Extend output result & minor fixes

configs/blogs/skl_2021_3.json

@@ -307,7 +307,7 @@
                 }
             ],
             "nu": [0.25],
-            "kernel": ["sigmoid"]
+            "kernel": ["poly"]
         },
         {
             "algorithm": "svr",

datasets/loader_classification.py

@@ -68,9 +68,11 @@ def airline(dataset_dir: Path) -> bool:
     Airline dataset
     http://kt.ijs.si/elena_ikonomovska/data.html
 
-    TaskType:binclass
-    NumberOfFeatures:13
-    NumberOfInstances:115M
+    Classification task. n_classes = 2.
+    airline X train dataset (92055213, 13)
+    airline y train dataset (92055213, 1)
+    airline X test dataset  (23013804,  13)
+    airline y test dataset  (23013804,  1)
     """
     dataset_name = 'airline'
     os.makedirs(dataset_dir, exist_ok=True)
@@ -126,9 +128,12 @@ def airline(dataset_dir: Path) -> bool:
 def airline_ohe(dataset_dir: Path) -> bool:
     """
     Dataset from szilard benchmarks: https://github.com/szilard/GBM-perf
-    TaskType:binclass
-    NumberOfFeatures:700
-    NumberOfInstances:10100000
+
+    Classification task. n_classes = 2.
+    airline-ohe X train dataset (1000000, 692)
+    airline-ohe y train dataset (1000000, 1)
+    airline-ohe X test dataset  (100000,  692)
+    airline-ohe y test dataset  (100000,  1)
     """
     dataset_name = 'airline-ohe'
     os.makedirs(dataset_dir, exist_ok=True)
@@ -289,9 +294,11 @@ def epsilon(dataset_dir: Path) -> bool:
     Epsilon dataset
     https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary.html
 
-    TaskType:binclass
-    NumberOfFeatures:2000
-    NumberOfInstances:500K
+    Classification task. n_classes = 2.
+    epsilon X train dataset (400000, 2000)
+    epsilon y train dataset (400000, 1)
+    epsilon X test dataset  (100000,  2000)
+    epsilon y test dataset  (100000,  1)
     """
     dataset_name = 'epsilon'
     os.makedirs(dataset_dir, exist_ok=True)
@@ -444,9 +451,11 @@ def higgs(dataset_dir: Path) -> bool:
     Higgs dataset from UCI machine learning repository
     https://archive.ics.uci.edu/ml/datasets/HIGGS
 
-    TaskType:binclass
-    NumberOfFeatures:28
-    NumberOfInstances:11M
+    Classification task. n_classes = 2.
+    higgs X train dataset (8799999, 28)
+    higgs y train dataset (8799999, 1)
+    higgs X test dataset  (2200000,  28)
+    higgs y test dataset  (2200000,  1)
     """
     dataset_name = 'higgs'
     os.makedirs(dataset_dir, exist_ok=True)
@@ -479,9 +488,11 @@ def higgs_one_m(dataset_dir: Path) -> bool:
 
     Only first 1.5M samples is taken
 
-    TaskType:binclass
-    NumberOfFeatures:28
-    NumberOfInstances:1.5M
+    Classification task. n_classes = 2.
+    higgs1m X train dataset (1000000, 28)
+    higgs1m y train dataset (1000000, 1)
+    higgs1m X test dataset  (500000,  28)
+    higgs1m y test dataset  (500000,  1)
     """
     dataset_name = 'higgs1m'
     os.makedirs(dataset_dir, exist_ok=True)

datasets/loader_multiclass.py

@@ -99,9 +99,11 @@ def covtype(dataset_dir: Path) -> bool:
     https://archive.ics.uci.edu/ml/datasets/covertype
 
     y contains 7 unique class labels from 1 to 7 inclusive.
-    TaskType:multiclass
-    NumberOfFeatures:54
-    NumberOfInstances:581012
+    Classification task. n_classes = 7.
+    covtype X train dataset (464809, 54)
+    covtype y train dataset (464809, 1)
+    covtype X test dataset  (116203,  54)
+    covtype y test dataset  (116203,  1)
     """
     dataset_name = 'covtype'
     os.makedirs(dataset_dir, exist_ok=True)
@@ -125,9 +127,11 @@ def letters(dataset_dir: Path) -> bool:
     """
     http://archive.ics.uci.edu/ml/datasets/Letter+Recognition
 
