Support n_jobs, other changes

Makefile

@@ -4,7 +4,7 @@ REGRESSION_SIZE = 1000000x50
 KMEANS_SAMPLES = 1000000
 KMEANS_FEATURES = 50
 KMEANS_SIZE = $(KMEANS_SAMPLES)x$(KMEANS_FEATURES)
-SVM_SAMPLES = 100000
+SVM_SAMPLES = 10000
 SVM_FEATURES = 100
 SVM_SIZE = $(SVM_SAMPLES)x$(SVM_FEATURES)
 LOGREG_SAMPLES = 100000
@@ -26,10 +26,16 @@ HOST = $(shell hostname)
 # This makes the makefile exit on failed benchmarks. We pipe the
 # benchmark outputs to "tee", which results in unexpected successes.
 SHELL = bash -o pipefail
+export USE_DAAL4PY_SKLEARN = yes
 
 # Other options
 NUM_THREADS = -1
 SVM_NUM_THREADS = 0
+
+ifeq ($(NUM_THREADS),1)
+ OMP_NUM_THREADS = $(NUM_THREADS)
+ export OMP_NUM_THREADS
+endif
 LOGREG_NUM_THREADS = $(SVM_NUM_THREADS)
 DFCLF_NUM_THREADS = $(SVM_NUM_THREADS)
 DFREG_NUM_THREADS = $(SVM_NUM_THREADS)
@@ -80,10 +86,12 @@ ARGS_NATIVE_kmeans = --num-threads "$(NUM_THREADS)" --header \
  --filei data/clustering/kmeans_$(KMEANS_SIZE).init.npy
 ARGS_NATIVE_svm2 = --fileX data/two/X-$(SVM_SIZE).npy \
  --fileY data/two/y-$(SVM_SIZE).npy \
- --num-threads $(SVM_NUM_THREADS) --header
+ --num-threads $(SVM_NUM_THREADS) --header \
+ --kernel rbf
 ARGS_NATIVE_svm5 = --fileX data/multi/X-$(SVM_SIZE).npy \
  --fileY data/multi/y-$(SVM_SIZE).npy \
- --num-threads $(SVM_NUM_THREADS) --header
+ --num-threads $(SVM_NUM_THREADS) --header \
+ --kernel rbf
 ARGS_NATIVE_logreg2 = --fileX data/two/X-$(LOGREG_SIZE).npy \
  --fileY data/two/y-$(LOGREG_SIZE).npy \
  --num-threads $(LOGREG_NUM_THREADS) --header
@@ -106,6 +114,7 @@ SKLEARN_linear = linear
 SKLEARN_pca_full = pca
 SKLEARN_pca_daal = pca
 SKLEARN_kmeans = kmeans
+SKLEARN_dbscan = dbscan
 SKLEARN_svm2 = svm
 SKLEARN_svm5 = svm
 SKLEARN_logreg2 = log_reg
@@ -122,10 +131,13 @@ ARGS_SKLEARN_pca_full = --size "$(REGRESSION_SIZE)" --svd-solver full
 ARGS_SKLEARN_kmeans = --data-multiplier "$(MULTIPLIER)" \
  --filex data/clustering/kmeans_$(KMEANS_SIZE).npy \
  --filei data/clustering/kmeans_$(KMEANS_SIZE).init.npy
+ARGS_SKLEARN_dbscan = --filex data/clustering/kmeans_$(KMEANS_SIZE).npy
 ARGS_SKLEARN_svm2 = --fileX data/two/X-$(SVM_SIZE).npy \
- --fileY data/two/y-$(SVM_SIZE).npy
+ --fileY data/two/y-$(SVM_SIZE).npy \
+ --kernel rbf
 ARGS_SKLEARN_svm5 = --fileX data/multi/X-$(SVM_SIZE).npy \
- --fileY data/multi/y-$(SVM_SIZE).npy
+ --fileY data/multi/y-$(SVM_SIZE).npy \
+ --kernel rbf
 ARGS_SKLEARN_logreg2 = --fileX data/two/X-$(LOGREG_SIZE).npy \
  --fileY data/two/y-$(LOGREG_SIZE).npy
 ARGS_SKLEARN_logreg5 = --fileX data/multi/X-$(LOGREG_SIZE).npy \
@@ -196,7 +208,7 @@ output/native/%.out: | DATA_% output/native/
  native/bin/$(NATIVE_$*) $(ARGS_NATIVE_$*) | tee $@
 
 output/sklearn/%.out: | DATA_% output/sklearn/
- python sklearn/$(SKLEARN_$*).py $(COMMON_ARGS) $(ARGS_SKLEARN_$*) | tee $@
+ taskset -c 28-56 python sklearn/$(SKLEARN_$*).py $(COMMON_ARGS) $(ARGS_SKLEARN_$*) | tee $@
 
 output/daal4py/%.out: | DATA_% output/daal4py/
  python daal4py/$(DAAL4PY_$*).py $(COMMON_ARGS) $(ARGS_DAAL4PY_$*) | tee $@

sklearn/df_clsf.py

@@ -29,7 +29,8 @@
  'sklearn.ensemble.RandomForestClassifier')
 parser.add_argument('--seed', type=int, default=12345,
  help='Seed to pass as random_state to the class')
-params = parse_args(parser, loop_types=('fit', 'predict'))
+params = parse_args(parser, loop_types=('fit', 'predict'),
+ n_jobs_supported=True)
 
