Update app.py

app.py

@@ -8,22 +8,45 @@ 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')
+# 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()
 
-# Data Cleaning (same as your existing code)
-penguins_cleaned = penguins.dropna()
-penguins_cleaned = penguins_cleaned.drop_duplicates()
+# Preprocessing steps (same as your original code)
+penguins = penguins.dropna()
+penguins.drop_duplicates(inplace=True)
 
-# Fill missing values (same as your existing code)
-numerical_cols = penguins.select_dtypes(include=['number']).columns
-penguins[numerical_cols] = penguins[numerical_cols].fillna(penguins[numerical_cols].mean())
-categorical_cols = penguins.select_dtypes(include=['object']).columns
-penguins[categorical_cols] = penguins[categorical_cols].fillna(penguins[categorical_cols].mode().iloc[0])
 
+# Streamlit app
+st.title('Penguin Species Prediction')
 
-# Feature Engineering and Model Training (same as your existing code)
+# 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)']
@@ -38,44 +61,12 @@ preprocessor = ColumnTransformer(
         ('cat', categorical_transformer, categorical_features)
     ])
 
-pipeline = Pipeline(steps=[
-    ('preprocessor', preprocessor),
-    ('classifier', KNeighborsClassifier())
-])
-
+pipeline = Pipeline(steps=[('preprocessor', preprocessor), ('classifier', KNeighborsClassifier())])
 pipeline.fit(X_train, y_train)
-y_pred = pipeline.predict(X_test)
-accuracy = accuracy_score(y_test, y_pred)
-
-# Streamlit App
-st.title("Penguin Species Classification")
-
-st.write("This app predicts the species of a penguin based on its features.")
-
-# Display the accuracy
-st.write(f"Model Accuracy: {accuracy}")
-
-# Input features for prediction
-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['Island'].unique())
-sex = st.selectbox("Sex", penguins['Sex'].unique())
-
-
-# Create a DataFrame for prediction
-new_penguin = 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 Species"):
-  prediction = pipeline.predict(new_penguin)
-  st.write(f"Predicted Species: {prediction[0]}")
+prediction = pipeline.predict(input_data)
+
+# Display prediction
+st.subheader('Prediction')
+st.write(f"Predicted Penguin Species: {prediction[0]}"