Update main.py

main.py

@@ -4,22 +4,29 @@
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import accuracy_score
 
+K = 5
+random_seed = 0
+test_ratio = 0.2
 
+def read_data():
+    with open('./breast-cancer-wisconsin.data', 'r') as data_fid:
+        lines = data_fid.readlines()
+        records = []
+        for line in lines:
+            if '?' in line:
+                line = line.replace('?', '11')
+            line = line.split(',')
+            line = [int(item) for item in line][1:]
+            records.append(line)
+    records = np.array(records)
+    X = records[:, :-1]
+    y = records[:, -1]
+    return X, y
 
-with open('./breast-cancer-wisconsin.data', 'r') as data_fid:
-    lines = data_fid.readlines()
-    records = []
-    for line in lines:
-        if '?' in line:
-            line = line.replace('?', '11')
-        line = line.split(',')
-        line = [int(item) for item in line][1:]
-        records.append(line)
-records = np.array(records)
-X = records[:,:-1]
-y = records[:,-1]
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
+X, y = read_data()
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_ratio, random_state=random_seed)
 
+# Naive Bayes
 clf = CategoricalNB()
 clf.fit(X_train, y_train)
 y_pred = clf.predict(X_test)
@@ -29,3 +36,5 @@
 # X_2 = X[Y==2] #benign
 # X_4 = X[Y==4] #cancer
 
+
+