=px.colors.sequential.Blues_r)
-            st.plotly_chart(fig, use_container_width=True)
-        
-        st.markdown("### اطلاعات کلی مزارع")
-        total_area = filtered_df['مساحت'].astype(float).sum()
+        with col1: st.plotly_chart(px.pie(filtered_df['واریته'].value_counts().reset_index(), values='count', names='واریته', title='توزیع واریته‌ها', color_discrete_sequence=px.colors.sequential.Greens_r), use_container_width=True)
+        with col2: st.plotly_chart(px.pie(filtered_df['سن'].value_counts().reset_index(), values='count', names='سن', title='توزیع سن محصول', color_discrete_sequence=px.colors.sequential.Blues_r), use_container_width=True)
         col1, col2, col3 = st.columns(3)
-        col1.metric("تعداد کل مزارع", f"{len(filtered_df)}")
-        col2.metric("مساحت کل (هکتار)", f"{total_area:.2f}")
-        col3.metric("تعداد کانال‌ها", f"{filtered_df['کانال'].nunique()}")
-        st_lottie(lottie_farm, height=300, key="farm_animation")
-    
+        col1.metric("تعداد مزارع", len(filtered_df))
+        col2.metric("مساحت کل (هکتار)", f"{filtered_df['مساحت'].astype(float).sum():.2f}")
+        col3.metric("تعداد کانال‌ها", filtered_df['کانال'].nunique())
+        st_lottie(lottie_farm, height=300)
     with tab2:
-        st.markdown("### نقشه مزارع")
         if not coordinates_df.empty:
             m = folium.Map(location=[31.45, 48.72], zoom_start=12, tiles='CartoDB positron')
             for _, farm in coordinates_df.iterrows():
-                lat, lon = farm['عرض جغرافیایی'], farm['طول جغرافیایی']
-                name = farm['مزرعه']
-                farm_info = filtered_df[filtered_df['مزرعه'] == name]
-                if not farm_info.empty:
-                    popup_text = f"""
-                    <div style="direction: rtl;">
-                        <h4>مزرعه {name}</h4>
-                        <p>واریته: {farm_info['واریته'].iloc[0]}</p>
-                        <p>سن: {farm_info['سن'].iloc[0]}</p>
-                        <p>مساحت: {farm_info['مساحت'].iloc[0]} هکتار</p>
-                    </div>
-                    """
-                    folium.Marker([lat, lon], popup=folium.Popup(popup_text, max_width=300), tooltip=f"مزرعه {name}", icon=folium.Icon(color='green', icon='leaf')).add_to(m)
+                if farm['مزرعه'] in filtered_df['مزرعه'].values:
+                    farm_info = filtered_df[filtered_df['مزرعه'] == farm['مزرعه']].iloc[0]
+                    popup_text = f"<div style='direction: rtl;'><h4>مزرعه {farm['مزرعه']}</h4><p>واریته: {farm_info['واریته']}</p><p>سن: {farm_info['سن']}</p><p>مساحت: {farm_info['مساحت']} هکتار</p></div>"
+                    folium.Marker([farm['عرض جغرافیایی'], farm['طول جغرافیایی']], popup=folium.Popup(popup_text, max_width=300), tooltip=f"مزرعه {farm['مزرعه']}", icon=folium.Icon(color='green', icon='leaf')).add_to(m)
             st.markdown('<div class="map-container">', unsafe_allow_html=True)
             folium_static(m, width=1000, height=600)
             st.markdown('</div>', unsafe_allow_html=True)
-    
     with tab3:
-        st.markdown("### نمودار رشد هفتگی")
         growth_data = generate_mock_growth_data(filtered_df)
         chart_tab1, chart_tab2 = st.tabs(["میانگین رشد", "رشد مزارع فردی"])
-        with chart_tab1:
-            fig = go.Figure()
-            fig.add_trace(go.Scatter(x=growth_data['average']['weeks'], y=growth_data['average']['heights'], mode='lines+markers', name='میانگین رشد', line=dict(color='#1a8754', width=3)))
-            fig.update_layout(title='میانگین رشد هفتگی', xaxis_title='هفته', yaxis_title='ارتفاع (سانتی‌متر)', font=dict(family='Vazirmatn'))
-            st.plotly_chart(fig, use_container_width=True)
