Merge pull request #27 from Techtonique/clustering2

Clustering2
Techtonique · Apr 18, 2024 · b2276fc · b2276fc
2 parents fe2b99b + 6950466
commit b2276fc
Show file tree

Hide file tree

Showing 17 changed files with 440 additions and 60 deletions.
diff --git a/CHANGES.md b/CHANGES.md
@@ -1,3 +1,7 @@
+# version 0.13.0
+
+- add clustering to `LSBoostRegressor`, `LSBoostClassifier`, and `AdaOpt`
+
 # version 0.12.3
 
 - add prediction intervals to `LSBoostRegressor` (split conformal prediction, 

diff --git a/examples/adaopt_classifier.py b/examples/adaopt_classifier.py
@@ -35,6 +35,16 @@
 print(obj.score(X_test, y_test))
 print(time()-start)
 
+obj = ms.AdaOpt(n_jobs=4, type_dist="euclidean", verbose=1, 
+                n_clusters_input=2)
+#obj = ms.AdaOpt()
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
 
 # data 2
 wine = load_wine()
@@ -52,6 +62,13 @@
 print(obj.score(X_test, y_test))
 print(time()-start)
 
+obj = ms.AdaOpt(n_clusters_input=3)
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
 
 # data 3
 iris = load_iris()
@@ -70,6 +87,14 @@
 print(obj.score(X_test, y_test))
 print(time()-start)
 
+obj = ms.AdaOpt(n_clusters_input=3)
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
+
 
 # data 4
 digits = load_digits()
@@ -105,57 +130,30 @@
 print(obj.score(X_test, y_test))
 print(time()-start)
 
+obj = ms.AdaOpt(n_iterations=50,
+           learning_rate=0.3,
+           reg_lambda=0.1,            
+           reg_alpha=0.5,
+           eta=0.01,
+           gamma=0.01, 
+           tolerance=1e-4,
+           row_sample=1, 
+           k=1, n_clusters_input=5,
+           n_jobs=3, type_dist="euclidean", verbose=1)
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
 
-# # data 5
-
-# zip_dir = "/Users/moudiki/Documents/Papers/adaopt/data/zip"
-# data_train = pd.read_csv(zip_dir + "/zip_train.csv", 
-#                          index_col=0)
-# data_test = pd.read_csv(zip_dir + "/zip_test.csv", 
-#                         index_col=0)
-
-# y_train = data_train.y.values
-# y_test = data_test.y.values
-# X_train =  np.ascontiguousarray(np.delete(data_train.values, 0, axis=1))
-# X_test =  np.ascontiguousarray(np.delete(data_test.values, 0, axis=1))
-
-# obj = ms.AdaOpt(type_dist="euclidean-f",
-#                 k=1, row_sample=1)
-# start = time()
-# obj.fit(X_train, y_train)
-# print(time()-start)
-# start = time()
-# print(obj.score(X_test, y_test))
-# print(time()-start)
-
-
-# # data 6
-
-# letter_dir = "/Users/moudiki/Documents/Papers/adaopt/data/letter"
-# data_letter = pd.read_csv(letter_dir + "/letter_recognition.csv", 
-#                           index_col=0)
-
-
-# y = data_letter.V1.values
-# X =  np.asarray(np.ascontiguousarray(np.delete(data_letter.values, 0, 
-#                                     axis=1)), dtype='float64')
-
-# np.random.seed(1323)
-# X_train, X_test, y_train, y_test = train_test_split(X, y, 
-#                                                     test_size=0.3)
-
-
-# obj = ms.AdaOpt(type_dist="euclidean-f",
-#                 k=1, row_sample=1)
-# start = time()
-# obj.fit(X_train, y_train)
-# print(time()-start)
-# start = time()
-# print(obj.score(X_test, y_test))
-# print(time()-start)
-
-# start = time()
-# preds = obj.predict(X_test)
-# print(time() - start)
-# print(metrics.classification_report(preds, y_test))
+# with clustering
+obj = ms.AdaOpt(n_clusters=25, k=1, 
+                n_clusters_input=3)
+start = time()
+obj.fit(X_train, y_train)
+print(time()-start)
+start = time()
+print(obj.score(X_test, y_test))
+print(time()-start)
 
diff --git a/examples/lsboost_classifier.py b/examples/lsboost_classifier.py
@@ -19,9 +19,12 @@
 #ridge
 
 print("\n")
-print("ridge -----")
+print("lsboost ridge -----")
 print("\n")
 
