Merge pull request #3 from rodrigo-arenas/0.3.X

0.3.0

README.md

@@ -4,7 +4,7 @@
 [![Python Version](https://img.shields.io/badge/python-3.6%20%7C%203.7%20%7C%203.8%20%7C%203.9-blue)](https://www.python.org/downloads/)
 
 # Sklearn-genetic-opt
-scikit-learn models hyperparameters tuning using evolutionary algorithms.
+scikit-learn models hyperparameters tuning, using evolutionary algorithms.
 
 This is meant to be an alternative from popular methods inside scikit-learn such as Grid Search and Random Grid Search.
 
@@ -24,33 +24,38 @@ pip install sklearn-genetic-opt
 ```python
 from sklearn_genetic import GASearchCV
 from sklearn_genetic.utils import plot_fitness_evolution
-from sklearn.tree import DecisionTreeClassifier
+from sklearn_genetic.space import Continuous, Categorical, Integer
+from sklearn.ensemble import RandomForestClassifier
 from sklearn.model_selection import train_test_split
 from sklearn.datasets import load_digits
 from sklearn.metrics import accuracy_score
 import matplotlib.pyplot as plt
 
 
 data = load_digits() 
+n_samples = len(data.images)
+X = data.images.reshape((n_samples, -1))
 y = data['target']
-X = data['data'] 
-
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
 
-clf = DecisionTreeClassifier()
+clf = RandomForestClassifier()
+
+param_grid = {'min_weight_fraction_leaf': Continuous(0.01, 0.5, distribution='log-uniform'),
+              'bootstrap': Categorical([True, False]),
+              'max_depth': Integer(2, 30), 
+              'max_leaf_nodes': Integer(2, 35), 
+              'n_estimators': Integer(100, 300)}
 
 evolved_estimator = GASearchCV(estimator=clf,
                                cv=3,
                                scoring='accuracy',
-                               population_size=25,
-                               generations=35,
+                               population_size=10,
+                               generations=25,
                                tournament_size=3,
                                elitism=True,
                                crossover_probability=0.8,
                                mutation_probability=0.1,
-                               continuous_parameters={'min_weight_fraction_leaf': (0, 0.5)},
-                               categorical_parameters={'criterion': ['gini', 'entropy']},
-                               integer_parameters={'max_depth': (2, 25), 'max_leaf_nodes': (2, 35)},
+                               param_grid=param_grid,
                                criteria='max',
                                algorithm='eaMuPlusLambda',
                                n_jobs=-1,
@@ -74,6 +79,3 @@ print("Stats achieved in each generation: ", evolved_estimator.history)
 print("Parameters and cv scores in each iteration: ", evolved_estimator.logbook)
 print("Best k solutions: ", evolved_estimator.hof)
 ```
-### Result
-
-![demo](./demo/geneticopt.gif)

demo/Boson_Houses_decision_tree.py

@@ -1,10 +1,11 @@
+import matplotlib.pyplot as plt
 from sklearn_genetic import GASearchCV
+from sklearn_genetic.space import Integer, Categorical, Continuous
 from sklearn_genetic.utils import plot_fitness_evolution
 from sklearn.datasets import load_boston
 from sklearn.model_selection import train_test_split
 from sklearn.tree import DecisionTreeRegressor
 from sklearn.metrics import r2_score
-import matplotlib.pyplot as plt
 
 
 data = load_boston()
@@ -16,6 +17,11 @@
 
 clf = DecisionTreeRegressor()
 
