Configs for xpu: decision forest classifier

bench.py

@@ -19,6 +19,7 @@
 import logging
 import sys
 import timeit
+import re
 
 import numpy as np
 import sklearn
@@ -64,8 +65,17 @@ def _parse_size(string, dim=2):
     return tup
 
 
+def is_float(string):
+    return bool(re.match(r"^[-+]?(?:\b[0-9]+(?:\.[0-9]*)?|\.[0-9]+\b)(?:[eE][-+]?[0-9]+\b)?$",
+                string))
+
+
 def float_or_int(string):
-    return float(string) if '.' in string else int(string)
+    return int(string) if string.isdigit() else float(string)
+
+
+def float_or_int_or_str(string):
+    return int(string) if string.isdigit() else float(string) if is_float(string) else string
 
 
 def get_optimal_cache_size(n_rows, dtype=np.double, max_cache=64):

configs/xpu/df_clsf.json

@@ -0,0 +1,113 @@
+{
+    "common": {
+        "lib": "sklearn",
+        "algorithm": "df_clsf",
+        "data-format": "pandas",
+        "data-order": "F",
+        "dtype": ["float32", "float64"],
+        "max-features": "sqrt",
+        "device": ["host", "cpu", "gpu", "none"]
+    },
+    "cases": [
+        {
+            "dataset": [
+                {
+                    "source": "npy",
+                    "name": "susy",
+                    "training":
+                    {
+                        "x": "data/susy_x_train.npy",
+                        "y": "data/susy_y_train.npy"
+                    },
+                    "testing":
+                    {
+                        "x": "data/susy_x_test.npy",
+                        "y": "data/susy_y_test.npy"
+                    }
+                }
+            ],
+            "num-trees": 10,
+            "max-depth": 5
+        },
+        {
+            "dataset": [
+                {
+                    "source": "npy",
+                    "name": "susy",
+                    "training":
+                    {
+                        "x": "data/susy_x_train.npy",
+                        "y": "data/susy_y_train.npy"
+                    },
+                    "testing":
+                    {
+                        "x": "data/susy_x_test.npy",
+                        "y": "data/susy_y_test.npy"
+                    }
+                }
+            ],
+            "num-trees": 100,
+            "max-depth": 8
+        },
+        {
+            "dataset": [
+                {
+                    "source": "npy",
+                    "name": "susy",
+                    "training":
+                    {
+                        "x": "data/susy_x_train.npy",
+                        "y": "data/susy_y_train.npy"
+                    },
+                    "testing":
+                    {
+                        "x": "data/susy_x_test.npy",
+                        "y": "data/susy_y_test.npy"
+                    }
+                }
+            ],
+            "num-trees": 20,
+            "max-depth": 16
+        },
+        {
+            "dataset": [
+                {
+                    "source": "npy",
+                    "name": "mnist",
+                    "training":
+                    {
+                        "x": "data/mnist_x_train.npy",
+                        "y": "data/mnist_y_train.npy"
+                    },
+                    "testing":
+                    {
+                        "x": "data/mnist_x_test.npy",
+                        "y": "data/mnist_y_test.npy"
+                    }
+                }
+            ],
+            "num-trees": 100,
+            "max-depth": 10
+        },
+        {
+            "dataset": [
+                {
+                    "source": "npy",
+                    "name": "hepmass_150K",
+                    "training":
+                    {
+                        "x": "data/hepmass_150K_x_train.npy",
+                        "y": "data/hepmass_150K_y_train.npy"
+                    },
+                    "testing":
+                    {
+                        "x": "data/hepmass_150K_x_test.npy",
+                        "y": "data/hepmass_150K_y_test.npy"
+                    }
+                }
+            ],
+            "num-trees": 50,
+            "max-depth": 15
+        }
+    ]
+}

datasets/load_datasets.py

@@ -23,8 +23,8 @@
 
 from .loader_classification import (a_nine_a, airline, airline_ohe, bosch,
                                     census, codrnanorm, creditcard, epsilon, fraud,
-                                    gisette, higgs, higgs_one_m, ijcnn,
-                                    klaverjas, santander, skin_segmentation)
+                                    gisette, hepmass_150K, higgs, higgs_one_m, ijcnn,
+                                    klaverjas, santander, skin_segmentation, susy)
 from .loader_multiclass import (connect, covertype, covtype, letters, mlsr,
                                 mnist, msrank, plasticc, sensit)
 from .loader_regression import (abalone, california_housing, fried,
@@ -49,6 +49,7 @@
     "fraud": fraud,
     "fried": fried,
     "gisette": gisette,
+    "hepmass_150K": hepmass_150K,
     "higgs": higgs,
     "higgs1m": higgs_one_m,
     "ijcnn": ijcnn,
@@ -63,6 +64,7 @@
     "santander": santander,
     "sensit": sensit,
     "skin_segmentation": skin_segmentation,
+    "susy": susy,
     "twodplanes": twodplanes,
     "year_prediction_msd": year_prediction_msd,
     "yolanda": yolanda,

