Create app.py

app.py

@@ -0,0 +1,61 @@
+import streamlit as st
+import numpy as np
+import matplotlib.pyplot as plt
+
+st.subheader("K nearest neighbor (KNN) classification")
+
+st_col = st.columns(1)[0]
+
+K = st.slider('Number of nearest neighbors (K)', min_value=1, max_value=10, value=5, step=1)
+
+from sklearn.neighbors import KNeighborsClassifier as KNN
+from sklearn.model_selection import cross_val_score
+
+from sklearn.datasets import make_blobs
+X, y = make_blobs(n_samples=1000, centers=3, n_features=2, cluster_std=6, random_state=42)
+ntrain = 100
+
+x_train = X[:ntrain]
+y_train = y[:ntrain]
+x_test = X[ntrain:]
+y_test = y[ntrain:]
+
+knn = KNN(n_neighbors=K)
+knn.fit(x_train, y_train)
+plt.figure()
+
+x = np.linspace(np.min(x_test[:, 0]), np.max(x_test[:, 0]), 200)
+y = np.linspace(np.min(x_test[:, 1]), np.max(x_test[:, 1]), 200)
+xx, yy = np.meshgrid(x, y)
+xy = np.c_[xx.ravel(), yy.ravel()]
+
+y_predicted = knn.predict(xy)
+#plt.pcolormesh(y_predicted.reshape(200, 200), cmap='jet')
+plt.pcolormesh(xx, yy, y_predicted.reshape(200, 200), cmap='jet', alpha=0.2)
+y_unique = np.unique(y_train)
+markers = '*x+'
+colors = 'bgr'
+for i in range(len(y_unique)):
+  plt.scatter(x_train[y_train == y_unique[i], 0],
+               x_train[y_train == y_unique[i], 1],
+               marker=markers[i],
+               c=colors[i])
+               
+
+with st_col:
+  st.pyplot(plt)
+  
+hide_streamlit_style = """
+            <style>
+            #MainMenu {visibility: hidden;}
+            footer {visibility: hidden;}
+            subheader {alignment: center;}
+            </style>
+            """
+st.markdown(hide_streamlit_style, unsafe_allow_html=True) 
+
+st.markdown("""
+            There are several points to note on the effect of K on the quality of model fit:
+            * Models with extremely small values of K learn the local patterns and do not generalize well thus they have a high variance or overfitting effect.
+            * Models with extremely high values of K suffer from averaging effect over the entire space and thus do not do well even on the train points. This is known as a high bias or underfitting effect.
+            """)