App.py

app.py

@@ -0,0 +1,89 @@
+import streamlit as st
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.datasets import make_blobs
+from sklearn.cluster import KMeans
+import pandas as pd
+from csv_create import blob_data
+import atexit
+
+# Function to plot the Voronoi diagram
+
+
+def plot_voronoi(X, kmeans, added_points):
+    # Create a meshgrid of points to plot the Voronoi diagram
+    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, 0.1),
+                         np.arange(y_min, y_max, 0.1))
+
+    # Predict the cluster labels for the meshgrid points
+    Z = kmeans.predict(np.c_[xx.ravel(), yy.ravel()])
+    Z = Z.reshape(xx.shape)
+
+    # Predict the cluster labels for the data points
+    y_pred = kmeans.predict(X)
+
+    # Plot the Voronoi diagram and the data points
+    plt.figure(figsize=(10, 8))
+    plt.contourf(xx, yy, Z, alpha=0.4)
+    plt.scatter(X[:, 0], X[:, 1], c=y_pred, alpha=0.8, edgecolors='k')
+    plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[
+                :, 1], marker='*', s=300, c='r')
+    if added_points:
+        for point in added_points:
+            plt.scatter(point[:, 0], point[:, 1], marker='x',
+                        s=200, linewidths=3, color='black')
+    plt.xlabel('Feature 1')
+    plt.ylabel('Feature 2')
+    plt.title('KMeans Clustering')
+    st.pyplot(plt)
+
+
+def run_kmeans_app():
+    # Create a clustered dataset using make_blobs
+    df = pd.read_csv('blobs.csv')
+    X = df[['feature1', 'feature2']].values
+
+    # Initialize KMeans with 3 clusters
+    kmeans = KMeans(n_clusters=3, random_state=42).fit(X)
+
+    # Streamlit app to add random data points and visualize the changing predictions
+    st.title('KMeans Clustering')
+    st.write('This app allows you to add random data points to an initial clustered dataset and visualize the changing predictions using a Voronoi diagram.')
+    st.write('Initial dataset:')
+    plot_voronoi(X, kmeans, added_points=[])
+
+    # Add random data points to the initial dataset
+    num_points = 1
+    added_points = []
+
+    button = st.button(f'Add random data point(s)')
+    if button:
+        # Generate a random data point
+        for i in range(num_points):
+            new_point = np.random.uniform(
+                low=X.min(), high=X.max(), size=(1, 2))
+            # added_points.append(new_point)
+            # Add the random data point to the dataset
+            X = np.vstack((X, new_point))
+        # Update the KMeans model with the new data point
+        kmeans = KMeans(n_clusters=3, random_state=42).fit(X)
+        df_new = pd.DataFrame(new_point, columns=["feature1", "feature2"])
+        df_new["label"] = kmeans.predict(new_point)
+        with open("blobs.csv", "a") as f:
+            df_new.to_csv(f, header=False, index=False)
+        # Plot the updated Voronoi diagram
+        st.write(f'Updated dataset after adding {i+1} random data point(s):')
+        plot_voronoi(X, kmeans, added_points)
+
+    # Concatenate the added points with the initial dataset
+    if added_points:
+        added_points = np.vstack(added_points)
+        X = np.vstack((X[:-len(added_points)], added_points))
+
+
+if __name__ == '__main__':
+    run_kmeans_app()
+
+atexit.register(blob_data)