-        with chart_tab2:
-            fig = go.Figure()
-            for i, farm_data in enumerate(growth_data['individual'][:5]):
-                fig.add_trace(go.Scatter(x=farm_data['weeks'], y=farm_data['heights'], mode='lines+markers', name=f"مزرعه {farm_data['farm_id']}"))
-            fig.update_layout(title='رشد هفتگی مزارع فردی', xaxis_title='هفته', yaxis_title='ارتفاع (سانتی‌متر)', font=dict(family='Vazirmatn'))
+        with chart_tab1: st.plotly_chart(go.Figure(go.Scatter(x=growth_data['average']['weeks'], y=growth_data['average']['heights'], mode='lines+markers', name='میانگین رشد', line=dict(color='#1a8754', width=3))).update_layout(title='میانگین رشد هفتگی', xaxis_title='هفته', yaxis_title='ارتفاع (cm)', font=dict(family='Vazirmatn')), use_container_width=True)
+        with chart_tab2: 
+            fig = go.Figure([go.Scatter(x=farm_data['weeks'], y=farm_data['heights'], mode='lines+markers', name=f"مزرعه {farm_data['farm_id']}") for farm_data in growth_data['individual'][:5]])
+            fig.update_layout(title='رشد هفتگی مزارع فردی', xaxis_title='هفته', yaxis_title='ارتفاع (cm)', font=dict(family='Vazirmatn'))
             st.plotly_chart(fig, use_container_width=True)
-    
-    with tab4:
-        st.markdown("### داده‌های مزارع")
-        st.dataframe(filtered_df, use_container_width=True, height=400, hide_index=True)
+    with tab4: st.dataframe(filtered_df, use_container_width=True, height=400, hide_index=True)
     st.markdown('</div>', unsafe_allow_html=True)
 
-# Map Page
+# --- Map ---
 elif selected == "نقشه مزارع":
     st.markdown('<div class="animate-load">', unsafe_allow_html=True)
     st.markdown("## نقشه مزارع با شاخص‌های ماهواره‌ای")
     col1, col2 = st.columns([1, 3])
     with col1:
-        st.markdown('<div class="glass-card">', unsafe_allow_html=True)
         selected_farm = st.selectbox("انتخاب مزرعه", options=coordinates_df['مزرعه'].tolist(), format_func=lambda x: f"مزرعه {x}")
         selected_date = st.date_input("انتخاب تاریخ", value=datetime.now())
-        selected_layer = st.selectbox("انتخاب شاخص", options=["NDVI", "NDMI", "EVI", "NDWI", "SoilMoisture"], format_func=lambda x: {"NDVI": "شاخص پوشش گیاهی (NDVI)", "NDMI": "شاخص رطوبت (NDMI)", "EVI": "شاخص پیشرفته گیاهی (EVI)", "NDWI": "شاخص آب (NDWI)", "SoilMoisture": "رطوبت خاک (Soil Moisture)"}[x])
-        heatmap_toggle = st.checkbox("نمایش نقشه حرارتی", value=False)
-        generate_map = st.button("تولید نقشه", type="primary", use_container_width=True)
-        st.markdown('</div>', unsafe_allow_html=True)
-    
+        selected_layer = st.selectbox("انتخاب شاخص", options=["NDVI", "NDMI", "EVI", "NDWI", "SoilMoisture"], format_func=lambda x: {"NDVI": "NDVI", "NDMI": "NDMI", "EVI": "EVI", "NDWI": "NDWI", "SoilMoisture": "رطوبت خاک"}[x])
+        heatmap_toggle = st.checkbox("نمایش نقشه حرارتی")
+        generate_map = st.button("تولید نقشه", type="primary")
     with col2:
         map_tab, stats_tab = st.tabs(["نقشه", "آمار و تحلیل"])
         with map_tab:
             if generate_map or 'last_map' not in st.session_state:
                 with st.spinner('در حال تولید نقشه...'):
-                    m = create_ee_map(selected_farm, selected_date.strftime('%Y-%m-%d'), selected_layer, heatmap=heatmap_toggle)
+                    m = create_ee_map(selected_farm, selected_date.strftime('%Y-%m-%d'), coordinates_df, selected_layer, heatmap_toggle)
                     if m:
                         st.session_state.last_map = m
                         folium_static(m, width=800, height=600)
-                        st.success(f"نقشه {selected_layer} برای مزرعه {selected_farm} تولید شد.")
