def train(self, **kwargs): self.job.training(self.tagset, streammanager(self.interface,self.training_subscription), **kwargs)
def classify(self, iterator=None, sc=None): if iterator is None: iterator = streammanager(self.interface,self.input_subscription) # classified will be able to be used to push output to output_subscription classified = self.job.run_classifier(iterator, stop_condition = sc) self.output(classified)
def train(self, **kwargs): self.job.training( self.tagset, streammanager(self.interface, self.training_subscription), **kwargs)
def classify(self, iterator=None, sc=None): if iterator is None: iterator = streammanager(self.interface, self.input_subscription) # classified will be able to be used to push output to output_subscription classified = self.job.run_classifier(iterator, stop_condition=sc) self.output(classified)
#accept file arg try: filetype = sys.argv[1] filename = sys.argv[2] except: print("Script run with invalid arguments") print("Usage: python3 tsnetest.py file_type data_file.tsv") print("Example Usage: python3 tsnetest.py neel NEEL2016-training.tsv") sys.exit(2) text = [] urls = [] #read through message objects, saving text in text array for message in streammanager(filetype, filename): text.append(message.text) urls.append(message.url) #fit and transform the text into vector form using TF-IDF vectors = TfidfVectorizer().fit_transform(text) print(repr(vectors)) #reduce dimensionality to 50 before running tsne X_reduced = TruncatedSVD(n_components=50, random_state=0).fit_transform(vectors) #run tsne, convert to two dimensions X_embedded = mytsne.TSNE(n_components=2, perplexity=40, verbose=2, urls=urls, text=text).fit_transform(X_reduced) trust = mytsne.trustworthiness(vectors, X_embedded) print("Trustworthiness: {}".format(trust))
#accept file arg try: filetype = sys.argv[1] filename = sys.argv[2] except: print("Script run with invalid arguments") print("Usage: python3 tsnetest.py file_type data_file.tsv") print("Example Usage: python3 tsnetest.py neel NEEL2016-training.tsv") sys.exit(2) text = [] urls = [] #read through message objects, saving text in text array for message in streammanager(filetype, filename): text.append(message.text) urls.append(message.url) #fit and transform the text into vector form using TF-IDF vectors = TfidfVectorizer().fit_transform(text) print(repr(vectors)) #reduce dimensionality to 50 before running tsne X_reduced = TruncatedSVD(n_components=50, random_state=0).fit_transform(vectors) #run tsne, convert to two dimensions X_embedded = mytsne.TSNE(n_components=2, perplexity=40, verbose=2,