def analyze():
if not request.json:
abort(400)
if "text" not in request.json:
return jsonify({"Error": '"text" param missing in post request.'})
doc = entities(english(request.json["text"]))
concepts = [{**concept} for concept in Concept.iter(doc)]
print("concepts:", concepts)
return jsonify(concepts)
from eot.wowool.native import Analyzer, Domain
from eot.wowool.annotation import Concept
from eot.wowool.error import Error
try:
english = Analyzer(language="dutch")
entities = Domain("dutch-entity")
doc = english("Jan Van Den Berg werkte als hoofdarts bij Omega Pharma.")
doc = entities(doc)
# filter some concepts
requested_concepts = set(['Person', 'Position', 'Company'])
concept_filter = lambda concept: concept.uri in requested_concepts
for concept in Concept.iter(doc, concept_filter):
print(f"literal: {concept.literal:<20}, stem={concept.stem}")
# flatten concepts into dict
print('-' * 40)
for concept in Concept.iter(doc, concept_filter):
print({**concept})
print('-' * 40)
for person in Concept.iter(doc, lambda concept: concept.uri == "Person"):
for person_parts in Concept.iter(
person, lambda concept: concept.uri.startswith("Person")):
print(
f"Person: {person_parts.uri:<20}, stem={person_parts.literal}")
except Error as ex:
print("Exception:", ex)
entity_filter = set(["Person", "Company", "Address", "City", "Facility"])
st.write("EyeOnText English Topics and Entities")
name = st.text_area("Enter Your text",
"""John Smith works at EyeOnText in Antwerp.""")
if st.button("Analyze"):
input_text = name
analyzer = Language("english")
entities = Domain("english-entity")
topicit = TopicIdentifier(language="english")
doc = entities(analyzer(input_text))
topics = topicit.get_topics(doc, 20)
# st.write("topics")
# st.write(pd.DataFrame(topics, columns=["topic", "relevancy"]))
combined_topics = {}
for topic in topics:
combined_topics[topic[0]] = ["topic", topic[0], topic[1]]
for concept in Concept.iter(doc,
lambda concept: concept.uri in entity_filter):
combined_topics[concept.literal] = [concept.uri, concept.literal, 1.0]
st.write(f"topics and {','.join(entity_filter)}")
st.write(
pd.DataFrame([v for k, v in combined_topics.items()],
columns=["type", "topic", 'relavancy']))
# Copyright (c) 2020 EyeOnText, All Rights Reserved.
# NOTICE: All information contained herein is, and remains the property of EyeOnText.
from eot.wowool.native import Language, Domain, Filter
from eot.wowool.annotation import Concept
a = Language("english")
dc = Domain("english-company")
doc = dc(a("this is a EyeOnText."))
call_plugin = Domain(source="""
rule:{ Company }= ::python::myplugin::call_this;
rule:{ Company }= Other@(name=f"{rule.literal()}" );
""")
doc = call_plugin(doc)
filter = Filter(['Other', 'Company', 'PLUGIN_COMPANY'])
doc = filter(doc)
concepts = [c for c in Concept.iter(doc)]
uris = [c.uri for c in concepts]
print(doc)
assert "PLUGIN_COMPANY" in uris, "Missing some plugin annotation"
assert "Company" in uris, "Missing some plugin annotation"
assert concepts[0].attributes["name"][0] == "EyeOnText", "Missing attributes."
# Copyright (c) 2020 EyeOnText, All Rights Reserved.
# NOTICE: All information contained herein is, and remains the property of EyeOnText.
from eot.wowool.native import Analyzer, Domain
from eot.wowool.annotation import Concept
from eot.wowool.error import Error
try:
dutch = Analyzer(language="dutch")
entities = Domain("dutch-entity")
doc = dutch("Jan Van Den Berg werkte als hoofdarts bij Omega Pharma.")
