Upload 3 files

IDS model version 2

XGBoost_Model_v1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e24dd8ae7e0b225b74239e64da6d8230f382fd7f4abeb611c9a68031bfdf9b7
+size 321731

app2.py

@@ -0,0 +1,167 @@
+import gradio as gr
+import joblib
+import numpy as np
+import pandas as pd
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.preprocessing import MinMaxScaler
+
+# Define the ScalableModel class
+class ScalableModel:
+    def __init__(self, model, feature_scaler=None, target_scaler=None):
+        self.model = model
+        self.feature_scaler = feature_scaler if feature_scaler else MinMaxScaler()
+        self.target_scaler = target_scaler if target_scaler else MinMaxScaler()
+    
+    def predict(self, X_test):
+        X_test_scaled = self.feature_scaler.transform(X_test)
+        predictions_scaled = self.model.predict(X_test_scaled).reshape(-1, 1)
+        return self.target_scaler.inverse_transform(predictions_scaled).flatten()
+
+# Load the trained model and scalers
+xgboost_model = joblib.load("XGBoost_Model_v1.pkl")  # Ensure the model is saved
+
+
+# Feature names (MUST match your training data exactly)
+feature_names = [
+    'garlic_kgs_organic_pesticides', #
+    'ginger_kgs_organic_pesticides', #
+    'plastic_tanks_120_ltrs_liquid_manure', #
+    'sacks_liquid_manure', #
+    'hoes_tools', #
+    'spades_tools', #
+    'pick_axes_tools', #
+    'forked_hoes_tools', #
+    'pangas_tools', #
+    'wheelbarrows_tools', #
+    'trowels_tools', #
+    'watering_cans_tools', #
+    'spray_pumps_tools', #
+    'Beans_seeds', #
+    'Maize_seeds', #
+    'Soyabean_seeds', #
+    'Gnuts_seeds', #
+    'Irish Potatoes_seeds', #
+    # 'Cassava (bags)',
+    # 'Mugavu tree seedlings',
+    # 'Onions (Kg)_seeds',
+    # 'Millet.1_seeds',
+    'GPS-Altitude',
+    'Land_size_agriculture',
+    'Time_to_collect_Water_for_Household_use_Minutes',
+    'Beans_total_yield', #
+    'Cassava_total_yield',
+    'Maize_total_yield',
+    'Sweet_potatoes_total_yield',
+    'Food_banana_total_yield',
+    'Coffee_total_yield'
+]
+
+
+# Define prediction function
+def predict_agriculture_value(*features):
+    input_data = np.array(features).reshape(1, -1)
+    # Check if all input values are zero
+    if np.all(input_data == 0):
+        return 0.0  # Return zero directly
+    
+    df_input = pd.DataFrame(input_data, columns=feature_names)
+    
+    # Use the model's built-in predict function
+    prediction = xgboost_model.predict(df_input)
+    
+    return float(prediction[0])
+
+# Create Gradio interface
+input_components = [gr.Number(label=feature) for feature in feature_names]
+
+iface = gr.Interface(
+    fn=predict_agriculture_value,
+    inputs=input_components,
+    outputs=gr.Number(label="Predicted Agriculture Value (USD)"),
+    title="Agriculture Value Prediction",
+    description="Enter input values to predict Agriculture Value (USD) using the trained XGBoost model."
+)
+
+# Run the Gradio app
+if __name__ == "__main__":
+    iface.launch()
+
+
+# # XGBoost Model
+
+# import gradio as gr
+# import joblib
+# import numpy as np
+# import pandas as pd
+# from xgboost import XGBRegressor
+# from sklearn.preprocessing import MinMaxScaler
+
+# # Define ScalableModel class
+# class ScalableModel:
+#     def __init__(self, model, feature_scaler=None, target_scaler=None):
+#         self.model = model
+#         self.feature_scaler = feature_scaler if feature_scaler else MinMaxScaler()
+#         self.target_scaler = target_scaler if target_scaler else MinMaxScaler()
+
+#     def fit(self, X_train, y_train):
+#         self.feature_scaler.fit(X_train)
+#         self.target_scaler.fit(y_train.values.reshape(-1, 1))
+#         self.model.fit(self.feature_scaler.transform(X_train), self.target_scaler.transform(y_train.values.reshape(-1, 1)).flatten())
+
+#     def predict(self, X_test):
+#         X_test_scaled = self.feature_scaler.transform(X_test)
+#         predictions_scaled = self.model.predict(X_test_scaled)
+#         return self.target_scaler.inverse_transform(predictions_scaled.reshape(-1, 1)).flatten()
+
+# # Load the trained XGBoost model
+# xgboost_model = joblib.load("XGBoost_Model_v1.pkl")
+
+# # Load the scalers
+# scalers = joblib.load("Scalers_XGBoost.pkl")
+# feature_scaler = scalers["feature_scaler"]
+# target_scaler = scalers["target_scaler"]
+
+# # Define feature names (must match training data)
+# feature_names = [
+#     'garlic_kgs_organic_pesticides', 'ginger_kgs_organic_pesticides',
+#     'plastic_tanks_120_ltrs_liquid_manure', 'sacks_liquid_manure',
+#     'hoes_tools', 'spades_tools', 'pick_axes_tools', 'forked_hoes_tools',
+#     'pangas_tools', 'wheelbarrows_tools', 'trowels_tools', 'watering_cans_tools',
+#     'spray_pumps_tools', 'Beans_seeds', 'Maize_seeds', 'Soyabean_seeds',
+#     'Gnuts_seeds', 'Irish Potatoes_seeds', 'GPS-Altitude', 'Land_size_agriculture',
+#     'Time_to_collect_Water_for_Household_use_Minutes', 'Beans_total_yield',
+#     'Cassava_total_yield', 'Maize_total_yield', 'Sweet_potatoes_total_yield',
+#     'Food_banana_total_yield', 'Coffee_total_yield'
+# ]
+
+# # Define prediction function
+# def predict_agriculture_value(*features):
+#     input_data = np.array(features).reshape(1, -1)
+
+#     # Scale the input features
+#     input_data_scaled = feature_scaler.transform(input_data)
+
+#     # Get scaled predictions
+#     prediction_scaled = xgboost_model.predict(input_data_scaled).reshape(-1, 1)
+
+#     # Inverse transform to get predictions in original scale
+#     prediction = target_scaler.inverse_transform(prediction_scaled).flatten()
+
+#     return float(prediction[0])
+
+# # Create Gradio interface
+# input_components = [gr.Number(label=feature) for feature in feature_names]
+
+# iface = gr.Interface(
+#     fn=predict_agriculture_value,
+#     inputs=input_components,
+#     outputs=gr.Number(label="Predicted Agriculture Value (USD)"),
+#     title="Agriculture Value Prediction",
+#     description="Enter input values to predict Agriculture Value (USD) using the trained XGBoost model."
+# )
+
+# # Run the Gradio app
+# if __name__ == "__main__":
+#     iface.launch()
+
+# print("Expected feature order:", feature_names)

