starting work with clustering algorithms

.vscode/settings.json

@@ -0,0 +1,6 @@
+{
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.autopep8"
+    },
+    "python.formatting.provider": "none"
+}

README.md

@@ -40,10 +40,9 @@ print(model_data)
 
 - Algorithm: <br>
 
-* `"neural-network"` <br>
-* `"kmeans-clustering"` <br>
-* `"kmedoid-clustering"` <br>
-* `"heirarchical-clustering"` <br>
+  -`"neural-network"` <br>
+
+  - `"kmeans-clustering"` <br> -`"kmedoid-clustering"` <br> -`"heirarchical-clustering"` <br>
 
 - Algorithm Specific Arguments
 

cluster/clusterer.py

@@ -0,0 +1,28 @@
+from dataclasses import dataclass
+from typing import Callable
+import numpy as np
+
+
+@dataclass
+class Clusterer:
+    cluster_func: Callable
+    options: dict
+
+    accuracy: float = 0
+
+    @staticmethod
+    def label():
+        return
+
+    def eval(y_pred, y_true) -> None:
+        return
+
+    @classmethod
+    def from_dict(cls, dct):
+        return cls(**dct)
+
+    def to_dict(self):
+        return {
+            "cluster_method": self.cluster_func.__name__,
+            "options": self.options,
+        }

cluster/kmeans.py

@@ -0,0 +1,13 @@
+import numpy as np
+
+
+def kmeans(
+    X_train: np.array,
+    y_train: np.array,
+    args: dict,
+):
+    # for this alg, the only argument
+    # is the number of clusters, k
+    # and max iterations
+
+    return

cluster/main.py

@@ -1,2 +1,23 @@
-def main():
+from sklearn.model_selection import train_test_split
+from typing import Callable
+import numpy as np
+
+# for determing which clustering funciton to call
+from cluster.opts import clustering_methods
+
+
+def main(
+    X: np.array,
+    y: np.array,
+    args: dict,
+):
+
+    cluster_alg: Callable = clustering_methods[args["algorithm"]]
+    X_train, X_test, y_train, y_test = train_test_split(
+        X,
+        y,
+        test_size=0.2,
+        random_state=8675309,
+    )
+
     return

cluster/opts.py

@@ -1,3 +1,3 @@
 clustering_methods = {
-
+    "kmeans": "KMeans",
 }

dataset/random.py

@@ -1,14 +0,0 @@
-import numpy as np
-
-
-def random_dataset(rows: int, features: int):
-    """
-    the random_dataset function is used to 
-    generate a random normal distribution of
-    data for testing different machine learning
-    algorithms specific to this project
-    """
-    rng = np.random.default_rng()
-    X = rng.normal(size=(rows, features))
-    y = rng.integers(5, size=(rows, 1))
-    return X, y