116 lines
3.6 KiB
Python
116 lines
3.6 KiB
Python
from nltk.tokenize import word_tokenize
|
|
from nltk import trigrams
|
|
from collections import defaultdict, Counter
|
|
import pandas as pd
|
|
import csv
|
|
|
|
|
|
class GapPredictor:
|
|
def __init__(self, alpha):
|
|
self.model = defaultdict(lambda: defaultdict(lambda: 0))
|
|
self.alpha = alpha
|
|
self.vocab = set()
|
|
self.DEFAULT_PREDICTION = "the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1"
|
|
|
|
@staticmethod
|
|
def preprocess_text(text):
|
|
text = text.lower().replace("-\\n", "").replace("\\n", " ")
|
|
return text
|
|
|
|
@staticmethod
|
|
def _prepare_train_data():
|
|
data = pd.read_csv(
|
|
"train/in.tsv.xz",
|
|
sep="\t",
|
|
error_bad_lines=False,
|
|
warn_bad_lines=False,
|
|
header=None,
|
|
quoting=csv.QUOTE_NONE,
|
|
nrows=90000,
|
|
)
|
|
|
|
train_labels = pd.read_csv(
|
|
"train/expected.tsv",
|
|
sep="\t",
|
|
error_bad_lines=False,
|
|
header=None,
|
|
quoting=csv.QUOTE_NONE,
|
|
nrows=90000,
|
|
)
|
|
|
|
train_data = data[[6, 7]]
|
|
train_data = pd.concat([train_data, train_labels], axis=1)
|
|
train_data["final"] = train_data[6] + train_data[0] + train_data[7]
|
|
|
|
return train_data
|
|
|
|
def train_model(self):
|
|
training_data = self._prepare_train_data()
|
|
for index, row in training_data.iterrows():
|
|
text = self.preprocess_text(str(row["final"]))
|
|
words = word_tokenize(text)
|
|
for w1, w2, w3 in trigrams(words, pad_right=True, pad_left=True):
|
|
if w1 and w2 and w3:
|
|
self.model[(w2, w3)][w1] += 1
|
|
self.model[(w1, w2)][w3] += 1
|
|
self.vocab.add(w1)
|
|
self.vocab.add(w2)
|
|
self.vocab.add(w3)
|
|
|
|
for word_pair in self.model:
|
|
num_n_grams = float(sum(self.model[word_pair].values()))
|
|
for word in self.model[word_pair]:
|
|
self.model[word_pair][word] = (
|
|
self.model[word_pair][word] + self.alpha
|
|
) / (num_n_grams + self.alpha * len(self.vocab))
|
|
|
|
def predict_probs(self, words):
|
|
if len(words) < 3:
|
|
return self.DEFAULT_PREDICTION
|
|
|
|
word1, word2 = words[0], words[1]
|
|
raw_prediction = dict(self.model[word1, word2])
|
|
prediction = dict(Counter(raw_prediction).most_common(6))
|
|
|
|
total_prob = 0.0
|
|
str_prediction = ""
|
|
|
|
for word, prob in prediction.items():
|
|
total_prob += prob
|
|
str_prediction += f"{word}:{prob} "
|
|
|
|
if total_prob == 0.0:
|
|
return self.DEFAULT_PREDICTION
|
|
|
|
remaining_prob = 1 - total_prob
|
|
|
|
if remaining_prob < 0.01:
|
|
remaining_prob = 0.01
|
|
|
|
str_prediction += f":{remaining_prob}"
|
|
|
|
return str_prediction
|
|
|
|
def prepare_output(self, input_file, output_file):
|
|
with open(output_file, "w") as file:
|
|
data = pd.read_csv(
|
|
input_file,
|
|
sep="\t",
|
|
error_bad_lines=False,
|
|
warn_bad_lines=False,
|
|
header=None,
|
|
quoting=csv.QUOTE_NONE,
|
|
)
|
|
for _, row in data.iterrows():
|
|
text = self.preprocess_text(str(row[7]))
|
|
words = word_tokenize(text)
|
|
prediction = self.predict_probs(words)
|
|
file.write(prediction + "\n")
|
|
|
|
|
|
predictor = GapPredictor(alpha=0.00002)
|
|
predictor.train_model()
|
|
|
|
predictor.prepare_output("dev-0/in.tsv.xz", "dev-0/out.tsv")
|
|
predictor.prepare_output("test-A/in.tsv.xz", "test-A/out.tsv")
|