Update pages/Prediction.py

pages/Prediction.py

@@ -1,50 +1,53 @@
 import pickle
-import requests
+import numpy as np
+import streamlit as st
+
+# Load the trained model
 with open("model.pkl", "rb") as file:
     model = pickle.load(file)
 
+# Function to take user inputs from text input fields with explanations
+def get_user_input():
+    st.sidebar.header('Enter Input Parameters')
 
+    # Soil Nutrients (Integer values)
+    nitrogen = st.sidebar.text_input('Nitrogen (N),'10')
+    phosphorus = st.sidebar.text_input('Phosphorus (P), '10')
+    potassium = st.sidebar.text_input('Potassium (K) , '10')
 
-# Define the feature names
-features = ['Nitrogen', 'Phosphorus', 'Potassium', 'Temperature', 'Humidity', 'pH_Value', 'Rainfall']
+    # Weather Conditions (Float values)
+    temperature = st.sidebar.text_input('Temperature (°C), '25.0')
+    humidity = st.sidebar.text_input('Humidity (%) , '60.0')
+    ph_value = st.sidebar.text_input('Soil pH , '7.0')
+    rainfall = st.sidebar.text_input('Rainfall (mm), '100.0')
+
+    # Convert input to correct data types
+    user_input = np.array([
+        int(nitrogen), int(phosphorus), int(potassium), 
+        float(temperature), float(humidity), float(ph_value), float(rainfall)
+    ]).reshape(1, -1)
 
-# Function to take user inputs for the features using Streamlit sliders
-def get_user_input():
-    st.sidebar.header('User Input Parameters')
-    nitrogen = st.sidebar.slider('Nitrogen', min_value=0.0, max_value=200.0, value=10.0)
-    phosphorus = st.sidebar.slider('Phosphorus', min_value=0.0, max_value=200.0, value=10.0)
-    potassium = st.sidebar.slider('Potassium', min_value=0.0, max_value=200.0, value=10.0)
-    temperature = st.sidebar.slider('Temperature (°C)', min_value=0.0, max_value=50.0, value=25.0)
-    humidity = st.sidebar.slider('Humidity (%)', min_value=0.0, max_value=100.0, value=60.0)
-    ph_value = st.sidebar.slider('pH Value', min_value=0.0, max_value=14.0, value=7.0)
-    rainfall = st.sidebar.slider('Rainfall (mm)', min_value=0.0, max_value=500.0, value=100.0)
-
-    # Create a numpy array from the user input
-    user_input = np.array([nitrogen, phosphorus, potassium, temperature, humidity, ph_value, rainfall]).reshape(1, -1)
     return user_input
 
 # Get user input
 user_input = get_user_input()
 
-# Preprocessing the input data (Scaling using StandardScaler)
-scaler = StandardScaler()
-user_input_scaled = scaler.fit_transform(user_input)
-
 # Predict the crop using the model
-prediction = model.predict(user_input_scaled)
+prediction = model.predict(user_input)
 
 # Display the prediction
 st.title('Crop Prediction Application')
 st.write('### Crop Prediction Based on Input Parameters')
-st.write(f'Predicted Crop: {prediction[0]}')
-
-# Optionally display some more useful information
-st.write('### Input Parameters:')
-st.write(f'Nitrogen: {user_input[0][0]}')
-st.write(f'Phosphorus: {user_input[0][1]}')
-st.write(f'Potassium: {user_input[0][2]}')
-st.write(f'Temperature: {user_input[0][3]}')
-st.write(f'Humidity: {user_input[0][4]}')
-st.write(f'pH Value: {user_input[0][5]}')
-st.write(f'Rainfall: {user_input[0][6]}')
+st.write(f'Predicted Crop: **{prediction[0]}**')
+
+# Display input values
+st.write('### Input Parameters Entered:')
+st.write(f'**Nitrogen (N):** {user_input[0][0]}')
+st.write(f'**Phosphorus (P):** {user_input[0][1]}')
+st.write(f'**Potassium (K):** {user_input[0][2]} ')
+st.write(f'**Temperature (°C):** {user_input[0][3]} ')
+st.write(f'**Humidity (%):** {user_input[0][4]} ')
+st.write(f'**Soil pH:** {user_input[0][5]} ')
+st.write(f'**Rainfall (mm):** {user_input[0][6]}')
+