Skip to content

Configs for xpu: decision forest regressor, linear regression, logistic regression #104

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
Jan 20, 2022
Merged

Configs for xpu: decision forest regressor, linear regression, logistic regression #104

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
a07e639
regression xpu configs
dmitrii-kriukov Jan 10, 2022
8cc810f
blank line
dmitrii-kriukov Jan 10, 2022
213ee6b
enable devices&dtypes
dmitrii-kriukov Jan 13, 2022
b613c75
regression xpu configs
dmitrii-kriukov Jan 10, 2022
d0ef134
blank line
dmitrii-kriukov Jan 10, 2022
37643ea
enable devices&dtypes
dmitrii-kriukov Jan 13, 2022
e05dfbf
Merge branch 'dev/dkriukov_lin_lof_df_reg' of https://github.com/dmit…
dmitrii-kriukov Jan 13, 2022
099da17
pep8
dmitrii-kriukov Jan 14, 2022
fb83752
fix susy y shape
dmitrii-kriukov Jan 14, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
133 changes: 133 additions & 0 deletions configs/xpu/df_regr.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,133 @@
{
"common": {
"lib": "sklearn",
"algorithm": "df_regr",
"data-format": "pandas",
"data-order": "F",
"dtype": ["float32", "float64"],
"max-features": 0.33,
"device": ["host", "cpu", "gpu", "none"]
},
"cases": [
{
"dataset": [
{
"source": "npy",
"name": "year_prediction_msd",
"training":
{
"x": "data/year_prediction_msd_x_train.npy",
"y": "data/year_prediction_msd_y_train.npy"
},
"testing":
{
"x": "data/year_prediction_msd_x_test.npy",
"y": "data/year_prediction_msd_y_test.npy"
}
}
],
"num-trees": [10, 100],
"max-depth": 5
},
{
"dataset": [
{
"source": "npy",
"name": "year_prediction_msd",
"training":
{
"x": "data/year_prediction_msd_x_train.npy",
"y": "data/year_prediction_msd_y_train.npy"
},
"testing":
{
"x": "data/year_prediction_msd_x_test.npy",
"y": "data/year_prediction_msd_y_test.npy"
}
}
],
"num-trees": [100, 20],
"max-depth": 8
},
{
"dataset": [
{
"source": "npy",
"name": "year_prediction_msd",
"training":
{
"x": "data/year_prediction_msd_x_train.npy",
"y": "data/year_prediction_msd_y_train.npy"
},
"testing":
{
"x": "data/year_prediction_msd_x_test.npy",
"y": "data/year_prediction_msd_y_test.npy"
}
}
],
"num-trees": 20,
"max-depth": 16
},
{
"dataset": [
{
"source": "npy",
"name": "higgs1m",
"training":
{
"x": "data/higgs1m_x_train.npy",
"y": "data/higgs1m_y_train.npy"
},
"testing":
{
"x": "data/higgs1m_x_test.npy",
"y": "data/higgs1m_y_test.npy"
}
}
],
"num-trees": [15, 20, 100],
"max-depth": 8
},
{
"dataset": [
{
"source": "npy",
"name": "higgs_10500K",
"training":
{
"x": "data/higgs_10500K_x_train.npy",
"y": "data/higgs_10500K_y_train.npy"
},
"testing":
{
"x": "data/higgs_10500K_x_test.npy",
"y": "data/higgs_10500K_y_test.npy"
}
}
],
"num-trees": 100,
"max-depth": 8
},
{
"dataset": [
{
"source": "npy",
"name": "higgs_10500K",
"training":
{
"x": "data/higgs_10500K_x_train.npy",
"y": "data/higgs_10500K_y_train.npy"
},
"testing":
{
"x": "data/higgs_10500K_x_test.npy",
"y": "data/higgs_10500K_y_test.npy"
}
}
],
"num-trees": 20,
"max-depth": 16
}
]
}
48 changes: 48 additions & 0 deletions configs/xpu/linear.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
{
"common": {
"lib": "sklearn",
"algorithm": "linear",
"data-format": "pandas",
"data-order": "F",
"dtype": ["float32", "float64"],
"device": ["host", "cpu", "gpu", "none"]
},
"cases": [
{
"dataset": [
{
"source": "npy",
"name": "year_prediction_msd",
"training":
{
"x": "data/year_prediction_msd_x_train.npy",
"y": "data/year_prediction_msd_y_train.npy"
},
"testing":
{
"x": "data/year_prediction_msd_x_test.npy",
"y": "data/year_prediction_msd_y_test.npy"
}
}
]
},
{
"dataset": [
{
"source": "npy",
"name": "higgs1m",
"training":
{
"x": "data/higgs1m_x_train.npy",
"y": "data/higgs1m_y_train.npy"
},
"testing":
{
"x": "data/higgs1m_x_test.npy",
"y": "data/higgs1m_y_test.npy"
}
}
]
}
]
}
89 changes: 89 additions & 0 deletions configs/xpu/log_reg.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,89 @@
{
"common": {
"lib": "sklearn",
"algorithm": "log_reg",
"data-format": "pandas",
"data-order": "F",
"dtype": ["float32", "float64"],
"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"
}
}
],
"maxiter": "20"
},
{
"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"
}
}
],
"maxiter": "10"
},
{
"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"
}
}
],
"no-fit-intercept": "",
"maxiter": "50"
},
{
"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"
}
}
],
"maxiter": "500"
}
]
}
3 changes: 2 additions & 1 deletion datasets/load_datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
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,
from .loader_regression import (abalone, california_housing, fried, higgs_10500K,
medical_charges_nominal, mortgage_first_q,
twodplanes, year_prediction_msd, yolanda, airline_regression)

Expand All @@ -52,6 +52,7 @@
"hepmass_150K": hepmass_150K,
"higgs": higgs,
"higgs1m": higgs_one_m,
"higgs_10500K": higgs_10500K,
"ijcnn": ijcnn,
"klaverjas": klaverjas,
"letters": letters,
Expand Down
2 changes: 1 addition & 1 deletion datasets/loader_classification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -715,7 +715,7 @@ def susy(dataset_dir: Path) -> bool:
nrows=nrows_train + nrows_test)

X = data[data.columns[1:]]
y = data[data.columns[0:1]]
y = data[data.columns[0:1]].values.ravel()

x_train, x_test, y_train, y_test = train_test_split(
X, y, train_size=nrows_train, test_size=nrows_test, shuffle=False)
Expand Down
40 changes: 40 additions & 0 deletions datasets/loader_regression.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -295,3 +295,43 @@ def airline_regression(dataset_dir: Path) -> bool:
np.save(os.path.join(dataset_dir, filename), data)
logging.info(f'dataset {dataset_name} is ready.')
return True


def higgs_10500K(dataset_dir: Path) -> bool:
"""
Higgs dataset from UCI machine learning repository
https://archive.ics.uci.edu/ml/datasets/HIGGS

Classification task. n_classes = 2.
higgs_10500K X train dataset (10500000, 28)
higgs_10500K y train dataset (10500000, 1)
higgs_10500K X test dataset (500000, 28)
higgs_10500K y test dataset (500000, 1)
"""
dataset_name = 'higgs_10500K'
os.makedirs(dataset_dir, exist_ok=True)

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00280/HIGGS.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 = 10500000, 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