Update pages/2_Simple_EDA.py

pages/2_Simple_EDA.py

@@ -14,16 +14,19 @@ st.markdown("""
 if "df" in st.session_state and st.session_state.df is not None:
     df = st.session_state.df
 
+    # Dataset Preview
     st.markdown("<h3 style='color: #2a52be;'>Dataset Preview📌</h3>", unsafe_allow_html=True)
     st.dataframe(df.head())
     
-
+    # Shape of the Data
     st.markdown("<h3 style='color: #843f5b;'>Dataset Shape</h3>", unsafe_allow_html=True)
     st.write(f"🔹 The dataset contains **{df.shape[0]} rows** and **{df.shape[1]} columns**.")
-
+    
+    # Column Names & Data Types
     st.markdown("<h3 style='color: #e25822;'>Column Names & Data Types</h3>", unsafe_allow_html=True)
     st.write(df.dtypes)
 
+    # 📝 Dataset Information (Equivalent to df.info())
     st.markdown("<h3 style='color: #9400d3;'>Dataset Information📝</h3>", unsafe_allow_html=True)
     
     buffer = io.StringIO()
@@ -34,6 +37,7 @@ if "df" in st.session_state and st.session_state.df is not None:
     st.markdown(f"<pre style='background-color: #f8f8f8; padding: 10px; border-radius: 5px; font-size: 14px; font-family: monospace;'>{info_str}</pre>", unsafe_allow_html=True)
 
 
+    # Numerical and categorical Columns
     st.markdown("<h3 style='color: #9400d3;'>Numerical and Categorical Columns</h3>", unsafe_allow_html=True)
     
     numerical_cols = df.select_dtypes(include=['int64', 'float64']).columns.tolist()
@@ -42,6 +46,7 @@ if "df" in st.session_state and st.session_state.df is not None:
     st.write(f"🔹 **Numerical Columns ({len(numerical_cols)}):** {', '.join(numerical_cols) if numerical_cols else 'None'}")
     st.write(f"🔹 **Categorical Columns ({len(categorical_cols)}):** {', '.join(categorical_cols) if categorical_cols else 'None'}")
 
+    # Unique Values in Categorical Columns
     st.markdown("<h3 style='color: #e25822;'>Unique Values in Categorical Columns</h3>", unsafe_allow_html=True)
     
     if categorical_cols:
@@ -62,6 +67,7 @@ if "df" in st.session_state and st.session_state.df is not None:
         st.info("No categorical columns detectedℹ️.")
 
 
+    # Summary Statistics
     st.markdown("<h3 style='color: #843f5b;'>Summary Statistics for Numerical Columns</h3>", unsafe_allow_html=True)
     
     st.write("🔹 **Basic statistical insights into the dataset:**")
@@ -73,7 +79,8 @@ if "df" in st.session_state and st.session_state.df is not None:
         st.write(df[categorical_cols].describe(include='object'))
     else:
         st.info("No categorical columns detectedℹ️.")
-
+    
+    # Checking for Missing Values
     st.markdown("<h3 style='color: #9400d3;'>Missing Values in the Dataset⚠️</h3>", unsafe_allow_html=True)
     missing_values = df.isnull().sum()
     
@@ -84,6 +91,7 @@ if "df" in st.session_state and st.session_state.df is not None:
         st.write("🔹 **Columns with Missing Values:**")
         st.write(missing_values[missing_values > 0])
 
+    # Checking for Duplicate Records
     st.markdown("<h3 style='color: #2a52be;'>Duplicate Records</h3>", unsafe_allow_html=True)
     duplicate_count = df.duplicated().sum()
     
@@ -94,6 +102,7 @@ if "df" in st.session_state and st.session_state.df is not None:
         st.write("🔹 **Example Duplicate Rows:**")
         st.dataframe(df[df.duplicated()].head())
 
+    # 📊 Outlier Detection
     st.markdown("<h3 style='color: #e25822;'>Outlier Detection</h3>", unsafe_allow_html=True)
     
     if numerical_cols:
@@ -121,4 +130,4 @@ if "df" in st.session_state and st.session_state.df is not None:
 
 
 else:
-    st.warning("No dataset found! Please upload a dataset first⚠️.")
+    st.warning("No dataset found! Please upload a dataset first⚠️.")