def demo(self, test_sents):
tagger = CRFTagger(feature_func=self.feature_detector)
tagger.set_model_file(self.modelpath)
for sent in test_sents:
tagged = tagger.tag(untag(sent))
for s in self._to_sentence(tagged):
print(s)
print(tagger.evaluate(test_sents))
def pyt_sent_tokenizer(self, paragraph):
"""단락을 문장으로 바꿔주는 함수입니다. 파이테스트용입니다.
Args:
paragraph(list(str)): 단락이 리스트 인자로 들어옵니다.
Returns:
sentences(list(list(str))): 단락을 문장단위로 잘라서 반환합니다.
"""
tagger = CRFTagger(feature_func=self.feature_detector)
tagger.set_model_file(self.modelpath)
words = re.split('\s+', paragraph.strip())
tagged = tagger.tag(words)
return self._to_sentence(tagged)
def batch_sent_tokenizer(self, paragraphs):
"""단락들을 문장으로 바꿔주는 함수입니다.
Args:
paragraphs(list(str)): 단락들이 리스트 인자로 들어옵니다.
Returns:
sentences(list(str)): 단락을 문장단위로 잘라서 반환합니다.
"""
tagger = CRFTagger(feature_func=self.feature_detector)
tagger.set_model_file(self.modelpath)
sentences = []
for paragraph in paragraphs:
words = re.split('\s', paragraph.strip())
tagged = tagger.tag(words)
sentences.append(self._to_sentence(tagged))
return sentences
y = np.array(y)
y_hat = np.array(y_hat)
print("hmm acc : ", (y == y_hat).mean())
#named entities recognition
import pickle
a = pickle.load(
open(
"/users/Etu0/3770640/M1/Sem2/TAL/TME1/maxent_ne_chunker/PY3/english_ace_multiclass.pickle",
"rb"))
from nltk.tag.crf import CRFTagger
tagger = CRFTagger()
tagger.train(alldocs, u'crf.model'
) # donner en plus le fichier de stockage du calcul des features
tagger.tag(['Je suis à la maison'])
print(tagger._get_features([u"Je"], 0))
from nltk.tag.perceptron import PerceptronTagger
tagger = PerceptronTagger(load=False)
tagger.train(alldocs)
# adT_seq: liste de liste de mots (=liste de phrase)
allpred_smart = [[t for w, t in tagger.tag(adT_seq[i])]
for i in range(len(adT_seq))]
allpred_stupid = [[tagger.tag([w])[0][1] for w in adT_seq[i]]
for i in range(len(adT_seq))]
def main(positive, death):
############# Compile the dataset ###############
## Load the dataset
text = list()
response = list()
file_path = [positive, death]
for path in file_path:
input_file = jsonlines.open(path)
for obj in input_file:
text.append(obj['text'])
response.append(obj['annotation']['part1.Response'])
## Tweet Preprocessing
prep_text = list()
for i in text:
prep_text.append(p.clean(i))
## Tag Keywords and Create Labels
### Focus on verbs--therefore, try lemmatization first
wnl = WordNetLemmatizer()
n_corpus = len(prep_text)
token_data = ["test"] * n_corpus
n = 0
for sent in prep_text:
token_data[n] = [
wnl.lemmatize(i, j[0].lower())
if j[0].lower() in ['a', 'n', 'v'] else wnl.lemmatize(i)
for i, j in pos_tag(word_tokenize(sent))
]
n = n + 1
### Create labels
death_list = ["die", "dead", "death", "pass", "away"]
n = 0
for sent in token_data:
for idx, token in enumerate(sent):
if ((token.lower() in ["test", "positive", "result"])
and (response[n] == ["yes"])):
sent[idx] = [sent[idx], "P-Yes"]
elif ((token.lower() in ["test", "positive", "result"])
and (response[n] == ["no"])):
sent[idx] = [sent[idx], "P-No"]
elif ((token.lower() in death_list) and (response[n] == ["yes"])):
sent[idx] = [sent[idx], "D-Yes"]
elif ((token.lower() in death_list) and (response[n] == ["no"])):
sent[idx] = [sent[idx], "D-No"]
else:
sent[idx] = [sent[idx], "Irr"]
