def __init__(self):
self.mc = 0
self.rtcl = 3
self.nrtcl = 5
self.scl = 4
self.server = 2
self.current = Node(2, 0, 4)
self.rt_queue = deque([])
self.nrt_queue = deque([])
self.preempt = -1
self.rt_iat = self.nrt_iat = self.rt_st = self.nrt_st = 0
# Results
self.m = 0
self.b = 0
self.nrt = 0
self.nnrt = 0
self.rt_times = []
self.nrt_times = []
self.rt_mean = []
self.nrt_mean = []
self.rt_percentile = []
self.nrt_percentile = []
self.results = Result()
import numpy as np
from util.file import *
from quantification.helpers import *
from util.plot_correction import plot_corr
from util.results import Result
VECTORSPATH = '../vectors'
sample_size = 200
samples_by_prevalence = 100
results_table = Result()
def add_results(results, dataset, method, approach):
for metric, score in results.items():
results_table.add(dataset=dataset,
method=method,
approach=approach,
metric=metric,
score=score)
for vectorset_name in list_dirs(VECTORSPATH):
print(vectorset_name)
vectorset = join(VECTORSPATH, vectorset_name)
train_x = np.load(join(vectorset, 'train.vec.npy'))
train_y = np.load(join(vectorset, 'train.y.npy'))
train_y_pred = np.load(join(vectorset, 'train.y_pred.npy'))
train_y_prob = np.load(join(vectorset, 'train.y_prob.npy'))
from data.tasks import WebisCLS10_task_generator, WebisCLS10_crossdomain_crosslingual_task_generator
from experiments.common import DCIclassify
from model.dci import DCI
from model.pivotselection import pivot_selection
import os
from time import time
from util.results import Result
dcf = 'cosine'
npivots = 450
optimize = True
dataset_home = '../datasets/Webis-CLS-10'
rperf = Result([
'dataset', 'task', 'method', 'acc', 'pivot_t', 'dci_t', 'svm_t', 'test_t'
])
for source, target, oracle, taskname in WebisCLS10_crossdomain_crosslingual_task_generator(
os.path.abspath(dataset_home)):
# pivot selection
tinit = time()
s_pivots, t_pivots = pivot_selection(npivots,
source.X,
source.y,
source.U,
target.U,
source.V,
target.V,
oracle=oracle,
phi=30,
from model.dci import DCI
from model.pivotselection import pivot_selection
import numpy as np
from util.results import Result
optimize = True
mds_home= '../datasets/MDS'
dataset_home='../datasets/Webis-CLS-10'
nfolds=5
outfile = './DCI.varpivot.dat'
if exists(outfile):
rperf = Result.load(outfile, False)
else:
rperf = Result(['dataset', 'task', 'method', 'fold', 'npivots', 'acc', 'dci_time', 'svm_time'])
pivot_range = [10,25,50,100,250,500,1000,1500,2000,2500,5000]
for source, target, fold, taskname in MDS_task_generator(abspath(mds_home), nfolds=nfolds):
s_pivots, t_pivots = pivot_selection(max(pivot_range), source.X, source.y, source.U, target.U,
source.V, target.V,
phi=1, cross=True)
for npivots in pivot_range:
for dcf in ['cosine','linear']:
dci = DCI(dcf=dcf, unify=False, post='normal')
acc, dci_time, svm_time, _ = DCIclassify(source, target, s_pivots[:npivots], t_pivots[:npivots], dci, optimize=True)
rperf.add(dataset='MDS', task=taskname, method=str(dci), fold=fold, npivots=npivots, acc=acc, dci_time=dci_time, svm_time=svm_time)
rperf.pivot(index=['dataset', 'task','npivots'], values=['acc', 'dci_time', 'svm_time'])
from sklearn.model_selection import cross_val_score, GridSearchCV
from sklearn.svm import LinearSVC
from data.domain import unify_feat_space
from data.tasks import MDS_task_generator, UpperMDS_task_generator
from os.path import abspath
from util.results import Result
dataset_home='../datasets/MDS'
nfolds=5
upper={}
parameters = {'C': [10 ** i for i in range(-5, 5)]}
results = Result(['dataset', 'task', 'method', 'fold', 'acc'])
for domain in UpperMDS_task_generator(abspath(dataset_home)):
svm = GridSearchCV(LinearSVC(), parameters, n_jobs=-1, verbose=1, cv=5)
upper[domain.domain] = cross_val_score(svm, domain.X, domain.y, cv=5).mean()
for source, target, fold, taskname in MDS_task_generator(abspath(dataset_home), nfolds=nfolds):
svm = GridSearchCV(LinearSVC(), parameters, n_jobs=-1, verbose=1, cv=5)
target_domain_name = target.domain
source, target = unify_feat_space(source, target)
svm.fit(source.X, source.y)
yte_ = svm.predict(target.X)
acc = (yte_ == target.y).mean()
results.add(dataset='MDS', task=taskname, method='Lower', fold=fold, acc=acc)
results.add(dataset='MDS', task=taskname, method='Upper', fold=fold, acc=upper[target_domain_name])
results.pivot(grand_totals=True)