+                        st.success(f"نقشه {selected_layer} تولید شد.")
             elif 'last_map' in st.session_state:
                 folium_static(st.session_state.last_map, width=800, height=600)
-        
         with stats_tab:
             if 'last_map' in st.session_state:
                 stats = calculate_farm_stats(selected_farm, selected_layer)
                 col1, col2, col3, col4 = st.columns(4)
-                with col1: st.metric(f"میانگین {selected_layer}", stats["mean"])
-                with col2: st.metric(f"حداکثر {selected_layer}", stats["max"])
-                with col3: st.metric(f"حداقل {selected_layer}", stats["min"])
-                with col4: st.metric("انحراف معیار", stats["std_dev"])
-                
-                if stats['stress_alerts']:
-                    for alert in stats['stress_alerts']:
-                        st.warning(alert)
-                
-                fig = px.histogram(x=stats["histogram_data"], nbins=20, title=f"توزیع مقادیر {selected_layer}", labels={"x": f"مقدار {selected_layer}", "y": "فراوانی"})
-                st.plotly_chart(fig, use_container_width=True)
-                
+                for col, label, value in [(col1, f"میانگین {selected_layer}", stats["mean"]), (col2, f"حداکثر {selected_layer}", stats["max"]), (col3, f"حداقل {selected_layer}", stats["min"]), (col4, "انحراف معیار", stats["std_dev"])]:
+                    col.metric(label, value)
+                for alert in stats['stress_alerts']: st.warning(alert)
+                st.plotly_chart(px.histogram(x=stats["histogram_data"], nbins=20, title=f"توزیع {selected_layer}", labels={"x": selected_layer, "y": "فراوانی"}), use_container_width=True)
                 st.markdown("### تحلیل سری زمانی")
                 period = st.selectbox("بازه زمانی", ["weekly", "monthly", "seasonal"], format_func=lambda x: {"weekly": "هفتگی", "monthly": "ماهانه", "seasonal": "فصلی"}[x])
                 ts_data = generate_time_series_data(selected_farm, selected_layer, period)
-                fig = px.line(ts_data, x='Date', y=selected_layer, title=f"روند تغییرات {selected_layer}")
-                st.plotly_chart(fig, use_container_width=True)
+                st.plotly_chart(px.line(ts_data, x='Date', y=selected_layer, title=f"روند {selected_layer}"), use_container_width=True)
     st.markdown('</div>', unsafe_allow_html=True)
 
-# Data Entry Page
+# --- Data Entry ---
 elif selected == "ورود اطلاعات":
     st.markdown('<div class="animate-load">', unsafe_allow_html=True)
-    st.markdown("## ورود اطلاعات روزانه مزارع")
+    st.markdown("## ورود اطلاعات روزانه")
     tab1, tab2 = st.tabs(["ورود دستی", "آپلود فایل"])
     with tab1:
         col1, col2 = st.columns(2)
-        with col1:
-            selected_week = st.selectbox("انتخاب هفته", [str(i) for i in range(1, 23)], format_func=lambda x: f"هفته {x}")
-        with col2:
-            selected_day = st.selectbox("انتخاب روز", ["شنبه", "یکشنبه", "دوشنبه", "سه‌شنبه", "چهارشنبه", "پنجشنبه"])
-        
