Update pages/3_Life cycle of ML.py

pages/3_Life cycle of ML.py

@@ -64,3 +64,132 @@ st.markdown("""
     </style>
 """, unsafe_allow_html=True)
 
+import webbrowser
+
+# Function to display detailed content for "Data Collection" page
+def data_collection_page():
+    st.write("### What is Data?")
+    st.write("""
+    Data refers to raw facts and figures that are collected and stored for analysis. 
+    It can be structured or unstructured and comes from various sources like sensors, logs, transactions, and more.
+    """)
+    
+    st.write("### Types of Data")
+    st.write("""
+    1. **Structured Data**: Organized data that follows a strict schema (e.g., rows and columns).
+    2. **Unstructured Data**: Data that doesn't follow a predefined model (e.g., images, text).
+    3. **Semi-Structured Data**: Data that has some organizational properties but isn't fully structured (e.g., JSON, XML).
+    """)
+
+    # Button to select Structured Data
+    selected_data_type = st.radio("Choose Data Type", ["Structured Data", "Unstructured Data", "Semi-Structured Data"])
+
+    if selected_data_type == "Structured Data":
+        display_structured_data_info()
+
+# Function to display structured data information and formats
+def display_structured_data_info():
+    st.write("### Structured Data")
+    st.write("Structured data is data that is highly organized and stored in a fixed format, like tables, rows, and columns.")
+    
+    # Button for each structured data format (Excel, CSV, XML)
+    data_formats = st.radio("Choose a Data Format", ["Excel", "CSV", "XML"])
+    
+    if data_formats == "Excel":
+        display_excel_info()
+    elif data_formats == "CSV":
+        display_csv_info()
+    elif data_formats == "XML":
+        display_xml_info()
+
+# Function to display Excel-related information
+def display_excel_info():
+    st.write("### Excel Format")
+    st.write("""
+    **What it is**: Excel is a popular spreadsheet format commonly used for storing and analyzing structured data.
+    
+    **How to read these files**:
+    - Use `pandas.read_excel()` to read Excel files in Python.
+    
+    **Issues encountered when handling Excel files**:
+    - Large files can cause memory issues.
+    - Compatibility problems with different Excel versions.
+    
+    **How to overcome these errors**:
+    - Break large files into smaller chunks.
+    - Use libraries like `openpyxl` for handling newer Excel files and `xlrd` for older ones.
+    """)
+
+    # Button to open the Jupyter Notebook or PDF with coding examples
+    if st.button("Open Excel Code Example"):
+        open_code_example("excel")
+
+# Function to display CSV-related information
+def display_csv_info():
+    st.write("### CSV Format")
+    st.write("""
+    **What it is**: CSV (Comma Separated Values) is a text format for representing tabular data, where values are separated by commas.
+    
+    **How to read these files**:
+    - Use `pandas.read_csv()` to read CSV files in Python.
+    
+    **Issues encountered when handling CSV files**:
+    - Improper handling of special characters or delimiters.
+    - Missing or inconsistent data.
+    
+    **How to overcome these errors**:
+    - Specify delimiters using the `delimiter` parameter.
+    - Handle missing data by using `fillna()` or `dropna()` methods in pandas.
+    """)
+
+    # Button to open the Jupyter Notebook or PDF with coding examples
+    if st.button("Open CSV Code Example"):
+        open_code_example("csv")
+
+# Function to display XML-related information
+def display_xml_info():
+    st.write("### XML Format")
+    st.write("""
+    **What it is**: XML (eXtensible Markup Language) is a flexible and structured format used to store data in a hierarchical manner.
+    
+    **How to read these files**:
+    - Use `pandas.read_xml()` to read XML files or `xml.etree.ElementTree` for more complex parsing.
+    
+    **Issues encountered when handling XML files**:
+    - Complex nested structures can be hard to parse.
+    - Compatibility issues between different XML schemas.
+    
+    **How to overcome these errors**:
+    - Use XPath or `lxml` for more advanced parsing.
+    - Handle encoding issues using the `encoding` parameter while reading the file.
+    """)
+
+    # Button to open the Jupyter Notebook or PDF with coding examples
+    if st.button("Open XML Code Example"):
+        open_code_example("xml")
+
+# Function to open a Jupyter Notebook or PDF for coding examples
+def open_code_example(data_format):
+    # Placeholder: Open a PDF/Jupyter notebook link for the data format
+    example_links = {
+        "excel": "https://yourlinktoexcelcode.com",
+        "csv": "https://yourlinktocsvcode.com",
+        "xml": "https://yourlinktoxmlcode.com",
+    }
+    
+    link = example_links.get(data_format)
+    if link:
+        webbrowser.open_new_tab(link)
+
+# Main Streamlit app
+def main():
+    st.title("Machine Learning Life Cycle")
+    st.sidebar.title("ML Life Cycle Navigation")
+    
+    # Button to go to "Data Collection" page
+    if st.sidebar.button("Data Collection"):
+        data_collection_page()
+
+# Run the main function to start the app
+if __name__ == "__main__":
+    main()