Update app.py

app.py

@@ -1,118 +1,118 @@
-import streamlit as st
-import numpy as np
-import matplotlib.pyplot as plt
-from sklearn.datasets import make_classification, make_circles, make_blobs, make_moons
-from sklearn.model_selection import train_test_split, learning_curve
-from sklearn.neighbors import KNeighborsClassifier
-from sklearn.naive_bayes import GaussianNB
-from sklearn.linear_model import LogisticRegression
-from sklearn.tree import DecisionTreeClassifier
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.svm import SVC
-from sklearn.metrics import accuracy_score, f1_score
-from mlxtend.plotting import plot_decision_regions
-
-# Display image
-# st.markdown("<div style='text-align: center;'>"
-#     "<img src='inno.jpg' width='700' height='400'>"
-#     "</div>", 
-#     unsafe_allow_html=True)
-from PIL import Image
-
-image = Image.open("Inno.jpg")
-image = image.resize((800, 500))  # Resize image before displaying
-st.image(image)
-
-# Streamlit app title with color
-st.markdown("<h1 style='text-align: center; color: #FF5733;'>Boundary Surfaces Visualization</h1>", unsafe_allow_html=True)
-
-# Select dataset
-data = st.sidebar.selectbox('Select Dataset', ('Classification', 'Circles', 'Blobs', 'Moons'))
-
-if data == 'Classification':
-    X, y = make_classification(n_samples=100, n_features=2, n_redundant=0, random_state=27)
-elif data == 'Circles':
-    X, y = make_circles(n_samples=100, factor=0.5, noise=0.05)
-elif data == 'Blobs':
-    X, y = make_blobs(n_samples=250, centers=2, n_features=2, cluster_std=1.0, random_state=27)
-elif data == 'Moons':
-    X, y = make_moons(n_samples=250, noise=0.1, random_state=27)
-
-# Split dataset
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=27)
-
-def plot_decision_surface(X, y, model, title):
-    plt.figure(figsize=(6,4))
-    plot_decision_regions(X, y, clf=model, colors="#7f7f7f,#bcbd22,#17becf")
-    plt.title(title)
-    st.pyplot(plt.gcf(), clear_figure=True)
-
-# Select classifier
-classifier_name = st.sidebar.selectbox('Select Classifier', 
-    ('KNN', 'Naive Bayes', 'Logistic Regression', 'Decision Tree', 'Random Forest', 'SVM'))
-
-# Initialize model based on user selection
-if classifier_name == 'KNN':
-    n_neighbors = st.sidebar.slider('Number of Neighbors (k)', 1, 15, 3)
-    weights = st.sidebar.radio('Weight Function', ('uniform', 'distance'))
-    algorithm = st.sidebar.selectbox('Algorithm', ('auto', 'ball_tree', 'kd_tree', 'brute'))
-    p = st.sidebar.slider("Distance Parameter (p)", 1, 5, 2)
-    model = KNeighborsClassifier(n_neighbors=n_neighbors, weights=weights, algorithm=algorithm,p=p)
-
-elif classifier_name == 'Naive Bayes':
-    model = GaussianNB()
-
-elif classifier_name == 'Logistic Regression':
-    model = LogisticRegression()
-
-elif classifier_name == 'Decision Tree':
-    model = DecisionTreeClassifier()
-
-elif classifier_name == 'Random Forest':
-    n_estimators = st.sidebar.slider('Number of Trees', 10, 200, 100)
-    model = RandomForestClassifier(n_estimators=n_estimators)
-
-elif classifier_name == 'SVM':
-    kernel = st.sidebar.selectbox('Kernel Type', ('linear', 'poly', 'rbf', 'sigmoid'))
-    C = st.sidebar.slider('Regularization (C)', 0.01, 10.0, 1.0)
-    model = SVC(kernel=kernel, C=C)
-
-# Train model
-model.fit(X_train, y_train)
-
-# Make predictions
-y_pred = model.predict(X_test)
-
-# Compute accuracy & F1-score
-accuracy = accuracy_score(y_test, y_pred)
-f1 = f1_score(y_test, y_pred)
-
-# Display metrics in Streamlit
-st.markdown("<h3 style='color: #4CAF50;'>📊 Model Performance</h3>", unsafe_allow_html=True)
-st.write(f"✅ **Accuracy:** {accuracy:.2f}")
-st.write(f"📏 **F1-score:** {f1:.2f}")
-
-# Plot decision boundary
-st.subheader("📍 Decision Boundary")
-plot_decision_surface(X, y, model, f'{classifier_name} Decision Surface')
-
-# Plot Learning Curve
-def plot_learning_curve(model, X, y):
-    train_sizes, train_scores, test_scores = learning_curve(model, X, y, cv=5, scoring='accuracy', train_sizes=np.linspace(0.1, 1.0, 10))
-    
-    train_mean = np.mean(train_scores, axis=1)
-    test_mean = np.mean(test_scores, axis=1)
-    
-    plt.figure(figsize=(6,4))
-    plt.plot(train_sizes, train_mean, 'o-', label="Training Accuracy", color="blue")
-    plt.plot(train_sizes, test_mean, 'o-', label="Validation Accuracy", color="red")
-    
-    plt.xlabel("Training Samples")
-    plt.ylabel("Accuracy")
-    plt.title(f"Learning Curve: {classifier_name}")
-    plt.legend()
-    st.pyplot(plt.gcf(), clear_figure=True)
-
-# Display Learning Curve
-st.subheader("📈 Learning Curve")
