Update pages/LIFE_CYCLE_OF_MACHINE_LEARNING.py

pages/LIFE_CYCLE_OF_MACHINE_LEARNING.py

@@ -72,7 +72,6 @@ def data_collection_page():
     if st.button("Back to Home"):
         st.session_state.page = "home"
 
-
 # ----------------- Structured Data Page -----------------
 def structured_data_page():
     st.title(":blue[Structured Data]")
@@ -132,7 +131,7 @@ excel_file = pd.ExcelFile('data.xlsx')
 print(excel_file.sheet_names)
     """, language='python')
 
-    st.link_button("Jupyter Notebook", "https://colab.research.google.com/drive/1ZTKWTknL-4IQ9QbAfcyKzIP-_lNxmz2P?usp=sharing")
+    st.markdown('[Jupyter Notebook](https://colab.research.google.com/drive/1ZTKWTknL-4IQ9QbAfcyKzIP-_lNxmz2P?usp=sharing)')
 
     if st.button("Back to Structured Data"):
         st.session_state.page = "structured_data"
@@ -142,9 +141,11 @@ def csv_page():
     st.title(":green[CSV Data Format]")
 
     st.write("### What is CSV?")
-    st.write("CSV (Comma-Separated Values) files store tabular data in plain text, where each line is a data record and columns are separated by commas.")
+    st.write("""
+    CSV (Comma-Separated Values) files store tabular data in plain text, where each line is a data record and columns are separated by commas.
+    """)
 
-    st.write("### How to Read CSV Files")
+    st.write("### Reading CSV Files")
     st.code("""
 import pandas as pd
 
@@ -169,7 +170,14 @@ except UnicodeDecodeError:
     print("Error: Encoding issue. Try specifying a different encoding like 'latin1' or 'utf-8'.")
     """, language='python')
 
-    st.link_button("Jupyter Notebook", "https://colab.research.google.com/drive/your_csv_guide_link")
+    st.markdown("### Tips for Handling CSV Files")
+    st.write("""
+    - Always verify the delimiter used (e.g., commas, semicolons).
+    - Check for encoding compatibility, especially when dealing with international characters.
+    - Handle missing data effectively using functions like `fillna()` or `dropna()`.
+    """)
+
+    st.markdown('[Jupyter Notebook](https://colab.research.google.com/drive/your_csv_guide_link)')
 
     if st.button("Back to Structured Data"):
         st.session_state.page = "structured_data"
@@ -180,9 +188,10 @@ def json_page():
 
     st.write("### What is JSON?")
     st.write("""
-    JSON (JavaScript Object Notation) is a lightweight data-interchange format.
+    JSON (JavaScript Object Notation) is a lightweight data-interchange format that's easy for humans to read and write, and easy for machines to parse and generate. JSON is often used in APIs, configuration files, and data transfer applications.
     """)
 
+    st.write("### Reading JSON Files")
     st.code("""
 import json
 
@@ -192,11 +201,32 @@ with open('data.json', 'r') as file:
     print(data)
     """, language='python')
 
-    st.link_button("Jupyter Notebook", "https://colab.research.google.com/drive/your_json_guide_link")
+    st.write("### Writing JSON Files")
+    st.code("""
+import json
 
-    if st.button("Back to Structured Data"):
-        st.session_state.page = "structured
+# Write data to JSON file
+data = {
+    "name": "Alice",
+    "age": 25,
+    "skills": ["Python", "Machine Learning"]
+}
+
+with open('data.json', 'w') as file:
+    json.dump(data, file, indent=4)
+    """, language='python')
+
+    st.markdown("### Tips for Handling JSON Files")
+    st.write("""
+    - JSON files can be nested, so you might need to navigate through dictionaries and lists.
+    - If the structure is complex, you can use libraries like `json_normalize()` in pandas to flatten the JSON into a more tabular format for easier analysis.
+    - JSON supports both strings and numbers, and other types like arrays and booleans, making it versatile for various data types.
+    """)
 
+    st.markdown('[Jupyter Notebook](https://colab.research.google.com/drive/your_json_guide_link)')
+
+    if st.button("Back to Structured Data"):
+        st.session_state.page = "structured_data"
 
 # ----------------- Unstructured Data Page -----------------
 def unstructured_data_page():
@@ -378,23 +408,24 @@ print(root.find('name').text)  # Output: Bob
     if st.button("Back to Data Collection"):
         st.session_state.page = "data_collection"
 
-# ----------------- Router -----------------
-def router():
-    if st.session_state.page == "home":
-        home_page()
-    elif st.session_state.page == "data_collection":
-        data_collection_page()
-    elif st.session_state.page == "structured_data":
-        structured_data_page()
-    elif st.session_state.page == "excel":
-        excel_page()
-    elif st.session_state.page == "csv":
-        csv_page()
-    elif st.session_state.page == "unstructured_data":
-        unstructured_data_page()
-    elif st.session_state.page == "semi_structured_data":
-        semi_structured_data_page()
-
+# Main control to call appropriate page
+if st.session_state.page == "home":
+    home_page()
+elif st.session_state.page == "data_collection":
+    data_collection_page()
+elif st.session_state.page == "structured_data":
+    structured_data_page()
+elif st.session_state.page == "excel":
+    excel_page()
+elif st.session_state.page == "csv":
+    csv_page()
+elif st.session_state.page == "json":
+    json_page()
+elif st.session_state.page == "unstructured_data":
+    unstructured_data_page()
+elif st.session_state.page == "semi_structured_data":
+    semi_structured_data_page()
+    
 # Run the router function
 if __name__ == "__main__":
-    router()  
+    router()