blobs.csv

@@ -0,0 +1,101 @@
+feature1,feature2,label
+-7.726420909219675,-8.39495681796181,2
+5.453396053597771,0.7423053675067768,1
+-2.978672008987702,9.556846171784287,0
+6.042673147164201,0.5713186211484511,1
+-6.521839830802987,-6.319325066907712,2
+3.649342511097413,1.40687195433796,1
+-2.1779341916491863,9.98983125532068,0
+4.4202069483905895,2.3302822554524782,1
+4.736956385576142,2.9418146744736213,1
+-3.6601912004750528,9.389984146543993,0
+-3.053580347577933,9.125208717908187,0
+-6.65216725654714,-5.572966838993518,2
+-6.357685625534373,-6.583124920042761,2
+-3.6155325970587784,7.818079504117651,0
+-1.7707310430573397,9.185654409388292,0
+-7.950519689212382,-6.397637178032761,2
+-6.602936391821251,-6.052926344239923,2
+-2.581207744633084,10.017819026090345,0
+-7.763484627352403,-6.726384487330419,2
+-6.406389566577725,-6.95293850593282,2
+-2.9726153158652124,8.548556374628065,0
+-6.956728900565374,-6.538957618459302,2
+-7.326142143218291,-6.023710798952474,2
+-2.147802017544336,10.55232269466429,0
+-2.5450236621627016,10.578929784012328,0
+-2.9698363940125376,10.071408354417237,0
+3.224508094177687,1.552524361175373,1
+-6.253959843386264,-7.737267149692229,2
+-7.854308861378591,-6.093024989533495,2
+-8.116577902029352,-8.200566206360223,2
+-7.559651912729761,-6.647855896114943,2
+4.935999113292677,2.234224956120621,1
+4.447517871446979,2.2747170262743444,1
+-5.721031612143866,-7.7007919116276575,2
+-0.9299848075453587,9.78172085735123,0
+-3.109836312971555,8.722592378405045,0
+-2.4416694183648264,7.589537941984865,0
+-2.185113653657955,8.629203847782005,0
+5.5552809539301755,2.3019207936004165,1
+4.731639612763604,-0.0143992306601608,1
+-8.257296559108362,-7.8179346331910695,2
+-2.9883718608980403,8.828627151534505,0
+4.605167066522858,0.8044916463212,1
+-3.837383671951181,9.211147364067445,0
+-2.6248459054409907,8.713182432609033,0
+3.5775751225019965,2.4467621145759137,1
+-8.487110425712498,-6.695475734743642,2
+-6.706446265300088,-6.49479221354711,2
+-6.866625299273363,-5.42657551611863,2
+3.8313852333349137,1.4714126403561956,1
+2.020133732138357,2.795072188315956,1
+4.644992292870563,1.7385825505655852,1
+-1.6966718006585522,10.370526156769145,0
+-6.619744396902846,-6.098286721498637,2
+-6.05756703115678,-4.9833166106219995,2
+-7.103089976477121,-6.1661090991838545,2
+-3.5220287433871738,9.328533460793595,0
+-2.267235351486716,7.101005883540523,0
+6.117772880969618,1.4548994656670846,1
+-4.234115455565783,8.45199859895735,0
+-6.5865547178525885,-7.5944610113023145,2
+3.937825742350749,1.6455075373429637,1
+-7.125015307154141,-7.633845757633436,2
+2.72110762092906,1.946655808491515,1
+-7.1442840243892265,-4.159940426686328,2
+-6.665533447021066,-8.125848371987935,2
+4.7001090461691275,4.436411796426018,1
+-7.769141620776793,-7.695919878241385,2
+4.110118632461063,2.486437117054088,1
+4.897429226950866,1.8987237681745648,1
+4.297164319701332,1.170892414719113,1
+-6.629134340805393,-6.533661383778971,2
+-8.070930688353918,-6.2235559846421165,2
+-2.1655793334842888,7.251245972835587,0
+4.739530201315743,1.4696940298245327,1
+-5.916251061906948,-6.467328666339449,2
+5.430910783271148,1.063782229145993,1
+-6.82141847270527,-8.023079891106569,2
+6.526064737438632,2.147747496772571,1
+3.0892154051619687,2.0417326587467595,1
+-2.147561598005116,8.369166373593197,0
+3.856625543891864,1.6511081677350563,1
+-1.686652710949561,7.793442478227299,0
+-5.013852680006513,-6.406276672364159,2
+-2.5226948477906843,7.956575199242421,0
+-2.300334028047995,7.054616004318546,0
+-1.0435488541311961,8.788509827711787,0
+3.720454601994298,3.5231040889582714,1
+-3.9877196134201776,8.294441919803614,0
+4.247770683095943,0.5096547358086134,1
+4.726925904466273,1.6741623334748645,1
+5.782701650743122,2.7251027166275064,1
+-3.417221698573961,7.60198242686303,0
+5.226735930028371,4.16362530975071,1
+-3.110904235282147,10.86656431270726,0
+-3.186119623358709,9.62596241703919,0
+-1.4781981005567992,9.94556624731452,0
+4.478593124562092,2.3772205407552702,1
+-5.7965759479759935,-5.826307541241044,2
+-3.348415146275389,8.705073752347108,0

csv_create.py

@@ -0,0 +1,21 @@
+from sklearn.datasets import make_blobs
+import pandas as pd
+import os
+
+
+def blob_data():
+    # Specify the file path
+    file_path = "blobs.csv"
+
+    # Check if the file exists
+    if os.path.isfile(file_path):
+        # Delete the file if it exists
+        os.remove(file_path)
+
+    # Generate 100 datapoints using make_blobs
+    X, y = make_blobs(n_samples=100, centers=3, n_features=2, random_state=42)
+
+    # Save data to a CSV file
+    df = pd.DataFrame(X, columns=["feature1", "feature2"])
+    df["label"] = y
+    df.to_csv("blobs.csv", index=False)