fixed errors from precommit hooks, mainly flake8

flake8 was giving incorrect compare types on some files.

"do not compare types. Use is, is not, or isinstance() instead."

Author: HashirA123

data/catalog/_data_main/process_data/process_utils_data.py

@@ -22,13 +22,15 @@ def get_one_hot_encoding(in_arr):
     output: m (ndarray): one-hot encoded matrix
             d (dict): also returns a dictionary original_val -> column in encoded matrix
     """
+    valid_types = (int, np.int64, float, np.float64)
 
     for k in in_arr:
-        if (
-            str(type(k)) != "<type 'numpy.float64'>"
-            and type(k) != int
-            and type(k) != np.int64
-        ):
+        # if (
+        #     str(type(k)) != "<type 'numpy.float64'>"
+        #     and type(k) != int
+        #     and type(k) != np.int64
+        # ):
+        if not isinstance(k, valid_types):
             print(str(type(k)))
             print("************* ERROR: Input arr does not have integer types")
             return None

methods/catalog/focus/model.py

@@ -46,9 +46,13 @@ def _filter_hinge_loss(n_class, mask_vector, features, sigma, temperature, model
     filtered_input = tf.boolean_mask(features, mask_vector)
 
     # if sigma or temperature are not scalars
-    if type(sigma) != float or type(sigma) != int:
+    if not isinstance(
+        sigma, (float, int)
+    ):  # type(sigma) != float or type(sigma) != int:
         sigma = tf.boolean_mask(sigma, mask_vector)
-    if type(temperature) != float or type(temperature) != int:
+    if not isinstance(
+        temperature, (float, int)
+    ):  # type(temperature) != float or type(temperature) != int:
         temperature = tf.boolean_mask(temperature, mask_vector)
 
     # compute loss

methods/catalog/larr/model.py

@@ -206,7 +206,9 @@ def get_counterfactuals(self, factuals: pd.DataFrame) -> pd.DataFrame:
                 "The model did not predict any failures in the original training data. It cannot search for the Lambda parameter"
             )
 
-        recourse_needed_X_train = df_train_processed.iloc[np.where(preds_gpu_probs == 0)]
+        recourse_needed_X_train = df_train_processed.iloc[
+            np.where(preds_gpu_probs == 0)
+        ]
         # recourse_needed_X_train = df_train_processed.values[:5]
 
         # first choose the optimal lambda value