Update pages/8Model Training.py

pages/8Model Training.py

@@ -7,160 +7,157 @@ import pandas as pd
 st.set_page_config(
     page_title="Model Building",
     page_icon="🚀",
-    layout="wide"
-)
+    layout="wide")
+
+if "current_page" not in st.session_state:
+    st.session_state.current_page = "main"
+
+def navigate_to(page_name):
+    st.session_state.current_page = page_name
+
 
 st.markdown("""
-    <h1 style="text-align: center; color: #BB3385;">🚀 Model Building</h1>
-    <p style="text-align: center; font-size: 18px;">
-        Let’s explore how machines learn — from raw data to smart predictions.
-    </p>
+    <h1 style="text-align: center; color: #BB3385;">Model Building</h1>
+    <p style="text-align: center; font-size: 18px;">Welcome to one of the most exciting parts of machine learning – teaching the machine how to learn!</p>
 """, unsafe_allow_html=True)
 
-# What is model training
 st.markdown("""
-    <h3 style='color:#9400d3;'>What is Model Training?</h3>
-    <p>Model training is the heart of machine learning. It’s the phase where a machine learns how to solve a problem by looking at data and finding patterns in it.</p>
+    <h3 style='color:#2a52be;'>What is Model Training?</h3>
+    <p><strong>Model training</strong> is the process of teaching a machine learning model to understand patterns from data.</p>
 
-    <p>To make it simple — the machine is like a student. To help it learn, it needs two things: data to learn from, and a method to learn with (called an algorithm).</p>
+    <p>The model learns with the help of:</p>
 
-    <p>Once the model understands the data well enough, it can start making predictions or decisions on new situations it hasn’t seen before.</p>
+    <p>• <strong>Data</strong> – examples that already have correct answers</p>
+    <p>• <strong>Algorithm</strong> – a method that helps the model learn from the data</p>
+
+    <p>Once the training is complete, the model can start making predictions or decisions on new, unseen data.</p>
 """, unsafe_allow_html=True)
 
-# Who are we training
 st.markdown("""
-    <h3 style='color:#9400d3;'>Who Are We Actually Training?</h3>
-    <p>It may sound strange, but we’re not training a person or a robot. We’re training a machine learning model — a smart system that starts with zero knowledge.</p>
+<h4 style='color:#BB3385;'>For Example</h4>
+Think of yourself as a teacher, and the machine as a student.
+
+You show math problems (inputs) and answers (outputs). The student starts to learn patterns.
+
+Just like that:
+- Machine = student
+- Data = problem
+- Algorithm = learning method
 
-    <p>It doesn’t know anything until we show it examples and explain how to learn from them using an algorithm. We guide the model to learn in the right way so it can solve problems on its own later.</p>
+After training, the model is ready to solve new problems.
 """, unsafe_allow_html=True)
 
-# What does it need
+
 st.markdown("""
-    <h3 style='color:#9400d3;'>What Does the Model Need to Learn?</h3>
-    <p>Just like a student needs a textbook and a teacher, a model needs two basic things:</p>
+    <h3 style='color:#2a52be;'>Who Are We Actually Training?</h3>
+    <p>We are training machines to learn — not robots or humans, but something called a <strong>machine learning model</strong>.This model is like a smart system that doesn’t know anything in the beginning. It needs examples and a method to understand those examples.</p>
+
+    <p>As programmers, the machine is guided to learn by providing:</p>
 
-    <p><strong>Data</strong> — the information it will learn from.</p>
-    <p><strong>Algorithm</strong> — the step-by-step method to learn from that data.</p>
+    <p>• <strong>Data</strong> – the examples it should learn from</p>
+    <p>• <strong>Algorithm</strong> – the method it should use to learn from the data</p>
 
-    <p>If the model isn’t learning well, we often keep the data as it is and try a different algorithm that might suit the problem better.</p>
+    <p>With the right guidance, the machine can learn how to make decisions on its own.The machine follows the steps given by the algorithm to learn from the data. If the learning doesn’t go well, we usually don’t change the data. Instead, we try using a better algorithm that suits the data.So, how we guide the machine using the algorithm is very important for its learning.</p>
 """, unsafe_allow_html=True)
 
-# Learning style
+
 st.markdown("""
-    <h3 style='color:#9400d3;'>Picking the Right Learning Style</h3>
-    <p>There’s no one-size-fits-all in machine learning. Depending on the problem and data, the model can learn in different ways:</p>
+    <h3 style='color:#2a52be;'>Picking the Right Learning Style</h3>
+    <p>Now that the data is ready, we need to choose how the machine should learn from it.</p>
 
