app.py

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.metrics import accuracy_score, f1_score
from mlxtend.plotting import plot_decision_regions

# Display image
st.image("inno.jpg", width=500)

# Streamlit app title
st.markdown("<h1 style='color:#17becf;'>ML Models Decision surface and learning curve</h1>", unsafe_allow_html=True)

# Select dataset
data = st.sidebar.selectbox('Type of data ', ('Classification', 'Circles', 'Blobs', 'Moons'))

if data == 'Classification':
    X, y = make_classification(n_samples=200, n_features=2, n_redundant=0, random_state=27)
elif data == 'Circles':
    X, y = make_circles(n_samples=200, factor=0.5, noise=0.05)
elif data == 'Blobs':
    X, y = make_blobs(n_samples=200, centers=2, n_features=2, cluster_std=1.0, random_state=27)
elif data == 'Moons':
    X, y = make_moons(n_samples=200, noise=0.1, random_state=42)

# Split dataset
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

def plot_decision_surface(X, y, model, title):
    plt.figure(figsize=(6,4))
    plot_decision_regions(X, y, clf=model)
    plt.title(title)
    st.pyplot(plt.gcf(), clear_figure=True)

# Select classifier
classifier_name = st.sidebar.selectbox('Select Classifier', ('KNN', 'Naive Bayes', 'Logistic Regression', 'DecisionTreeClassifier'))

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'))
    
    model = KNeighborsClassifier(n_neighbors=n_neighbors, weights=weights, algorithm=algorithm)
    
elif classifier_name == 'Naive Bayes':
    model = GaussianNB()
    
elif classifier_name == 'DecisionTreeClassifier':
    model = DecisionTreeClassifier()
    
else:
    model = LogisticRegression()

# 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.subheader("Model Performance")
st.write(f"*Accuracy:* {accuracy:.2f}")
st.write(f"*F1-score:* {f1:.2f}")

# Plot 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")
    plt.plot(train_sizes, test_mean, 'o-', label="Validation Accuracy")
    
    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)