134 lines
3.3 KiB
Python
134 lines
3.3 KiB
Python
#!/usr/bin/env python
|
|
# coding: utf-8
|
|
|
|
# In[2]:
|
|
|
|
|
|
import pandas as pd
|
|
import csv
|
|
import regex as re
|
|
from nltk import bigrams, word_tokenize
|
|
from collections import Counter, defaultdict
|
|
import string
|
|
import unicodedata
|
|
from tqdm import tqdm
|
|
|
|
pd.set_option('display.max_columns', None)
|
|
pd.set_option('display.max_rows', None)
|
|
|
|
NROWS = 50000
|
|
ALPHA = 0.1
|
|
|
|
|
|
def etl():
|
|
data = pd.read_csv(
|
|
"train/in.tsv.xz",
|
|
sep="\t",
|
|
error_bad_lines=False,
|
|
header=None,
|
|
quoting=csv.QUOTE_NONE,
|
|
nrows=NROWS
|
|
)
|
|
train_labels = pd.read_csv(
|
|
"train/expected.tsv",
|
|
sep="\t",
|
|
error_bad_lines=False,
|
|
header=None,
|
|
quoting=csv.QUOTE_NONE,
|
|
nrows=NROWS
|
|
)
|
|
|
|
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]
|
|
|
|
model = defaultdict(lambda: defaultdict(lambda: 0))
|
|
return train_data, model
|
|
|
|
|
|
def clean(text):
|
|
text = str(text).lower().replace("-\\n", "").replace("\\n", " ")
|
|
return re.sub(r"\p{P}", "", text)
|
|
|
|
|
|
def train_model(data):
|
|
print("1/2")
|
|
for _, row in tqdm(data.iterrows()):
|
|
words = word_tokenize(clean(row["final"]))
|
|
for word_1, word_2 in bigrams(words, pad_left=True, pad_right=True):
|
|
if word_1 and word_2:
|
|
vocab.add(word_1)
|
|
vocab.add(word_2)
|
|
model[word_1][word_2] += 1
|
|
print("2/2")
|
|
for word_1 in tqdm(model):
|
|
total_count = float(sum(model[word_1].values()))
|
|
for word_2 in model[word_1]:
|
|
model[word_1][word_2] /= total_count
|
|
|
|
|
|
def predict(word):
|
|
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):
|
|
data = pd.read_csv(
|
|
read_path, sep="\t", error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE
|
|
)
|
|
with open(save_path, "w", encoding="utf-8") as file:
|
|
for _, row in tqdm(data.iterrows()):
|
|
words = word_tokenize(clean(row[6]))
|
|
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])
|
|
file.write(prediction + "\n")
|
|
|
|
def plus_alpha_smoothing():
|
|
model_len = len(model)
|
|
for word_1 in tqdm(model):
|
|
word_1_occurrences = sum(model[word_1].values())
|
|
for word_2 in model[word_1]:
|
|
model[word_1][word_2] += ALPHA
|
|
model[word_1][word_2] /= float(word_1_occurrences + ALPHA + len(word_2))
|
|
|
|
|
|
print("Loading data...")
|
|
train_data, model = etl()
|
|
vocab = set()
|
|
print("Training model...")
|
|
train_model(train_data)
|
|
print("Smoothing...")
|
|
plus_alpha_smoothing()
|
|
print("Predicting...")
|
|
print("Dev set")
|
|
predict_data("dev-0/in.tsv.xz", "dev-0/out.tsv")
|
|
print("Test set")
|
|
predict_data("test-A/in.tsv.xz", "test-A/out.tsv")
|
|
|
|
|
|
# In[ ]:
|
|
|
|
|
|
|
|
|