Create app.py

app.py

@@ -0,0 +1,76 @@
+import pandas as pd
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.compose import ColumnTransformer
+from sklearn.pipeline import Pipeline
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+import gradio as gr
+import ee
+import folium
+
+# Setup Earth Engine
+service_account = 'earth-engine-service-account@ee-esmaeilkiani1387.iam.gserviceaccount.com'  # Replace with your service account
+credentials = ee.ServiceAccountCredentials(service_account, 'ee-esmaeilkiani1387-1b2c5e812a1d.json')  # Replace with your credentials file
+ee.Initialize(credentials)
+
+# Load and preprocess data
+data = pd.read_csv('merged_data_for_model.csv')  # Replace with your data file path
+features = ['Age', 'Variety', 'Date']
+target = ['Brix', 'Purity', 'Pol', 'RS']
+X = data[features]
+y = data[target]
+
+numerical_features = ['Age']
+categorical_features = ['Variety']
+preprocessor = ColumnTransformer(
+    transformers=[
+        ('num', StandardScaler(), numerical_features),
+        ('cat', OneHotEncoder(handle_unknown='ignore', sparse_output=False), categorical_features),
+    ])
+
+X['Date'] = pd.to_datetime(X['Date']).astype(int) / 10**9
+
+# Model pipeline
+pipeline = Pipeline([
+    ('preprocessor', preprocessor),
+    ('regressor', LinearRegression()),
+])
+
+# Split data and train model
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+pipeline.fit(X_train, y_train)
+
+
+def predict_brix_purity_pol_rs(farm_name, age, variety, date):
+    # Convert inputs to appropriate format
+    age = float(age)
+    date = pd.to_datetime(date).astype(int) / 10**9
+    input_data = pd.DataFrame([[age, variety, date]], columns=['Age', 'Variety', 'Date'])
+    
+    # Preprocess input data
+    input_data_processed = preprocessor.transform(input_data)
+
+    # Make prediction
+    prediction = pipeline.predict(input_data_processed)[0]
+
+    return prediction[0], prediction[1], prediction[2], prediction[3]
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict_brix_purity_pol_rs,
+    inputs=[
+        gr.Textbox(label="نام مزرعه"),
+        gr.Number(label="سن"),
+        gr.Textbox(label="واریته"),
+        gr.Textbox(label="تاریخ (YYYY-MM-DD)"),
+    ],
+    outputs=[
+        gr.Number(label="Brix"),
+        gr.Number(label="Purity"),
+        gr.Number(label="Pol"),
+        gr.Number(label="RS"),
+    ],
+    title="پیش‌بینی Brix، Purity، Pol و RS",
+)
+
+iface.launch()