def test_add_entry_value_none(self):
key = "test"
value = None
list_entries = [{"str": key}]
vocabulary = Vocabulary()
vocabulary.add_entry(key, value)
self.assertEqual(list_entries, vocabulary.temp_vocabulary['entries'])
def test_add_entry(self):
key = "New York"
value = "Knicks"
list_entries = [{"str": key, "category": value}]
vocabulary = Vocabulary()
vocabulary.add_entry(key, value)
self.assertEqual(list_entries, vocabulary.temp_vocabulary['entries'])
def test_create_input_stream_none(self, con):
name = "some name"
some_dict = {
"id": "some value",
'name': 'some name',
'entries': [{
'str': 'some entry'
}]
}
some_entry = "some entry"
voc = Vocabulary()
voc.name(name)
voc.add_entry(some_entry)
response = Mock()
response.json.return_value = some_dict
con.return_value = response
res = voc.create()
self.assertEqual(str(res), str(some_dict))
def test_update(self, con):
some_id = "some id"
some_name = 'some name'
some_key = 'some key'
some_dict = {
"id": None,
'name': 'some name',
'entries': [{
'str': 'some entry'
}]
}
voc = Vocabulary()
voc.name(some_name)
voc.add_entry(some_key)
response = Mock()
response.json.return_value = some_dict
con.return_value = response
res = voc.update(some_id)
self.assertEqual(str(res), str(some_dict))
def test_create_input_stream(self, con):
name = "some name"
some_tsv_file = 'test.tsv'
with open(some_tsv_file, "w") as f:
f.write("Delete me!")
some_dict = {
"id": "some value",
'name': 'some name',
'entries': [{
'str': 'some entry'
}]
}
some_entry = "some entry"
voc = Vocabulary()
voc.name(name)
voc.add_entry(some_entry)
voc.source(some_tsv_file)
response = Mock()
response.json.return_value = some_dict
con.return_value = response
res = voc.create()
self.assertEqual(str(res), str(some_dict))
os.remove("test.tsv")
from qtcurate.result import Result
API_KEY = "YOUR-API-KEY"
DOCUMENT = "resources/sample.pdf"
# Initialise with api key
Qt.init(API_KEY)
# 1- Upload the sample document for processing
list_of_documents = []
document = Document()
doc = document.create(DOCUMENT)
list_of_documents.append(doc)
# 2- Create vocabulary
vocabulary = Vocabulary()
vocabulary.add_entry("Industrials")
vocabulary.add_entry("Quasi-Governments")
vocabulary.add_entry("Governments")
vocabulary.name("Allocations (%)").create()
# 3- Creator Extractor - Regex must have 1 capturing group
extractor = Extractor()
extractor.set_vocabulary(vocabulary.get_id())
extractor.set_validator("^ +(\\d[\\d\\.\\,]+\\d)")
extractor.set_type(Type.DOUBLE)
# 4- Run
model = Model()
model.set_description("test data process")
model.add_extractor(extractor)
model.with_documents(list_of_documents)
def test_add_entry_value_type(self):
key = "test"
value = ["Knicks"]
vocabulary = Vocabulary()
with self.assertRaises(QtArgumentError):
vocabulary.add_entry(key, value)
from qtcurate.vocabulary import Vocabulary
from qtcurate.qt import Qt
API_KEY = "YOUR-API-KEY"
FILE_NAME = "resources/revenue.tsv"
# Initialise with api key
Qt.init(API_KEY)
vocabulary = Vocabulary()
# Create entries of vocabulary
vocabulary.add_entry("Apple Inc.", "AAPL")
vocabulary.add_entry("Amazon.com", "AMZN")
vocabulary.entries({"str": "Alphabet Inc.", "category": "GOOG"})
# Create Vocabulary
try:
vocabulary.name("some name").add_entry("Apple Inc.", "AAPL").create()
except Exception as e:
print(e)
# Fetch from current object
print("Fetch vocabulary")
print(vocabulary.fetch(vocabulary.get_id()))
# Create list of vocabularies from tsv file
print("Create list of the vocabularies from TSV file")
tsv_voc = Vocabulary()
tsv_voc.name("revenue")
tsv_voc.source(FILE_NAME)