pages/Life_cycle_of_ML.py

import streamlit as st

# Function to display lifecycle descriptions
def display_lifecycle_stage(stage_name, description):
    st.subheader(stage_name)
    st.write(description)

# Title
st.title("Enhanced Machine Learning Life Cycle")

# Markdown Diagram with Shapes and Colors
st.markdown(
    """
    <style>
    .shape-box { 
        background-color: rgba(255, 221, 193, 0.8); 
        padding: 10px; 
        border-radius: 5px; 
        text-align: center; 
        margin-bottom: 10px;
    }
    .shape-circle { 
        background-color: rgba(193, 225, 255, 0.8); 
        padding: 10px; 
        border-radius: 50%; 
        text-align: center; 
        margin-bottom: 10px;
    }
    .shape-diamond { 
        background-color: rgba(193, 255, 193, 0.8); 
        padding: 10px; 
        clip-path: polygon(50% 0%, 100% 50%, 50% 100%, 0% 50%);
        text-align: center; 
        margin-bottom: 10px;
    }
    </style>

    <div class="shape-box">Problem Statement</div>
    <div class="shape-circle">Data Collection</div>
    <div class="shape-box">Simple EDA</div>
    <div class="shape-diamond">Data Preprocessing</div>
    <div class="shape-box">EDA</div>
    <div class="shape-circle">Feature Engineering</div>
    <div class="shape-box">Training</div>
    <div class="shape-diamond">Testing</div>
    <div class="shape-box">Deploying</div>
    <div class="shape-circle">Monitoring</div>
    """,
    unsafe_allow_html=True,
)

# Buttons for each stage
st.markdown("### Select a Lifecycle Stage to Learn More:")
col1, col2 = st.columns(2)

with col1:
    if st.button("Problem Statement"):
        display_lifecycle_stage(
            "Problem Statement",
            "Defining the problem and setting objectives for the machine learning project."
        )
    if st.button("Simple EDA"):
        display_lifecycle_stage(
            "Simple EDA",
            "Performing initial exploratory data analysis to understand data distribution and trends."
        )
    if st.button("EDA"):
        display_lifecycle_stage(
            "EDA",
            "Detailed exploratory data analysis for deeper insights into data patterns."
        )
    if st.button("Training"):
        display_lifecycle_stage(
            "Training",
            "Fitting the model using the training dataset to learn patterns and relationships."
        )
    if st.button("Deploying"):
        display_lifecycle_stage(
            "Deploying",
            "Deploying the trained model to production for real-world use."
        )

with col2:
    if st.button("Data Collection"):
        st.switch_page("pages/Data_Collection.py")
        display_lifecycle_stage(
            "Data Collection",
            "Gathering the data required for the machine learning project."
        )
    if st.button("Data Preprocessing"):
        display_lifecycle_stage(
            "Data Preprocessing",
            "Cleaning and transforming the data to prepare it for analysis."
        )
    if st.button("Feature Engineering"):
        display_lifecycle_stage(
            "Feature Engineering",
            "Creating new features or modifying existing ones to improve model performance."
        )
    if st.button("Testing"):
        display_lifecycle_stage(
            "Testing",
            "Evaluating the model's performance using a separate testing dataset."
        )
    if st.button("Monitoring"):
        display_lifecycle_stage(
            "Monitoring",
            "Monitoring the deployed model's performance and maintaining its accuracy."
        )