-plot_learning_curve(model, X, y)
+import streamlit as st
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.datasets import make_classification, make_circles, make_blobs, make_moons
+from sklearn.model_selection import train_test_split, learning_curve
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.naive_bayes import GaussianNB
+from sklearn.linear_model import LogisticRegression
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.svm import SVC
+from sklearn.metrics import accuracy_score, f1_score
+from mlxtend.plotting import plot_decision_regions
+
+# Display image
+# st.markdown("<div style='text-align: center;'>"
+#     "<img src='inno.jpg' width='700' height='400'>"
+#     "</div>", 
+#     unsafe_allow_html=True)
+from PIL import Image
+
+# image = Image.open("Inno.jpg")
+# image = image.resize((800, 500))  # Resize image before displaying
+st.image("innomatics-footer-logo.webp", use_container_width=True, width=300)
+
+# Streamlit app title with color
+st.markdown("<h1 style='text-align: center; color: #FF5733;'>Boundary Surfaces Visualization</h1>", unsafe_allow_html=True)
+
+# Select dataset
+data = st.sidebar.selectbox('Select Dataset', ('Classification', 'Circles', 'Blobs', 'Moons'))
+
+if data == 'Classification':
+    X, y = make_classification(n_samples=100, n_features=2, n_redundant=0, random_state=27)
+elif data == 'Circles':
+    X, y = make_circles(n_samples=100, factor=0.5, noise=0.05)
+elif data == 'Blobs':
+    X, y = make_blobs(n_samples=250, centers=2, n_features=2, cluster_std=1.0, random_state=27)
+elif data == 'Moons':
+    X, y = make_moons(n_samples=250, noise=0.1, random_state=27)
+
+# Split dataset
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=27)
+
+def plot_decision_surface(X, y, model, title):
+    plt.figure(figsize=(6,4))
+    plot_decision_regions(X, y, clf=model, colors="#7f7f7f,#bcbd22,#17becf")
+    plt.title(title)
+    st.pyplot(plt.gcf(), clear_figure=True)
+
+# Select classifier
+classifier_name = st.sidebar.selectbox('Select Classifier', 
+    ('KNN', 'Naive Bayes', 'Logistic Regression', 'Decision Tree', 'Random Forest', 'SVM'))
+
+# Initialize model based on user selection
+if classifier_name == 'KNN':
+    n_neighbors = st.sidebar.slider('Number of Neighbors (k)', 1, 15, 3)
+    weights = st.sidebar.radio('Weight Function', ('uniform', 'distance'))
+    algorithm = st.sidebar.selectbox('Algorithm', ('auto', 'ball_tree', 'kd_tree', 'brute'))
+    p = st.sidebar.slider("Distance Parameter (p)", 1, 5, 2)
+    model = KNeighborsClassifier(n_neighbors=n_neighbors, weights=weights, algorithm=algorithm,p=p)
+
+elif classifier_name == 'Naive Bayes':
+    model = GaussianNB()
+
+elif classifier_name == 'Logistic Regression':
+    model = LogisticRegression()
+
+elif classifier_name == 'Decision Tree':
+    model = DecisionTreeClassifier()
+
+elif classifier_name == 'Random Forest':
+    n_estimators = st.sidebar.slider('Number of Trees', 10, 200, 100)
+    model = RandomForestClassifier(n_estimators=n_estimators)
+
+elif classifier_name == 'SVM':
+    kernel = st.sidebar.selectbox('Kernel Type', ('linear', 'poly', 'rbf', 'sigmoid'))
+    C = st.sidebar.slider('Regularization (C)', 0.01, 10.0, 1.0)
+    model = SVC(kernel=kernel, C=C)
+
+# Train model
+model.fit(X_train, y_train)
+
+# Make predictions
+y_pred = model.predict(X_test)
+
+# Compute accuracy & F1-score
+accuracy = accuracy_score(y_test, y_pred)
+f1 = f1_score(y_test, y_pred)
+
+# Display metrics in Streamlit
+st.markdown("<h3 style='color: #4CAF50;'>📊 Model Performance</h3>", unsafe_allow_html=True)
+st.write(f"✅ **Accuracy:** {accuracy:.2f}")
+st.write(f"📏 **F1-score:** {f1:.2f}")
+
+# Plot decision boundary
+st.subheader("📍 Decision Boundary")
+plot_decision_surface(X, y, model, f'{classifier_name} Decision Surface')
+
+# Plot Learning Curve
+def plot_learning_curve(model, X, y):
+    train_sizes, train_scores, test_scores = learning_curve(model, X, y, cv=5, scoring='accuracy', train_sizes=np.linspace(0.1, 1.0, 10))
+    
+    train_mean = np.mean(train_scores, axis=1)
+    test_mean = np.mean(test_scores, axis=1)
+    
+    plt.figure(figsize=(6,4))
+    plt.plot(train_sizes, train_mean, 'o-', label="Training Accuracy", color="blue")
+    plt.plot(train_sizes, test_mean, 'o-', label="Validation Accuracy", color="red")
+    
+    plt.xlabel("Training Samples")
+    plt.ylabel("Accuracy")
+    plt.title(f"Learning Curve: {classifier_name}")
+    plt.legend()
+    st.pyplot(plt.gcf(), clear_figure=True)
+
+# Display Learning Curve
+st.subheader("📈 Learning Curve")
+plot_learning_curve(model, X, y)