n = n + 1
## Shuffle and split into train data and dev data
token_data = shuffle(token_data, random_state=6)
train_data, dev_data = train_test_split(token_data,
test_size=0.3,
random_state=616)
print(
f"The number of sentences in training data: {len(train_data)}; The number of sentences in dev data: {len(dev_data)};"
)
############# Fit A CRF Model And Predict ###############
condition_to_func = {
"base": my_features,
"include_neighbors": neighbor_features
}
for cond, func in condition_to_func.items():
# initialize
crf = CRFTagger(feature_func=func)
crf.train(train_data, 'model.tagger')
# Test
crf._feature_func(prep_text[0].split(), 7)
crf.tag_sents([['I', 'get', 'covid'], ['he', 'test', 'positive']])
# Output
filename = cond + "_final_output.tsv"
with open(filename, 'w') as pred_file:
for sent in dev_data:
sent_words = [item[0] for item in sent]
gold_tags = [item[1] for item in sent]
with_tags = crf.tag(sent_words)
for i, output in enumerate(with_tags):
original_word, tag_prediction = output
line_as_str = f"{original_word}\t{gold_tags[i]}\t{tag_prediction}\n"
pred_file.write(line_as_str)
# add an empty line after each sentence
pred_file.write("\n")
############# Evaluation ###############
## Extract Data with Meaning Labels
cond_list = ['base', 'include_neighbors']
for cond in cond_list:
filename = cond + "_final_output.tsv"
with open(filename) as fd:
rd = csv.reader(fd, delimiter="\t", quotechar='"')
D_data = []
P_data = []
for row in rd:
if len(row) > 1:
if row[1] in ['P-Yes', 'P-No']:
P_data.append(row)
elif row[1] in ['D-Yes', 'D-No']:
D_data.append(row)
column_name = ['token', 'label', 'prediction']
P_df = pd.DataFrame(P_data, columns=column_name)
D_df = pd.DataFrame(D_data, columns=column_name)
Total_df = P_df.append(D_df)
# Accuracy
## Overall Accuracy
T_a = accuracy_score(Total_df['label'], Total_df['prediction'])
## Accuracy, Precision, and Recall for two events
accuracy = []
precision = []
recall = []
for df in [P_df, D_df]:
accuracy.append(accuracy_score(df['label'], df['prediction']))
precision.append(
sum(1 for item in range(0,
len(df) - 1)
if ('Yes' in df['label'][item]
and 'Yes' in df['prediction'][item])) /
sum(1 for item in range(0,
len(df) - 1)
if ('Yes' in df['prediction'][item])))
recall.append(
sum(1 for item in range(0,
len(df) - 1)
if ('Yes' in df['label'][item]
and 'Yes' in df['prediction'][item])) /
sum(1 for item in range(0,
len(df) - 1)
if ('Yes' in df['label'][item])))
## F-1
f1 = []
for num in [0, 1]:
f1.append((2 * precision[num] * recall[num]) /
(precision[num] + recall[num]))
# Report performance
print("condition: " + cond)
print(f"Overall Accuracy {T_a:0.03}")
covid_event = ['Test Positive', 'Death Case']
num = 0
for event in covid_event:
print(
f"Scores for {event} : \taccuracy {accuracy[num]:0.03}\tprecision {precision[num]:0.03}\trecall {recall[num]:0.03}\tF1 {f1[num]:0.03}"
)
num = num + 1
## Basicline Performance / Confusion Matrix
print("Confusion Matrix:")
print(pd.crosstab(Total_df['label'], Total_df['prediction']))
print("Training data:")
labels = ["P-Yes", "P-No", "D-Yes", "D-No"]
for label in labels:
train_data2 = np.concatenate(train_data).flat
n_label = sum(1 for item in train_data2 if item == label)
print(f"Number of {label}: {n_label}")