def print_output(library, algorithm, stages, columns, params, functions, times, accuracy_type, accuracies, data): if params.output_format == 'csv': print_header(columns, params) for i in range(len(accuracies)): print_row(columns, params, prep_function=functions[2 * i], function=functions[2 * i + 1], time=times[2 * i], prep_time=times[2 * i + 1], accuracy=accuracies[i]) elif params.output_format == 'json': output = [] output.append({ 'library': library, 'algorithm': algorithm, 'input_data': { 'data_format': params.data_format, 'data_order': params.data_order, 'data_type': str(params.dtype), 'dataset_name': params.dataset_name, 'rows': data[0].shape[0], 'columns': data[0].shape[1] } }) if hasattr(params, 'n_classes'): output[-1]['input_data'].update({'classes': params.n_classes}) for i in range(len(stages)): result = { 'stage': stages[i], } if 'daal' in stages[i]: result.update({ 'conversion_to_daal4py': times[2 * i], 'prediction_time': times[2 * i + 1] }) elif 'train' in stages[i]: result.update({ 'matrix_creation_time': times[2 * i], 'training_time': times[2 * i + 1] }) else: result.update({ 'matrix_creation_time': times[2 * i], 'prediction_time': times[2 * i + 1] }) if accuracies[i] is not None: result.update({f'{accuracy_type}': accuracies[i]}) output.append(result) print(json.dumps(output, indent=4))
def test_predict(X, X_init): algorithm = kmeans(fptype=getFPType(X), nClusters=params.n_clusters, maxIterations=0, assignFlag=True, accuracyThreshold=0.0) return algorithm.compute(X, X_init) columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size', 'n_clusters', 'time') print_header(columns, params) # Time fit fit_time, _ = time_mean_min(test_fit, X, X_init, outer_loops=params.fit_outer_loops, inner_loops=params.fit_inner_loops) print_row(columns, params, function='KMeans.fit', time=fit_time) # Time predict predict_time, _ = time_mean_min(test_predict, X, X_init, outer_loops=params.predict_outer_loops, inner_loops=params.predict_inner_loops) print_row(columns, params, function='KMeans.predict', time=predict_time)
except ImportError: from sklearn.ensemble import RandomForestRegressor # Load data X = np.load(params.filex.name) y = np.load(params.filey.name) # Create our random forest regressor regr = RandomForestRegressor(n_estimators=params.num_trees, max_depth=params.max_depth, max_features=params.max_features, random_state=params.seed) columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size', 'num_trees', 'time') params.size = size_str(X.shape) params.dtype = X.dtype print_header(columns, params) # Time fit and predict fit_time, _ = time_mean_min(regr.fit, X, y, outer_loops=params.fit_outer_loops, inner_loops=params.fit_inner_loops) print_row(columns, params, function='df_regr.fit', time=fit_time) predict_time, y_pred = time_mean_min(regr.predict, X, outer_loops=params.predict_outer_loops, inner_loops=params.predict_inner_loops) print_row(columns, params, function='df_regr.predict', time=predict_time)
# Time fit and predict fit_time, res = time_mean_min(test_fit, X, y, penalty='l2', C=params.C, verbose=params.verbose, fit_intercept=params.fit_intercept, tol=params.tol, max_iter=params.maxiter, solver=params.solver, outer_loops=params.fit_outer_loops, inner_loops=params.fit_inner_loops) beta, intercept, solver_result, params.multiclass = res print_row(columns, params, function='LogReg.fit', time=fit_time) predict_time, yp = time_mean_min(test_predict, X, beta, intercept=intercept, multi_class=params.multiclass, outer_loops=params.predict_outer_loops, inner_loops=params.predict_inner_loops) y_pred = np.argmax(yp, axis=1) acc = 100 * accuracy_score(y_pred, y) print_row(columns, params, function='LogReg.predict', time=predict_time, accuracy=acc)
X.shape[0], eigenvalues, eigenvectors, whiten=params.whiten) columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size', 'svd_solver', 'n_components', 'whiten', 'time') print_header(columns, params) # Time fit fit_time, res = time_mean_min(test_fit, X, outer_loops=params.fit_outer_loops, inner_loops=params.fit_inner_loops) print_row(columns, params, function='PCA.fit', time=fit_time) # Time transform transform_time, tr = time_mean_min(test_transform, Xp, *res[:3], outer_loops=params.transform_outer_loops, inner_loops=params.transform_inner_loops) print_row(columns, params, function='PCA.transform', time=transform_time) if params.write_results: np.save('pca_daal4py_X.npy', X) np.save('pca_daal4py_Xp.npy', Xp) np.save('pca_daal4py_eigvals.npy', res[1]) np.save('pca_daal4py_eigvecs.npy', res[2]) np.save('pca_daal4py_tr.npy', tr)
