clustering plot for kmeans

app.py

@@ -54,4 +54,4 @@ def index():
 
 
 if __name__ == "__main__":
-    app.run(debug=False)
+    app.run(debug=True)

cluster/clusterer.py

@@ -7,6 +7,7 @@ import numpy as np
 @dataclass
 class Clusterer:
     cluster_func: Callable
+    plot = None
 
     def eval(
         self,

cluster/kmeans.py

@@ -74,4 +74,5 @@ class Kmeans(Clusterer):
             "k": self.k,
             "max_iter": self.max_iter,
             "clusters": cluster_data,
+            "plot": self.plot,
         }

cluster/main.py

@@ -3,6 +3,7 @@ import numpy as np
 from cluster.clusterer import Clusterer
 # for determing which clustering funciton to call
 from cluster.opts import clustering_methods
+from cluster.plot import plot
 
 
 def main(
@@ -17,4 +18,5 @@ def main(
     alg = cluster_alg.from_dict(cluster_args)
 
     alg.build(X)
+    plot(clusterer=alg, X=X)
     return alg.to_dict(X)

cluster/plot.py

@@ -0,0 +1,43 @@
+import io
+import base64
+import numpy as np
+import matplotlib
+import matplotlib.pyplot as plt 
+import seaborn as sns
+from cluster.clusterer import Clusterer
+
+
+matplotlib.use("Agg")
+sns.set()
+
+def plot(clusterer: Clusterer, X: np.array) -> None:
+    cluster_data = clusterer.to_dict(X)["clusters"]
+    # plot the clusters and data points
+    fig, ax = plt.subplots(figsize=(8, 6))
+    for cluster in cluster_data:
+        sns.scatterplot(
+            x=[point[0] for point in cluster["points"]],
+            y=[point[1] for point in cluster["points"]],
+            label=f"Cluster {cluster['cluster_id']}",
+            ax=ax,
+        )
+        ax.scatter(
+            x=cluster["centroid"][0],
+            y=cluster["centroid"][1],
+            marker="x",
+            s=100,
+            linewidth=2,
+            color="red",
+        )
+    ax.legend()
+    ax.set_title("K-means Clustering")
+    ax.set_ylabel("Normalized Petal Length (cm)")
+    ax.set_xlabel("Normalized Petal Length (cm)")
+    clusterer.plot = plt_bytes(fig)
+
+
+def plt_bytes(fig) -> str:
+    buf = io.BytesIO()
+    fig.savefig(buf, format="png")
+    plt.close(fig)
+    return base64.b64encode(buf.getvalue()).decode("utf-8")

example/neural_network.py

@@ -3,7 +3,6 @@ import seaborn as sns
 import requests
 import json
 
-# ENDPOINT: str = "https://data-mining-from-scratch-backend.onrender.com/"
 
 ENDPOINT: str = "http://127.0.0.1:5000/"
 

neural_network/neural_network.py

@@ -51,6 +51,8 @@ class NeuralNetwork:
             "func_prime": self.func_prime.__name__,
             "hidden_size": self.hidden_size,
             "mse": self.mse,
-            "loss_history": self.loss_history,
+            # not returning this because we are making our own
+            # plots and this can be a lot of data
+            # "loss_history": self.loss_history,
             "plot": self.plot,
         }