+        selected_week, selected_day = col1.selectbox("انتخاب هفته", [str(i) for i in range(1, 23)], format_func=lambda x: f"هفته {x}"), col2.selectbox("انتخاب روز", ["شنبه", "یکشنبه", "دوشنبه", "سه‌شنبه", "چهارشنبه", "پنجشنبه"])
         filtered_farms = farm_df[farm_df['روز'] == selected_day]
         data_key = f"data_{selected_week}_{selected_day}"
         if data_key not in st.session_state:
-            st.session_state[data_key] = pd.DataFrame({
-                'مزرعه': filtered_farms['مزرعه'],
-                'ایستگاه 1': [0] * len(filtered_farms),
-                'ایستگاه 2': [0] * len(filtered_farms),
-                'ایستگاه 3': [0] * len(filtered_farms),
-                'ایستگاه 4': [0] * len(filtered_farms),
-                'ایستگاه 5': [0] * len(filtered_farms),
-                'چاهک 1': [0] * len(filtered_farms),
-                'چاهک 2': [0] * len(filtered_farms),
-                'رطوبت غلاف': [0] * len(filtered_farms),
-                'نیتروژن': [0] * len(filtered_farms),
-                'میانگین ارتفاع': [0] * len(filtered_farms)
-            })
-        
+            st.session_state[data_key] = pd.DataFrame({col: [0 if col != 'مزرعه' else farm for farm in filtered_farms['مزرعه']] for col in ['مزرعه', 'ایستگاه 1', 'ایستگاه 2', 'ایستگاه 3', 'ایستگاه 4', 'ایستگاه 5', 'چاهک 1', 'چاهک 2', 'رطوبت غلاف', 'نیتروژن', 'میانگین ارتفاع']})
         edited_df = st.data_editor(st.session_state[data_key], use_container_width=True)
-        for i in range(len(edited_df)):
-            stations = [edited_df.iloc[i][f'ایستگاه {j}'] for j in range(1, 6)]
-            valid_stations = [s for s in stations if s > 0]
-            if valid_stations:
-                edited_df.iloc[i, edited_df.columns.get_loc('میانگین ارتفاع')] = round(sum(valid_stations) / len(valid_stations), 1)
+        edited_df['میانگین ارتفاع'] = [round(np.mean([s for s in row[1:6] if s > 0])) if any(s > 0 for s in row[1:6]) else 0 for row in edited_df.iloc[:, 1:6].values]
         st.session_state[data_key] = edited_df
-        
         if st.button("ذخیره اطلاعات", type="primary"):
             new_data = edited_df.copy()
-            new_data['Farm_ID'] = new_data['مزرعه']
-            new_data['Week'] = int(selected_week)
-            new_data['Measurement_Date'] = (datetime.now() - timedelta(weeks=(22 - int(selected_week)))).strftime('%Y-%m-%d')
-            new_data['Height'] = new_data['میانگین ارتفاع']
+            new_data['Farm_ID'], new_data['Week'], new_data['Measurement_Date'], new_data['Height'] = new_data['مزرعه'], int(selected_week), (datetime.now() - timedelta(weeks=(22 - int(selected_week)))).strftime('%Y-%m-%d'), new_data['میانگین ارتفاع']
             new_data = new_data.merge(farm_df[['مزرعه', 'واریته', 'سن', 'مساحت', 'کانال', 'اداره']], left_on='Farm_ID', right_on='مزرعه', how='left')
             st.session_state.heights_df = pd.concat([st.session_state.heights_df, new_data], ignore_index=True)
             st.success(f"داده‌های هفته {selected_week} ذخیره شدند.")