-    TaskType:multiclass
-    NumberOfFeatures:16
-    NumberOfInstances:20.000
+    Classification task. n_classes = 26.
+    letters X train dataset (16000, 16)
+    letters y train dataset (16000, 1)
+    letters X test dataset  (4000,  16)
+    letters y test dataset  (4000,  1)
     """
     dataset_name = 'letters'
     os.makedirs(dataset_dir, exist_ok=True)
@@ -204,9 +208,11 @@ def msrank(dataset_dir: Path) -> bool:
     """
     Dataset from szilard benchmarks: https://github.com/szilard/GBM-perf
 
-    TaskType:multiclass
-    NumberOfFeatures:137
-    NumberOfInstances:1.2M
+    Multiclass classification task
+    msrank X train dataset (958671, 137)
+    msrank y train dataset (958671, 1)
+    msrank X test dataset  (241521,  137)
+    msrank y test dataset  (241521,  1)
     """
     dataset_name = 'msrank'
     os.makedirs(dataset_dir, exist_ok=True)

datasets/loader_regression.py

@@ -32,9 +32,10 @@ def abalone(dataset_dir: Path) -> bool:
     """
     https://archive.ics.uci.edu/ml/machine-learning-databases/abalone
 
-    TaskType:regression
-    NumberOfFeatures:8
-    NumberOfInstances:4177
+    abalone x train dataset (3341, 8)
+    abalone y train dataset (3341, 1)
+    abalone x test dataset  (836,  8)
+    abalone y train dataset (836,  1)
     """
     dataset_name = 'abalone'
     os.makedirs(dataset_dir, exist_ok=True)
@@ -196,9 +197,10 @@ def year_prediction_msd(dataset_dir: Path) -> bool:
     YearPredictionMSD dataset from UCI repository
     https://archive.ics.uci.edu/ml/datasets/yearpredictionmsd
 
-    TaskType:regression
-    NumberOfFeatures:90
-    NumberOfInstances:515345
+    year_prediction_msd x train dataset (463715, 11)
+    year_prediction_msd y train dataset (463715, 1)
+    year_prediction_msd x test dataset  (51630,  11)
+    year_prediction_msd y train dataset (51630,  1)
     """
     dataset_name = 'year_prediction_msd'
     os.makedirs(dataset_dir, exist_ok=True)

sklearn_bench/kmeans.py

@@ -48,7 +48,8 @@ def main():
 
     def fit_kmeans(X, X_init):
         alg = KMeans(n_clusters=params.n_clusters, tol=params.tol,
-                     max_iter=params.maxiter, init=X_init, n_init=1)
+                     max_iter=params.maxiter, init=X_init, n_init=params.n_init,
+                     algorithm=params.algorithm, random_state=params.random_state)
         alg.fit(X)
         return alg
 
@@ -83,5 +84,12 @@ def fit_kmeans(X, X_init):
     parser.add_argument('--maxiter', type=int, default=100,
                         help='Maximum number of iterations')
     parser.add_argument('--n-clusters', type=int, help='Number of clusters')
+    parser.add_argument('--algorithm', type=str, default='full',
+                        help='K-means algorithm to use')
+    parser.add_argument('--n_init', type=int, default=10,
+                        help='Number of time the k-means algorithm '
+                        'will be run with different centroid seeds')
+    parser.add_argument('--random_state', type=int, default=777,
+                        help='Random state')
     params = bench.parse_args(parser)
     bench.run_with_context(params, main)