Update app.py

app.py

@@ -7,68 +7,61 @@ 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
+# 1. Load Data
+# Assuming your data is in a file called 'penguins_lter.csv'
+penguins = pd.read_csv('penguins_lter.csv') 
+penguins = penguins.dropna()  # Handle missing values
+penguins.drop_duplicates(inplace=True)  # Remove duplicates
 
-# Data cleaning and preprocessing (same as your original code)
-penguins_cleaned = penguins.dropna()
-penguins_cleaned = penguins_cleaned.drop_duplicates()
+# 2. Define Features and Target
+X = penguins.drop('Species', axis=1) 
+y = penguins['Species']
 
-# Numerical and Categorical Features (same as original code)
+# 3. Split Data
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# 4. Create Preprocessing Pipeline
 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())
-])
 
+preprocessor = ColumnTransformer(
+    transformers=[
+        ('num', numerical_transformer, numerical_features),
+        ('cat', categorical_transformer, categorical_features)
+    ])
 
-# Streamlit app
-st.title("Penguin Species Classification")
+# 5. Create and Train Model Pipeline
+pipeline = Pipeline(steps=[('preprocessor', preprocessor), ('classifier', KNeighborsClassifier())])
+pipeline.fit(X_train, y_train)
 
-# Display the dataset (optional)
-if st.checkbox("Show Dataset"):
-    st.write(penguins_cleaned)
+# 6. Streamlit App
+st.title('Penguin Species Prediction')
 
-# 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())
+# 6.1 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()))
+culmen_depth = st.sidebar.slider('Culmen Depth (mm)', float(penguins['Culmen Depth (mm)'].min()), float(penguins['Culmen Depth (mm)'].max()))
+flipper_length = st.sidebar.slider('Flipper Length (mm)', float(penguins['Flipper Length (mm)'].min()), float(penguins['Flipper Length (mm)'].max()))
+body_mass = st.sidebar.slider('Body Mass (g)', float(penguins['Body Mass (g)'].min()), float(penguins['Body Mass (g)'].max()))
+sex = st.sidebar.selectbox('Sex', penguins['Sex'].unique())
 
-# Create a dataframe for the input
+# 6.2 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],
-    '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)
+# 6.3 Make Prediction
+prediction = pipeline.predict(input_data)
 
-  st.write(f"Predicted Species: {prediction[0]}")
+# 6.4 Display Prediction
+st.subheader('Prediction')
+st.write(f"Predicted Penguin Species: {prediction[0]}")