PCA Config Update and Imports Fix

configs/skl_config.json

@@ -65,7 +65,6 @@
             "tol": [0.0]
         },
         {
-            "lib": ["daal4py"],
             "algorithm": "pca",
             "dataset": [
                 {
@@ -97,9 +96,18 @@
                     "training": {
                         "n_samples": 30000
                     }
+                },
+                {
+                    "source": "synthetic",
+                    "type": "classification",
+                    "n_classes": 2,
+                    "n_features": 4000,
+                    "training": {
+                        "n_samples": 6000
+                    }
                 }
             ],
-            "svd-solver": ["correlation"],
+            "svd-solver": ["full"],
             "n-components": [10]
         },
         {

sklearn_bench/dbscan.py

@@ -19,7 +19,6 @@
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
-from sklearn.cluster import DBSCAN
 from sklearn.metrics.cluster import davies_bouldin_score
 
 parser = argparse.ArgumentParser(description='scikit-learn DBSCAN benchmark')
@@ -30,6 +29,8 @@
                     'neighborhood to consider a point a core point')
 params = bench.parse_args(parser, n_jobs_supported=True)
 
+from sklearn.cluster import DBSCAN
+
 # Load generated data
 X, _, _, _ = bench.load_data(params, add_dtype=True)
 

sklearn_bench/df_clsf.py

@@ -21,7 +21,6 @@
 import bench
 
 import numpy as np
-from sklearn.ensemble import RandomForestClassifier
 from sklearn.metrics import accuracy_score
 
 parser = argparse.ArgumentParser(description='scikit-learn random forest '
@@ -47,6 +46,8 @@
 
 params = bench.parse_args(parser)
 
+from sklearn.ensemble import RandomForestClassifier
+
 # Load and convert data
 X_train, X_test, y_train, y_test = bench.load_data(params)
 

sklearn_bench/df_regr.py

@@ -19,7 +19,6 @@
 import argparse
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
-from sklearn.ensemble import RandomForestRegressor
 
 parser = argparse.ArgumentParser(description='scikit-learn random forest '
                                              'regression benchmark')
@@ -45,6 +44,8 @@
 
 params = bench.parse_args(parser)
 
+from sklearn.ensemble import RandomForestRegressor
+
 # Load and convert data
 X_train, X_test, y_train, y_test = bench.load_data(params)
 

sklearn_bench/distances.py

@@ -19,7 +19,6 @@
 import argparse
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
-from sklearn.metrics.pairwise import pairwise_distances
 
 parser = argparse.ArgumentParser(description='scikit-learn pairwise distances '
                                              'benchmark')
@@ -28,6 +27,8 @@
                     help='Metric to test for pairwise distances')
 params = bench.parse_args(parser)
 
+from sklearn.metrics.pairwise import pairwise_distances
+
 # Load data
 X, _, _, _ = bench.load_data(params, generated_data=['X_train'], add_dtype=True)
 

sklearn_bench/elasticnet.py

@@ -20,8 +20,6 @@
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
 
-from sklearn.linear_model import ElasticNet
-
 parser = argparse.ArgumentParser(description='scikit-learn elastic-net regression '
                                              'benchmark')
 parser.add_argument('--no-fit-intercept', dest='fit_intercept', default=False,
@@ -37,6 +35,8 @@
                     help='Tolerance for solver.')
 params = bench.parse_args(parser)
 
+from sklearn.linear_model import ElasticNet
+
 # Load data
 X_train, X_test, y_train, y_test = bench.load_data(params)
 

sklearn_bench/kmeans.py

@@ -20,7 +20,6 @@
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
 import numpy as np
-from sklearn.cluster import KMeans
 from sklearn.metrics.cluster import davies_bouldin_score
 
 parser = argparse.ArgumentParser(description='scikit-learn K-means benchmark')
@@ -33,6 +32,8 @@
 parser.add_argument('--n-clusters', type=int, help='Number of clusters')
 params = bench.parse_args(parser)
 
+from sklearn.cluster import KMeans
+
 # Load and convert generated data
 X_train, X_test, _, _ = bench.load_data(params)
 

sklearn_bench/knn_clsf.py

@@ -20,7 +20,6 @@
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
 import numpy as np
-from sklearn.neighbors import KNeighborsClassifier
 from sklearn.metrics import accuracy_score
 
 parser = argparse.ArgumentParser(
@@ -40,6 +39,8 @@
                     help='Distance metric to use')
 params = bench.parse_args(parser)
 
