def download(self):
"""
Download Stanford Sentiment Treebank to data directory
"""
path = Path(self.filename)
path.parent.mkdir(parents=True, exist_ok=True)
generic_download(
url="https://s3.amazonaws.com/enso-data/SST-binary.csv",
text_column="Text",
target_column="Target",
filename=SST_FILENAME)
def _download_data(cls):
#Download Stanford Sentiment Treebank to data directory
path = Path(cls.classifier_dataset_path)
if path.exists():
return
path.parent.mkdir(parents=True, exist_ok=True)
generic_download(
url="https://s3.amazonaws.com/enso-data/SST-binary.csv",
text_column="Text",
target_column="Target",
filename=SST_FILENAME
)
#Download Reuters Dataset to enso `data` directory
path = Path(cls.sequence_dataset_path)
if not path.exists():
path.parent.mkdir(parents=True, exist_ok=True)
if not os.path.exists(cls.sequence_dataset_path):
url = "https://raw.githubusercontent.com/dice-group/n3-collection/master/reuters.xml"
r = requests.get(url)
with open(cls.sequence_dataset_path, "wb") as fp:
fp.write(r.content)
with codecs.open(cls.sequence_dataset_path, "r", "utf-8") as infile:
soup = bs(infile, "html.parser")
docs = []
docs_labels = []
for elem in soup.find_all("document"):
texts = []
labels = []
# Loop through each child of the element under "textwithnamedentities"
for c in elem.find("textwithnamedentities").children:
if type(c) == Tag:
if c.name == "namedentityintext":
label = "Named Entity" # part of a named entity
else:
label = "<PAD>" # irrelevant word
texts.append(c.text)
labels.append(label)
docs.append(texts)
docs_labels.append(labels)
with open(cls.processed_path, 'wt') as fp:
json.dump((docs, docs_labels), fp)
def download(self):
"""
Download Stanford Sentiment Treebank to data directory
"""
path = Path(self.filename)
path.parent.mkdir(parents=True, exist_ok=True)
generic_download(
url="https://s3.amazonaws.com/enso-data/SST-binary.csv",
text_column="Text",
target_column="Target",
filename=SST_FILENAME
)
def download(self):
"""
Download Stanford Sentiment Treebank to data directory
"""
path = Path(self.filename)
path.parent.mkdir(parents=True, exist_ok=True)
generic_download(
url=
"https://www.figure-eight.com/wp-content/uploads/2016/03/McDonalds-Yelp-Sentiment-DFE.csv",
text_column="review",
target_column="policies_violated",
filename=SST_FILENAME,
target_transformation=target_transform)
def download(self):
"""
Download Stanford Sentiment Treebank to data directory
"""
path = Path(self.filename)
path.parent.mkdir(parents=True, exist_ok=True)
generic_download(
url="https://www.figure-eight.com/wp-content/uploads/2016/03/McDonalds-Yelp-Sentiment-DFE.csv",
text_column="review",
target_column="policies_violated",
filename=SST_FILENAME,
target_transformation=target_transform
)
def _download_sst(cls):
"""
Download Stanford Sentiment Treebank to data directory
"""
path = Path(cls.dataset_path)
if path.exists():
return
path.parent.mkdir(parents=True, exist_ok=True)
generic_download(
url="https://s3.amazonaws.com/enso-data/SST-binary.csv",
text_column="Text",
target_column="Target",
filename=SST_FILENAME)
