def main():
x_ij, y_ij = ds.load_svmlight_file(
"/fefs/scratch/bsc19/bsc19029/PERFORMANCE/datasets/train",
block_size=(5000, 22), n_features=22, store_sparse=True)
csvm = CascadeSVM(c=10000, gamma=0.01)
performance.measure("CSVM", "ijcnn1", csvm.fit, x_ij, y_ij)
def main():
x_kdd = ds.load_txt_file(
"/fefs/scratch/bsc19/bsc19029/PERFORMANCE/datasets/train.csv",
block_size=(11482, 122))
x_kdd = x_kdd[:, :121]
pca = PCA(arity=48)
performance.measure("PCA", "KDD99", pca.fit, x_kdd)
def main():
x_kdd = ds.load_txt_file(
"/fefs/scratch/bsc19/bsc19029/PERFORMANCE/datasets/train.csv",
block_size=(11482, 122))
y_kdd = x_kdd[:, 121:122]
x_kdd = x_kdd[:, :121]
rf = RandomForestClassifier(n_estimators=100, distr_depth=2)
performance.measure("RF", "KDD99", rf.fit, x_kdd, y_kdd)
def main():
file = "/fefs/scratch/bsc19/bsc19029/PERFORMANCE/datasets/data_scaled.csv"
data = ds.load_txt_file(file, block_size=(10000, 5))
dbscan = DBSCAN(eps=0.19,
min_samples=5,
max_samples=5000,
n_regions=17,
dimensions=[0, 1])
performance.measure("DBSCAN", "gaia", dbscan.fit, data)
def main():
x_mn, y_mn = ds.load_svmlight_file(
"/fefs/scratch/bsc19/bsc19029/PERFORMANCE/datasets/train.scaled",
block_size=(5000, 780),
n_features=780,
store_sparse=False)
rf = RandomForestClassifier(n_estimators=100, distr_depth=2)
performance.measure("RF", "mnist", rf.fit, x_mn, y_mn)
def main():
n_samples = 300000000
n_chunks = 1536
chunk_size = int(np.ceil(n_samples / n_chunks))
n_features = 100
n_clusters = 500
x = ds.random_array((n_samples, n_features), (chunk_size, n_features))
km = KMeans(n_clusters=n_clusters, max_iter=5, tol=0, arity=48)
performance.measure("KMeans", "300M", km.fit, x)
def main():
n_blocks = 384
data = "/gpfs/projects/bsc19/COMPSs_DATASETS/dislib/recommendation" \
"/netflix/netflix_data_libsvm.txt"
n_factors = 100
n_features = 480189
block_size = (int(ceil(17770 / n_blocks)),
int(ceil(n_features / n_blocks)))
x, y = ds.load_svmlight_file(data, block_size=block_size,
n_features=n_features, store_sparse=True)
als = ALS(tol=0.0001, random_state=676, n_f=n_factors, max_iter=10,
verbose=False)
performance.measure("ALS", "Netflix", als, x)
def main():
x_kdd = ds.load_txt_file(
"/gpfs/projects/bsc19/COMPSs_DATASETS/dislib/kdd99/train.csv",
block_size=(11482, 122))
x_kdd = shuffle(x_kdd)
y_kdd = x_kdd[:, 121:122]
x_kdd = x_kdd[:, :121]
x_ij, y_ij = ds.load_svmlight_file(
"/gpfs/projects/bsc19/COMPSs_DATASETS/dislib/ijcnn1/train",
block_size=(5000, 22), n_features=22, store_sparse=True)
csvm = CascadeSVM(c=10000, gamma=0.01)
performance.measure("CSVM", "KDD99", csvm.fit, x_kdd, y_kdd)
performance.measure("CSVM", "ijcnn1", csvm.fit, x_ij, y_ij)
def main():
n_blocks = 384
data = "/fefs/scratch/bsc19/bsc19029/PERFORMANCE/datasets/" \
"netflix_data_libsvm.txt"
n_factors = 100
n_features = 480189
block_size = (int(ceil(17770 / n_blocks)),
int(ceil(n_features / n_blocks)))
x, y = ds.load_svmlight_file(data,
block_size=block_size,
n_features=n_features,
store_sparse=True)
als = ALS(tol=0.0001,
random_state=676,
n_f=n_factors,
max_iter=10,
verbose=False)
performance.measure("ALS", "Netflix", als.fit, x)
def main():
x = ds.random_array((20000, 20000), (100, 100))
performance.measure("TR", "20K", x.transpose)