Update app.py

app.py

@@ -6,10 +6,16 @@ from sklearn.preprocessing import StandardScaler
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.metrics import classification_report
 
-# Load your data (replace with your actual file path)
-df = pd.read_csv('penguins_lter.csv')
+# Load your data (replace with your actual data loading)
+# Assuming you have a CSV file named 'penguins_lter.csv' in your working directory
+try:
+    df = pd.read_csv('penguins_lter.csv')
+except FileNotFoundError:
+    st.error("Error: 'penguins_lter.csv' not found. Please upload the file or adjust the path.")
+    st.stop()
 
-# Data preprocessing (same as in your previous code)
+
+# Data preprocessing (handle missing values)
 numeric_cols = df.select_dtypes(include=['number']).columns
 for col in numeric_cols:
     df[col].fillna(df[col].mean(), inplace=True)
@@ -18,56 +24,39 @@ categorical_cols = df.select_dtypes(exclude=['number']).columns
 for col in categorical_cols:
     df[col].fillna(df[col].mode()[0], inplace=True)
 
-# Feature Engineering and Model Training (same as in your previous code)
+
+# Model training and prediction (same as your original code)
+
+# Assuming 'Species' is your target variable
 X = df.drop('Species', axis=1)
 y = df['Species']
+
+# Convert categorical features to numerical using one-hot encoding
 X = pd.get_dummies(X, drop_first=True)
+
+# Split data into training and testing sets
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
+# Create a pipeline
 pipeline = Pipeline([
     ('scaler', StandardScaler()),
     ('knn', KNeighborsClassifier(n_neighbors=5))
 ])
+
+# Train the pipeline
 pipeline.fit(X_train, y_train)
+
+# Make predictions
 y_pred = pipeline.predict(X_test)
-report = classification_report(y_test, y_pred, output_dict=True)
+
 
 # Streamlit app
 st.title("Penguin Species Classification")
 
-st.write("This app predicts the species of a penguin based on its features.")
+st.write("This app predicts the species of a penguin based on its physical characteristics.")
 
-# Display the classification report
+# Display classification report
 st.subheader("Classification Report")
-st.write(pd.DataFrame(report).transpose())
-
-
-# Add input fields for user input (example)
-st.sidebar.header("Penguin Features")
-
-# Example input fields (replace with your actual features)
-bill_length_mm = st.sidebar.number_input("Bill Length (mm)", min_value=0.0, value=40.0)
-bill_depth_mm = st.sidebar.number_input("Bill Depth (mm)", min_value=0.0, value=15.0)
-# ... Add more input fields for other features ...
-
-#Create a dictionary to store the user inputs
-user_input_dict = {
-    'bill_length_mm': bill_length_mm,
-    'bill_depth_mm': bill_depth_mm,
-    # ... Add other features here
-}
-
-# Create a dataframe for prediction
-user_input_df = pd.DataFrame([user_input_dict])
-user_input_df = pd.get_dummies(user_input_df, drop_first=True) # Apply the same one-hot encoding
-
-
-if st.sidebar.button("Predict"):
-    # Align the columns of user_input_df and X_train
-    missing_cols = set(X_train.columns) - set(user_input_df.columns)
-    for c in missing_cols:
-        user_input_df[c] = 0  # Add missing columns with value 0
-    user_input_df = user_input_df[X_train.columns] # Reorder the columns
+st.text(classification_report(y_test, y_pred))
 
-    prediction = pipeline.predict(user_input_df)
-    st.write(f"Predicted Species: {prediction[0]}")
+st.dataframe(df.head())