datasets/loader_classification.py

@@ -446,6 +446,55 @@ def gisette(dataset_dir: Path) -> bool:
     return True
 
 
+def hepmass_150K(dataset_dir: Path) -> bool:
+    """
+    HEPMASS dataset from UCI machine learning repository (
+    https://archive.ics.uci.edu/ml/datasets/HEPMASS).
+
+    Classification task. n_classes = 2.
+    hepmass_150K X train dataset (100000, 28)
+    hepmass_150K y train dataset (100000, 1)
+    hepmass_150K X test dataset  (50000,  28)
+    hepmass_150K y test dataset  (50000,  1)
+    """
+    dataset_name = 'hepmass_150K'
+    os.makedirs(dataset_dir, exist_ok=True)
+
+    url_test = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00347/all_test.csv.gz'
+    url_train = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00347/all_train.csv.gz'
+
+    local_url_test = os.path.join(dataset_dir, os.path.basename(url_test))
+    local_url_train = os.path.join(dataset_dir, os.path.basename(url_train))
+
+    if not os.path.isfile(local_url_test):
+        logging.info(f'Started loading {dataset_name}, test')
+        retrieve(url_test, local_url_test)
+    if not os.path.isfile(local_url_train):
+        logging.info(f'Started loading {dataset_name}, train')
+        retrieve(url_train, local_url_train)
+    logging.info(f'{dataset_name} is loaded, started parsing...')
+
+    nrows_train, nrows_test, dtype = 100000, 50000, np.float32
+    data_test: Any = pd.read_csv(local_url_test, delimiter=",",
+                                 compression="gzip", dtype=dtype,
+                                 nrows=nrows_test)
+    data_train: Any = pd.read_csv(local_url_train, delimiter=",",
+                                  compression="gzip", dtype=dtype,
+                                  nrows=nrows_train)
+
+    x_test = np.ascontiguousarray(data_test.values[:nrows_test, 1:], dtype=dtype)
+    y_test = np.ascontiguousarray(data_test.values[:nrows_test, 0], dtype=dtype)
+    x_train = np.ascontiguousarray(data_train.values[:nrows_train, 1:], dtype=dtype)
+    y_train = np.ascontiguousarray(data_train.values[:nrows_train, 0], dtype=dtype)
+
+    for data, name in zip((x_train, x_test, y_train, y_test),
+                          ('x_train', 'x_test', 'y_train', 'y_test')):
+        filename = f'{dataset_name}_{name}.npy'
+        np.save(os.path.join(dataset_dir, filename), data)
+    logging.info(f'dataset {dataset_name} is ready.')
+    return True
+
+
 def higgs(dataset_dir: Path) -> bool:
     """
     Higgs dataset from UCI machine learning repository
@@ -637,3 +686,43 @@ def skin_segmentation(dataset_dir: Path) -> bool:
         np.save(os.path.join(dataset_dir, filename), data)
     logging.info(f'dataset {dataset_name} is ready.')
     return True
+
+
+def susy(dataset_dir: Path) -> bool:
+    """
+    SUSY dataset from UCI machine learning repository (
+    https://archive.ics.uci.edu/ml/datasets/SUSY).
+
+    Classification task. n_classes = 2.
+    susy X train dataset (4500000, 28)
+    susy y train dataset (4500000, 1)
+    susy X test dataset  (500000,  28)
+    susy y test dataset  (500000,  1)
+    """
+    dataset_name = 'susy'
+    os.makedirs(dataset_dir, exist_ok=True)
+
+    url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00279/SUSY.csv.gz'
+    local_url = os.path.join(dataset_dir, os.path.basename(url))
+    if not os.path.isfile(local_url):
+        logging.info(f'Started loading {dataset_name}')
+        retrieve(url, local_url)
+    logging.info(f'{dataset_name} is loaded, started parsing...')
+
+    nrows_train, nrows_test, dtype = 4500000, 500000, np.float32
+    data: Any = pd.read_csv(local_url, delimiter=",", header=None,
+                            compression="gzip", dtype=dtype,
+                            nrows=nrows_train + nrows_test)
+
+    X = data[data.columns[1:]]
+    y = data[data.columns[0:1]]
+
+    x_train, x_test, y_train, y_test = train_test_split(
+        X, y, train_size=nrows_train, test_size=nrows_test, shuffle=False)
+
+    for data, name in zip((x_train, x_test, y_train, y_test),
+                          ('x_train', 'x_test', 'y_train', 'y_test')):
+        filename = f'{dataset_name}_{name}.npy'
+        np.save(os.path.join(dataset_dir, filename), data)
+    logging.info(f'dataset {dataset_name} is ready.')
+    return True

sklearn_bench/df_clsf.py

@@ -81,7 +81,7 @@ def main():
                         help='The function to measure the quality of a split')
     parser.add_argument('--num-trees', type=int, default=100,
                         help='Number of trees in the forest')
-    parser.add_argument('--max-features', type=bench.float_or_int, default=None,
+    parser.add_argument('--max-features', type=bench.float_or_int_or_str, default=None,
                         help='Upper bound on features used at each split')
     parser.add_argument('--max-depth', type=int, default=None,
                         help='Upper bound on depth of constructed trees')

sklearn_bench/df_regr.py

@@ -72,7 +72,7 @@ def main():
                         help='The function to measure the quality of a split')
     parser.add_argument('--num-trees', type=int, default=100,
                         help='Number of trees in the forest')
-    parser.add_argument('--max-features', type=bench.float_or_int, default=None,
+    parser.add_argument('--max-features', type=bench.float_or_int_or_str, default=None,
                         help='Upper bound on features used at each split')
     parser.add_argument('--max-depth', type=int, default=None,
                         help='Upper bound on depth of constructed trees')