     with tab2:
-        uploaded_file = st.file_uploader("فایل اکسل خود را آپلود کنید", type=["xlsx", "xls", "csv"])
+        uploaded_file = st.file_uploader("فایل اکسل یا CSV", type=["xlsx", "xls", "csv"])
         if uploaded_file:
             df = pd.read_csv(uploaded_file) if uploaded_file.name.endswith('.csv') else pd.read_excel(uploaded_file)
             st.dataframe(df)
             if st.button("ذخیره فایل"): st.success("فایل ذخیره شد.")
     st.markdown('</div>', unsafe_allow_html=True)
 
-# Data Analysis Page
+# --- Data Analysis ---
 elif selected == "تحلیل داده‌ها":
     st.markdown('<div class="animate-load">', unsafe_allow_html=True)
     st.markdown("## تحلیل هوشمند داده‌ها")
     tab1, tab2, tab3, tab4 = st.tabs(["تحلیل رشد", "مقایسه واریته‌ها", "تحلیل رطوبت", "پیش‌بینی"])
-    
     with tab1:
         growth_data = generate_mock_growth_data(farm_df)
-        chart_data = []
-        for farm_data in growth_data['individual']:
-            for i, week in enumerate(farm_data['weeks']):
-                chart_data.append({'Farm': farm_data['farm_id'], 'Week': week, 'Height': farm_data['heights'][i]})
-        chart_df = pd.DataFrame(chart_data)
-        chart = alt.Chart(chart_df).mark_line(point=True).encode(x='Week:Q', y='Height:Q', color='Farm:N').interactive()
-        st.altair_chart(chart, use_container_width=True)
-    
+        chart_df = pd.DataFrame([{'Farm': farm['farm_id'], 'Week': week, 'Height': height} for farm in growth_data['individual'] for week, height in zip(farm['weeks'], farm['heights'])])
+        st.altair_chart(alt.Chart(chart_df).mark_line(point=True).encode(x='Week:Q', y='Height:Q', color='Farm:N').interactive(), use_container_width=True)
     with tab2:
         variety_heights = {variety: np.random.normal(150, 20, 100) for variety in farm_df['واریته'].unique()}
-        fig = go.Figure()
-        for variety in variety_heights:
-            fig.add_trace(go.Box(y=variety_heights[variety], name=variety))
-        fig.update_layout(title='مقایسه ارتفاع بر اساس واریته', yaxis_title='ارتفاع (سانتی‌متر)', font=dict(family="Vazirmatn"))
+        fig = go.Figure([go.Box(y=heights, name=variety) for variety, heights in variety_heights.items()])
+        fig.update_layout(title='مقایسه ارتفاع بر اساس واریته', yaxis_title='ارتفاع (cm)', font=dict(family="Vazirmatn"))
         st.plotly_chart(fig, use_container_width=True)
-    
     with tab3:
-        farms = farm_df['مزرعه'].unique()[:10]
-        dates = pd.date_range(end=datetime.now(), periods=30)
-        moisture_data = [{'Farm': farm, 'Date': date, 'Moisture': max(0, min(100, np.random.uniform(50, 80) + np.random.normal(0, 5)))} for farm in farms for date in dates]
-        moisture_df = pd.DataFrame(moisture_data)
-        fig = px.line(moisture_df, x='Date', y='Moisture', color='Farm', title='روند رطوبت مزارع')
-        
-        # Correlation analysis
-        correlation_data = [{'Moisture': m, 'Height': 100 + m * 1.5 + np.random.normal(0, 20)} for m in moisture_df['Moisture']]
-        corr_df = pd.DataFrame(correlation_data)
-        fig_corr = px.scatter(corr_df, x='Moisture', y='Height', title='همبستگی رطوبت و ارتفاع', trendline='ols')
-        st.plotly_chart(fig, use_container_width=True)
