def main(readcsv=read_csv, method='defaultDense'):
# Input data set parameters
train_file = os.path.join('data', 'batch', 'k_nearest_neighbors_train.csv')
predict_file = os.path.join('data', 'batch',
'k_nearest_neighbors_test.csv')
# Read data. Let's use 5 features per observation
nFeatures = 5
nClasses = 5
train_data = readcsv(train_file, range(nFeatures))
train_labels = readcsv(train_file, range(nFeatures, nFeatures + 1))
# Create an algorithm object and call compute
train_algo = d4p.bf_knn_classification_training(nClasses=nClasses)
# 'weights' is optional argument, let's use equal weights
# in this case results must be the same as without weights
weights = np.ones((train_data.shape[0], 1))
train_result = train_algo.compute(train_data, train_labels, weights)
# Now let's do some prediction
predict_data = readcsv(predict_file, range(nFeatures))
predict_labels = readcsv(predict_file, range(nFeatures, nFeatures + 1))
# Create an algorithm object and call compute
predict_algo = d4p.bf_knn_classification_prediction(nClasses=nClasses)
predict_result = predict_algo.compute(predict_data, train_result.model)
# We expect less than 170 mispredicted values
assert np.count_nonzero(predict_labels != predict_result.prediction) < 170
return (train_result, predict_result, predict_labels)
def compute(train_data, train_labels, predict_data, nClasses):
# Create an algorithm object and call compute
train_algo = d4p.bf_knn_classification_training(nClasses=nClasses)
train_result = train_algo.compute(train_data, train_labels)
# Create an algorithm object and call compute
predict_algo = d4p.bf_knn_classification_prediction(nClasses=nClasses)
predict_result = predict_algo.compute(predict_data, train_result.model)
return predict_result
def main(readcsv=read_csv, method='defaultDense'):
# Input data set parameters
train_file = os.path.join('..', 'data', 'batch',
'k_nearest_neighbors_train.csv')
predict_file = os.path.join('..', 'data', 'batch',
'k_nearest_neighbors_test.csv')
# Read data. Let's use 5 features per observation
nFeatures = 5
nClasses = 5
train_data = readcsv(train_file, range(nFeatures))
train_labels = readcsv(train_file, range(nFeatures, nFeatures + 1))
predict_data = readcsv(predict_file, range(nFeatures))
predict_labels = readcsv(predict_file, range(nFeatures, nFeatures + 1))
train_data = to_numpy(train_data)
train_labels = to_numpy(train_labels)
predict_data = to_numpy(predict_data)
try:
from dppl import device_context, device_type
gpu_context = lambda: device_context(device_type.gpu, 0)
except:
from daal4py.oneapi import sycl_context
gpu_context = lambda: sycl_context('gpu')
# It is possible to specify to make the computations on GPU
with gpu_context():
sycl_train_data = sycl_buffer(train_data)
sycl_train_labels = sycl_buffer(train_labels)
sycl_predict_data = sycl_buffer(predict_data)
# Create an algorithm object and call compute
train_algo = d4p.bf_knn_classification_training(nClasses=nClasses)
train_result = train_algo.compute(sycl_train_data, sycl_train_labels)
# Create an algorithm object and call compute
predict_algo = d4p.bf_knn_classification_prediction()
predict_result = predict_algo.compute(sycl_predict_data,
train_result.model)
# We expect less than 170 mispredicted values
assert np.count_nonzero(predict_labels != predict_result.prediction) < 170
return (predict_result, predict_labels)