Update pages/LIFE_CYCLE_OF_MACHINE_LEARNING.py

pages/LIFE_CYCLE_OF_MACHINE_LEARNING.py

@@ -0,0 +1,179 @@
+import streamlit as st
+
+# Page navigation state
+if 'page' not in st.session_state:
+    st.session_state.page = "home"  # Default page is "home"
+
+# ----------------- Home Page -----------------
+def home_page():
+    st.title(":green[Lifecycle of a Machine Learning Project]")
+    st.markdown("Click on a stage to learn more about it.")
+
+    # Button for Data Collection (Redirects to 'data_collection' page)
+    if st.button(":orange[📊 Data Collection]"):
+        st.session_state.page = "data_collection"
+
+    # Buttons for other stages with brief explanations
+    if st.button(":blue[🌟 Problem Statement]"):
+        st.markdown("### Problem Statement\nIdentify the problem you want to solve and set clear objectives and success criteria.")
+    
+    if st.button(":blue[🛠️ Simple EDA]"):
+        st.markdown("### Simple EDA\nPerform exploratory data analysis to understand data distributions and relationships.")
+    
+    if st.button(":blue[Data Pre-Processing]"):
+        st.markdown("### Data Pre-Processing\nConvert raw data into cleaned data.")
+
+    if st.button(":blue[📈 Exploratory Data Analysis (EDA)]"):
+        st.markdown("### Exploratory Data Analysis (EDA)\nVisualize and analyze the data to understand its distributions and relationships.")
+
+    if st.button(":blue[🏋️ Feature Engineering]"):
+        st.markdown("### Feature Engineering\nCreate new features from existing data.")
+
+    if st.button(":blue[🤖 Model Training]"):
+        st.markdown("### Model Training\nTrain the model using the training data and optimize its parameters.")
+
+    if st.button(":blue[🔧 Model Testing]"):
+        st.markdown("### Model Testing\nAssess the model's performance using various metrics and cross-validation techniques.")
+
+    if st.button(":blue[🚀 Model Deployment]"):
+        st.markdown("### Model Deployment\nIntegrate the trained model into a production environment and monitor its performance.")
+
+    if st.button(":blue[📝 Monitoring]"):
+        st.markdown("### Monitoring\nPeriodically retrain the model with new data and update features as needed.")
+
+# ----------------- Data Collection Page -----------------
+def data_collection_page():
+    st.title(":red[Data Collection]")
+    st.markdown("### Data Collection\nThis page discusses the process of Data Collection.")
+    st.markdown("Types of Data: **Structured**, **Unstructured**, **Semi-Structured**")
+
+    # Button for Structured Data
+    if st.button(":blue[🌟 Structured Data]"):
+        st.session_state.page = "structured_data"
+
+    # Button for Unstructured Data
+    if st.button(":blue[📷 Unstructured Data]"):
+        st.session_state.page = "unstructured_data"
+
+    # Button for Semi-Structured Data
+    if st.button(":blue[🗃️ Semi-Structured Data]"):
+        st.session_state.page = "semi_structured_data"
+
+    # Back to Home button
+    if st.button("Back to Home"):
+        st.session_state.page = "home"
+
+# ----------------- Structured Data Page -----------------
+def structured_data_page():
+    st.title(":blue[Structured Data]")
+    st.markdown("""
+    Structured data is highly organized and typically stored in tables like spreadsheets or databases. It is easy to search and analyze.
+    """)
+    st.markdown("### Examples: Excel files, CSV files")
+
+    # Button for Excel Details
+    if st.button(":green[📊 Excel]"):
+        st.session_state.page = "excel"
+
+    # Back to Data Collection
+    if st.button("Back to Data Collection"):
+        st.session_state.page = "data_collection"
+
+# ----------------- Excel Data Page -----------------
+def excel_page():
+    st.title(":green[Excel Data Format]")
+
+    # 4a. What it is
+    st.write("### What is Excel?")
+    st.write("Excel is a spreadsheet tool for storing data in tabular format with rows and columns. Common file extensions: `.xls`, `.xlsx`.")
+
+    # 4b. How to read Excel files
+    st.write("### How to Read Excel Files")
+    st.code("""
+import pandas as pd
+
+# Read an Excel file
+df = pd.read_excel('data.xlsx', sheet_name='Sheet1')
+print(df)
+    """, language='python')
+
+    # 4c. Issues encountered
+    st.write("### Issues Encountered")
+    st.write("""
+- **File not found**: Incorrect file path.
+- **Sheet name error**: Specified sheet doesn't exist.
+- **Missing libraries**: `openpyxl` or `xlrd` might be missing.
+""")
+
+    # 4d. Solutions
+    st.write("### Solutions to These Issues")
+    st.code("""
+# Install required libraries
+# pip install openpyxl xlrd
+
+# Handle missing file
+try:
+    df = pd.read_excel('data.xlsx', sheet_name='Sheet1')
+except FileNotFoundError:
+    print("File not found. Check the file path.")
+
+# List available sheet names
+excel_file = pd.ExcelFile('data.xlsx')
+print(excel_file.sheet_names)
+    """, language='python')
+
+    # Download Button for Jupyter Notebook
+    with open("excel_handling_guide.ipynb", "rb") as file:
+        st.download_button(
+            label="Download Jupyter Notebook",
+            data=file,
+            file_name="excel_handling_guide.ipynb",
+            mime="application/octet-stream"
+        )
+
+    # Back to Structured Data
+    if st.button("Back to Structured Data"):
+        st.session_state.page = "structured_data"
+
+# ----------------- Unstructured Data Page -----------------
+def unstructured_data_page():
+    st.title(":blue[Unstructured Data]")
+    st.markdown("""
+    Unstructured data does not have a predefined format. Examples include text documents, images, videos, and audio files.
+    """)
+
+    # Back to Data Collection
+    if st.button("Back to Data Collection"):
+        st.session_state.page = "data_collection"
+
+# ----------------- Semi-Structured Data Page -----------------
+def semi_structured_data_page():
+    st.title(":blue[Semi-Structured Data]")
+    st.markdown("""
+    Semi-structured data has some organizational properties but doesn't fit into strict tables. Examples: JSON, XML files.
+    """)
+
+    # Back to Data Collection
+    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 == "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()
+
+