requirements.txt

@@ -0,0 +1,48 @@
+asttokens==3.0.0
+comm==0.2.2
+contourpy==1.3.1
+cycler==0.12.1
+debugpy==1.8.13
+decorator==5.2.1
+et_xmlfile==2.0.0
+executing==2.2.0
+fonttools==4.56.0
+ipykernel==6.29.5
+ipython==9.0.2
+ipython_pygments_lexers==1.1.1
+jedi==0.19.2
+joblib==1.4.2
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+kiwisolver==1.4.8
+matplotlib==3.10.1
+matplotlib-inline==0.1.7
+nest-asyncio==1.6.0
+numpy==2.2.3
+openpyxl==3.1.5
+packaging==24.2
+pandas==2.2.3
+parso==0.8.4
+pexpect==4.9.0
+pillow==11.1.0
+platformdirs==4.3.6
+prompt_toolkit==3.0.50
+psutil==7.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+Pygments==2.19.1
+pyparsing==3.2.1
+python-dateutil==2.9.0.post0
+pytz==2025.1
+pyzmq==26.3.0
+scikit-learn==1.6.1
+scipy==1.15.2
+seaborn==0.13.2
+six==1.17.0
+stack-data==0.6.3
+threadpoolctl==3.5.0
+tornado==6.4.2
+traitlets==5.14.3
+tzdata==2025.1
+wcwidth==0.2.13
+gradio>=3.50.0