def __new__(cls, data, address='localhost:9465', batch=100, max_iter=100):
from orangecontrib.remote import aborted, save_state
import Orange.data.sql.table
cont = Continuize(multinomial_treatment=Continuize.Remove,
normalize_continuous=None)
data = cont(data)
pca = Orange.projection.IncrementalPCA()
percent = batch / data.approx_len() * 100
if percent < 100:
data_sample = data.sample_percentage(percent, no_cache=True)
else:
data_sample = data
data_sample.download_data(1000000)
data_sample = Orange.data.Table.from_numpy(
Orange.data.Domain(data_sample.domain.attributes), data_sample.X)
model = pca(data_sample)
save_state(model)
for i in range(max_iter if percent < 100 else 0):
data_sample = data.sample_percentage(percent, no_cache=True)
data_sample.download_data(1000000)
data_sample = Orange.data.Table.from_numpy(
Orange.data.Domain(data_sample.domain.attributes),
data_sample.X)
model.partial_fit(data_sample)
model.iteration = i
save_state(model)
if aborted():
break
return model
def __new__(cls, data, address='localhost:9465', batch=100, max_iter=100):
from orangecontrib.remote import aborted, save_state
import Orange.data.sql.table
cont = Continuize(multinomial_treatment=Continuize.Remove)
data = cont(data)
pca = Orange.projection.IncrementalPCA()
percent = batch / data.approx_len() * 100
if percent < 100:
data_sample = data.sample_percentage(percent, no_cache=True)
else:
data_sample = data
data_sample.download_data(1000000)
data_sample = Orange.data.Table.from_numpy(
Orange.data.Domain(data_sample.domain.attributes),
data_sample.X)
model = pca(data_sample)
save_state(model)
for i in range(max_iter if percent < 100 else 0):
data_sample = data.sample_percentage(percent, no_cache=True)
data_sample.download_data(1000000)
data_sample = Orange.data.Table.from_numpy(
Orange.data.Domain(data_sample.domain.attributes),
data_sample.X)
model.partial_fit(data_sample)
model.iteration = i
save_state(model)
if aborted():
break
return model
def __new__(cls, data, batch=100, max_iter=100):
cont = Continuize(multinomial_treatment=Continuize.Remove)
data = cont(data)
model = Orange.projection.IncrementalPCA()
percent = batch / data.approx_len() * 100
for i in range(max_iter):
data_sample = data.sample_percentage(percent, no_cache=True)
if not data_sample:
continue
data_sample.download_data(1000000)
data_sample = Orange.data.Table.from_numpy(
Orange.data.Domain(data_sample.domain.attributes),
data_sample.X)
model = model.partial_fit(data_sample)
model.iteration = i
save_state(model)
if aborted() or data_sample is data:
break
return model
def __new__(cls, data, batch=100, max_iter=100):
cont = Continuize(multinomial_treatment=Continuize.Remove)
data = cont(data)
model = Orange.projection.IncrementalPCA()
percent = batch / data.approx_len() * 100
for i in range(max_iter):
data_sample = data.sample_percentage(percent, no_cache=True)
if not data_sample:
continue
data_sample.download_data(1000000)
data_sample = Orange.data.Table.from_numpy(
Orange.data.Domain(data_sample.domain.attributes),
data_sample.X)
model = model.partial_fit(data_sample)
model.iteration = i
save_state(model)
if aborted() or data_sample is data:
break
return model