End of ML

- fixes for clustering
- fixes in general

src/learning/functions.py

@@ -1,5 +1,8 @@
 import numpy as np
 
+from learning.data import ConfusionMatrix, Data, Dataset, TargetType
+from sklearn.metrics import silhouette_score, r2_score
+
 NOT_ZERO = 1e-15
 LEAKY_RELU = 0.2
 
@@ -45,20 +48,34 @@ def cross_entropy_loss(h0:np.ndarray, y:np.ndarray) -> float:
 # Randoms
 # **********
 
-def pearson(h0:np.ndarray, y:np.ndarray) -> float:
-    diff1 = h0 - h0.mean()
-    diff2 = y - y.mean()
-    num = np.sum(diff1 * diff2)
-    den = np.sqrt(np.sum(diff1**2)) * np.sqrt(np.sum(diff2**2))
-    return num / den
-
-def r_squared(h0:np.ndarray, y:np.ndarray) -> float:
-    y_mean = np.mean(y)
-    ss_resid = np.sum((y - h0) ** 2)
-    ss_total = np.sum((y - y_mean) ** 2)
-    return 1 - (ss_resid / ss_total)
-
 def with_bias(x:np.ndarray) -> np.ndarray:
     shape = (x.shape[0], 1) if len(x.shape) != 1 else (1,)
     ones = np.ones(shape)
     return np.hstack([ones, x])
+
+def print_metrics(target:TargetType, dataset:Data, h0:np.ndarray) -> None:
+    if target == TargetType.Regression:
+        print(f"R^2        : {r2_score(dataset.y, h0):0.5f}")
+        print(f"Pearson    : {np.corrcoef(dataset.y, h0)[0, 1]:0.5f}")
+    elif target != TargetType.NoTarget:
+        if h0.ndim == 1: h0 = np.where(h0 > 0.5, 1, 0)
+        ConfusionMatrix(dataset.y, h0).print()
+    else:
+        print(f"Silhouette : {silhouette_score(dataset.x, h0):0.5f}")
+    print("========================")
+
+def print_silhouette_weka(ds:Dataset, file_weka:str):
+    test, _, _, _ = ds.get_dataset()[2].as_tuple()
+    test = np.round(test, 6)
+
+    weka = Dataset(file_weka, "", TargetType.NoTarget)
+    weka.factorize(["cluster"])
+
+    weka, _, _, _ = weka.get_dataset(test_frac=0, valid_frac=0)[0].as_tuple()
+    weka_x, weka_y = weka[:, :-1], weka[:, -1:]
+
+    bau = [np.where((weka_x == x).all(axis=1))[0][0] for x in test]
+    weka_x, weka_y = weka_x[bau], weka_y[bau].ravel()
+
+    score = silhouette_score(weka_x, weka_y)
+    print(score)