Update pages/2Simple_EDA.py

pages/2Simple_EDA.py

@@ -1,5 +1,6 @@
 import streamlit as st
 import pandas as pd
+import io
 
 st.markdown("""
     <div style="text-align: center; margin-bottom: 20px;">
@@ -14,27 +15,115 @@ if "df" in st.session_state and st.session_state.df is not None:
     df = st.session_state.df
 
     # Dataset Preview
-    st.markdown("<h2 style='color: #2a52be;'>Dataset Preview📌</h2>", unsafe_allow_html=True)
+    st.markdown("<h3 style='color: #2a52be;'>Dataset Preview📌</h3>", unsafe_allow_html=True)
     st.dataframe(df.head())
     
     # Shape of the Data
-    st.markdown("<h2 style='color: #843f5b;'>Dataset Shape📏</h2>", unsafe_allow_html=True)
+    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("<h2 style='color: #e25822;'>Column Names & Data Types🛠</h2>", unsafe_allow_html=True)
+    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("<h2 style='color: #9400d3;'>📝 Dataset Information</h2>", unsafe_allow_html=True)
+    
+    buffer = io.StringIO()
+    df.info(buf=buffer)
+    info_str = buffer.getvalue()
+    st.text(info_str)
+
+    # 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()
+    categorical_cols = df.select_dtypes(include=['object', 'category']).columns.tolist()
+    
+    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:
+        for col in categorical_cols:
+            unique_count = df[col].nunique()
+            st.write(f"**{col}:** {unique_count} unique values")
+    else:
+        st.info("No categorical columns detectedℹ️.")
+    
+    # Value Counts in Categorical Columns
+    st.markdown("<h3 style='color: #9400d3;'>Value Counts in Categorical Columns</h3>", unsafe_allow_html=True)
+    
+    if categorical_cols:
+        for col in categorical_cols:
+            st.write(f"🔹 **{col} Value Distribution:**")
+            st.write(df[col].value_counts().head(10))  # Show top 10 categories
+    else:
+        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:**")
+    st.write(df.describe())
+
+    st.markdown("<h3 style='color: #2a52be;'>Summary Statistics for Categorical Columns</h3>", unsafe_allow_html=True)
+    
+    if categorical_cols:
+        st.write(df[categorical_cols].describe(include='object'))
+    else:
+        st.info("No categorical columns detectedℹ️.")
     
     # Checking for Missing Values
-    st.markdown("<h2 style='color: #9400d3;'>Missing Values in the Dataset⚠️</h2>", unsafe_allow_html=True)
+    st.markdown("<h3 style='color: #9400d3;'>Missing Values in the Dataset⚠️</h3>", unsafe_allow_html=True)
     missing_values = df.isnull().sum()
     
     if missing_values.sum() == 0:
-        st.success("✅ No missing values found!")
+        st.success("No missing values found!")
     else:
         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()
+    
+    if duplicate_count == 0:
+        st.success("No duplicate records found!")
+    else:
+        st.warning(f"Found {duplicate_count} duplicate rows in the dataset.")
+        st.write("🔹 **Example Duplicate Rows:**")
+        st.dataframe(df[df.duplicated()].head())
+
+    # 📊 Outlier Detection
+    st.markdown("<h3 style='color: #e25822;'>📉 Outlier Detection in Numerical Columns</h3>", unsafe_allow_html=True)
+    
+    if numerical_cols:
+        outlier_info = {}
+        
+        for col in numerical_cols:
+            Q1 = df[col].quantile(0.25)
+            Q3 = df[col].quantile(0.75)
+            IQR = Q3 - Q1
+            lower_bound = Q1 - 1.5 * IQR
+            upper_bound = Q3 + 1.5 * IQR
+            outliers = ((df[col] < lower_bound) | (df[col] > upper_bound)).sum()
+            
+            if outliers > 0:
+                outlier_info[col] = outliers
+    
+        if outlier_info:
+            st.warning("⚠️ Outliers detected in the following numerical columns:")
+            for col, count in outlier_info.items():
+                st.write(f"🔹 **{col}:** {count} outliers")
+        else:
+            st.success("✅ No significant outliers detected!")
+    else:
+        st.info("ℹ️ No numerical columns detected.")
+
 
 else:
     st.warning("No dataset found! Please upload a dataset first⚠️.")