challenging-america-word-ga.../bigram/bigram.py

105 lines
3.2 KiB
Python
Raw Normal View History

2023-04-26 15:16:55 +02:00
import csv
import pandas as pd
import regex as re
import nltk
import tqdm
from nltk import bigrams, word_tokenize
from collections import Counter, defaultdict
import string
nltk.download("punkt")
most_common_en_word = "the:0.4 be:0.2 to:0.1 of:0.05 and:0.025 a:0.0125 :0.2125"
train_count = 125000
# train set
train_data = pd.read_csv("train/in.tsv.xz", sep="\t", on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE, nrows=train_count)
# training labels
train_labels = pd.read_csv("train/expected.tsv", sep="\t", on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE,nrows=train_count)
dev_data = pd.read_csv("dev-0/in.tsv.xz", sep="\t", on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
test_data = pd.read_csv("test-A/in.tsv.xz", sep="\t", on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
def prepare_text(text):
text = text.lower().replace("-\\n", "").replace("\\n", " ")
text = re.sub(r"\p{P}", "", text)
return text
def train_bigrams():
for _, row in tqdm.tqdm(train_data.iterrows()):
text = prepare_text(str(row["final"]))
words = word_tokenize(text)
for w1, w2 in bigrams(words, pad_right=True, pad_left=True):
if all([w1, w2]):
model[w2][w1] += 1
for w_pair in model:
ngram_count = float(sum(model[w_pair].values()))
for w2 in model[w_pair]:
model[w_pair][w2] /= ngram_count
def predict_probs(word):
raw_prediction = dict(model[word])
prediction = dict(Counter(raw_prediction).most_common(6))
total_prob = 0.0
str_prediction = ""
for w, prob in prediction.items():
total_prob += prob
str_prediction += f"{w}:{prob} "
if total_prob == 0.0:
return most_common_en_word
remaining_prob = 1 - total_prob
if remaining_prob < 0.01:
remaining_prob = 0.01
str_prediction += f":{remaining_prob}"
return str_prediction
def write_output():
with open("dev-0/out.tsv", "w") as file:
for _, row in dev_data.iterrows():
text = prepare_text(str(row[7]))
words = word_tokenize(text)
if len(words) < 2:
prediction = most_common_en_word
else:
prediction = predict_probs(words[0])
file.write(prediction + "\n")
with open("test-A/out.tsv", "w") as file:
for _, row in test_data.iterrows():
text = prepare_text(str(row[7]))
words = word_tokenize(text)
if len(words) < 2:
prediction = most_common_en_word
else:
prediction = predict_probs(words[0])
file.write(prediction + "\n")
if __name__ == "__main__":
# Preapare train data
print("Preparing data...")
train_data = train_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]
# declare model
print("Preparing model...")
model = defaultdict(lambda: defaultdict(lambda: 0))
# train model
print("Model training...")
train_bigrams()
# write outputs
print("Writing outputs...")
write_output()