Create app.py

app.py

@@ -0,0 +1,47 @@
+import gradio as gr
+import pandas as pd
+import joblib
+import pickle
+
+# Load the trained model
+with open('Fertilizer_recommender.pkl', 'rb') as f:
+    model = pickle.load(f)
+
+# Step 4: Define prediction function with data preprocessing
+def recommend_fertilizer(temperature, humidity, moisture, soil_type, crop_type, nitrogen, phosphorous, potassium):
+    # Example mappings for soil type and crop type (replace with your actual mappings)
+    soil_type_mapping = {"Sandy": 1, "Clay": 2, "Loam": 3}
+    crop_type_mapping = {"Wheat": 1, "Rice": 2, "Maize": 3}
+
+    # Convert soil_type and crop_type to numerical values using the mappings
+    soil_type_numerical = soil_type_mapping.get(soil_type, -1)  # -1 for unknown soil type
+    crop_type_numerical = crop_type_mapping.get(crop_type, -1)  # -1 for unknown crop type
+
+    # Prepare the input data for the model
+    input_data = [[temperature, humidity, moisture, soil_type_numerical, crop_type_numerical, nitrogen, phosphorous, potassium]]
+
+    # Make the prediction
+    prediction = model.predict(input_data)
+    return prediction[0]
+
+# Step 5: Create Gradio interface
+iface = gr.Interface(
+    fn=recommend_fertilizer,
+    inputs=[
+        gr.Number(label="Temperature"),
+        gr.Number(label="Humidity"),
+        gr.Number(label="Moisture"),
+        gr.Textbox(label="Soil Type"),  # Use Textbox for soil type input
+        gr.Textbox(label="Crop Type"),   # Use Textbox for crop type input
+        gr.Number(label="Nitrogen"),
+        gr.Number(label="Phosphorous"),
+        gr.Number(label="Potassium"),
+    ],
+    outputs=gr.Text(label="Recommended Fertilizer"),
+    title="Fertilizer Recommender",
+    description="Enter the environmental and crop details to get the best fertilizer recommendation.",
+    api_name="/api/predict_fertilizer"
+)
+
+# Step 6: Launch the app with show_error enabled
+iface.launch(show_error=True) # Added show_error=True to see detailed error messages