doc = entities(doc)
mydomain = Domain(source=r"""
rule:{ Person .. <'werken'> .. Company }= PersonWorkCompany@(verb="work");
rule:{ Person .. Company }= PersonCompany;
""")
doc = mydomain(doc)
# filter some concepts
requested_concepts = set(
['Person', 'Company', 'PersonWorkCompany', 'PersonCompany'])
concept_filter = lambda concept: concept.uri in requested_concepts
for concept in Concept.iter(doc, concept_filter):
print(f"{concept.uri} -> {concept.literal}")
except Error as ex:
print("Exception:", ex)
try:
analyzer = Analyzer(language="dutch")
rule_source = """
// Compound Sample:
// capture all the word with verzekering
lexicon:(input="component"){
verzekering } = INSURANCE_COMP;
// capture only the real verzekering not verzekeringsmaatschapijen
lexicon:(input="head"){
verzekering } = INSURANCE_HEAD;
// capture the cost of the insurance.
rule:{ h'verzekering' { <+currency> } = INSURANCE_PRICE };
"""
compounds = Domain(source=rule_source)
input = "Er zijn verzekeringsmaatschapijen €40.000.000 en verzekeringen: autoverzekeringen €100, fietsverzekering €10"
doc = compounds(analyzer(input))
print("-" * 80)
print(rule_source)
print("-" * 80)
print(input)
print("-" * 80)
print(f"{'uri':<20s} | {'literal':<30s} | {'stem'}")
print("-" * 80)
for concept in Concept.iter(
doc, lambda concept: concept.uri.startswith("INSURANCE")):
print(f"{concept.uri:<20s} | {concept.literal:<30s} | {concept.stem}")
except Error as ex:
print("Exception:", ex)
// capture the cost of the insurance.
rule:{ {h'försäkring'} = INSURANCE_TYPE { Num +currency } = INSURANCE_PRICE };
"""
compounds = Domain(source=rule_source)
input = "Det finns försäkringsbolag 40000 euro och försäkring: bilförsäkring 100 euro, cykelförsäkring 200 SEK "
doc = compounds(analyzer(input))
print(doc)
print("-" * 80)
print(rule_source)
print("-" * 80)
print(input)
print("-" * 80)
print(f"{'uri':<20s} | {'literal':<30s} | {'stem'}")
print("-" * 80)
for concept in Concept.iter(
doc, lambda concept: concept.uri == "INSURANCE_COMPONENT"):
print(f"{concept.uri:<20s} | {concept.literal:<30s} | {concept.stem}")
print("-" * 80)
for concept in Concept.iter(
doc, lambda concept: concept.uri == "INSURANCE_HEAD"):
print(f"{concept.uri:<20s} | {concept.literal:<30s} | {concept.stem}")
print("-" * 80)
for concept in Concept.iter(
doc, lambda concept: concept.uri == "INSURANCE_PRICE" or concept.
uri == "INSURANCE_TYPE"):
print(f"{concept.uri:<20s} | {concept.literal:<30s} | {concept.stem}")
except Error as ex:
print("Exception:", ex)
f = open(output_directory + "cypher-out.cypher", "w")
webpage = open(output_directory + "index.html", "w")
for i, ip in enumerate(InputProviders(input_provider_path)):
print(f"Processing File no {i}: {ip.id()}")
doc = english(ip)
doc = entities(doc)
doc = myrule(doc)
requested_concepts = set([
'EngineType', 'Battery', 'Flying', 'Range', 'BatteryDensity',
'EnginePower', 'Manufacturer', 'City', 'Time', 'Price', 'Website',
'Reference_Title', 'Reference_Name', 'Year', 'Speed', 'Management',
'System'
])
concept_filter = lambda concept: concept.uri in requested_concepts
for concept in Concept.iter(doc):
# print( f"Tagname: {concept.uri}, literal: {concept.literal:<20}, stem={concept.stem}" )
# Unpack concept
print({**concept})
print("-" * 10)
graphit = EntityGraph(graph_config)
from pathlib import Path
filename = Path(ip.id()).stem
graphit.slots = {}
graphit.slots['Document'] = {"data": filename}
graphit.slots['Title'] = {"expr": "Reference_Title"}
results = graphit(doc)
print(results.df_from)