arf and csv test

k.py

@@ -3,10 +3,35 @@ from sklearn.datasets import load_wine
 from mfs import MFS
 from mfs.Metrics import Metrics
 from stree import Stree
+import numpy as np
+from scipy.io import arff
+from sklearn.preprocessing import StandardScaler
 
 mfsc = MFS(discrete=False)
 mfsd = MFS(discrete=True)
-X, y = load_wine(return_X_y=True)
+
+# Xo, y = load_wine(return_X_y=True)
+# X = Xo.copy()
+# scaler = StandardScaler()
+# for c in range(X.shape[1]):
+#     X[:, c] = scaler.fit_transform(X[:, c].reshape(-1, 1)).reshape(-1)
+
+
+# data = np.genfromtxt("balance-scale.csv")
+# X = data[:, -1:]
+# y = data[:, -1]
+
+
+data, meta = arff.loadarff(
+    "/Users/rmontanana/Code/stree_datasets/data/tanveer/balance-scale/balance-scale.arff"
+)
+train = np.array([data["f1"], data["f2"], data["f3"], data["f4"]])
+y = data["clase"]
+X = train.T
+
+
+for c in range(X.shape[1]):
+    print(f"Mean: {np.mean(X[:,c])} Std: {np.std(X[:,c])}")
 m, n = X.shape
 print("* Differential entropy in X")
 for i in range(n):
@@ -39,5 +64,14 @@ clf = Stree(random_state=0)
 print("cfs discreto", clf.fit(X[:, cfs_d], y).score(X[:, cfs_d], y))
 print("cfs continuo", clf.fit(X[:, cfs_f], y).score(X[:, cfs_f], y))
 clf = Stree(random_state=0)
-subf = fcfb_f[:6]
+# subf = fcfb_f[:6]
+subf = fcfb_f
 print("fcfb", clf.fit(X[:, subf], y).score(X[:, subf], y))
+
+for c in range(X.shape[1]):
+    for k in range(X.shape[1]):
+        ac = 0
+        for v in range(X[:, c].shape[0]):
+            if X[v, c] == X[v, k]:
+                ac += 1
+        print(f"{c} {k} {ac}")