-    <p><strong>Supervised learning</strong> – when the data has both questions and answers (like input and label).</p>
-    <p><strong>Unsupervised learning</strong> – when the data has no labels, and the model has to discover patterns on its own.</p>
-    <p><strong>Semi-supervised</strong> – when some data is labeled and some is not.</p>
-    <p><strong>Reinforcement learning</strong> – when the model learns by trial and error through rewards.</p>
+    <p>There are different learning styles, just like there are different ways people learn.</p>
 
-    <p>Most beginners start with supervised learning because it’s easier to understand and works well in many real-world problems.</p>
-""", unsafe_allow_html=True)
+- **Supervised** – learning from labeled data
+- **Unsupervised** – learning without answers 
+- **Semi-supervised** – mix of both
+- **Reinforcement** – learn by doing
 
-# Classification vs Regression
-st.markdown("""
-    <h3 style='color:#9400d3;'>Classification vs Regression</h3>
-    <p>In supervised learning, there are two main types of problems:</p>
+    <p>In supervised learning, there are two main types of tasks — classification and regression.</p>
+
+    <p>• <strong>Classification</strong> is used when the goal is to predict a category or group.</p>
+    <p>  For example: "Yes" or "No", or types like "Apple", "Banana", or "Orange".</p>
 
-    <p><strong>Classification</strong> – when the goal is to predict a category (like spam or not spam).</p>
-    <p><strong>Regression</strong> – when the goal is to predict a number (like the price of a house).</p>
+    <p>• <strong>Regression</strong> is used when the goal is to predict a number or value.</p>
+    <p>  For example: price, temperature, or a score.</p>
 
-    <p>The choice depends on the type of output needed. If the result is a group or label, it’s classification. If it’s a number, it’s regression.</p>
+    <p>The choice depends on the type of output expected — category or number.</p>
+    <p>Both are powerful and used in different kinds of problems.</p>
 """, unsafe_allow_html=True)
 
-# Data representation
+
 st.markdown("""
-    <h3 style='color:#9400d3;'>How Do We Represent Data?</h3>
-    <p>To help the model learn, the data must be given in a format it can understand. We write it like this:</p>
+    <h3 style='color:#2a52be;'>How Do We Represent Data to the Model?</h3>
+    <p>When training a machine learning model, the data must be given in a proper structure that the model can understand.</p>
 
+    <p>This structure usually looks like this:</p>
     <p><strong>D = { (xi, yi) }</strong></p>
 
-    <p>Each (xi, yi) pair represents one example, where:</p>
-    <p>xi is the input, and yi is the output the model should learn to predict.</p>
-
-    <p>If the output is a label, it’s classification. If it’s a number, it’s regression.</p>
-""", unsafe_allow_html=True)
+    <p>This means the dataset contains pairs of input and output values. Each pair has two parts:</p>
 
-# Preparing the data
-st.markdown("""
-    <h3 style='color:#9400d3;'>Preparing the Data Before Training</h3>
-    <p>Every dataset has two parts:</p>
+    <p>• <strong>xi</strong> is the input — the information passed to the model.</p>
+    <p>• <strong>yi</strong> is the output — the result the model should learn or predict.</p>
 
-    <p>The inputs are called <strong>features</strong>. These are the columns that help the model make decisions.</p>
-    <p>The output is called the <strong>target</strong> or <strong>label</strong>. This is what the model is supposed to learn.</p>
+    <p>How to know what kind of problem it is:</p>
+    <p>• If the output is a label or category, it's a <strong>classification</strong> problem.</p>
+    <p>• If the output is a number, it's a <strong>regression</strong> problem.</p>
 
-    <p>We first separate the features from the target so that the model clearly knows what to learn from and what to predict.</p>
+    <p>This is how the data is organized so the model can start learning from it effectively.</p>
 """, unsafe_allow_html=True)
 
-# Splitting the data
+
 st.markdown("""
-    <h3 style='color:#9400d3;'>Splitting the Data</h3>
-    <p>Once the features and target are ready, the next step is to divide the data into two sets.</p>
+    <h3 style='color:#2a52be;'>Preparing and Splitting the Data</h3>
 
-    <p>One set is used for training the model. This is what the model learns from.</p>
-    <p>The other set is for testing. This helps check if the model has learned well enough to work on new data.</p>
+    <p>Before training a machine learning model, the data must be prepared properly. This step is very important because it helps the model understand what to learn and how to learn it.</p>
 
-    <p>The data is usually split randomly. Some common ratios are:</p>
-    <p>80% training and 20% testing, or 70% training and 30% testing.</p>
+    <p>Every dataset has two main parts:</p>
+    <p>- <strong>Features</strong>: These are the input columns. They provide the information used to make predictions.</p>
+    <p>- <strong>Target</strong>: This is the output column. It contains the values the model needs to learn and predict.</p>
 
