Merge pull request #299 from jseabold/pickle-xgbooster

ENH: Pickle xgbooster enhancments. Thanks!

demo/guide-python/sklearn_examples.py

@@ -4,18 +4,17 @@ Created on 1 Apr 2015
 
 @author: Jamie Hall
 '''
-
+import pickle
 import xgboost as xgb
 
 import numpy as np
 from sklearn.cross_validation import KFold
-from sklearn.grid_search import GridSearchCV
 from sklearn.metrics import confusion_matrix, mean_squared_error
+from sklearn.grid_search import GridSearchCV
 from sklearn.datasets import load_iris, load_digits, load_boston
 
 rng = np.random.RandomState(31337)
 
-
 print("Zeros and Ones from the Digits dataset: binary classification")
 digits = load_digits(2)
 y = digits['target']
@@ -60,4 +59,9 @@ clf.fit(X,y)
 print(clf.best_score_)
 print(clf.best_params_)
 
-
+# The sklearn API models are picklable
+print("Pickling sklearn API models")
+# must open in binary format to pickle
+pickle.dump(clf, open("best_boston.pkl", "wb"))
+clf2 = pickle.load(open("best_boston.pkl", "rb"))
+print(np.allclose(clf.predict(X), clf2.predict(X)))

demo/guide-python/sklearn_parallel.py

@@ -0,0 +1,35 @@
+import os
+
+if __name__ == "__main__":
+    # NOTE: on posix systems, this *has* to be here and in the
+    # `__name__ == "__main__"` clause to run XGBoost in parallel processes
+    # using fork, if XGBoost was built with OpenMP support. Otherwise, if you
+    # build XGBoost without OpenMP support, you can use fork, which is the
+    # default backend for joblib, and omit this.
+    try:
+        from multiprocessing import set_start_method
+    except ImportError:
+        raise ImportError("Unable to import multiprocessing.set_start_method."
+                          " This example only runs on Python 3.4")
+    set_start_method("forkserver")
+
+    import numpy as np
+    from sklearn.grid_search import GridSearchCV
+    from sklearn.datasets import load_boston
+    import xgboost as xgb
+
+    rng = np.random.RandomState(31337)
+
+    print("Parallel Parameter optimization")
+    boston = load_boston()
+
+    os.environ["OMP_NUM_THREADS"] = "2"  # or to whatever you want
+    y = boston['target']
+    X = boston['data']
+    xgb_model = xgb.XGBRegressor()
+    clf = GridSearchCV(xgb_model, {'max_depth': [2, 4, 6],
+                                   'n_estimators': [50, 100, 200]}, verbose=1,
+                       n_jobs=2)
+    clf.fit(X, y)
+    print(clf.best_score_)
+    print(clf.best_params_)