import streamlit as st
import pandas as pd
import pickle
import sklearn  # Ensure scikit-learn is imported

# Load the pre-trained model
try:
    with open('logreg_model.pkl', 'rb') as model_file:
        model = pickle.load(model_file)
except Exception as e:
    st.error("Failed to load model. Ensure that the scikit-learn version matches the one used to create the model file.")
    st.error(f"Error Details: {e}")
    st.stop()

st.title('Iris Variety Prediction')

# User Input Form
with st.form(key='form_parameters'):
    sepal_length = st.slider('Sepal Length (cm)', 4.0, 8.0, 5.0)
    sepal_width = st.slider('Sepal Width (cm)', 2.0, 4.5, 3.0)
    petal_length = st.slider('Petal Length (cm)', 1.0, 7.0, 1.5)
    petal_width = st.slider('Petal Width (cm)', 0.1, 2.5, 0.2)
    st.markdown('---')

    submitted = st.form_submit_button('Predict')

# Data Inference
if submitted:
    # Create DataFrame for prediction
    data_inf = {
        'Id': 0,
        'SepalLengthCm': sepal_length,
        'SepalWidthCm': sepal_width,
        'PetalLengthCm': petal_length,
        'PetalWidthCm': petal_width
    }

    data_inf = pd.DataFrame([data_inf])

    # Predict using the model
    try:
        y_pred_inf = model.predict(data_inf)
        st.write('## Iris Variety: **' + str(y_pred_inf[0]) + '**')
    except Exception as e:
        st.error("Prediction failed. Please ensure the input format is correct and compatible with the model.")
        st.error(f"Error Details: {e}")