Fixed some code style issues #207

Author: dpuenteramirez

instance_selection/_CNN.py

@@ -79,7 +79,7 @@ def filter(self, samples, y):
                     indexes.append(index)
                     store_not_modified = True
             delete_multiple_element(handbag, indexes)
-        del handbag
+
         samples = pd.DataFrame(store, columns=self.x_attr)
         y = pd.DataFrame(
             np.array(store_classes, dtype=object).flatten().astype(int))

instance_selection/_LocalSets.py

@@ -146,10 +146,6 @@ class LSSm(LocalSets):
 
     """
 
-    def __init__(self):
-        """A constructor for the class."""
-        super().__init__()
-
     def filter(self, instances, labels):
         """
         The function takes in a dataframe of instances and a dataframe of
@@ -200,10 +196,6 @@ class LSBo(LocalSets):
 
     """
 
-    def __init__(self):
-        """A constructor for the class."""
-        super(LSBo, self).__init__()
-
     def filter(self, instances, labels):
         """
         > The function takes in a dataframe of instances and a dataframe of

instance_selection/_MSS.py

@@ -90,10 +90,9 @@ def _enemy_distance(dat, tar):
             for sample_1, x1_class in zip(dat, tar):
                 if x1_class == x_class:
                     continue
-                else:
-                    euc = np.linalg.norm(sample - sample_1)
-                    if euc < distance:
-                        distance = euc
+                euc = np.linalg.norm(sample - sample_1)
+                if euc < distance:
+                    distance = euc
             solution.append([sample, x_class, distance])
 
         solution.sort(key=lambda x: x[2])

semisupervised/DemocraticCoLearning.py

@@ -395,7 +395,7 @@ def predict(self, samples):
         confidence = [0 for _ in range(self.n_labels)]
         for index, j in enumerate(gj):
             izq = (j + 0.5) / (j + 1)
-            div = True if j != 0 else False
+            div = j != 0
             if div:
                 der = [
                     (gj_h[0][index] * self.w1) / gj[index],

semisupervised/DensityPeaks.py

@@ -16,7 +16,6 @@
 from sklearn.svm import SVC
 
 from instance_selection import ENN
-
 from .utils import split
 
 
@@ -32,19 +31,19 @@ class STDPNF:
     """
 
     def __init__(
-        self,
-        dc=None,
-        distance_metric="euclidean",
-        k=3,
-        gauss_cutoff=True,
-        percent=2.0,
-        density_threshold=None,
-        distance_threshold=None,
-        anormal=True,
-        filtering=False,
-        classifier=None,
-        classifier_params=None,
-        filter_method=None,
+            self,
+            dc=None,
+            distance_metric="euclidean",
+            k=3,
+            gauss_cutoff=True,
+            percent=2.0,
+            density_threshold=None,
+            distance_threshold=None,
+            anormal=True,
+            filtering=False,
+            classifier=None,
+            classifier_params=None,
+            filter_method=None,
     ):
         """Semi Supervised Algorithm based on Density Peaks."""
         self.dc = dc
@@ -70,6 +69,22 @@ def __init__(
         else:
             self.filter = None
 
+        self.y = None
+        self.l = None
+        self.u = None
+        self.classifier_stdpnf = None
+        self.order = None
+        self.structure = None
+        self.structure_stdnpf = None
+        self.n_id = None
+        self.distances = None
+        self.max_dis = None
+        self.min_dis = None
+        self.rho = None
+        self.delta = None
+        self.nneigh = None
+        self.data = None
+
     def __build_distance(self):
         """
         Calculate distance dict.
@@ -106,7 +121,8 @@ def __auto_select_dc(self):
 
         while True:
             nneighs = (
-                sum([1 for v in self.distances.values() if v < dc]) / self.n_id**2
+                    sum([1 for v in self.distances.values() if
+                         v < dc]) / self.n_id ** 2
             )
             if 0.01 <= nneighs <= 0.02:
                 break
@@ -460,7 +476,7 @@ def _fit_stdpnf(self):
         while count <= max(self.order.values()):
             unlabeled_rows = self.structure_stdnpf.loc[
                 self.structure_stdnpf["label"] == -1
-            ].index.to_list()
+                ].index.to_list()
             unlabeled_indexes = []
             for row in unlabeled_rows:
                 if self.order[row] == count:
@@ -476,7 +492,7 @@ def _fit_stdpnf(self):
             else:
                 labeled_data = self.structure_stdnpf.loc[
                     self.structure_stdnpf["label"] != -1
-                ]
+                    ]
                 complete = labeled_data["sample"]
                 complete_y = labeled_data["label"]
 
@@ -486,14 +502,15 @@ def _fit_stdpnf(self):
 
             labeled_data = self.structure_stdnpf.loc[
                 self.structure_stdnpf["label"] != -1
-            ]
+                ]
             self.classifier_stdpnf.fit(
                 labeled_data["sample"].tolist(), labeled_data["label"].tolist()
             )
 
             count += 1
 
-        labeled_data = self.structure_stdnpf.loc[self.structure_stdnpf["label"] != -1]
+        labeled_data = self.structure_stdnpf.loc[
+            self.structure_stdnpf["label"] != -1]
         self.classifier_stdpnf.fit(
             labeled_data["sample"].tolist(), labeled_data["label"].tolist()
         )
@@ -516,7 +533,8 @@ def _results_to_structure(self, complete, result):
             if not is_in:
                 results_to_unlabeled.append(r)
         for r in results_to_unlabeled:
-            self.structure_stdnpf.at[np.array(self.structure_stdnpf["sample"], r)][
+            self.structure_stdnpf.at[
+                np.array(self.structure_stdnpf["sample"], r)][
                 "label"
             ] = -1
 

utils/arff2dataset.py

@@ -20,6 +20,8 @@ def arff_data(dataset_path, attr=False):
     defaults to False (optional)
     :return: A bunch object with the data, target and attributes.
     """
+    if not ".arff" in str(dataset_path).lower():
+        raise ValueError("File does not an ARFF extension.")
     file = open(dataset_path, "r")
     attrs, data = _read_file(file)
     file.close()
@@ -33,8 +35,7 @@ def arff_data(dataset_path, attr=False):
 
     if not attr:
         return Bunch(data=data, target=labels)
-    else:
-        return Bunch(data=data, target=labels, attr=attrs)
+    return Bunch(data=data, target=labels, attr=attrs)
 
 
 def _read_file(file):