Merge pull request #845 from rasbt/v0.19

0.19 release

README.md

@@ -143,6 +143,4 @@ according to the terms and conditions of the Creative Commons Attribution 4.0 In
 
 ## Contact
 
-I received a lot of feedback and questions about mlxtend recently, and I thought that it would be worthwhile to set up a public communication channel. Before you write an email with a question about mlxtend, please consider posting it here since it can also be useful to others! Please join the [Google Groups Mailing List](https://groups.google.com/forum/#!forum/mlxtend)!
-
-If Google Groups is not for you, please feel free to write me an [email](mailto:[email protected]) or consider filing an issue on [GitHub's issue tracker](https://github.com/rasbt/mlxtend/issues) for new feature requests or bug reports. In addition, I setup a [Gitter channel](https://gitter.im/rasbt/mlxtend?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge) for live discussions.
+The best way to ask questions is via the [GitHub Discussions channel](https://github.com/rasbt/mlxtend/discussions). In case you encounter usage bugs, please don't hesitate to use the [GitHub's issue tracker](https://github.com/rasbt/mlxtend/issues) directly. 

docs/sources/CHANGELOG.md

@@ -7,11 +7,15 @@ The CHANGELOG for the current development version is available at
 
 ---
 
-### Version 0.18.1 (TBD)
+### Version 0.19.0 (09/02/2021)
 
 ##### Downloads
 
-- -
+- [Source code (zip)](https://github.com/rasbt/mlxtend/archive/v0.19.0.zip)
+
+- [Source code (tar.gz)](https://github.com/rasbt/mlxtend/archive/v0.19.0.tar.gz)
+
+
 
 ##### New Features
 

docs/sources/user_guide/evaluate/bootstrap_point632_score.ipynb

@@ -54,7 +54,7 @@
     "\n",
     "Now, to address the bias that is due to this the sampling with replacement, Bradley Efron proposed the *.632 Estimate* that we mentioned earlier, which is computed via the following equation:\n",
     "\n",
-    "$$\\text{ACC}_{boot} = \\frac{1}{b} \\sum_{i=1}^b \\big(0.632 \\cdot \\text{ACC}_{h, i} + 0.368 \\cdot \\text{ACC}_{r, i}\\big), $$\n",
+    "$$\\text{ACC}_{boot} = \\frac{1}{b} \\sum_{i=1}^b \\big(0.632 \\cdot \\text{ACC}_{h, i} + 0.368 \\cdot \\text{ACC}_{train}\\big), $$\n",
     "\n",
     "where $\\text{ACC}_{train}$ is the accuracy computed on the whole training set, and $\\text{ACC}_{h, i}$ is the accuracy on the out-of-bag sample.\n",
     "\n",
@@ -63,7 +63,7 @@
     "Now, while the *.632 Boostrap* attempts to address the pessimistic bias of the estimate, an optimistic bias may occur with models that tend to overfit so that Bradley Efron and Robert Tibshirani proposed the *The .632+ Bootstrap Method* (Efron and Tibshirani, 1997). Instead of using a fixed \"weight\" $\\omega = 0.632$ in\n",
     "\n",
     "$$\n",
-    "ACC_{\\text{boot}} = \\frac{1}{b} \\sum_{i=1}^b \\big(\\omega \\cdot \\text{ACC}_{h, i} + (1-\\omega) \\cdot \\text{ACC}_{r, i} \\big), $$\n",
+    "ACC_{\\text{boot}} = \\frac{1}{b} \\sum_{i=1}^b \\big(\\omega \\cdot \\text{ACC}_{h, i} + (1-\\omega) \\cdot \\text{ACC}_{train} \\big), $$\n",
     "\n",
     "we compute the weight $\\gamma$ as\n",
     "\n",
@@ -73,7 +73,7 @@
     "\n",
     "$$R = \\frac{(-1) \\times (\\text{ACC}_{h, i} - \\text{ACC}_{train})}{\\gamma - (1 -\\text{ACC}_{h, i})}.$$\n",
     "\n",
-    "(Since we are plugging $\\omega$ into the equation for computing $$ACC_{boot}$$ that we defined above, $$\\text{ACC}_{h, i}$$ and $\\text{ACC}_{r, i}$ still refer to the out-of-bag accuracy in the *i*th bootstrap round and the whole training set accuracy, respectively.)\n",
+    "(Since we are plugging $\\omega$ into the equation for computing $$ACC_{boot}$$ that we defined above, $$\\text{ACC}_{h, i}$$ and $\\text{ACC}_{train}$ still refer to the out-of-bag accuracy in the *i*th bootstrap round and the whole training set accuracy, respectively.)\n",
     "\n",
     "Further, we need to determine the *no-information rate* $\\gamma$ in order to compute *R*. For instance, we can compute $\\gamma$ by fitting a model to a dataset that contains all possible combinations between samples $x_{i'}$ and target class labels $y_{i}$ — we pretend that the observations and class labels are independent:\n",
     "\n",

mlxtend/__init__.py

@@ -4,4 +4,4 @@
 #
 # License: BSD 3 clause
 
-__version__ = '0.19.0dev'
+__version__ = '0.19.0'