app.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)
penguins = pd.read_csv('penguins_lter.csv')  # Make sure 'penguins_lter.csv' is in your app's directory or accessible

# Data cleaning and preprocessing (same as your original code)
penguins_cleaned = penguins.dropna()
penguins_cleaned = penguins_cleaned.drop_duplicates()

# Numerical and Categorical Features (same as original code)
numerical_features = ['Culmen Length (mm)', 'Culmen Depth (mm)', 'Flipper Length (mm)', 'Body Mass (g)']
categorical_features = ['Island', 'Sex']

# Preprocessing pipeline (same as original code)
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)
])

# Machine Learning pipeline (same as original code)
pipeline = Pipeline(steps=[
    ('preprocessor', preprocessor),
    ('classifier', KNeighborsClassifier())
])


# Streamlit app
st.title("Penguin Species Classification")

# Display the dataset (optional)
if st.checkbox("Show Dataset"):
    st.write(penguins_cleaned)

# User input features
st.header("Enter Penguin Features:")
culmen_length = st.number_input("Culmen Length (mm)", min_value=0.0)
culmen_depth = st.number_input("Culmen Depth (mm)", min_value=0.0)
flipper_length = st.number_input("Flipper Length (mm)", min_value=0.0)
body_mass = st.number_input("Body Mass (g)", min_value=0.0)
island = st.selectbox("Island", penguins_cleaned['Island'].unique())
sex = st.selectbox("Sex", penguins_cleaned['Sex'].unique())

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

# Make Prediction
if st.button('Predict'):
  # Assuming 'species' is your target variable (same as original code)
  X = penguins_cleaned.drop('Species', axis=1)
  y = penguins_cleaned['Species']

  # Fit the model
  X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
  pipeline.fit(X_train, y_train)

  prediction = pipeline.predict(input_data)

  st.write(f"Predicted Species: {prediction[0]}")