Xgb datasets adding #60
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -16,6 +16,7 @@ | |
|
|
||
| import argparse | ||
| import json | ||
| import logging | ||
| import sys | ||
| import timeit | ||
|
|
||
|
|
@@ -200,15 +201,16 @@ def parse_args(parser, size=None, loop_types=(), | |
| from sklearnex import patch_sklearn | ||
| patch_sklearn() | ||
| except ImportError: | ||
| logging.info('Failed to import sklearnex.patch_sklearn.' | ||
| 'Use stock version scikit-learn', file=sys.stderr) | ||
| params.device = 'None' | ||
| else: | ||
| if params.device != 'None': | ||
| logging.info( | ||
| 'Device context is not supported for stock scikit-learn.' | ||
| 'Please use --no-intel-optimized=False with' | ||
| f'--device={params.device} parameter. Fallback to --device=None.', | ||
| file=sys.stderr) | ||
| params.device = 'None' | ||
|
|
||
| # disable finiteness check (default) | ||
|
|
@@ -218,7 +220,7 @@ def parse_args(parser, size=None, loop_types=(), | |
| # Ask DAAL what it thinks about this number of threads | ||
| num_threads = prepare_daal_threads(num_threads=params.threads) | ||
| if params.verbose: | ||
| logging.info(f'@ DAAL gave us {num_threads} threads') | ||
|
|
||
| n_jobs = None | ||
| if n_jobs_supported: | ||
|
|
@@ -234,7 +236,7 @@ def parse_args(parser, size=None, loop_types=(), | |
|
|
||
| # Very verbose output | ||
| if params.verbose: | ||
| logging.info(f'@ params = {params.__dict__}') | ||
|
|
||
| return params | ||
|
|
||
|
|
@@ -249,8 +251,8 @@ def set_daal_num_threads(num_threads): | |
| if num_threads: | ||
| daal4py.daalinit(nthreads=num_threads) | ||
| except ImportError: | ||
| logging.info('@ Package "daal4py" was not found. Number of threads ' | ||
| 'is being ignored') | ||
|
|
||
|
|
||
| def prepare_daal_threads(num_threads=-1): | ||
|
|
@@ -484,7 +486,7 @@ def print_output(library, algorithm, stages, params, functions, | |
| output = [] | ||
| for i in range(len(stages)): | ||
| result = gen_basic_dict(library, algorithm, stages[i], params, | ||
| data[i], alg_instance, alg_params if i == 0 else None) | ||
|
There was a problem hiding this comment. Not clear why only first stage has There was a problem hiding this comment. It seems like in all benchmarks all stages in each case has similar parameters. So, since the the parameter list is usually quite long, we can reduce the length of benchmark output by printing this section only once. There was a problem hiding this comment. @RukhovichIV, Excel report generator filters benchmark cases basing on parameters, output should not be shortened for correct work of generator There was a problem hiding this comment. rolled back that change, but very upset about it :( |
||
| result.update({'time[s]': times[i]}) | ||
| if accuracy_type is not None: | ||
| result.update({f'{accuracy_type}': accuracies[i]}) | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,5 +1,4 @@ | ||
| { | ||
| "common": { | ||
| "lib": ["cuml"], | ||
| "data-format": ["cudf"], | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,109 +1,120 @@ | ||
| { | ||
| "common": { | ||
| "lib": "modelbuilders", | ||
|
There was a problem hiding this comment. Add note to README that parameters might be set with single value or list of values |
||
| "data-format": "pandas", | ||
| "data-order": "F", | ||
| "dtype": "float32", | ||
| "algorithm": "lgbm_mb" | ||
| }, | ||
| "cases": [ | ||
| { | ||
| "dataset": [ | ||
| { | ||
| "source": "npy", | ||
| "name": "airline-ohe", | ||
| "training": | ||
| { | ||
| "x": "data/airline-ohe_x_train.npy", | ||
| "y": "data/airline-ohe_y_train.npy" | ||
| }, | ||
| "testing": | ||
| { | ||
| "x": "data/airline-ohe_x_test.npy", | ||
| "y": "data/airline-ohe_y_test.npy" | ||
| } | ||
| } | ||
| ], | ||
| "reg-alpha": 0.9, | ||
| "max-bin": 256, | ||
| "scale-pos-weight": 2, | ||
| "learning-rate": 0.1, | ||
| "subsample": 1, | ||
| "reg-lambda": 1, | ||
| "min-child-weight": 0, | ||
| "max-depth": 8, | ||
| "max-leaves": 256, | ||
| "n-estimators": 1000, | ||
| "objective": "binary" | ||
| }, | ||
| { | ||
| "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" | ||
| } | ||
| } | ||
| ], | ||
| "reg-alpha": 0.9, | ||
| "max-bin": 256, | ||
| "scale-pos-weight": 2, | ||
| "learning-rate": 0.1, | ||
| "subsample": 1, | ||
| "reg-lambda": 1, | ||
| "min-child-weight": 0, | ||
| "max-depth": 8, | ||
| "max-leaves": 256, | ||
| "n-estimators": 1000, | ||
| "objective": "binary" | ||
| }, | ||
| { | ||
| "dataset": [ | ||
| { | ||
| "source": "csv", | ||
| "name": "mortgage1Q", | ||
| "training": | ||
| { | ||
| "x": "data/mortgage_x.csv", | ||
| "y": "data/mortgage_y.csv" | ||
| } | ||
| } | ||
| ], | ||
| "n-estimators": 100, | ||
| "objective": "regression", | ||
| "max-depth": 8, | ||
| "scale-pos-weight": 2, | ||
| "learning-rate": 0.1, | ||
| "subsample": 1, | ||
| "reg-alpha": 0.9, | ||
| "reg-lambda": 1, | ||
| "min-child-weight": 0, | ||
| "max-leaves": 256 | ||
| }, | ||
| { | ||
| "dataset": [ | ||
| { | ||
| "source": "npy", | ||
| "name": "msrank", | ||
| "training": | ||
| { | ||
| "x": "data/msrank_x_train.npy", | ||
| "y": "data/msrank_y_train.npy" | ||
| }, | ||
| "testing": | ||
| { | ||
| "x": "data/msrank_x_test.npy", | ||
| "y": "data/msrank_y_test.npy" | ||
| } | ||
| } | ||
| ], | ||
| "max-bin": 256, | ||
| "learning-rate": 0.3, | ||
| "subsample": 1, | ||
| "reg-lambda": 2, | ||
| "min-child-weight": 1, | ||
| "min-split-loss": 0.1, | ||
| "max-depth": 8, | ||
| "max-leaves": 256, | ||
| "n-estimators": 200, | ||
| "objective": "multiclass" | ||
| } | ||
| ] | ||
| } | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.