def compute_pmi(story):
total = 0 #this will be what is returned at the end
id, deps = chains.extract_dependency_pairs(
story
) #unpacks the tuple into a dictionary of story id, which is a number and deps which is a dictionary of a list of tuples
for dependency_pairs1 in deps.values():
total += entity_pmi(dependency_pairs1)
return total
table = chains.ProbabilityTable(json.load(fp))
total, correct = 0, 0
# load testing data
test = chains.load_data("test.csv")
with open("answers.txt", "w") as f:
# header for the csv
f.write("InputStoryid,AnswerRightEnding\n")
test_tqdm = tqdm.tqdm(test)
for t in test_tqdm:
one, two = parse_test_instance(t)
_, one_deps = chains.extract_dependency_pairs(one)
_, two_deps = chains.extract_dependency_pairs(two)
# logic to choose between one and two
prog_one = chains.protagonist(one)
prog_two = chains.protagonist(two)
pmi_one, pmi_two = 0, 0
for entity_id, deps in one_deps.items():
for first, second in list(zip(deps, deps[1:])):
pmi_one += table.pmi(first[0], first[1], second[0],
second[1])
for entity_id, deps in two_deps.items():
for first, second in list(zip(deps, deps[1:])):
return [
chains.ParsedStory(id, id, chains.nlp(" ".join(story[2:6] + [a])),
*(sentences + [chains.nlp(a)]))
for a in alternatives
]
def story_answer(story):
"""Tells you the correct answer. Return (storyid, index). 1 for the first ending, 2 for the second ending"""
#obviously you can't use this information until you've chosen your answer!
return story.InputStoryid, story.AnswerRightEnding
# Load training data and build the model
#data, table = chains.process_corpus("train.csv", 100)
#print(table.pmi("move", "nsubj", "move", "nsubj"))
# load the pre-built model
with open("all.json") as fp:
table = chains.ProbabilityTable(json.load(fp))
# load testing data
test = chains.load_data("val.csv")
for t in test:
one, two = parse_test_instance(t)
one_deps = chains.extract_dependency_pairs(one)
pprint(one[2:])
pprint(two[2:])
# logic to choose between one and two
pprint("answer:" + str(story_answer(t)))
for verb in verbs:
for child in verb.children:
# Add the word/dependency pair to the identified entity
tup = (verb.lemma_, child.dep_)
list.append(tup)
return list
# # load testing data
test = chains.load_data("val.csv")
result = [0, 0]
for t in test:
one, two = parse_test_instance2(t) #does have ending
three, four = parse_test_instance(t) #doesnt have ending
one_deps = chains.extract_dependency_pairs(three)
two_deps = chains.extract_dependency_pairs(four)
one_deps1 = chains.extract_dependency_pairs(one)
two_deps1 = chains.extract_dependency_pairs(two)
one_pmi = []
two_pmi = []
decision_verb = extract_dependency_five(one.five)
decision_verb2 = extract_dependency_five(two.five)
correct_ans = '0'
if (len(decision_verb) == 0 | len(decision_verb2) == 0): continue
for choice in decision_verb:
if (choice in one_deps1[1][0]) & (len(one_deps[1][0]) != 0):
one_pmi.append(