+param_grid = {'ccp_alpha': Continuous(0, 1),
+              'criterion': Categorical(['mse', 'mae']),
+              'max_depth': Integer(2, 20),
+              'min_samples_split': Integer(2, 30)}
+
 evolved_estimator = GASearchCV(clf,
                                cv=3,
                                scoring='r2',
@@ -26,11 +32,9 @@
                                keep_top_k=4,
                                crossover_probability=0.9,
                                mutation_probability=0.05,
-                               continuous_parameters={'ccp_alpha': (0, 1)},
-                               categorical_parameters={'criterion': ['mse', 'mae']},
-                               integer_parameters={'max_depth': (2, 20), 'min_samples_split': (2, 30)},
+                               param_grid=param_grid,
                                criteria='max',
-                               algorithm='eaMuPlusLambda',
+                               algorithm='eaMuCommaLambda',
                                n_jobs=-1)
 
 evolved_estimator.fit(X_train, y_train)

demo/Demo_Digits_Dataset.py

@@ -1,12 +1,14 @@
+import scipy.stats as stats
+import numpy as np
+import warnings
 from sklearn_genetic import GASearchCV
+from sklearn_genetic.space import Continuous, Categorical
 from sklearn.linear_model import SGDClassifier
 from sklearn.model_selection import train_test_split, GridSearchCV, RandomizedSearchCV
-import scipy.stats as stats
 from sklearn.utils.fixes import loguniform
 from sklearn.datasets import load_digits
 from sklearn.metrics import accuracy_score
-import numpy as np
-import warnings
+
 
 warnings.filterwarnings("ignore")
 
@@ -50,16 +52,18 @@
 
 #  3. Genetic Algorithm
 
+param_grid = {'l1_ratio': Continuous(0, 1),
+              'alpha': Continuous(1e-4, 1, distribution='log-uniform'),
+              'average': Categorical([True, False])}
+
 evolved_estimator = GASearchCV(clf,
                                cv=3,
                                scoring='accuracy',
                                population_size=12,
                                generations=8,
                                tournament_size=3,
                                elitism=True,
-                               continuous_parameters={'l1_ratio': (0, 1), 'alpha': (1e-4, 1)},
-                               categorical_parameters={'average': [True, False]},
-                               integer_parameters={},
+                               param_grid=param_grid,
                                n_jobs=-1)
 
 evolved_estimator.fit(X_train, y_train)

demo/Digits_decision_tree.py

@@ -1,9 +1,11 @@
+import warnings
 from sklearn_genetic import GASearchCV
+from sklearn_genetic.space import Categorical, Integer, Continuous
 from sklearn.model_selection import train_test_split
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.datasets import load_digits
 from sklearn.metrics import accuracy_score
-import warnings
+
 
 warnings.filterwarnings("ignore")
 
@@ -16,6 +18,10 @@
 
 clf = DecisionTreeClassifier()
 
+params_grid = {'min_weight_fraction_leaf': Continuous(0, 0.5),
+               'criterion': Categorical(['gini', 'entropy']),
+               'max_depth': Integer(2, 20), 'max_leaf_nodes': Integer(2, 30)}
+
 evolved_estimator = GASearchCV(clf,
                                cv=3,
                                scoring='accuracy',
@@ -25,9 +31,8 @@
                                elitism=True,
                                crossover_probability=0.9,
                                mutation_probability=0.05,
-                               continuous_parameters={'min_weight_fraction_leaf': (0, 0.5)},
-                               categorical_parameters={'criterion': ['gini', 'entropy']},
-                               integer_parameters={'max_depth': (2, 20), 'max_leaf_nodes': (2, 30)},
+                               param_grid=params_grid,
+                               algorithm='eaMuPlusLambda',
                                n_jobs=-1,
                                verbose=True)
 

setup.py

@@ -7,11 +7,10 @@
 HERE = pathlib.Path(__file__).parent
 
 README = (HERE / "README.md").read_text()
-
 setup(
     name="sklearn-genetic-opt",
-    version="0.2.1",
-    description="Sklearn models hyperparameters tuning using evolutionary algorithms",
+    version="0.3.0",
+    description="Scikit-lean models hyperparameters tuning, using evolutionary algorithms",
     long_description=README,
     long_description_content_type="text/markdown",
     url="https://github.com/rodrigo-arenas/Sklearn-genetic-opt",

sklearn_genetic/__init__.py

@@ -1,3 +1,3 @@
-from sklearn_genetic.genetic_search import GASearchCV
+from .genetic_search import GASearchCV
 
 __all__ = ['GASearchCV']