-    <p>After splitting, the names usually look like this:</p>
-    <p>X_train and y_train for the training data.</p>
-    <p>X_test and y_test for the testing data.</p>
+    <p>First, the features and the target are separated. This helps the model focus on what to learn from and what to predict.</p>
 
-    <p>This step makes sure the model is learning and not just memorizing.</p>
-""", unsafe_allow_html=True)
+    <p>Then, the data is split into two sets:</p>
+    <p>- One set for <strong>training</strong>: used to teach the model.</p>
+    <p>- One set for <strong>testing</strong>: used to check how well the model learned.</p>
 
+    <p>Common ways to split the data include:</p>
+    <p>- 80% training and 20% testing</p>
+    <p>- 70% training and 30% testing</p>
+    <p>- 60% training and 40% testing</p>
 
-st.markdown("""
-    <h2 style='color:#9400d3;'>Summary</h2>
-    <p>Model building is all about teaching a machine to learn from data.</p>
-
-    <p>✔️ Model training means helping a machine understand patterns using data and an algorithm.</p>
-    <p>✔️ We train a machine learning model — a smart system that learns to make predictions.</p>
-    <p>✔️ The machine needs data (examples) and an algorithm (learning method).</p>
-    <p>✔️ We choose how the machine learns — supervised, unsupervised, semi-supervised, or reinforcement.</p>
-    <p>✔️ In supervised learning, we use classification (for categories) or regression (for numbers).</p>
-    <p>✔️ Data is represented as input-output pairs like (xi, yi).</p>
-    <p>✔️ We prepare data by separating inputs (features) and outputs (target).</p>
-    <p>✔️ Finally, we split the data into training and testing sets to help the model learn and to evaluate its performance.</p>
-""", unsafe_allow_html=True)
+    <p>The split should be random so that every data point has a fair chance. A data point should appear in only one of the two sets — never both.</p>
 
+    <p>After splitting, these names are used:</p>
+    <p>- <strong>X_train</strong>: inputs for training</p>
+    <p>- <strong>y_train</strong>: target values for training</p>
+    <p>- <strong>X_test</strong>: inputs for testing</p>
+    <p>- <strong>y_test</strong>: target values for testing</p>
 
-st.markdown("""
-    <h3 style='color:#9400d3;'>🤖 Try It Out: Train a Simple Model</h3>
-    <p>This example shows how a basic machine learning model is trained using a few lines of code.</p>
+    <p>This process ensures the model is trained properly and can be tested fairly on data it hasn’t seen before.</p>
 """, unsafe_allow_html=True)
 
-from sklearn.linear_model import LinearRegression
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import mean_squared_error
 
-# Generate sample data
-X = np.random.rand(100, 1) * 10  # Input feature
-y = 3 * X.squeeze() + np.random.randn(100) * 2  # Output with noise
+st.markdown("""
+    <h4 style='color:#2a52be;'>Visual: Train/Test Split</h4>
+    <p>This diagram shows how the dataset is divided into training and testing sets.</p>
+""", unsafe_allow_html=True)
 
-# Split into training and testing
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+# Sample split: 80% train, 20% test
+train_ratio = 0.8
+test_ratio = 0.2
 
-# Train a model
-model = LinearRegression()
-model.fit(X_train, y_train)
+fig, ax = plt.subplots(figsize=(6, 1.5))
 
-# Make predictions
-y_pred = model.predict(X_test)
+# Plotting the train/test areas
+ax.barh(y=0, width=train_ratio, color="#66c2a5", edgecolor='black', label='Training Data')
+ax.barh(y=0, width=test_ratio, left=train_ratio, color="#fc8d62", edgecolor='black', label='Testing Data')
 
-# Show model performance
-mse = mean_squared_error(y_test, y_pred)
-st.success(f"Model trained successfully! ✅ Mean Squared Error on test data: {round(mse, 2)}")
+# Formatting
+ax.set_xlim(0, 1)
+ax.set_yticks([])
+ax.set_xticks([0.1, 0.3, 0.5, 0.7, 0.9])
+ax.set_title("Train/Test Split (80/20)", fontsize=12)
+ax.legend(loc="upper right")
+ax.axis("off")
 
-# Show plot
-fig, ax = plt.subplots()
-ax.scatter(X_test, y_test, label="Actual", color="blue")
-ax.plot(X_test, y_pred, color="red", label="Predicted Line")
-ax.set_xlabel("X")
-ax.set_ylabel("y")
-ax.set_title("Actual vs Predicted")
-ax.legend()
 st.pyplot(fig)