Update pages/EDA.py

pages/EDA.py

@@ -58,14 +58,16 @@ for col in num_cols:
 st.write("Number of Outliers Detected:")
 st.write(outlier_counts)
 
+import streamlit as st
+
 # Title with color
 st.markdown("<h2 style='text-align: left; color: #2E86C1;'>Why Use the IQR Method?</h2>", unsafe_allow_html=True)
 
-# Explanation with bullet points
+# Explanation with smaller font size
 st.markdown("""
 <style>
     .why-text {
-        font-size: 10px;
+        font-size: 14px;  /* Decreased font size */
         color: #333;
         background-color: #f9f9f9;
         padding: 10px;
@@ -73,11 +75,10 @@ st.markdown("""
     }
 </style>
 <div class='why-text'>
-    1. Other methods like mean and standard deviation can be heavily influenced by extreme values.<br><br>
-    2. IQR focuses only on the middle 50% of data (between Q1 and Q3), making it less affected by extreme values.<br><br>
-    3. Other methods may remove outliers entirely, leading to data loss.<br><br>
-    4. Instead of dropping rows, the IQR method replaces outliers with the mean of the column, keeping the dataset size the same.<br><br>
-    5. This is useful when we don’t want to lose important information but still need to control extreme values.
+    1. Other methods like mean and standard deviation can be heavily influenced by extreme values.**<br><br>
+    2. IQR focuses only on the middle 50% of data (between Q1 and Q3), making it less affected by extreme values.**<br><br>
+    3. Other methods may remove outliers entirely, leading to data loss.**<br><br>
+    4. Instead of dropping rows, the IQR method replaces outliers with the mean of the column, keeping the dataset size the same.**<br><br>
+    5. This is useful when we don’t want to lose important information but still need to control extreme values.**
 </div>
 """, unsafe_allow_html=True)
-