 # Get some RandomForestClassifier
 if params.use_sklearn_class:

sklearn/df_regr.py

@@ -27,7 +27,8 @@
  'sklearn.ensemble.RandomForestRegressor')
 parser.add_argument('--seed', type=int, default=12345,
  help='Seed to pass as random_state to the class')
-params = parse_args(parser, loop_types=('fit', 'predict'))
+params = parse_args(parser, loop_types=('fit', 'predict'),
+ n_jobs_supported=True)
 
 # Get some RandomForestRegressor
 if params.use_sklearn_class:

sklearn/distances.py

@@ -11,7 +11,8 @@
  'benchmark')
 parser.add_argument('--metrics', nargs='*', default=['cosine', 'correlation'],
  help='Metrics to test for pairwise_distances')
-params = parse_args(parser, size=(1000, 150000), dtypes=('f8', 'f4'))
+params = parse_args(parser, size=(1000, 150000), dtypes=('f8', 'f4'),
+ n_jobs_supported=True)
 
 # Generate random data
 X = np.random.rand(*params.shape).astype(params.dtype)

sklearn/kmeans.py

@@ -18,7 +18,8 @@
  type=int, help='Data multiplier')
 parser.add_argument('--maxiter', type=int, default=100,
  help='Maximum number of iterations')
-params = parse_args(parser, loop_types=('fit', 'predict'))
+params = parse_args(parser, loop_types=('fit', 'predict'),
+ n_jobs_supported=True)
 
 # Load generated data
 X = np.load(params.filex)

sklearn/linear.py

@@ -13,7 +13,7 @@
  action='store_false',
  help="Don't fit intercept (assume data already centered)")
 params = parse_args(parser, size=(1000000, 50), dtypes=('f8', 'f4'),
- loop_types=('fit', 'predict'))
+ loop_types=('fit', 'predict'), n_jobs_supported=True)
 
 # Generate random data
 X = np.random.rand(*params.shape).astype(params.dtype)

sklearn/log_reg.py

@@ -35,7 +35,10 @@
  help="Tolerance for solver. If solver == 'newton-cg', "
  "then the default is 1e-3. Otherwise, the default "
  "is 1e-10.")
-params = parse_args(parser, loop_types=('fit', 'predict'))
+parser.add_argument('--tile', type=int, default=100, help="Create (tile)x size dataset"
+ )
+params = parse_args(parser, loop_types=('fit', 'predict'),
+ n_jobs_supported=True)
 
 # Load generated data
 X = np.load(params.filex.name)
@@ -71,6 +74,10 @@
  verbose=params.verbose)
 print_row(columns, params, function='LogReg.fit', time=fit_time)
 
+X = np.tile(X, (params.tile, 1))
+y = np.tile(y, params.tile)
+params.size = size_str(X.shape)
+
 predict_time, y_pred = time_mean_min(clf.predict, X,
  outer_loops=params.predict_outer_loops,
  inner_loops=params.predict_inner_loops,

sklearn/svm.py

@@ -5,7 +5,7 @@
 import argparse
 from bench import parse_args, time_mean_min, print_header, print_row, size_str
 import numpy as np
-from sklearn.svm import SVC
+from sklearn.svm import SVC, LinearSVC
 from sklearn.metrics import accuracy_score
 
 
@@ -71,9 +71,15 @@ def get_optimal_cache_size(n_features, dtype=np.double, max_cache=64):
 params.n_classes = len(np.unique(y))
 
 # Create our C-SVM classifier
-clf = SVC(C=params.C, kernel=params.kernel, max_iter=params.maxiter,
- cache_size=params.cache_size_mb, tol=params.tol,
- shrinking=params.shrinking, gamma=params.gamma)
+if params.using_daal or params.kernel != 'linear':
+ clf = SVC(C=params.C, kernel=params.kernel, max_iter=params.maxiter,
+ cache_size=params.cache_size_mb, tol=params.tol,
+ shrinking=params.shrinking, gamma=params.gamma)
+else:
+ clf = LinearSVC(C=params.C, max_iter=params.maxiter, tol=params.tol)
+
+if params.verbose:
+ print(clf)
 
 columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size',
  'kernel', 'cache_size_mb', 'C', 'sv_len', 'n_classes', 'accuracy',
@@ -90,7 +96,10 @@ def get_optimal_cache_size(n_features, dtype=np.double, max_cache=64):
  goal_outer_loops=params.fit_goal,
  time_limit=params.fit_time_limit,
  verbose=params.verbose)
-params.sv_len = clf.support_.shape[0]
+if hasattr(clf, 'support_'):
+ params.sv_len = clf.support_.shape[0]
+else:
+ params.sv_len = '?'
 print_row(columns, params, function='SVM.fit', time=fit_time)
 
 predict_time, y_pred = time_mean_min(clf.predict, X,