134 lines
3.6 KiB
Python
134 lines
3.6 KiB
Python
#!/usr/bin/env python
|
|
# coding: utf-8
|
|
|
|
# In[136]:
|
|
|
|
import nltk
|
|
from nltk import trigrams
|
|
from nltk.tokenize import word_tokenize
|
|
from collections import defaultdict, Counter
|
|
from nltk import ngrams
|
|
import pandas as pd
|
|
import csv
|
|
import re
|
|
|
|
|
|
# In[172]:
|
|
def clean_text(text):
|
|
text = text.lower().replace('-\\n', '').replace('\\n', ' ')
|
|
text = re.sub(r'\p{P}', '', text)
|
|
|
|
return text
|
|
|
|
model = defaultdict(lambda: defaultdict(lambda: 0))
|
|
|
|
|
|
# In[173]:
|
|
|
|
|
|
train_file_in = pd.read_csv("train/in.tsv.xz", sep="\t", error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE, nrows=200000)
|
|
train_file_out = pd.read_csv("train/expected.tsv", sep="\t", error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE, nrows=200000)
|
|
|
|
print("read train file")
|
|
# In[174]:
|
|
|
|
|
|
stop_words= nltk.corpus.stopwords.words('english')
|
|
|
|
def get_20common_2grams(text, n):
|
|
outputTrigrams = []
|
|
n_grams = ngrams(nltk.tokenize.word_tokenize(text), n)
|
|
for grams in n_grams:
|
|
outputTrigrams.append(grams)
|
|
return outputTrigrams
|
|
|
|
def get_20common_2grams_no_stop(text, n):
|
|
tokenized_world = nltk.tokenize.word_tokenize(text)
|
|
stop_words= nltk.corpus.stopwords.words('english')
|
|
tokenized_no_stop = [i for i in tokenized_world if i not in stop_words]
|
|
n_grams = ngrams(tokenized_no_stop, n)
|
|
return n_grams
|
|
|
|
def predict(word_before, word_after):
|
|
prob_list = dict(Counter(model[(word_before, word_after)]).most_common(6)).items()
|
|
predictions = []
|
|
prob_sum = 0.0
|
|
for key, value in prob_list:
|
|
prob_sum += value
|
|
predictions.append(f'{key}:{value}')
|
|
if prob_sum == 0.0:
|
|
return 'the:0:2 be:0.2 to:0.2 of:0.15 and:0.15 :0.1'
|
|
remaining_prob = 1 - prob_sum
|
|
if remaining_prob < 0.01:
|
|
predictions.append(f':{0.01}')
|
|
return ' '.join(predictions)
|
|
|
|
|
|
# In[175]:
|
|
|
|
|
|
train = train_file_in[[6, 7]]
|
|
train = pd.concat([train, train_file_out], axis=1)
|
|
|
|
train["result"] = train[6] + train[0] + train[7]
|
|
|
|
|
|
# In[ ]:
|
|
|
|
|
|
for index, row in train.iterrows():
|
|
text = str(row["result"]).lower().replace('-\\n', '').replace('\\n', ' ')
|
|
words = word_tokenize(text)
|
|
for w1, w2, w3 in trigrams(words, pad_right=True, pad_left=True):
|
|
if w1 and w2 and w3:
|
|
model[(w2, w3)][w1] += 1
|
|
|
|
|
|
# In[ ]:
|
|
print("train model")
|
|
|
|
for key in model:
|
|
total_count = float(sum(model[key].values()))
|
|
for value in model[key]:
|
|
model[key][value] /= total_count
|
|
|
|
|
|
# In[ ]:
|
|
|
|
|
|
dev_data = pd.read_csv('dev-0/in.tsv.xz', sep='\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)
|
|
test_a_data = pd.read_csv('test-A/in.tsv.xz', sep='\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)
|
|
|
|
|
|
# In[ ]:
|
|
print("dev_0");
|
|
|
|
with open('dev-0/out.tsv', 'w', encoding="utf-8") as file:
|
|
for index, row in dev_data.iterrows():
|
|
text = str(row[7]).lower().replace('-\\n', '').replace('\\n', ' ')
|
|
words = word_tokenize(text)
|
|
if len(words) < 4:
|
|
print(words)
|
|
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[0], words[1])
|
|
file.write(prediction + '\n')
|
|
|
|
print("test_A");
|
|
with open('test-A/out.tsv', 'w', encoding="utf-8") as file:
|
|
for index, row in test_a_data.iterrows():
|
|
text = str(row[7]).lower().replace('-\\n', '').replace('\\n', ' ')
|
|
words = word_tokenize(text)
|
|
if len(words) < 4:
|
|
print(words)
|
|
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[0], words[1])
|
|
file.write(prediction + '\n')
|
|
|
|
# In[ ]:
|
|
|
|
|
|
|
|
|