def get_methods_singletask(header, random_restarts=-1):
FEATURES_BOW, FEATURES_BROWN, _, _=extract_feature_indices(header)
GPCONSTRUCTOR=lambda kernel_constructor, name, random_restarts: MCGP(kernel_constructor=kernel_constructor, labels=LABELS,
name=name, random_restarts=random_restarts)
methodsmultitask=[
lambda: SklearnBaseline(lambda: DummyClassifier("most_frequent"), "MostFrequent", [0]),
lambda: GPCONSTRUCTOR(kernel_constructor=lambda: single_task_kernel(FEATURES_BOW, False, "BOW"),
name="BOWGPjoinedfeatures",
random_restarts=random_restarts),
lambda: GPCONSTRUCTOR(kernel_constructor=lambda: single_task_kernel(FEATURES_BROWN, False, "BROWN"),
name="BROWNGPjoinedfeatures",
random_restarts=random_restarts)
]
return methodsmultitask, map(lambda x: x().name, methodsmultitask)
def __init__(self, X, y, train_set_ratios, foldtorun, splitter, evaluation_measures,
methodnamesmultitask, methodsmultitask, methodnamessingletask, methodssingletask, print_metrics,
header, random_restarts=-1, results={}, filter_retweets=True):
self.X = X
self.y = y
self.methodnamesmultitask = methodnamesmultitask
self.methodsmultitask = methodsmultitask
self.methodnamessingletask = methodnamessingletask
self.methodssingletask = methodssingletask
self.foldtorun = foldtorun
self.splitter = splitter
self.evaluation_measures=evaluation_measures
self.print_metrics = print_metrics
self.results = results
self.header=header
_, _, self.postprocessed_task_column_id, self.rttypecol_processed_column_id=extract_feature_indices(header)
self.methodnames_all = self.methodnamesmultitask+self.methodnamessingletask
self.filter_retweets = filter_retweets
foldtorun=int(sys.argv[1])
methodname=sys.argv[2]
train_set_ratios=[int(sys.argv[3])]
fname=sys.argv[4]
random_restarts=int(sys.argv[5])
filter_retweets=bool(int(sys.argv[6]))
if len(sys.argv)>=8:
#if random number generator seed has been passed
seed=int(sys.argv[7])
import numpy as np
np.random.seed(seed)
else:
initialize_seed_with_currtime()
X, y, header = load_data(fname, labels_to_keep=LABELS)
_, _, postprocessed_task_column_id, _=extract_feature_indices(header)
splitter = foldsplitter(X, postprocessed_task_column_id, train_set_ratios)
evaluation_measures = [sklearn.metrics.accuracy_score]
tasks_number=len(set(X[:, postprocessed_task_column_id]))
methodsmultitask, methodnamesmultitask = get_methods_multitask(tasks_number, header, random_restarts=random_restarts)
methodssingletask, methodnamessingletask = get_methods_singletask(header, random_restarts=random_restarts)
if methodname != None:
#if we are interested in keeping only one method
methodnamesmultitask, methodsmultitask = filter_methods(methodnamesmultitask, methodsmultitask, methodname)
methodnamessingletask, methodssingletask = filter_methods(methodnamessingletask, methodssingletask, methodname)
experiment = Experiment(X, y, train_set_ratios, foldtorun, splitter, evaluation_measures, methodnamesmultitask, methodsmultitask,
methodnamessingletask, methodssingletask, print_metrics=print_metrics_multiclass,
random_restarts=random_restarts, results={}, header=header, filter_retweets=filter_retweets)
foldtorun = int(sys.argv[1])
methodname = sys.argv[2]
train_set_ratios = [int(sys.argv[3])]
fname = sys.argv[4]
random_restarts = int(sys.argv[5])
filter_retweets = bool(int(sys.argv[6]))
if len(sys.argv) >= 8:
#if random number generator seed has been passed
seed = int(sys.argv[7])
import numpy as np
np.random.seed(seed)
else:
initialize_seed_with_currtime()
X, y, header = load_data(fname, labels_to_keep=LABELS)
_, _, postprocessed_task_column_id, _ = extract_feature_indices(header)
splitter = foldsplitter(X, postprocessed_task_column_id, train_set_ratios)
evaluation_measures = [sklearn.metrics.accuracy_score]
tasks_number = len(set(X[:, postprocessed_task_column_id]))
methodsmultitask, methodnamesmultitask = get_methods_multitask(
tasks_number, header, random_restarts=random_restarts)
methodssingletask, methodnamessingletask = get_methods_singletask(
header, random_restarts=random_restarts)
if methodname != None:
#if we are interested in keeping only one method
methodnamesmultitask, methodsmultitask = filter_methods(
methodnamesmultitask, methodsmultitask, methodname)
methodnamessingletask, methodssingletask = filter_methods(
methodnamessingletask, methodssingletask, methodname)
