76 lines
2.0 KiB
Python
76 lines
2.0 KiB
Python
import pandas as pd
|
|
import nltk
|
|
from collections import Counter, defaultdict
|
|
from utils import get_csv, check_prerequisites, ENCODING, clean_text
|
|
|
|
|
|
def main():
|
|
check_prerequisites()
|
|
|
|
data = get_csv("train/in.tsv.xz")
|
|
|
|
train_words = get_csv("train/expected.tsv")
|
|
|
|
train_data = data[[7, 6]]
|
|
train_data = pd.concat([train_data, train_words], axis=1)
|
|
|
|
train_data[760] = train_data[7] + train_data[0] + train_data[6]
|
|
|
|
model = defaultdict(lambda: defaultdict(lambda: 0))
|
|
|
|
train_model(train_data, model)
|
|
|
|
predict_data("dev-0/in.tsv.xz", "dev-0/out.tsv", model)
|
|
predict_data("test-A/in.tsv.xz", "test-A/out.tsv", model)
|
|
|
|
|
|
def train_model(data, model):
|
|
for _, row in data.iterrows():
|
|
words = nltk.word_tokenize(clean_text(row[760]))
|
|
for w1, w2 in nltk.bigrams(words, pad_left=True, pad_right=True):
|
|
if w1 and w2:
|
|
model[w2][w1] += 1
|
|
for w2 in model:
|
|
total_count = float(sum(model[w2].values()))
|
|
for w1 in model[w2]:
|
|
model[w2][w1] /= total_count
|
|
|
|
|
|
def predict(word, model):
|
|
predictions = dict(model[word])
|
|
most_common = dict(Counter(predictions).most_common(5))
|
|
|
|
total_prob = 0.0
|
|
str_prediction = ""
|
|
|
|
for word, prob in most_common.items():
|
|
total_prob += prob
|
|
str_prediction += f"{word}:{prob} "
|
|
|
|
if not total_prob:
|
|
return "the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1"
|
|
|
|
if 1 - total_prob >= 0.01:
|
|
str_prediction += f":{1-total_prob}"
|
|
else:
|
|
str_prediction += f":0.01"
|
|
|
|
return str_prediction
|
|
|
|
|
|
def predict_data(read_path, save_path, model):
|
|
data = get_csv(read_path)
|
|
|
|
with open(save_path, "w", encoding=ENCODING) as f:
|
|
for _, row in data.iterrows():
|
|
words = nltk.word_tokenize(clean_text(row[7]))
|
|
if len(words) < 3:
|
|
prediction = "the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1"
|
|
else:
|
|
prediction = predict(words[-1], model)
|
|
f.write(prediction + "\n")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|