Fix parameters for RF in config and fix n_jobs for original scikit-learn (#51)

Author: PetrovKP

bench.py

@@ -95,7 +95,7 @@ def get_optimal_cache_size(n_rows, dtype=np.double, max_cache=64):
 
 
 def parse_args(parser, size=None, loop_types=(),
-               n_jobs_supported=False, prefix='sklearn'):
+               n_jobs_supported=True, prefix='sklearn'):
     '''
     Add common arguments useful for most benchmarks and parse.
 

configs/skl_config.json

@@ -146,8 +146,7 @@
             "num-trees": [50],
             "max-depth": [16],
             "max-leaf-nodes": [131072],
-            "max-features": [0.2],
-            "use-sklearn-class": [""]
+            "max-features": [0.2]
         },
         {
             "algorithm": "ridge",

sklearn_bench/dbscan.py

@@ -27,7 +27,7 @@
 parser.add_argument('-m', '--min-samples', default=5, type=int,
                     help='The minimum number of samples required in a '
                     'neighborhood to consider a point a core point')
-params = bench.parse_args(parser, n_jobs_supported=True)
+params = bench.parse_args(parser)
 
 from sklearn.cluster import DBSCAN
 

sklearn_bench/df_clsf.py

@@ -60,7 +60,8 @@
                              max_leaf_nodes=params.max_leaf_nodes,
                              min_impurity_decrease=params.min_impurity_decrease,
                              bootstrap=params.bootstrap,
-                             random_state=params.seed)
+                             random_state=params.seed,
+                             n_jobs=params.n_jobs)
 
 params.n_classes = len(np.unique(y_train))
 

sklearn_bench/df_regr.py

@@ -58,7 +58,8 @@
                              max_leaf_nodes=params.max_leaf_nodes,
                              min_impurity_decrease=params.min_impurity_decrease,
                              bootstrap=params.bootstrap,
-                             random_state=params.seed)
+                             random_state=params.seed,
+                             n_jobs=params.n_jobs)
 
 fit_time, _ = bench.measure_function_time(regr.fit, X_train, y_train, params=params)
 

sklearn_bench/knn_clsf.py

@@ -49,7 +49,8 @@
 knn_clsf = KNeighborsClassifier(n_neighbors=params.n_neighbors,
                                 weights=params.weights,
                                 algorithm=params.method,
-                                metric=params.metric)
+                                metric=params.metric,
+                                n_jobs=params.n_jobs)
 
 # Measure time and accuracy on fitting
 train_time, _ = bench.measure_function_time(knn_clsf.fit, X_train, y_train, params=params)