challenging-america-word-ga.../run.py
2022-04-04 15:07:07 +02:00

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()