Update pages/6_Feature_Engineering.py

pages/6_Feature_Engineering.py

@@ -153,23 +153,31 @@ if file_type == "One-Hot Vectorization":
     - This technique is called One-Hot Vectorization
     ''')
 
-    st.markdown('''Example for One-Hot Vectorization is : 
-    - There is a corpus contains 3 documents d1, d2, d3
-    - d1 ➡️ Toy is good
-    - d2 ➡️ Toy is not good
-    - d3 ➡️ Bad toy
-        - It converts d1 into v1 where (v1 is numerical representation of d1)
-        - It converts d2 into v2 where (v2 is numerical representation of d2)
-        - It converts d3 into v3 where (v3 is numerical representation of d3)
-    - Creates a vocabulary ➡️ {toy, is, good, not, bad }
-    - len(vocavulary) = 5 in 5 dimension
-    - Each word is represented as 5-dim where every dimension belongs to unique word
-    - toy ➡️ [1,0,0,0,0] , is ➡️ [0,1,0,0,0] , good ➡️ [0,0,1,0,0] , not ➡️ [0,0,0,1,0] , bad ➡️ [0,0,0,0,1]
-    - d1 → v1 → [[1,0,0,0,0] , [0,1,0,0,0] , [0,0,1,0,0]]
-    - d2 → v2 → [[1,0,0,0,0] , [0,1,0,0,0] , [0,0,0,1,0] , [0,0,1,0,0]]
-    - d3 → v3 → [[0,0,0,0,1], [1,0,0,0,0]]
-    - Here we're converting each and every word into vector form and combining it to form vector this technique is known as **One-Hot Vectorization**
-    ''')
+    st.markdown("""
+        | **Word** | **Vector Representation** |
+        |----------|--------------------------|
+        |  **toy**  | [1,0,0,0,0] |
+        |  **is**   | [0,1,0,0,0] |
+        |  **good** | [0,0,1,0,0] |
+        |  **not**  | [0,0,0,1,0] |
+        |  **bad**  | [0,0,0,0,1] |
+    """, unsafe_allow_html=True)
+
+    st.markdown("""
+        ### 📝 Document Representations:
+        - **d₁ → v₁** → `[[1,0,0,0,0] , [0,1,0,0,0] , [0,0,1,0,0]]`  
+        - **d₂ → v₂** → `[[1,0,0,0,0] , [0,1,0,0,0] , [0,0,0,1,0] , [0,0,1,0,0]]`  
+        - **d₃ → v₃** → `[[0,0,0,0,1], [1,0,0,0,0]]`  
+
+    ✅ This **One-Hot Vectorization** technique **converts words into numerical vectors** while preserving their uniqueness.  
+    """)
+
+    st.markdown("""
+        ### 🎯 Key Takeaways:
+        - 🔹 **Each word** is represented as a **5-dimensional** vector.  
+        - 🔹 **Every dimension** corresponds to a **unique word** in the vocabulary.  
+        - 🔹 This method is **useful** for transforming text into a **numerical format** for Machine Learning tasks.
+    """)