def main(): parser = argparse.ArgumentParser(description='daal4py SVC benchmark with ' 'linear kernel') parser.add_argument('-x', '--filex', '--fileX', type=argparse.FileType('r'), required=True, help='Input file with features, in NPY format') parser.add_argument('-y', '--filey', '--fileY', type=argparse.FileType('r'), required=True, help='Input file with labels, in NPY format') parser.add_argument('-C', dest='C', type=float, default=0.01, help='SVM slack parameter') parser.add_argument('--kernel', choices=('linear', ), default='linear', help='SVM kernel function') parser.add_argument('--maxiter', type=int, default=2000, help='Maximum iterations for the iterative solver. ' '-1 means no limit.') parser.add_argument('--max-cache-size', type=int, default=64, help='Maximum cache size, in gigabytes, for SVM.') parser.add_argument('--tau', type=float, default=1e-12, help='Tau parameter for working set selection scheme') parser.add_argument('--tol', type=float, default=1e-16, help='Tolerance') parser.add_argument('--no-shrinking', action='store_false', default=True, dest='shrinking', help="Don't use shrinking heuristic") params = parse_args(parser, loop_types=('fit', 'predict'), prefix='daal4py') # Load data and cast to float64 X_train = np.load(params.filex.name).astype('f8') y_train = np.load(params.filey.name).astype('f8') cache_size_bytes = get_optimal_cache_size(X_train.shape[0], max_cache=params.max_cache_size) params.cache_size_mb = cache_size_bytes / 2**20 params.cache_size_bytes = cache_size_bytes params.n_classes = np.unique(y_train).size # This is necessary for daal y_train[y_train == 0] = -1 y_train = y_train[:, np.newaxis] columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size', 'kernel', 'cache_size_mb', 'C', 'sv_len', 'n_classes', 'accuracy', 'time') params.size = size_str(X_train.shape) params.dtype = X_train.dtype print_header(columns, params) # Time fit and predict fit_time, res = time_mean_min(test_fit, X_train, y_train, params, outer_loops=params.fit_outer_loops, inner_loops=params.fit_inner_loops) res, support, indices, n_support = res params.sv_len = support.shape[0] print_row(columns, params, function='SVM.fit', time=fit_time) predict_time, yp = time_mean_min(test_predict, X_train, res, params, outer_loops=params.predict_outer_loops, inner_loops=params.predict_inner_loops) print_row(columns, params, function='SVM.predict', time=predict_time, accuracy=f'{100*accuracy_score(yp, y_train):.3}')
parser.add_argument('--metrics', nargs='*', default=['cosine', 'correlation'], choices=('cosine', 'correlation'), help='Metrics to test for pairwise_distances') params = parse_args(parser, size=(1000, 150000), dtypes=('f8', 'f4'), prefix='daal4py') # Generate random data X = np.random.rand(*params.shape).astype(params.dtype) columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size', 'time') print_header(columns, params) for metric in params.metrics: pairwise_distances = getattr(daal4py, f'{metric}_distance') def test_distances(pairwise_distances, X): algorithm = pairwise_distances(fptype=getFPType(X)) return algorithm.compute(X) time, _ = time_mean_min(test_distances, pairwise_distances, X, outer_loops=params.outer_loops, inner_loops=params.inner_loops) print_row(columns, params, function=metric.capitalize(), time=time)
parser.add_argument('--solver', default='auto', help='Solver used for training') params = parse_args(parser, size=(1000000, 50), dtypes=('f8', 'f4'), loop_types=('fit', 'predict')) # Generate random data X = np.random.rand(*params.shape).astype(params.dtype) Xp = np.random.rand(*params.shape).astype(params.dtype) y = np.random.rand(*params.shape).astype(params.dtype) # Create our regression object regr = Ridge(fit_intercept=params.fit_intercept, solver=params.solver) columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size', 'time') print_header(columns, params) # Time fit fit_time, _ = time_mean_min(regr.fit, X, y, outer_loops=params.fit_outer_loops, inner_loops=params.fit_inner_loops) print_row(columns, params, function='Ridge.fit', time=fit_time) # Time predict predict_time, yp = time_mean_min(regr.predict, Xp, outer_loops=params.predict_outer_loops, inner_loops=params.predict_inner_loops) print_row(columns, params, function='Ridge.predict', time=predict_time)
max_depth=params.max_depth, max_features=params.max_features, random_state=params.seed) columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size', 'num_trees', 'n_classes', 'accuracy', 'time') params.n_classes = len(np.unique(y)) params.size = size_str(X.shape) params.dtype = X.dtype print_header(columns, params) # Time fit and predict fit_time, _ = time_mean_min(clf.fit, X, y, outer_loops=params.fit_outer_loops, inner_loops=params.fit_inner_loops) print_row(columns, params, function='df_clsf.fit', time=fit_time) predict_time, y_pred = time_mean_min(clf.predict, X, outer_loops=params.predict_outer_loops, inner_loops=params.predict_inner_loops) acc = 100 * accuracy_score(y_pred, y) print_row(columns, params, function='df_clsf.predict', time=predict_time, accuracy=acc)