Update pages/3_Life cycle of ML.py

pages/3_Life cycle of ML.py

@@ -1,4 +1,5 @@
 import streamlit as st
+import pandas as pd
 from graphviz import Digraph
 
 custom_css = """
@@ -91,3 +92,91 @@ for step in steps:
 if selected_step:
     st.markdown(f"<h2>{selected_step}</h2>", unsafe_allow_html=True)
     st.markdown(f"<p style='font-size:1.1rem; text-align:center;'>{descriptions[selected_step]}</p>", unsafe_allow_html=True)
+
+st.markdown("<hr>", unsafe_allow_html=True)
+
+    for step in steps:
+        if st.button(step):
+            if step == "Data Collection":
+                st.experimental_set_query_params(page="Data Collection")
+
+elif page == "Data Collection":
+    st.markdown("<h1>Data Collection</h1>", unsafe_allow_html=True)
+    st.markdown(
+        "<p>Data is the foundational aspect of any ML project. It comes in three primary types: "
+        "Structured, Unstructured, and Semi-Structured data.</p>", 
+        unsafe_allow_html=True
+    )
+
+    if st.button("Structured Data"):
+        st.experimental_set_query_params(page="Structured Data: Excel")
+
+elif page == "Structured Data: Excel":
+    st.markdown("<h1>Structured Data: Excel</h1>", unsafe_allow_html=True)
+    st.write("**What is Excel?**")
+    st.write("Excel files store data in a tabular format, widely used in business and analytics.")
+
+    st.write("**How to read Excel files:**")
+    st.code("""
+# Load an Excel file
+excel_data = pd.read_excel('file.xlsx')
+""", language="python")
+
+    st.write("**Common issues:**")
+    st.write("- Missing headers or irregular data.")
+    st.write("- Multiple sheets requiring separate handling.")
+
+    st.write("**How to handle issues:**")
+    st.write("- Use `sheet_name` to specify sheets.")
+    st.code("""
+data = pd.read_excel('file.xlsx', sheet_name='Sheet1')
+""", language="python")
+
+    st.download_button("Download Documentation", "This is Excel-related documentation.", file_name="Excel_Guide.pdf")
+
+elif page == "Structured Data: CSV":
+    st.markdown("<h1>Structured Data: CSV</h1>", unsafe_allow_html=True)
+    st.write("**What is CSV?**")
+    st.write("CSV files store data as plain text, where columns are separated by commas.")
+
+    st.write("**How to read CSV files:**")
+    st.code("""
+import pandas as pd
+# Load a CSV file
+csv_data = pd.read_csv('file.csv')
+""", language="python")
+
+    st.write("**Common issues:**")
+    st.write("- Encoding problems.")
+    st.write("- Missing values.")
+
+    st.write("**How to handle issues:**")
+    st.write("- Use `encoding` to handle encoding errors.")
+    st.code("""
+data = pd.read_csv('file.csv', encoding='utf-8')
+""", language="python")
+
+    st.download_button("Download Documentation", "This is CSV-related documentation.", file_name="CSV_Guide.pdf")
+
+elif page == "Structured Data: XML":
+    st.markdown("<h1>Structured Data: XML</h1>", unsafe_allow_html=True)
+    st.write("**What is XML?**")
+    st.write("XML files store hierarchical data using tags.")
+
+    st.write("**How to read XML files:**")
+    st.code("""
+# Parse XML data
+from xml.etree import ElementTree
+
+tree = ElementTree.parse('file.xml')
+root = tree.getroot()
+""", language="python")
+
+    st.write("**Common issues:**")
+    st.write("- Nested structures making data extraction complex.")
+
+    st.write("**How to handle issues:**")
+    st.write("- Use libraries like `xml.etree.ElementTree` or `lxml` for parsing.")
+
+    st.download_button("Download Documentation", "This is XML-related documentation.", file_name="XML_Guide.pdf")
+