Merge pull request #35 from Techtonique/lsboost-lilbro

Lsboost lilbro

Makefile

@@ -32,7 +32,9 @@ clean-build: ## remove build artifacts
 	rm -fr build/	
 	rm -fr .eggs/
 	find . -name '*.egg-info' -exec rm -fr {} +
-	find . -name '*.egg' -exec rm -f {} +	
+	find . -name '*.egg' -exec rm -f {} +
+	find . -name '*.so' -exec rm -f {} +
+	find . -name '*.c' -exec rm -f {} +	
 
 clean-pyc: ## remove Python file artifacts
 	find . -name '*.pyc' -exec rm -f {} +
@@ -89,7 +91,10 @@ dist: clean ## builds source and wheel package
 	ls -l dist
 
 install: clean ## install the package to the active Python's site-packages
-	python3 -m pip install .
+	python3 -m pip install . --verbose
 
 run-examples: ## run all examples with one command
-	find examples -maxdepth 2 -name "*.py" -exec  python3 {} \;
+	find examples -maxdepth 2 -name "*.py" -exec  python3 {} \;
+
+run-lazy: ## run all lazy estimators examples with one command
+	find examples -maxdepth 2 -name "*lazy*.py" -exec  python3 {} \;

examples/genboost_classifier.py

@@ -0,0 +1,204 @@
+import numpy as np 
+from sklearn.datasets import load_digits, load_breast_cancer, load_wine, load_iris
+from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.kernel_ridge import KernelRidge
+from time import time
+from os import chdir
+from sklearn import metrics
+import os 
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
+print(os.path.relpath(os.path.dirname(__file__)))
+
+#wd="/workspace/mlsauce/mlsauce/examples"
+#
+#chdir(wd)
+
+import mlsauce as ms
+
+#ridge
+
+print("\n")
+print("GenericBoosting Decision tree -----")
+print("\n")
+
+print("\n")
+print("breast_cancer data -----")
+
+# data 1
+breast_cancer = load_breast_cancer()
+X = breast_cancer.data
+y = breast_cancer.target
+# split data into training test and test set
+np.random.seed(15029)
+X_train, X_test, y_train, y_test = train_test_split(X, y, 
+                                                    test_size=0.2)
+
+clf = DecisionTreeRegressor()
+clf2 = KernelRidge()
+
+obj = ms.GenericBoostingClassifier(clf, tolerance=1e-2)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
+print(obj.obj['loss'])
+
+obj = ms.GenericBoostingClassifier(clf, tolerance=1e-2, n_clusters=2)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
+print(obj.obj['loss'])
+
+
+# data 2
+print("\n")
+print("wine data -----")
+
+wine = load_wine()
+Z = wine.data
+t = wine.target
+np.random.seed(879423)
+X_train, X_test, y_train, y_test = train_test_split(Z, t, 
+                                                    test_size=0.2)
+
+obj = ms.GenericBoostingClassifier(clf)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
+print(obj.obj['loss'])
+
+obj = ms.GenericBoostingClassifier(clf, n_clusters=3)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
+print(obj.obj['loss'])
+
+# data 3
+print("\n")
+print("iris data -----")
+
+iris = load_iris()
+Z = iris.data
+t = iris.target
+np.random.seed(734563)
+X_train, X_test, y_train, y_test = train_test_split(Z, t, 
+                                                    test_size=0.2)
+
+
+obj = ms.GenericBoostingClassifier(clf)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
+print(obj.obj['loss'])
+
+
+print("\n")
+print("GenericBoosting  KRR -----")
+print("\n")
+
+obj = ms.GenericBoostingClassifier(clf2, tolerance=1e-2)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
+print(obj.obj['loss'])
+
+obj = ms.GenericBoostingClassifier(clf2, tolerance=1e-2, n_clusters=2)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
+print(obj.obj['loss'])
+
+
+# data 2
+print("\n")
+print("wine data -----")
+
+wine = load_wine()
+Z = wine.data
+t = wine.target
+np.random.seed(879423)
+X_train, X_test, y_train, y_test = train_test_split(Z, t, 
+                                                    test_size=0.2)
+
+obj = ms.GenericBoostingClassifier(clf2)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
+print(obj.obj['loss'])
+
+obj = ms.GenericBoostingClassifier(clf2, n_clusters=3)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
+print(obj.obj['loss'])
+
+# data 3
+print("\n")
+print("iris data -----")
+
+iris = load_iris()
+Z = iris.data
+t = iris.target
+np.random.seed(734563)
+X_train, X_test, y_train, y_test = train_test_split(Z, t, 
+                                                    test_size=0.2)
+
+
+obj = ms.GenericBoostingClassifier(clf2)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
+print(obj.obj['loss'])
+

examples/genboost_regressor.py

@@ -0,0 +1,54 @@
+import subprocess
+import sys
+import os 
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
+
+subprocess.check_call([sys.executable, "-m", "pip", "install", "matplotlib"])
+
+import mlsauce as ms
+import numpy as np 
+import matplotlib.pyplot as plt
+from sklearn.datasets import load_diabetes
+from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score
+from sklearn.tree import DecisionTreeRegressor
+from time import time
+from os import chdir
+from sklearn import metrics
+
+
+print("\n")
+print("diabetes data -----")
+
+regr = DecisionTreeRegressor()
+
+diabetes = load_diabetes()
+X = diabetes.data
+y = diabetes.target
+# split data into training test and test set
+np.random.seed(15029)
+X_train, X_test, y_train, y_test = train_test_split(X, y, 
+                                                    test_size=0.2)
+
+obj = ms.GenericBoostingRegressor(regr, col_sample=0.9, row_sample=0.9)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(np.sqrt(np.mean(np.square(obj.predict(X_test) - y_test))))
+print(time()-start)
+
+print(obj.obj['loss'])
+
+obj = ms.GenericBoostingRegressor(regr, col_sample=0.9, row_sample=0.9, n_clusters=2)
+print(obj.get_params())
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(np.sqrt(np.mean(np.square(obj.predict(X_test) - y_test))))
+print(time()-start)
+
+print(obj.obj['loss'])

examples/lazy_booster_classification.py

@@ -0,0 +1,29 @@
+import os 
+import mlsauce as ms 
+from sklearn.datasets import load_breast_cancer, load_iris, load_wine, load_digits
+from sklearn.model_selection import train_test_split
+from time import time
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
+#load_models = [load_breast_cancer, load_iris, load_wine, load_digits]
+load_models = [load_breast_cancer, load_iris, load_wine]
+#load_models = [load_breast_cancer]
+
+for model in load_models: 
+
+    data = model()
+    X = data.data
+    y= data.target
+
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = .2, random_state = 13)
+
+    clf = ms.LazyBoostingClassifier(verbose=1, ignore_warnings=False, 
+                                    custom_metric=None, preprocess=False)
+
+    start = time()
+    models, predictioms = clf.fit(X_train, X_test, y_train, y_test)
+    print(f"\nElapsed: {time() - start} seconds\n")
+
+    print(models)
+

examples/lazy_booster_regression.py

@@ -0,0 +1,17 @@
+import os 
+import mlsauce as ms
+from sklearn.datasets import load_diabetes
+from sklearn.model_selection import train_test_split
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
+data = load_diabetes()
+X = data.data
+y= data.target
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = .2, random_state = 123)
+
+regr = ms.LazyBoostingRegressor(verbose=0, ignore_warnings=True, 
+                                custom_metric=None, preprocess=True)
+models, predictioms = regr.fit(X_train, X_test, y_train, y_test)
+model_dictionary = regr.provide_models(X_train, X_test, y_train, y_test)
+print(models)