Add ML intuitions py file

app.py

@@ -9,6 +9,10 @@ import matplotlib.pyplot as plt
 import seaborn as sns
 import pandas as pd
 import time
+from sklearn.datasets import make_classification, make_circles, make_moons
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.svm import SVC
 
 def load_and_train_model():
     data = load_breast_cancer()
@@ -25,6 +29,19 @@ def load_and_train_model():
 
     return model, X, y, acc, cm, data
 
+# Helper function to plot decision boundary
+def plot_decision_boundary(clf, X, y, ax, title):
+    h = .02
+    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
+    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
+    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
+                         np.arange(y_min, y_max, h))
+    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
+    Z = Z.reshape(xx.shape)
+    ax.contourf(xx, yy, Z, alpha=0.3)
+    ax.scatter(X[:, 0], X[:, 1], c=y, edgecolors='k', s=40)
+    ax.set_title(title)
+
 def main():
     st.set_page_config(page_title="Breast Cancer Classifier", layout="wide")
 
@@ -33,7 +50,7 @@ def main():
     X = pd.DataFrame(data.data, columns=data.feature_names)
     y = pd.Series(data.target)
 
-    st.subheader("Classifying breast cancer - with Logistic Regression")
+    st.subheader("Breast Cancer Classification with Logistic Regression")
 
     #st.write(f"**Problem Statement**")
     with st.expander("📌 What we're trying to accomplish..."):
@@ -146,6 +163,32 @@ def main():
 
         These examples underline the importance of **feature engineering** and **domain knowledge** in building effective ML systems.
         """)
+    
+        # Create 3 plots for different domains
+        fig, axes = plt.subplots(1, 3, figsize=(20, 6))
+
+        # 1. Healthcare - Linearly Separable
+        X1, y1 = make_classification(n_samples=200, n_features=2, n_redundant=0,
+                                    n_informative=2, n_clusters_per_class=1, class_sep=2.0, random_state=1)
+        clf1 = make_pipeline(StandardScaler(), SVC(kernel='linear', C=1.0))
+        clf1.fit(X1, y1)
+        plot_decision_boundary(clf1, X1, y1, axes[0], "Healthcare (Linear SVM)")
+
+        # 2. Finance - Concentric Circles
+        X2, y2 = make_circles(n_samples=200, factor=0.5, noise=0.05, random_state=2)
+        clf2 = make_pipeline(StandardScaler(), SVC(kernel='rbf', C=1.0, gamma='auto'))
+        clf2.fit(X2, y2)
+        plot_decision_boundary(clf2, X2, y2, axes[1], "Finance (RBF SVM - Circles)")
+
+        # 3. Retail - Semi Circles
+        X3, y3 = make_moons(n_samples=200, noise=0.1, random_state=3)
+        clf3 = make_pipeline(StandardScaler(), SVC(kernel='rbf', C=1.0, gamma='auto'))
+        clf3.fit(X3, y3)
+        plot_decision_boundary(clf3, X3, y3, axes[2], "Retail (RBF SVM - Moons)")
+
+        # Show plot in Streamlit
+        st.pyplot(fig)    
+    
         
     # feature discriminatio
     # Load dataset