s434780/challenging-america-word-gap-prediction
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

434780

Browse Source
This commit is contained in:
alesad7 2022-04-03 22:23:38 +02:00
parent 5e504b2d51
commit 020c748f99
1 changed files with 28 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
run.py
View File

@ -1,13 +1,30 @@
from nltk import trigrams, word_tokenize
from collections import defaultdict, Counter
import pandas as pd
import csv
import regex as re
from collections import Counter, defaultdict
def preprocess(text):
text = text.lower().replace('-\\n', '').replace('\\n', ' ')
return re.sub(r'\p{P}', '', text)
train_set = pd.read_csv(
'train/in.tsv.xz',
sep='\t',
on_bad_lines='skip',
header=None,
uoting=csv.QUOTE_NONE,
nrows=20000)
train_labels = pd.read_csv(
'train/expected.tsv',
sep='\t',
on_bad_lines='skip',
header=None,
quoting=csv.QUOTE_NONE,
nrows=20000)
def data_preprocessing(text):
return re.sub(r'\p{P}', '', text.lower().replace('-\\n', '').replace('\\n', ' '))
def predict(before, after):
@ -27,7 +44,7 @@ def make_prediction(file):
data = pd.read_csv(f'{file}/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
with open(f'{file}/out.tsv', 'w', encoding='utf-8') as file_out:
for _, row in data.iterrows():
before, after = word_tokenize(preprocess(str(row[6]))), word_tokenize(preprocess(str(row[7])))
before, after = word_tokenize(data_preprocessing(str(row[6]))), word_tokenize(data_preprocessing(str(row[7])))
if len(before) < 3 or len(after) < 3:
prediction = 'to:0.02 be:0.02 the:0.02 or:0.01 not:0.01 and:0.01 a:0.01 :0.9'
else:
@ -35,19 +52,17 @@ def make_prediction(file):
file_out.write(prediction + '\n')
train_data = pd.read_csv('train/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE, nrows=20000)
train_labels = pd.read_csv('train/expected.tsv', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE, nrows=20000)
train_data = train_data[[6, 7]]
train_data = pd.concat([train_data, train_labels], axis=1)
train_data['line'] = train_data[6] + train_data[0] + train_data[7]
train_set = train_set[[6, 7]]
train_set = pd.concat([train_set, train_labels], axis=1)
train_set['line'] = train_set[6] + train_set[0] + train_set[7]
trigram = defaultdict(lambda: defaultdict(lambda: 0))
rows = train_data.iterrows()
rows_len = len(train_data)
rows = train_set.iterrows()
rows_len = len(train_set)
for index, (_, row) in enumerate(rows):
text = preprocess(str(row['line']))
text = data_preprocessing(str(row['line']))
words = word_tokenize(text)
for word_1, word_2, word_3 in trigrams(words, pad_right=True, pad_left=True):
if word_1 and word_2 and word_3: