Update pages/3_Life cycle of ML project.py

pages/3_Life cycle of ML project.py

@@ -161,4 +161,245 @@ def data_collection_page():
     st.subheader("Manual Collection")
     st.write("""
     - Collect data manually through surveys, questionnaires, interviews, or direct observations.
-    """)
+    """)
+
+
+
+
+
+
+    # Buttons for types of data
+    st.subheader("Data Types")
+    if st.button("Structured Data"):
+        st.session_state.previous_page = '2_data_collection'
+        st.session_state.page = 'structured_data'
+    
+    if st.button("Semi-Structured Data"):
+        st.session_state.previous_page = '2_data_collection'
+        st.session_state.page = 'semi_structured_data'
+    
+    if st.button("Unstructured Data"):
+        st.session_state.previous_page = '2_data_collection'
+        st.session_state.page = 'unstructured_data'
+
+    # Back button to return to main page
+    if st.button("Back to Main"):
+        st.session_state.previous_page = '2_data_collection'
+        st.session_state.page = 'main'
+
+
+def structured_data_page():
+    st.title("Structured Data")
+    st.write("""
+    Structured data refers to data that is organized into a tabular format with rows and columns, such as in a database or spreadsheet.
+    """)
+
+    # Additional buttons for types of structured data
+    st.subheader("Types of Structured Data")
+    if st.button("Excel Files"):
+        st.session_state.page = 'excel_data'
+    if st.button("SQL Databases"):
+        st.session_state.page = 'sql_data'
+
+    if st.button("Back to Data Collection"):
+        st.session_state.page = '2_data_collection'
+
+
+def semi_structured_data_page():
+    st.title("Semi-Structured Data")
+    st.write("""
+    Semi-structured data has some form of organization but is not as rigid as structured data. It may include elements such as tags, metadata, etc.
+    """)
+
+    # Additional buttons for types of semi-structured data
+    st.subheader("Types of Semi-Structured Data")
+    if st.button("CSV Files"):
+        st.session_state.page = 'csv_data'
+    if st.button("JSON Files"):
+        st.session_state.page = 'json_data'
+    if st.button("XML Files"):
+        st.session_state.page = 'xml_data'
+    if st.button("HTML Files"):
+        st.session_state.page = 'html_data'
+
+    if st.button("Back to Data Collection"):
+        st.session_state.page = '2_data_collection'
+
+
+def unstructured_data_page():
+    st.title("Unstructured Data")
+    st.write("""
+    Unstructured data does not have a predefined format or structure. It includes data such as images, videos, and text.
+    """)
+
+    # Additional buttons for types of unstructured data
+    st.subheader("Types of Unstructured Data")
+    if st.button("Images"):
+        st.session_state.page = 'image_data'
+    if st.button("Videos"):
+        st.session_state.page = 'video_data'
+    if st.button("Audio"):
+        st.session_state.page = 'audio_data'
+    if st.button("Text"):
+        st.session_state.page = 'text_data'
+
+    if st.button("Back to Data Collection"):
+        st.session_state.page = '2_data_collection'
+
+
+# Individual Data Pages (Examples)
+def excel_data_page():
+    st.title("Handling Excel Files")
+    st.header("Understanding Data Format:")
+    st.markdown("""- Can only be created using applications like Microsoft Excel.
+                   - It is always structured data because it organizes data in rows and columns.
+                   - XLSX files are also called Workbooks because they can contain multiple sheets.""")
+    st.subheader("Workbook and Sheets")
+    st.markdown("""*An XLSX file is similar to a Book:*
+                - The Workbook acts as the book itself.
+                - Each Sheet inside the workbook is like a Page.
+                - Each Sheet can be thought of as an individual CSV file.
+                """)
+    st.markdown("""*Why Use XLSX Instead of CSV?*
+
+                - If you have to choose between a CSV file and an XLSX file, always choose XLSX because:
+                - It does not have parser errors or encoding issues that are common in CSV files.
+                - It contains pure structured data.
+                """)
+    st.subheader("Default Extension and Handling of XLSX")
+    st.markdown("""
+                - The default extension for Excel files is :blue-background[.xlsx.]
+                - Multiple Sheets = Workbook.
+                - Each sheet in an XLSX file can be processed separately.
+                """)
+    st.subheader("Reading XLSX Files into a DataFrame Using Pandas")
+    st.markdown(""" To work with Excel files in Python, you use the pandas library:
+                - *Read a Single Sheet*
+                - Use the :blue-background[pd.read_excel()] function to read an XLSX file into a DataFrame.
+                - By default, it reads the first sheet :blue-background[(index 0)].
+                """)
+    
+
+    code = '''import pandas as pd
+    df = pd.read_excel('file.xlsx', sheet_name=0)  # Reads the first sheet
+    print(df)
+            '''
+    st.code(code, language="python")
+    st.markdown("""
+    - *Key Notes:*
+    - Each sheet in the XLSX file can be loaded as a single DataFrame.
+    - Sheet indices start from 0 (zero-based indexing).
+    """)
+
+    st.subheader("Converting Multiple Sheets to CSV Files")
+    st.write("If you want to save each sheet in an XLSX file as a separate CSV file:")
+    st.write("*Step 1:* Read the workbook and load sheets.")
+    code = '''
+xlsx_file = 'file.xlsx'
+xls = pd.ExcelFile(xlsx_file)
+            '''
+    st.code(code, language="python")
+    st.write("*Step 2:* Loop through all the sheets and save them as separate CSV files:")
+    code = '''
+for sheet_name in xls.sheet_names:  # Loop through all sheet names
+    df = pd.read_excel(xlsx_file, sheet_name=sheet_name)
+    df.to_csv(f'{sheet_name}.csv', index=False)  # Save each sheet as a CSV
+            '''
+    st.code(code, language="python")
+    st.write("Result: Each sheet is now saved as an individual CSV file.")
+    
+    
+    
+    
+    
+
+
+    if st.button("Back to Structured Data"):
+        st.session_state.page = 'structured_data'
+
+def sql_data_page():
+    st.title("SQL Databases")
+    st.write("SQL databases store data in structured tables, and data is queried using SQL commands.")
+    if st.button("Back to Structured Data"):
+        st.session_state.page = 'structured_data'
+
+def csv_data_page():
+    st.title("CSV Files")
+    st.write("CSV files store data in a comma-separated format and are often used for exchanging semi-structured data.")
+    if st.button("Back to Semi-Structured Data"):
+        st.session_state.page = 'semi_structured_data'
+
+def json_data_page():
+    st.title("JSON Files")
+    st.write("JSON files store data in a key-value format and are widely used in web development.")
+    if st.button("Back to Semi-Structured Data"):
+        st.session_state.page = 'semi_structured_data'
+
+def xml_data_page():
+    st.title("XML Files")
+    st.write("XML files store data in a hierarchical format and are often used for semi-structured data.")
+    if st.button("Back to Semi-Structured Data"):
+        st.session_state.page = 'semi_structured_data'
+
+def html_data_page():
+    st.title("HTML Files")
+    st.write("HTML files are used to store web page content and are typically semi-structured data.")
+    if st.button("Back to Semi-Structured Data"):
+        st.session_state.page = 'semi_structured_data'
+
+def image_data_page():
+    st.title("Images")
+    st.write("Images are a form of unstructured data, often stored in formats like JPEG, PNG, and TIFF.")
+    if st.button("Back to Unstructured Data"):
+        st.session_state.page = 'unstructured_data'
+
+def video_data_page():
+    st.title("Videos")
+    st.write("Videos are a form of unstructured data, often stored in formats like MP4, AVI, and MKV.")
+    if st.button("Back to Unstructured Data"):
+        st.session_state.page = 'unstructured_data'
+
+def audio_data_page():
+    st.title("Audio")
+    st.write("Audio files are a form of unstructured data, often stored in formats like MP3, WAV, and AAC.")
+    if st.button("Back to Unstructured Data"):
+        st.session_state.page = 'unstructured_data'
+
+def text_data_page():
+    st.title("Text")
+    st.write("Text data is unstructured and can come from sources like emails, documents, and social media.")
+    if st.button("Back to Unstructured Data"):
+        st.session_state.page = 'unstructured_data'
+
+
+# Main logic to render pages based on session state
+if st.session_state.page == 'main':
+    main_page()
+elif st.session_state.page == '2_data_collection':
+    data_collection_page()
+elif st.session_state.page == 'structured_data':
+    structured_data_page()
+elif st.session_state.page == 'semi_structured_data':
+    semi_structured_data_page()
+elif st.session_state.page == 'unstructured_data':
+    unstructured_data_page()
+elif st.session_state.page == 'excel_data':
+    excel_data_page()
+elif st.session_state.page == 'sql_data':
+    sql_data_page()
+elif st.session_state.page == 'csv_data':
+    csv_data_page()
+elif st.session_state.page == 'json_data':
+    json_data_page()
+elif st.session_state.page == 'xml_data':
+    xml_data_page()
+elif st.session_state.page == 'html_data':
+    html_data_page()
+elif st.session_state.page == 'image_data':
+    image_data_page()
+elif st.session_state.page == 'video_data':
+    video_data_page()
+elif st.session_state.page == 'audio_data':
+    audio_data_page()
+elif st.session_state.page == 'text_data':
+    text_data_page()