improve categorical data generation.

yzhao062 · Nov 12, 2020 · 4b62599 · 4b62599
1 parent df8cd11
commit 4b62599
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 7 deletions.
diff --git a/CHANGES.txt b/CHANGES.txt
@@ -111,6 +111,7 @@ v<0.8.3>, <09/19/2020> -- Add model persistence documentation (save and load).
 v<0.8.4>, <10/13/2020> -- Fix COPOD code inconsistency (issue #239).
 v<0.8.4>, <10/24/2020> -- Fix LSCP minor bug (issue #180).
 v<0.8.4>, <11/02/2020> -- Add support for Tensorflow 2.
+v<0.8.4>, <11/12/2020> -- Merge PR #!02 for categortical data generation.
 
 
 
diff --git a/examples/generate_data_categorical_example.py b/examples/generate_data_categorical_example.py
@@ -11,6 +11,7 @@
 import sys
 import numpy as np
 import matplotlib.pyplot as plt
+
 # temporary solution for relative imports in case pyod is not installed
 # if pyod is installed, no need to use the following line
 
@@ -19,16 +20,16 @@
 
 from pyod.utils.data import generate_data_categorical
 
-
 if __name__ == "__main__":
     contamination = 0.1  # percentage of outliers
 
     # Generate sample data in clusters
-    X_train, X_test, y_train, y_test = generate_data_categorical(n_train=200, n_test=50,
-                                                                 n_category_in=8, n_category_out=5,
-                                                                 n_informative=1, n_features=1,
-                                                                 contamination=contamination,
-                                                                 shuffle=True, random_state=42)
+    X_train, X_test, y_train, y_test = generate_data_categorical \
+        (n_train=200, n_test=50,
+         n_category_in=8, n_category_out=5,
+         n_informative=1, n_features=1,
+         contamination=contamination,
+         shuffle=True, random_state=42)
 
     # note that visalizing it can only be in 1 dimension!
     cats = list(np.ravel(X_train))

diff --git a/pyod/utils/data.py b/pyod/utils/data.py
@@ -494,7 +494,6 @@ def generate_data_categorical(n_train=1000, n_test=500, n_features=2,
                               n_informative=2, n_category_in=2,
                               n_category_out=2, contamination=0.1,
                               shuffle=True, random_state=None):
-
     """Utility function to generate synthesized categorical data.
 
     Parameters