Update app.py

app.py

@@ -1,65 +1,44 @@
 import streamlit as st
-import pickle
 import pandas as pd
+import pickle
+from sklearn.preprocessing import LabelEncoder, StandardScaler, OneHotEncoder
+from sklearn.compose import ColumnTransformer
 from sklearn.pipeline import Pipeline
-import numpy as np
+from sklearn.neighbors import KNeighborsClassifier
 
-# Load the model and encoders
+# Load the saved model and encoders
 with open('model_penguin_706.pkl', 'rb') as file:
     model, species_encoder, island_encoder, sex_encoder = pickle.load(file)
 
-# Streamlit app layout
+# Create the Streamlit app
 st.title('Penguin Species Prediction')
 
-# Create user input fields
-st.sidebar.header('Input Features')
-
-# User inputs
-species = st.sidebar.selectbox('Species', species_encoder.classes_)
-island = st.sidebar.selectbox('Island', island_encoder.classes_)
-sex = st.sidebar.selectbox('Sex', sex_encoder.classes_)
-
-# Slider for numeric inputs
-bill_length_mm = st.sidebar.slider('Bill Length (mm)', 30.0, 60.0, 45.0)
-bill_depth_mm = st.sidebar.slider('Bill Depth (mm)', 10.0, 25.0, 18.0)
-flipper_length_mm = st.sidebar.slider('Flipper Length (mm)', 170.0, 240.0, 200.0)
-body_mass_g = st.sidebar.slider('Body Mass (g)', 2500.0, 6000.0, 4000.0)
-
-# Add missing columns with default values
-culmen_length_mm = 40.0  # Default value, update with realistic values if available
-culmen_depth_mm = 15.0  # Default value, update with realistic values if available
-
-# Prepare the input data (ensure columns are in the same order as expected by the model)
-input_data = pd.DataFrame({
-    'species': [species],
-    'island': [island],
-    'sex': [sex],
-    'bill_length_mm': [bill_length_mm],
-    'bill_depth_mm': [bill_depth_mm],
-    'flipper_length_mm': [flipper_length_mm],
-    'body_mass_g': [body_mass_g],
-    'culmen_length_mm': [culmen_length_mm],
-    'culmen_depth_mm': [culmen_depth_mm]
-})
-
-# Check for NaN values in the input data
-if input_data.isna().any().any():
-    st.warning("Input data contains NaN values. Filling with default values.")
-    input_data = input_data.fillna(0)  # Replace NaN values with 0 or appropriate value
-
-# Apply encoding to categorical features (check column names here!)
-input_data['species'] = species_encoder.transform(input_data['species'])
-input_data['island'] = island_encoder.transform(input_data['island'])
-input_data['sex'] = sex_encoder.transform(input_data['sex'])
-
-# Ensure the columns are in the correct order
-if isinstance(model, Pipeline):
-    preprocessor = model.named_steps.get('preprocessor')  # Replace with actual step name if different
-    if preprocessor:
-        input_data = preprocessor.transform(input_data)  # Apply any necessary transformations
-
-# Make prediction
-prediction = model.predict(input_data)
-
-# Show the result
-st.write(f'Predicted Species: {species_encoder.inverse_transform(prediction)}')
+# Input fields for user data
+island = st.selectbox('Island', ['Torgersen', 'Biscoe', 'Dream'])
+culmen_length_mm = st.number_input('Culmen Length (mm)', min_value=0.0)
+culmen_depth_mm = st.number_input('Culmen Depth (mm)', min_value=0.0)
+flipper_length_mm = st.number_input('Flipper Length (mm)', min_value=0.0)
+body_mass_g = st.number_input('Body Mass (g)', min_value=0.0)
+sex = st.selectbox('Sex', ['MALE', 'FEMALE'])
+
+
+# Create a button to trigger prediction
+if st.button('Predict Species'):
+    # Create a DataFrame from user inputs
+    x_new = pd.DataFrame({
+        'island': [island],
+        'culmen_length_mm': [culmen_length_mm],
+        'culmen_depth_mm': [culmen_depth_mm],
+        'flipper_length_mm': [flipper_length_mm],
+        'body_mass_g': [body_mass_g],
+        'sex': [sex]
+    })
+
+    # Make the prediction
+    y_pred_new = model.predict(x_new)
+
+    # Inverse transform the prediction
+    result = species_encoder.inverse_transform(y_pred_new)
+
+    # Display the prediction
+    st.write('Predicted Species:', result[0])