Merge pull request #25 from Techtonique/faster-ridge

Faster ridge

CHANGES.md

@@ -1,8 +1,10 @@
-# version 0.12.0
+# version 0.12.1
 
 - add prediction intervals to `LSBoostRegressor` (split conformal prediction, 
   split conformal prediction with KDE, and split conformal prediction bootstrap)
-  see `examples/lsboost_regressor_pi.py` for examples
+  see `examples/lsboost_regressor_pi.py` for examples 
+- do not rescale columns with zero variance in `LSBoostRegressor` and `LSBoostClassifier`
+- faster ridge regression for `LSBoostRegressor`
 
 # version 0.9.0
 

examples/adaopt_classifier.py

@@ -11,7 +11,9 @@
 #chdir(wd)
 
 import mlsauce as ms
+import os 
 
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
 
 
 

examples/download_dataset.py

@@ -1,4 +1,8 @@
 import mlsauce as ms 
+import os 
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
 
 # `ms.download` parameters 
 # pkgname="MASS"

examples/lasso_regressor.py

@@ -5,6 +5,10 @@
 from time import time
 from os import chdir
 from sklearn import metrics
+import os 
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
 
 # data 2
 diabetes = load_diabetes()

examples/lsboost_classifier.py

@@ -4,6 +4,10 @@
 from time import time
 from os import chdir
 from sklearn import metrics
+import os 
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
 
 
 #wd="/workspace/mlsauce/mlsauce/examples"

examples/lsboost_regressor.py

@@ -1,5 +1,9 @@
 import subprocess
 import sys
+import os 
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
 
 subprocess.check_call([sys.executable, "-m", "pip", "install", "matplotlib"])
 

examples/lsboost_regressor_pi.py

@@ -1,5 +1,9 @@
 import subprocess
 import sys
+import os 
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
 
 subprocess.check_call([sys.executable, "-m", "pip", "install", "matplotlib"])
 
@@ -31,7 +35,7 @@
 print(obj.get_params())
 start = time()
 obj.fit(X_train, y_train)
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 start = time()
 preds = obj.predict(X_test, return_pi=True, method="splitconformal")
 print(time()-start)
@@ -44,7 +48,7 @@
 print(obj.get_params())
 start = time()
 obj.fit(X_train, y_train)
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 start = time()
 preds = obj.predict(X_test, return_pi=True, 
                     method="splitconformal")
@@ -58,7 +62,7 @@
 print(obj.get_params())
 start = time()
 obj.fit(X_train, y_train)
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 start = time()
 preds = obj.predict(X_test, return_pi=True, 
                     method="splitconformal")
@@ -78,7 +82,7 @@
 print(obj.get_params())
 start = time()
 obj.fit(X_train, y_train)
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 start = time()
 preds = obj.predict(X_test, return_pi=True, method="splitconformal")
 print(time()-start)
@@ -91,7 +95,7 @@
 print(obj.get_params())
 start = time()
 obj.fit(X_train, y_train)
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 start = time()
 preds = obj.predict(X_test, return_pi=True, 
                     method="splitconformal")
@@ -105,7 +109,7 @@
 print(obj.get_params())
 start = time()
 obj.fit(X_train, y_train)
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 start = time()
 preds = obj.predict(X_test, return_pi=True, 
                     method="splitconformal")
@@ -133,7 +137,7 @@
 print(obj.get_params())
 start = time()
 obj.fit(X_train, y_train)
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 start = time()
 preds = obj.predict(X_test, return_pi=True, method="splitconformal")
 print(time()-start)
@@ -150,7 +154,7 @@
 start = time()
 preds = obj.predict(X_test, return_pi=True, 
                     method="splitconformal")
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 print(f"splitconformal bootstrap coverage 3: {np.mean((preds.upper >= y_test)*(preds.lower <= y_test))}")   
 
 
@@ -160,7 +164,7 @@
 print(obj.get_params())
 start = time()
 obj.fit(X_train, y_train)
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 start = time()
 preds = obj.predict(X_test, return_pi=True, 
                     method="splitconformal")
@@ -181,7 +185,7 @@
 print(obj.get_params())
 start = time()
 obj.fit(X_train, y_train)
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 start = time()
 preds = obj.predict(X_test, return_pi=True, method="splitconformal")
 print(time()-start)
@@ -208,7 +212,7 @@
 print(obj.get_params())
 start = time()
 obj.fit(X_train, y_train)
-print(time()-start)
+print(f"Elapsed: {time()-start}")
 start = time()
 preds = obj.predict(X_test, return_pi=True, 
                     method="splitconformal")

examples/plot_ridge_lasso_coeffs.py

@@ -1,5 +1,8 @@
 import subprocess
 import sys
+import os 
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
 
 subprocess.check_call([sys.executable, "-m", "pip", "install", "matplotlib"])
 

examples/ridge_regressor.py

@@ -4,6 +4,10 @@
 from time import time
 from os import chdir
 from sklearn import metrics
+import os 
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
 
 
 #wd="/workspace/mlsauce/mlsauce/examples"

examples/stump_classifier.py

@@ -4,6 +4,10 @@
 from time import time
 from os import chdir
 from sklearn import metrics
+import os 
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
 
 
 #wd="/workspace/mlsauce/mlsauce/examples"

mlsauce.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mlsauce
-Version: 0.11.0
+Version: 0.12.1
 Summary: Miscellaneous Statistical/Machine Learning tools
 Maintainer: T. Moudiki
 Maintainer-email: [email protected]

mlsauce/adaopt/_adaopt.py

@@ -176,7 +176,7 @@ def fit(self, X, y, **kwargs):
         self.alphas = res["alphas"]
         self.n_iterations = res["n_iterations"]
         self.scaled_X_train = np.array(res["scaled_X_train"], dtype=np.float64)
-
+        self.n_classes_ = len(np.unique(y)) # for compatibility with sklearn 
         return self
 
     def predict(self, X, **kwargs):