Skip to content

Commit f9cf09b

Browse files
author
Igor Rukhovich
committed
Changed all datasets to npy, applied Kirill's comments
1 parent 8bdc7f2 commit f9cf09b

13 files changed

+402
-402
lines changed

‎bench.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -419,7 +419,7 @@ def load_data(params, generated_data=[], add_dtype=False, label_2d=False,
419419
# load and convert data from npy/csv file if path is specified
420420
if param_vars[file_arg] is not None:
421421
if param_vars[file_arg].name.endswith('.npy'):
422-
data = np.load(param_vars[file_arg].name)
422+
data = np.load(param_vars[file_arg].name, allow_pickle=True)
423423
else:
424424
data = read_csv(param_vars[file_arg].name, params)
425425
full_data[element] = convert_data(

‎configs/cuml_config.json

Lines changed: 47 additions & 47 deletions
Original file line numberDiff line numberDiff line change
@@ -103,31 +103,31 @@
103103
"dtype": ["float32"],
104104
"dataset": [
105105
{
106-
"source": "csv",
106+
"source": "npy",
107107
"name": "higgs1m",
108108
"training":
109109
{
110-
"x": "data/higgs1m_x_train.csv",
111-
"y": "data/higgs1m_y_train.csv"
110+
"x": "data/higgs1m_x_train.npy",
111+
"y": "data/higgs1m_y_train.npy"
112112
},
113113
"testing":
114114
{
115-
"x": "data/higgs1m_x_test.csv",
116-
"y": "data/higgs1m_y_test.csv"
115+
"x": "data/higgs1m_x_test.npy",
116+
"y": "data/higgs1m_y_test.npy"
117117
}
118118
},
119119
{
120-
"source": "csv",
120+
"source": "npy",
121121
"name": "airline-ohe",
122122
"training":
123123
{
124-
"x": "data/airline-ohe_x_train.csv",
125-
"y": "data/airline-ohe_y_train.csv"
124+
"x": "data/airline-ohe_x_train.npy",
125+
"y": "data/airline-ohe_y_train.npy"
126126
},
127127
"testing":
128128
{
129-
"x": "data/airline-ohe_x_test.csv",
130-
"y": "data/airline-ohe_y_test.csv"
129+
"x": "data/airline-ohe_x_test.npy",
130+
"y": "data/airline-ohe_y_test.npy"
131131
}
132132
}
133133
],
@@ -226,17 +226,17 @@
226226
"algorithm": "svm",
227227
"dataset": [
228228
{
229-
"source": "csv",
229+
"source": "npy",
230230
"name": "ijcnn",
231231
"training":
232232
{
233-
"x": "data/ijcnn_x_train.csv",
234-
"y": "data/ijcnn_y_train.csv"
233+
"x": "data/ijcnn_x_train.npy",
234+
"y": "data/ijcnn_y_train.npy"
235235
},
236236
"testing":
237237
{
238-
"x": "data/ijcnn_x_test.csv",
239-
"y": "data/ijcnn_y_test.csv"
238+
"x": "data/ijcnn_x_test.npy",
239+
"y": "data/ijcnn_y_test.npy"
240240
}
241241
}
242242
],
@@ -247,17 +247,17 @@
247247
"algorithm": "svm",
248248
"dataset": [
249249
{
250-
"source": "csv",
250+
"source": "npy",
251251
"name": "a9a",
252252
"training":
253253
{
254-
"x": "data/a9a_x_train.csv",
255-
"y": "data/a9a_y_train.csv"
254+
"x": "data/a9a_x_train.npy",
255+
"y": "data/a9a_y_train.npy"
256256
},
257257
"testing":
258258
{
259-
"x": "data/a9a_x_test.csv",
260-
"y": "data/a9a_y_test.csv"
259+
"x": "data/a9a_x_test.npy",
260+
"y": "data/a9a_y_test.npy"
261261
}
262262
}
263263
],
@@ -268,17 +268,17 @@
268268
"algorithm": "svm",
269269
"dataset": [
270270
{
271-
"source": "csv",
271+
"source": "npy",
272272
"name": "gisette",
273273
"training":
274274
{
275-
"x": "data/gisette_x_train.csv",
276-
"y": "data/gisette_y_train.csv"
275+
"x": "data/gisette_x_train.npy",
276+
"y": "data/gisette_y_train.npy"
277277
},
278278
"testing":
279279
{
280-
"x": "data/gisette_x_test.csv",
281-
"y": "data/gisette_y_test.csv"
280+
"x": "data/gisette_x_test.npy",
281+
"y": "data/gisette_y_test.npy"
282282
}
283283
}
284284
],
@@ -289,17 +289,17 @@
289289
"algorithm": "svm",
290290
"dataset": [
291291
{
292-
"source": "csv",
292+
"source": "npy",
293293
"name": "klaverjas",
294294
"training":
295295
{
296-
"x": "data/klaverjas_x_train.csv",
297-
"y": "data/klaverjas_y_train.csv"
296+
"x": "data/klaverjas_x_train.npy",
297+
"y": "data/klaverjas_y_train.npy"
298298
},
299299
"testing":
300300
{
301-
"x": "data/klaverjas_x_test.csv",
302-
"y": "data/klaverjas_y_test.csv"
301+
"x": "data/klaverjas_x_test.npy",
302+
"y": "data/klaverjas_y_test.npy"
303303
}
304304
}
305305
],
@@ -310,17 +310,17 @@
310310
"algorithm": "svm",
311311
"dataset": [
312312
{
313-
"source": "csv",
313+
"source": "npy",
314314
"name": "skin_segmentation",
315315
"training":
316316
{
317-
"x": "data/skin_segmentation_x_train.csv",
318-
"y": "data/skin_segmentation_y_train.csv"
317+
"x": "data/skin_segmentation_x_train.npy",
318+
"y": "data/skin_segmentation_y_train.npy"
319319
},
320320
"testing":
321321
{
322-
"x": "data/skin_segmentation_x_test.csv",
323-
"y": "data/skin_segmentation_y_test.csv"
322+
"x": "data/skin_segmentation_x_test.npy",
323+
"y": "data/skin_segmentation_y_test.npy"
324324
}
325325
}
326326
],
@@ -452,12 +452,12 @@
452452
"algorithm": "train_test_split",
453453
"dataset": [
454454
{
455-
"source": "csv",
455+
"source": "npy",
456456
"name": "census",
457457
"training":
458458
{
459-
"x": "data/census_x.csv",
460-
"y": "data/census_y.csv"
459+
"x": "data/census_x_train.npy",
460+
"y": "data/census_y_train.npy"
461461
}
462462
}
463463
],
@@ -468,12 +468,12 @@
468468
"algorithm": "lasso",
469469
"dataset": [
470470
{
471-
"source": "csv",
472-
"name": "mortgage",
471+
"source": "npy",
472+
"name": "mortgage1Q",
473473
"training":
474474
{
475-
"x": "data/mortgage_x.csv",
476-
"y": "data/mortgage_y.csv"
475+
"x": "data/mortgage1Q_x_train.npy",
476+
"y": "data/mortgage1Q_y_train.npy"
477477
}
478478
}
479479
],
@@ -484,17 +484,17 @@
484484
"algorithm": "elasticnet",
485485
"dataset": [
486486
{
487-
"source": "csv",
487+
"source": "npy",
488488
"name": "year_prediction_msd",
489489
"training":
490490
{
491-
"x": "data/year_prediction_msd_x_train.csv",
492-
"y": "data/year_prediction_msd_y_train.csv"
491+
"x": "data/year_prediction_msd_x_train.npy",
492+
"y": "data/year_prediction_msd_y_train.npy"
493493
},
494494
"testing":
495495
{
496-
"x": "data/year_prediction_msd_x_test.csv",
497-
"y": "data/year_prediction_msd_y_test.csv"
496+
"x": "data/year_prediction_msd_x_test.npy",
497+
"y": "data/year_prediction_msd_y_test.npy"
498498
}
499499
}
500500
],

