From e88eb480f58e5b2bdaf5ac6b57c0d83e94b26c3a Mon Sep 17 00:00:00 2001
From: "rodrigo.arenas" <31422766+rodrigo-arenas@users.noreply.github.com>
Date: Fri, 21 Jan 2022 11:21:04 -0500
Subject: [PATCH 1/2] sample mechanism in GAFeatureSelectionCV

---
 docs/release_notes.rst            | 11 +++++++++++
 sklearn_genetic/_version.py       |  2 +-
 sklearn_genetic/genetic_search.py | 14 ++++++++++++--
 sklearn_genetic/utils/random.py   | 20 ++++++++++++++++++++
 4 files changed, 44 insertions(+), 3 deletions(-)
 create mode 100644 sklearn_genetic/utils/random.py

diff --git a/docs/release_notes.rst b/docs/release_notes.rst
index ae393f1..98edfcf 100644
--- a/docs/release_notes.rst
+++ b/docs/release_notes.rst
@@ -3,6 +3,17 @@ Release Notes
 
 Some notes on new features in various releases
 
+What's new in 0.8.1dev0
+-----------------------
+
+^^^^^^^^^
+Features:
+^^^^^^^^^
+
+* If the `max_features` parameter from :class:`~sklearn_genetic.GAFeatureSelectionCV` is set,
+  the initial population is now sampled giving more probability to solutions with less than `max_features` features.
+
+
 What's new in 0.8.0
 -------------------
 
diff --git a/sklearn_genetic/_version.py b/sklearn_genetic/_version.py
index 777f190..fc79097 100644
--- a/sklearn_genetic/_version.py
+++ b/sklearn_genetic/_version.py
@@ -1 +1 @@
-__version__ = "0.8.0"
+__version__ = "0.8.1dev0"
diff --git a/sklearn_genetic/genetic_search.py b/sklearn_genetic/genetic_search.py
index 55414f9..b375b94 100644
--- a/sklearn_genetic/genetic_search.py
+++ b/sklearn_genetic/genetic_search.py
@@ -24,6 +24,7 @@
     create_gasearch_cv_results_,
     create_feature_selection_cv_results_,
 )
+from .utils.random import weighted_choice
 
 
 class GASearchCV(BaseSearchCV):
@@ -940,6 +941,7 @@ def __init__(
         self.n_features = None
         self.X_ = None
         self.y_ = None
+        self.features_proportion = None
         self.callbacks = None
         self.best_features_ = None
         self.best_estimator_ = None
@@ -999,7 +1001,11 @@ def _register(self):
 
         # Register the array to choose the features
         # Each binary value represents if the feature is selected or not
-        self.toolbox.register("features", random.randint, 0, 1)
+
+        if self.features_proportion:
+            self.toolbox.register("features", weighted_choice, self.features_proportion)
+        else:
+            self.toolbox.register("features", random.randint, 0, 1)
 
         self.toolbox.register(
             "individual",
@@ -1107,10 +1113,11 @@ def evaluate(self, individual):
         self.logbook.record(parameters=current_generation_features)
 
         # Penalize individuals with more features than the max_features parameter
+
         if self.max_features and (
             n_selected_features > self.max_features or n_selected_features == 0
         ):
-            score = -self.criteria_sign * 10000
+            score = -self.criteria_sign * 100000
 
         return [score, n_selected_features]
 
@@ -1136,6 +1143,9 @@ def fit(self, X, y, callbacks=None):
         self.X_, self.y_ = check_X_y(X, y)
         self.n_features = X.shape[1]
 
+        if self.max_features:
+            self.features_proportion = self.max_features/self.n_features
+
         # Make sure the callbacks are valid
         self.callbacks = check_callback(callbacks)
 
diff --git a/sklearn_genetic/utils/random.py b/sklearn_genetic/utils/random.py
new file mode 100644
index 0000000..ea323af
--- /dev/null
+++ b/sklearn_genetic/utils/random.py
@@ -0,0 +1,20 @@
+import random
+
+
+def weighted_choice(weight):
+    """
+    Parameters
+    ----------
+    weight: float
+        Weight of choosing a chromosome
+
+    Returns
+    -------
+        Bool random (not uniform) choice
+    """
+
+    # This help to don't generate individuals of the same size on average
+    p = random.uniform(0, weight)
+    choice = random.choices([0, 1], [1-p, p])[0]
+
+    return choice

From 4fc9ce71bb756e1f2971a9aed0699ba53bfcce31 Mon Sep 17 00:00:00 2001
From: "rodrigo.arenas" <31422766+rodrigo-arenas@users.noreply.github.com>
Date: Wed, 9 Mar 2022 12:02:56 -0500
Subject: [PATCH 2/2] Version 0.8.1 release

---
 docs/release_notes.rst      | 4 ++--
 sklearn_genetic/_version.py | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/docs/release_notes.rst b/docs/release_notes.rst
index 98edfcf..a20f504 100644
--- a/docs/release_notes.rst
+++ b/docs/release_notes.rst
@@ -3,8 +3,8 @@ Release Notes
 
 Some notes on new features in various releases
 
-What's new in 0.8.1dev0
------------------------
+What's new in 0.8.1
+-------------------
 
 ^^^^^^^^^
 Features:
diff --git a/sklearn_genetic/_version.py b/sklearn_genetic/_version.py
index fc79097..8088f75 100644
--- a/sklearn_genetic/_version.py
+++ b/sklearn_genetic/_version.py
@@ -1 +1 @@
-__version__ = "0.8.1dev0"
+__version__ = "0.8.1"