def main():
parser = argparse.ArgumentParser()
parser.add_argument("--pmb")
parser.add_argument("--sick")
parser.add_argument("--sick2pd")
parser.add_argument("--out")
args = parser.parse_args()
# Final model
data = Loader.load_data("../NLI2FOLI/SICK/SICK_train.txt")
data = data.append(Loader.load_data("../NLI2FOLI/SICK/SICK_trial.txt"))
test = Loader.load_data(args.sick)
data["postags"] = FeatureExtractor.postag_tokenizer(data["tokens"])
test["postags"] = FeatureExtractor.postag_tokenizer(test["tokens"])
# The countvectorizer features with postagging appended to each token
bag_of_words_plus_pos = ColumnTransformer([
("POS", CountVectorizer(tokenizer=lambda x: x,
preprocessor=lambda x: x), "postags")
])
m = Model(data)
m.add_feature(bag_of_words_plus_pos, "Feature")
m.train_model(
RandomForestClassifier(n_estimators=900,
criterion="entropy",
max_depth=729))
with open('model.pkl', 'wb') as fid:
pickle.dump(m, fid)
with open('model.pkl', 'rb') as fid:
m = pickle.load(fid)
try:
m.test_model(test, test["entailment_judgment"])
labels = m.model.classes_
cm = confusion_matrix(test["entailment_judgment"], m.prediction)
print_cm(cm, labels)
except:
m.test_model(test)
with open(args.out, "w") as file:
for idx, pred in enumerate(m.prediction):
pid = test.iloc[idx]['pair_ID']
file.write("{}:{}\n".format(pid, pred))
print("Successfully generated prediction on test data.")
def test():
data = Loader.load_data("../NLI2FOLI/SICK/SICK_train.txt")
test = Loader.load_data("../NLI2FOLI/SICK/SICK_trial.txt")
encoder = FeatureExtractor.generate_postag_onehot(data["tokens"])
data["postags"] = FeatureExtractor.postag_tokenizer(data["tokens"])
test["postags"] = FeatureExtractor.postag_tokenizer(test["tokens"])
data["antons"] = FeatureExtractor.antonym_relations(data["pair_ID"])
test["antons"] = FeatureExtractor.antonym_relations(test["pair_ID"])
data["synons"] = FeatureExtractor.synonym_relations(
data["tokens"], data["pair_ID"])
test["synons"] = FeatureExtractor.synonym_relations(
test["tokens"], test["pair_ID"])
# Features
# You don't have to do anything here
# These are all the features we have
# The tfidf features with both sentences seperated
bag_of_words = ColumnTransformer([("A", TfidfVectorizer(), "sentence_A"),
("B", TfidfVectorizer(), "sentence_B")])
# The countvectorizer features with postagging appended to each token
bag_of_words_plus_pos = ColumnTransformer([
("POS", CountVectorizer(tokenizer=lambda x: x,
preprocessor=lambda x: x), "postags")
])
# The One-hot-encoded postag features for both sentences
postags_A = POSTAGTransformer(encoder, "sentence_A", maxlen=800)
postags_B = POSTAGTransformer(encoder, "sentence_B", maxlen=800)
# The negation features for both sentences
negation_A = NEGTransformer("sentence_A")
negation_B = NEGTransformer("sentence_B")
# The antonyms and synonyms features
antons = DumbTransfromer("antons")
synons = DumbTransfromer("synons")
# classifiers
# Every classifiers should be put in a tuple with its name on the right hand side
# You may tweak the hyperparameters
nb = (MultinomialNB(alpha=0.1), "Naive Bayes")
knn = (KNeighborsClassifier(), "KNN")
svm = (SVC(kernel="linear", C=0.7), "SVM")
forest = (RandomForestClassifier(n_estimators=1000,
max_depth=128), "Random Forest")
mlp = (MLPClassifier(1000), "Multi layer Perceptrons")
classifiers = [nb, knn, svm, forest, mlp]
# for n in range(5, 10):
# hyperforest = (RandomForestClassifier(
# n_estimators=n*100, max_depth=n**3), f"Random Forest with {n*100} of estimators and a max depth of {n**3}")
# classifiers.append(hyperforest)
# Feature_combs
# Feature combinations are a list of tuples
# Give the combination a name on the right hand side
combs = [([bag_of_words], "TFIDF"),
([bag_of_words_plus_pos], "Combined + Postagging"),
([bag_of_words, postags_A, postags_B], "TFIDF + One hot postags"),
([postags_A, postags_B], "OneHotPosTag only"),
([bag_of_words, negation_A, negation_B], "TFIDF + NEGATION"),
([negation_A, negation_B], "NEGATION_ONLY"),
([bag_of_words, antons, synons], "TFIDF + ANTONYMS + SYNONYMS"),
([bag_of_words, antons], "TFIDF + ANTONYMS"),
([bag_of_words, synons], "TFIDF + SYNONYMS"),
([
bag_of_words, postags_B, postags_A, negation_A, negation_B,
antons, synons
], "All features")]
# The seach function takes the combination, classifier list and the train test data.
# The result will be printed and exported to a csv file called search result
# It also returns the dictionary of all the accuracys
search(combs, classifiers, data, test)
for line in ss_file:
line = line.split("|")
nr = line[0]
synsets = line[1].rstrip().split(",")[:-1]
wn_synsets = []
for ss in synsets:
ss = wn.synset(ss)
wn_synsets.append(ss)
wordnet_ss[nr] = wn_synsets
return wordnet_ss
if __name__ == "__main__":
data = Loader.load_data("../NLI2FOLI/SICK/SICK_train.txt")
test = Loader.load_data("../NLI2FOLI/SICK/SICK_trial.txt")
model = Model(data)
encoder = FeatureExtractor.generate_postag_onehot(data["tokens"])
data["postags"] = FeatureExtractor.postag_tokenizer(data["tokens"])
test["postags"] = FeatureExtractor.postag_tokenizer(test["tokens"])
data["antons"] = FeatureExtractor.antonym_relations(data["pair_ID"])
test["antons"] = FeatureExtractor.antonym_relations(test["pair_ID"])
data["synons"] = FeatureExtractor.synonym_relations(
data["tokens"], data["pair_ID"])
test["synons"] = FeatureExtractor.synonym_relations(
