Update app.py

app.py

@@ -1,3 +1,4 @@
+
 import streamlit as st
 import numpy as np
 import pandas as pd
@@ -11,13 +12,15 @@ import io
 def main():
     st.title("California Housing Analysis")
 
+    # Load the California housing dataset
     california = datasets.fetch_california_housing()
     df = pd.DataFrame(california.data, columns=california.feature_names)
     df['MedHouseVal'] = california.target
 
+    # Displaying initial data information
     st.write("## Data Sample")
     st.write(df.head())
-    
+
     st.write("## Data Statistics")
     st.write(df.describe())
 
@@ -26,7 +29,7 @@ def main():
     df.info(buf=buffer)
     s = buffer.getvalue()
     st.text(s)
-    
+
     st.write("## Missing Values")
     st.write(df.isnull().sum())
 
@@ -37,7 +40,7 @@ def main():
     # Drop the target from the predictors list
     predictor_options = df.columns.drop(target).tolist()
     
-    # Add multiselect for user to choose predictor variables
+    # Multiselect widget to select predictor variables for regression
     predictors = st.multiselect(
         'Select predictor variables for regression:',
         options=predictor_options,
@@ -59,10 +62,12 @@ def main():
     else:
         st.write("Scatter plot is only available for a single predictor.")
 
-    # Regression analysis
+    # Splitting data for regression
     X = df[predictors]
     y = df[target]
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    # Perform linear regression
     model = LinearRegression()
     model.fit(X_train, y_train)
     y_pred = model.predict(X_test)
@@ -73,6 +78,7 @@ def main():
     st.write(f'RMSE: {rmse}')
     st.write(f'R-squared: {r2}')
 
+    # Visualizing the regression results
     if len(predictors) == 1:
         fig, ax = plt.subplots()
         ax.scatter(X_train, y_train, color='blue', label='Training data')
@@ -98,3 +104,4 @@ if __name__ == "__main__":
 
 
 
+