Merge pull request #4 from Stealeristaken/deneme

added optinal pca and optinal iteration

Author: cobanov

tasnif/calculations.py

@@ -49,10 +49,13 @@ def calculate_pca(embeddings, pca_dim):
     return pca_embeddings
 
 
-def calculate_kmeans(pca_embeddings, num_classes):
+def calculate_kmeans(pca_embeddings, num_classes, iter=10):
     """
     The function `calculate_kmeans` performs KMeans clustering on PCA embeddings data to assign
     labels and centroids.
+    :param pca_embeddings: The `pca_embeddings` parameter is a NumPy array containing the data points.
+    :param num_classes: The `num_classes` parameter is an integer that specifies the number of clusters.
+    :param iter: The `iter` parameter is an integer that specifies the number of iterations for the KMeans algorithm. Default is 10. Should be a positive integer.
     """
 
     if not isinstance(pca_embeddings, np.ndarray):
@@ -64,7 +67,7 @@ def calculate_kmeans(pca_embeddings, num_classes):
         )
 
     try:
-        centroid, labels = kmeans2(data=pca_embeddings, k=num_classes, minit="points")
+        centroid, labels = kmeans2(data=pca_embeddings, k=num_classes, minit="points", iter=iter)
         counts = np.bincount(labels)
         info("KMeans calculated.")
         return centroid, labels, counts

tasnif/tasnif.py

@@ -42,20 +42,26 @@ def read(self, folder_path):
         self.image_paths = read_images_from_directory(folder_path)
         self.images = read_with_pil(self.image_paths)
 
-    def calculate(self):
+    def calculate(self, pca=True, iter=10):
         """
         The function calculates embeddings, performs PCA, and applies K-means clustering to the
         embeddings. It will not perform these operations if no images have been read.
+
+        :param pca: The `pca` parameter is a boolean that specifies whether to perform PCA or not. Default is True
+        :param iter: The `iter` parameter is an integer that specifies the number of iterations for the KMeans algorithm. Default is 10.
         """
 
         if not self.images:
             raise ValueError("The images list can not be empty. Please call the read method before calculating.")
 
         self.embeddings = get_embeddings(use_gpu=self.use_gpu, images=self.images)
-        self.pca_embeddings = calculate_pca(self.embeddings, self.pca_dim)
-        self.centroid, self.labels, self.counts = calculate_kmeans(
-            self.pca_embeddings, self.num_classes
-        )
+        if pca:
+            self.pca_embeddings = calculate_pca(self.embeddings, self.pca_dim)
+            self.centroid, self.labels, self.counts = calculate_kmeans(self.pca_embeddings, self.num_classes, iter = iter)
+        else:
+            self.centroid, self.labels, self.counts = calculate_kmeans(
+                self.embeddings, self.num_classes, iter = iter
+            )
 
     def export(self, output_folder="./"):
         """