-        st.plotly_chart(fig_corr, use_container_width=True)
+        moisture_df = pd.DataFrame([{'Farm': farm, 'Date': date, 'Moisture': max(0, min(100, np.random.uniform(50, 80) + np.random.normal(0, 5)))} for farm in farm_df['مزرعه'].unique()[:10] for date in pd.date_range(end=datetime.now(), periods=30)])
+        st.plotly_chart(px.line(moisture_df, x='Date', y='Moisture', color='Farm', title='روند رطوبت مزارع'), use_container_width=True)
+        corr_df = pd.DataFrame({'Moisture': moisture_df['Moisture'], 'Height': moisture_df['Moisture'] * 1.5 + np.random.normal(0, 20, len(moisture_df))})
+        st.plotly_chart(px.scatter(corr_df, x='Moisture', y='Height', title='همبستگی رطوبت و ارتفاع', trendline='ols'), use_container_width=True)
         st.info(f"ضریب همبستگی: {corr_df['Moisture'].corr(corr_df['Height']):.2f}")
-    
     with tab4:
         selected_farm = st.selectbox("انتخاب مزرعه", options=farm_df['مزرعه'].tolist(), format_func=lambda x: f"مزرعه {x}")
-        weeks = list(range(1, 16))
-        heights = [50 + i * 10 + np.random.normal(0, 5) for i in weeks]
-        historical_df = pd.DataFrame({'Week': weeks, 'Height': heights})
-        rf_preds, lstm_preds = predict_growth_advanced(selected_farm, historical_df)
-        future_weeks = list(range(16, 23))
-        
-        fig = go.Figure()
-        fig.add_trace(go.Scatter(x=weeks, y=heights, mode='lines+markers', name='داده‌های تاریخی'))
-        fig.add_trace(go.Scatter(x=future_weeks, y=rf_preds, mode='lines+markers', name='پیش‌بینی Random Forest', line=dict(dash='dash')))
-        fig.add_trace(go.Scatter(x=future_weeks, y=lstm_preds, mode='lines+markers', name='پیش‌بینی LSTM', line=dict(dash='dot')))
-        fig.update_layout(title=f'پیش‌بینی رشد مزرعه {selected_farm}', xaxis_title='هفته', yaxis_title='ارتفاع (سانتی‌متر)', font=dict(family='Vazirmatn'))
+        historical_df = pd.DataFrame({'Week': range(1, 16), 'Height': [50 + i * 10 + np.random.normal(0, 5) for i in range(15)]})
+        rf_preds, lstm_preds = predict_growth_advanced(historical_df)
+        fig = go.Figure([go.Scatter(x=historical_df['Week'], y=historical_df['Height'], mode='lines+markers', name='داده‌های تاریخی'),
+                         go.Scatter(x=range(16, 23), y=rf_preds, mode='lines+markers', name='پیش‌بینی RF', line=dict(dash='dash')),
+                         go.Scatter(x=range(16, 23), y=lstm_preds, mode='lines+markers', name='پیش‌بینی LSTM', line=dict(dash='dot'))])
+        fig.update_layout(title=f'پیش‌بینی رشد مزرعه {selected_farm}', xaxis_title='هفته', yaxis_title='ارتفاع (cm)', font=dict(family='Vazirmatn'))
         st.plotly_chart(fig, use_container_width=True)
-        
-        # Clustering
         clustered_df, centers = cluster_farms(farm_df)
-        fig = px.scatter(clustered_df, x='مساحت', y='سن', color='Cluster', title='گروه‌بندی مزارع', labels={'مساحت': 'مساحت (هکتار)', 'سن': 'سن (سال)'})
-        st.plotly_chart(fig, use_container_width=True)
+        st.plotly_chart(px.scatter(clustered_df, x='مساحت', y='سن', color='Cluster', title='گروه‌بندی مزارع', labels={'مساحت': 'مساحت (هکتار)', 'سن': 'سن (سال)'}), use_container_width=True)
     st.markdown('</div>', unsafe_allow_html=True)
 
-# Reporting Page
+# --- Reporting ---
 elif selected == "گزارش‌گیری":