+from sklearn.neighbors import KNeighborsClassifier
+
 # Load generated data
 X_train, X_test, y_train, y_test = bench.load_data(params)
 params.n_classes = len(np.unique(y_train))

sklearn_bench/lasso.py

@@ -19,7 +19,6 @@
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
-from sklearn.linear_model import Lasso
 
 parser = argparse.ArgumentParser(description='scikit-learn lasso regression '
                                              'benchmark')
@@ -34,6 +33,8 @@
                     help='Tolerance for solver.')
 params = bench.parse_args(parser)
 
+from sklearn.linear_model import Lasso
+
 # Load data
 X_train, X_test, y_train, y_test = bench.load_data(params)
 

sklearn_bench/linear.py

@@ -20,7 +20,6 @@
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
-from sklearn.linear_model import LinearRegression
 
 parser = argparse.ArgumentParser(description='scikit-learn linear regression '
                                              'benchmark')
@@ -29,6 +28,8 @@
                     help="Don't fit intercept (assume data already centered)")
 params = bench.parse_args(parser)
 
+from sklearn.linear_model import LinearRegression
+
 # Load data
 X_train, X_test, y_train, y_test = bench.load_data(
     params, generated_data=['X_train', 'y_train'])

sklearn_bench/log_reg.py

@@ -20,8 +20,8 @@
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
 import numpy as np
-from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import accuracy_score
+
 parser = argparse.ArgumentParser(description='scikit-learn logistic '
                                              'regression benchmark')
 parser.add_argument('--no-fit-intercept', dest='fit_intercept',
@@ -45,6 +45,8 @@
                          'is 1e-10.')
 params = bench.parse_args(parser, loop_types=('fit', 'predict'))
 
+from sklearn.linear_model import LogisticRegression
+
 # Load generated data
 X_train, X_test, y_train, y_test = bench.load_data(params)
 

sklearn_bench/pca.py

@@ -19,7 +19,6 @@
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
-from sklearn.decomposition import PCA
 
 parser = argparse.ArgumentParser(description='scikit-learn PCA benchmark')
 parser.add_argument('--svd-solver', type=str, choices=['full'],
@@ -30,6 +29,8 @@
                     help='Perform whitening')
 params = bench.parse_args(parser)
 
+from sklearn.decomposition import PCA
+
 # Load random data
 X_train, X_test, _, _ = bench.load_data(params, generated_data=['X_train'])
 

sklearn_bench/ridge.py

@@ -19,7 +19,6 @@
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
-from sklearn.linear_model import Ridge
 
 parser = argparse.ArgumentParser(description='scikit-learn ridge regression '
                                              'benchmark')
@@ -32,6 +31,8 @@
                     help='Regularization strength')
 params = bench.parse_args(parser)
 
+from sklearn.linear_model import Ridge
+
 # Load data
 X_train, X_test, y_train, y_test = bench.load_data(params,
                                                    generated_data=['X_train', 'y_train'])

sklearn_bench/svm.py

@@ -21,7 +21,6 @@
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
 import numpy as np
-from sklearn.svm import SVC
 from sklearn.metrics import accuracy_score
 
 parser = argparse.ArgumentParser(description='scikit-learn SVM benchmark')
@@ -43,6 +42,8 @@
                     dest='shrinking', help="Don't use shrinking heuristic")
 params = bench.parse_args(parser, loop_types=('fit', 'predict'))
 
+from sklearn.svm import SVC
+
 # Load data
 X_train, X_test, y_train, y_test = bench.load_data(params)
 

sklearn_bench/train_test_split.py

@@ -20,7 +20,6 @@
 import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import bench
-from sklearn.model_selection import train_test_split
 
 parser = argparse.ArgumentParser(
     description='scikit-learn train_test_split benchmark')
@@ -40,6 +39,8 @@
                          '(only for IDP scikit-learn)')
 params = bench.parse_args(parser)
 
+from sklearn.model_selection import train_test_split
+
 # Load generated data
 X, y, _, _ = bench.load_data(params)