app-penguins.py

import streamlit as st
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score

# Load your data (replace with your actual data loading)
# Assuming penguins.csv is in the same directory as your Streamlit app
try:
    penguins = pd.read_csv('penguins_lter.csv')
except FileNotFoundError:
    st.error("Error: penguins_lter.csv not found. Please make sure the file is in the same directory as the app.")
    st.stop()

# Preprocessing steps (same as your original code)
penguins = penguins.dropna()
penguins.drop_duplicates(inplace=True)


# Streamlit app
st.title('Penguin Species Prediction')

# Sidebar for user input
st.sidebar.header('Input Features')

island = st.sidebar.selectbox('Island', penguins['Island'].unique())
culmen_length = st.sidebar.slider('Culmen Length (mm)', float(penguins['Culmen Length (mm)'].min()), float(penguins['Culmen Length (mm)'].max()), float(penguins['Culmen Length (mm)'].mean()))
culmen_depth = st.sidebar.slider('Culmen Depth (mm)', float(penguins['Culmen Depth (mm)'].min()), float(penguins['Culmen Depth (mm)'].max()), float(penguins['Culmen Depth (mm)'].mean()))
flipper_length = st.sidebar.slider('Flipper Length (mm)', float(penguins['Flipper Length (mm)'].min()), float(penguins['Flipper Length (mm)'].max()), float(penguins['Flipper Length (mm)'].mean()))
body_mass = st.sidebar.slider('Body Mass (g)', float(penguins['Body Mass (g)'].min()), float(penguins['Body Mass (g)'].max()), float(penguins['Body Mass (g)'].mean()))
sex = st.sidebar.selectbox('Sex', penguins['Sex'].unique())

# Create input DataFrame
input_data = pd.DataFrame({
    'Island': [island],
    'Culmen Length (mm)': [culmen_length],
    'Culmen Depth (mm)': [culmen_depth],
    'Flipper Length (mm)': [flipper_length],
    'Body Mass (g)': [body_mass],
    'Sex': [sex]
})

# Prepare the model (same as before, including your pipeline)
X = penguins.drop('Species', axis=1)
y = penguins['Species']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

numerical_features = ['Culmen Length (mm)', 'Culmen Depth (mm)', 'Flipper Length (mm)', 'Body Mass (g)']
categorical_features = ['Island', 'Sex']

numerical_transformer = Pipeline(steps=[('scaler', StandardScaler())])
categorical_transformer = Pipeline(steps=[('onehot', OneHotEncoder(handle_unknown='ignore'))])

preprocessor = ColumnTransformer(
    transformers=[
        ('num', numerical_transformer, numerical_features),
        ('cat', categorical_transformer, categorical_features)
    ])

pipeline = Pipeline(steps=[('preprocessor', preprocessor), ('classifier', KNeighborsClassifier())])
pipeline.fit(X_train, y_train)

# Make prediction
prediction = pipeline.predict(input_data)

# Display prediction
st.subheader('Prediction')
st.write(f"Predicted Penguin Species: {prediction[0]}")