     st.markdown('<div class="animate-load">', unsafe_allow_html=True)
     st.markdown("## گزارش‌گیری پیشرفته")
-    start_date = st.date_input("تاریخ شروع", value=datetime.now() - timedelta(days=30))
-    end_date = st.date_input("تاریخ پایان", value=datetime.now())
+    start_date, end_date = st.date_input("تاریخ شروع", value=datetime.now() - timedelta(days=30)), st.date_input("تاریخ پایان", value=datetime.now())
     report_type = st.selectbox("نوع گزارش", ["گزارش کلی", "گزارش رشد", "گزارش رطوبت", "گزارش مقایسه‌ای واریته‌ها"])
     if st.button("تولید گزارش"):
         with st.spinner('در حال تولید گزارش...'):
-            time.sleep(2)
+            time.sleep(1)  # Reduced for speed
             if report_type == "گزارش کلی":
-                st.markdown("### گزارش کلی وضعیت مزارع")
+                st.markdown("### گزارش کلی")
                 col1, col2 = st.columns(2)
-                with col1:
-                    fig = px.pie(values=farm_df['اداره'].value_counts().values, names=farm_df['اداره'].value_counts().index, title='توزیع مزارع بر اساس اداره')
-                    st.plotly_chart(fig)
-                with col2:
-                    weeks = list(range(1, 23))
-                    heights = [100 + i * 5 + np.random.normal(0, 10) for i in weeks]
-                    fig = px.line(x=weeks, y=heights, title='روند رشد کلی مزارع', labels={'x': 'هفته', 'y': 'ارتفاع (سانتی‌متر)'})
-                    st.plotly_chart(fig)
+                with col1: st.plotly_chart(px.pie(values=farm_df['اداره'].value_counts().values, names=farm_df['اداره'].value_counts().index, title='توزیع مزارع بر اساس اداره'))
+                with col2: st.plotly_chart(px.line(x=range(1, 23), y=[100 + i * 5 + np.random.normal(0, 10) for i in range(22)], title='روند رشد کلی', labels={'x': 'هفته', 'y': 'ارتفاع (cm)'}))
     st.markdown('</div>', unsafe_allow_html=True)
 
-# Settings Page
+# --- Settings ---
 elif selected == "تنظیمات":
     st.markdown('<div class="animate-load">', unsafe_allow_html=True)
-    st.markdown("## تنظیمات سیستم")
+    st.markdown("## تنظیمات")
     tab1, tab2 = st.tabs(["تنظیمات کاربری", "تنظیمات سیستم"])
-    with tab1:
-        user_name = st.text_input("نام کاربری", value="کاربر نمونه")
-        user_email = st.text_input("ایمیل", value="[email protected]")
-    with tab2:
-        system_language = st.selectbox("زبان سیستم", ["فارسی", "English", "العربية"])
-        date_format = st.selectbox("فرمت تاریخ", ["YYYY/MM/DD", "DD/MM/YYYY", "MM/DD/YYYY"])
+    with tab1: st.text_input("نام کاربری", value="کاربر نمونه"), st.text_input("ایمیل", value="[email protected]")
+    with tab2: st.selectbox("زبان سیستم", ["فارسی", "English", "العربية"]), st.selectbox("فرمت تاریخ", ["YYYY/MM/DD", "DD/MM/YYYY", "MM/DD/YYYY"])
     st.markdown('</div>', unsafe_allow_html=True)
 
-# Footer
+# --- Footer ---
 st.markdown("""
 <footer style="position: fixed; left: 0; bottom: 0; width: 100%; background-color: #1a8754; color: white; text-align: center; padding: 10px 0;">
-    <p>© سامانه هوشمند پایش مزارع نیشکر کشت و صنعت دهخدا | طراحی شده توسط تیم مطالعات کاربردی توسعه</p>
+    <p>© سامانه هوشمند پایش مزارع نیشکر دهخدا | طراحی شده توسط تیم مطالعات کاربردی توسعه</p>
 </footer>
 """, unsafe_allow_html=True)
 st.markdown('</body>', unsafe_allow_html=True)