+print("\n")
+print("breast_cancer data -----")
+
 # data 1
 breast_cancer = load_breast_cancer()
 X = breast_cancer.data
@@ -42,6 +45,17 @@
 
 print(obj.obj['loss'])
 
+obj = ms.LSBoostClassifier(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'])
+
 # MORE DATA NEEDED # MORE DATA NEEDED # MORE DATA NEEDED
 obj = ms.LSBoostClassifier(backend="gpu")
 print(obj.get_params())
@@ -55,6 +69,9 @@
 print(obj.obj['loss'])
 
 # data 2
+print("\n")
+print("wine data -----")
+
 wine = load_wine()
 Z = wine.data
 t = wine.target
@@ -73,6 +90,17 @@
 
 print(obj.obj['loss'])
 
+obj = ms.LSBoostClassifier(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'])
+
 # MORE DATA NEEDED # MORE DATA NEEDED # MORE DATA NEEDED
 obj = ms.LSBoostClassifier(backend="gpu")
 print(obj.get_params())
@@ -86,6 +114,9 @@
 print(obj.obj['loss'])
 
 # data 3
+print("\n")
+print("iris data -----")
+
 iris = load_iris()
 Z = iris.data
 t = iris.target
@@ -119,10 +150,13 @@
 #lasso
 
 print("\n")
-print("lasso -----")
+print("lsboost lasso -----")
 print("\n")
 
 # data 1
+print("\n")
+print("breast_cancer data -----")
+
 breast_cancer = load_breast_cancer()
 X = breast_cancer.data
 y = breast_cancer.target
@@ -152,6 +186,9 @@
 # print(time()-start)
 
 # data 2
+print("\n")
+print("wine data -----")
+
 wine = load_wine()
 Z = wine.data
 t = wine.target
@@ -179,6 +216,9 @@
 # print(time()-start)
 
 # data 3
+print("\n")
+print("iris data -----")
+
 iris = load_iris()
 Z = iris.data
 t = iris.target
@@ -196,6 +236,17 @@
 print(obj.score(X_test, y_test))
 print(time()-start)
 
+obj = ms.LSBoostClassifier(solver="lasso", 
+                           n_clusters=3, 
+                           clustering_method="gmm")
+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)
+
 # MORE DATA NEEDED # MORE DATA NEEDED # MORE DATA NEEDED
 # obj = ms.LSBoostClassifier(backend="gpu", solver="lasso")
 # print(obj.get_params())

diff --git a/examples/lsboost_regressor.py b/examples/lsboost_regressor.py
@@ -23,6 +23,10 @@
 print("\n")
 
 # data 2
+
+print("\n")
+print("diabetes data -----")
+
 diabetes = load_diabetes()
 X = diabetes.data
 y = diabetes.target
@@ -42,6 +46,17 @@
 
 print(obj.obj['loss'])
 
+obj = ms.LSBoostRegressor(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'])
+
 # MORE DATA NEEDED # MORE DATA NEEDED # MORE DATA NEEDED
 obj = ms.LSBoostRegressor(backend="gpu")
 print(obj.get_params())
@@ -61,6 +76,9 @@
 print("\n")
 
 # data 2
+print("\n")
+print("diabetes data -----")
+
 diabetes = load_diabetes()
 X = diabetes.data
 y = diabetes.target
@@ -80,6 +98,17 @@
 
 print(obj.obj['loss'])
 
+obj = ms.LSBoostRegressor(solver="lasso", 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'])
+
 # MORE DATA NEEDED # MORE DATA NEEDED # MORE DATA NEEDED
 # obj = ms.LSBoostRegressor(backend="gpu", solver="lasso")
 # print(obj.get_params())

diff --git a/mlsauce.egg-info/PKG-INFO b/mlsauce.egg-info/PKG-INFO
@@ -0,0 +1,36 @@
+Metadata-Version: 2.1
+Name: mlsauce
+Version: 0.13.0
+Summary: Miscellaneous Statistical/Machine Learning tools
+Maintainer: T. Moudiki
+Maintainer-email: [email protected]
+License: BSD3 Clause Clear
+Platform: linux
+Platform: macosx
+Platform: windows
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Requires-Python: >=3.5
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: Cython
+Requires-Dist: joblib
+Requires-Dist: pandas
+Requires-Dist: requests
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: tqdm
+Requires-Dist: jax
+Requires-Dist: jaxlib
+Provides-Extra: alldeps
+Requires-Dist: numpy>=1.13.0; extra == "alldeps"
+Requires-Dist: scipy>=0.19.0; extra == "alldeps"
+
+Miscellaneous Statistical/Machine Learning tools