def test_parsing_introduction_segment(self):
segment = "introduction"
section = ""
sub_section = ""
fetch_content = FetchFromES()
results = fetch_content.fetch_lesson_content_from_es(
"What's the Weather like")
parse_content = ParseESResults(results, segment)
segment_content = parse_content.parse_segment_content()
self.assertIsNotNone(segment_content)
def test_parsing_lesson_segment_and_section(self):
segment = "lessons"
lesson = "What's the weather like"
section = "Introducing the Read Aloud"
sub_section = ""
fetch_content = FetchFromES()
results = fetch_content.fetch_lesson_content_from_es(
"What's Weather like")
parse_content = ParseESResults(results, segment, lesson, section)
section_content = parse_content.parse_section_content("sections")
self.assertIsNotNone(section_content)
def test_parsing_introduction_segment_and_section(self):
segment = "introduction"
lesson = "What's the weather like"
section = "Recommended resources"
sub_section = ""
fetch_content = FetchFromES()
results = fetch_content.fetch_lesson_content_from_es(
"What's Weather like")
parse_content = ParseESResults(results, segment, lesson, section)
section_content = parse_content.parse_section_content("sections")
self.assertIsNotNone(section_content)
def test_parsing_lesson_segment_and_additional_section(self):
segment = "lessons"
lesson = "What's the weather like"
section = "PRIMARY FOCUS OF LESSON"
sub_section = ""
fetch_content = FetchFromES()
results = fetch_content.fetch_lesson_content_from_es(
"What's Weather like")
parse_content = ParseESResults(results, segment, lesson, section)
section_content = parse_content.parse_section_content(
"additional_sections")
self.assertIsNotNone(section_content)
def take_quiz(self,params):
lesson = "What's the Weather like"
fetch_assessment_qna = FetchFromES()
quiz_content = fetch_assessment_qna.fetch_assessment_qna_from_es(lesson)
user_response = params["query"]
question = ''
validation_result = ''
filename=get_user_context_file(params)
context= get_assesment_context(filename)
response=''
context["lesson"] = lesson
question_number = context["status"]["present_question"]
context["status"]["total_questions"] = len(quiz_content)
if params["intent"]=="smartlearning.assessment" and context["status"]["present_question"]>0 and context["status"]["present_question"]!=context["status"]["total_questions"] and context["status"]["staroverprompt"]!=True:
response+="Would you like to continue the quiz from where you left last time or start over again?"
question_number= context["status"]["previous_question"]
context["status"]["staroverprompt"]=True
save_assesment_context(context,filename)
elif context["status"]["staroverprompt"]==True:
if params["query"] =="start over" :
context["status"]["present_question"]=0
context["status"]["previous_question"]=0
question_number = context["status"]["present_question"]
context = self.update_context(context)
else:
validation_result+="ok lets continue < break time = '1s' />"
question_number= context["status"]["previous_question"]
if question_number < context["status"]["total_questions"]:
question = quiz_content[question_number]["question"]
context["status"]["staroverprompt"]=False
save_assesment_context(context,filename)
response = validation_result
response = response + (question if question else "quiz completed")
else:
if question_number > 0:
validation_result += self.validate_response(user_response,context,quiz_content)
context = self.update_context(context)
if question_number < context["status"]["total_questions"]:
question = quiz_content[question_number]["question"]
save_assesment_context(context,filename)
response = validation_result
response = response + (question if question else "quiz completed")
return response
def __init__(self, params, context):
self.params = params
self.context = context
fetch_content = FetchFromES()
self.results = fetch_content.fetch_lesson_content_from_es(
"What's the Weather like")
def get_answer(query):
"""
Question Ananlyzer
1. question classification
2. rephrasing question with synonyms
"""
answer_type = classify_question(query)
nlp_lib_answer_type = get_ner_type_for_answer_type[answer_type]
query = rephrase_query_with_synonyms(query)
"""
Loading the PreProcess class to pre-process queries and passages
Pre Processing query to remove punctuations, stopwords and replace words(verbs) with their lemmatized forms
"""
pre_process = PreProcess()
query_object = pre_process.pre_process(query)
# entity_tagger = AnnotatorPipeline([EntityTagger()])
# entity_tagger.process(query_object)
'''
DOC (PASSAGES)-RETRIEVAL FROM ELASTICSEARCH
'''
document_fetcher = FetchFromES()
documents = document_fetcher.fetch_document_from_es(query)
"""
joining all documents to convert into single document seperated by "\n\n" (denotes the start of a new passage)
"""
merged_document = "\n\n".join(documents)
passages = merged_document.split("\n\n")
"""
Pre Processing documents to remove punctuations, stopwords and replace words(verbs) with their lemmatized forms
"""
passage_objects = []
for passage in passages:
passage_object = pre_process.pre_process(passage)
passage_objects.append(passage_object)
"""
CANDIDATE PASSAGES EXTRACTOR
"""
passage_extractor = PassageExtraction(query_object, nlp_lib_answer_type,
passage_objects)
candidate_passages = passage_extractor.process()
"""
Checking for presence of at least one candidate passage
"""
if candidate_passages and candidate_passages[0]:
"""
SENTENCE EXTRACTION
Considering 1st passage(among candidate passages) as the required passage; using this passage to extract sentence
Sentence retrieval is on the basis of keyword percent match, similarity score and longest sub-sequence match
Final sentence selected after sorting above features
"""
sentence_extractor = SentenceExtraction(
query_object.text, nlp_lib_answer_type,
candidate_passages[0][0].text, candidate_passages[0][0].raw_text)
final_sentence = sentence_extractor.process()
return final_sentence.raw_text
else:
"""
candidate passages have no elements when at least 2 keywords from query are not present in either of the passages
"""
return "REPHRASE THE QUESTION"
#
# """
# ANSWER EXTRACTION
# """
#
# answer_extractor = AnswerExtraction(query_object,nlp_lib_answer_type,final_sentence)
# print(answer_extractor.extract_answer())
# if __name__== "__main__":
#
# data = ['LOC:other-When are the plants full of leaves, flowers and fruits?']
# for question in data:
# if question:
# query = question.split("-")[1].replace('\n','')
# print(get_answer(query))
def test_fetch_documents_for_qna_processor(self):
fetch_qna = FetchFromES()
query = "seasons year"
results = fetch_qna.fetch_document_from_es(query)
print (results)
def test_fetch_assessment_qna(self):
fetch_qna = FetchFromES()
lesson_name = "What's the weather like"
results = fetch_qna.fetch_assessment_qna_from_es(lesson_name)
print (results)
def test_es_fetch_content(self):
es_db = FetchFromES()
results = es_db.fetch_lesson_content_from_es("What's the Weather Like")
self.assertIsNotNone(results)
def test_es_index_exists(self):
es_db = FetchFromES()
es_db.check_index_exists()
def test_es_connection(self):
es_db = FetchFromES()
es_db.check_es_connection()
def __init__(self):
fetch_content = FetchFromES()
self.results = fetch_content.fetch_lesson_content_from_es(
"What's Weather like")