‎configs/modelbuilders/lgbm_mb_cpu_config.json

Lines changed: 6 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -68,12 +68,12 @@
6868
{
6969
"dataset": [
7070
{
71-
"source": "csv",
71+
"source": "npy",
7272
"name": "mortgage1Q",
7373
"training":
7474
{
75-
"x": "data/mortgage_x.csv",
76-
"y": "data/mortgage_y.csv"
75+
"x": "data/mortgage1Q_x_train.npy",
76+
"y": "data/mortgage1Q_y_train.npy"
7777
}
7878
}
7979
],
@@ -92,16 +92,11 @@
9292
"dataset": [
9393
{
9494
"source": "npy",
95-
"name": "msrank",
95+
"name": "mlsr",
9696
"training":
9797
{
98-
"x": "data/msrank_x_train.npy",
99-
"y": "data/msrank_y_train.npy"
100-
},
101-
"testing":
102-
{
103-
"x": "data/msrank_x_test.npy",
104-
"y": "data/msrank_y_test.npy"
98+
"x": "data/mlsr_x_train.npy",
99+
"y": "data/mlsr_y_train.npy"
105100
}
106101
}
107102
],

‎configs/modelbuilders/xgb_mb_cpu_config.json

Lines changed: 6 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -72,12 +72,12 @@
7272
{
7373
"dataset": [
7474
{
75-
"source": "csv",
75+
"source": "npy",
7676
"name": "mortgage1Q",
7777
"training":
7878
{
79-
"x": "data/mortgage_x.csv",
80-
"y": "data/mortgage_y.csv"
79+
"x": "data/mortgage1Q_x_train.npy",
80+
"y": "data/mortgage1Q_y_train.npy"
8181
}
8282
}
8383
],
@@ -96,16 +96,11 @@
9696
"dataset": [
9797
{
9898
"source": "npy",
99-
"name": "msrank",
99+
"name": "mlsr",
100100
"training":
101101
{
102-
"x": "data/msrank_x_train.npy",
103-
"y": "data/msrank_y_train.npy"
104-
},
105-
"testing":
106-
{
107-
"x": "data/msrank_x_test.npy",
108-
"y": "data/msrank_y_test.npy"
102+
"x": "data/mlsr_x_train.npy",
103+
"y": "data/mlsr_y_train.npy"
109104
}
110105
}
111106
],

0 commit comments

Comments
 (0)