move metrics to metrics.py

Author: AkiRusProd

decision_tree_classifier.py

@@ -1,5 +1,6 @@
 import numpy as np 
-from utils import generate_clusterization_data, split_data, accuracy
+from utils import generate_clusterization_data, split_data
+from metrics import accuracy
 
 
 

gradient_boosting_classifier.py

@@ -1,7 +1,8 @@
 import numpy as np 
 
 from decision_tree_regressor import DecisionTreeRegressor, Node
-from utils import generate_clusterization_data, split_data, accuracy
+from utils import generate_clusterization_data, split_data
+from metrics import accuracy
 
 #https://maelfabien.github.io/machinelearning/GradientBoostC/#gradient-boosting-classification-steps
 #https://www.youtube.com/watch?v=jxuNLH5dXCs&ab_channel=StatQuestwithJoshStarmer

logistic_regression.py

@@ -1,7 +1,8 @@
 import numpy as np
 import matplotlib.pyplot as plt
 from tqdm import tqdm
-from  utils import generate_clusterization_data, split_data, accuracy
+from utils import generate_clusterization_data, split_data
+from metrics import accuracy
 
 
 #https://www.python-unleashed.com/post/derivation-of-the-binary-cross-entropy-loss-gradient

roc_auc.py metrics.py

@@ -1,10 +1,11 @@
 import numpy as np
 import matplotlib.pyplot as plt
 from logistic_regression import LogisticRegression
-from utils import generate_clusterization_data, split_data, accuracy
+from utils import generate_clusterization_data, split_data
 
 
-#In fact roc_curve cannot be considered a separate algorithm; it is an evaluation metric in binary classification problems
+def accuracy(targets, predictions):
+    return np.equal(targets, predictions).mean()
 
 def roc_сurve(y_true: np.ndarray[int], y_score: np.ndarray[float]):
     sorted_indices = np.argsort(y_score)[::-1]

naive_bayes_classifier.py

@@ -1,5 +1,6 @@
 import numpy as np
-from utils import generate_clusterization_data, split_data, accuracy
+from utils import generate_clusterization_data, split_data
+from metrics import accuracy
 
 
 

random_forest_classifier.py

@@ -1,6 +1,7 @@
 import numpy as np
 from decision_tree_classifier import DecisionTreeClassifier
-from utils import generate_clusterization_data, split_data, accuracy
+from utils import generate_clusterization_data, split_data
+from metrics import accuracy
 
 
 #https://en.wikipedia.org/wiki/Random_forest

svm.py

@@ -1,6 +1,7 @@
 import numpy as np
 import matplotlib.pyplot as plt
-from utils import generate_clusterization_data, split_data, accuracy
+from utils import generate_clusterization_data, split_data
+from metrics import accuracy
 
 
 

utils.py

@@ -77,5 +77,3 @@ def split_data(X, y = None, ratio = 0.25):
     return X_train, X_test, y_train, y_test
 
 
-def accuracy(targets, predictions):
-    return np.equal(targets, predictions).mean()