File size: 5,576 Bytes
0beb932 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 |
# -*- coding: utf-8 -*-
"""
Created on Fri Jul 28 08:29:31 2023
@author: ASUS
"""
import pandas as pd
import os
import glob
import re
import unicodedata2
from underthesea import word_tokenize
path = 'raw_data/'
files = glob.glob(os.path.join(path, "*.csv"))
def read_csv_file(file):
raw_df = pd.DataFrame()
for file in files:
drop_idx = []
df = pd.read_csv(file)
for index, row in df.iterrows():
if len(row['comments'].split(" ")) < 10:
drop_idx.append(index)
df = df.drop(drop_idx, axis=0)
df.reset_index(inplace=True)
raw_df = pd.concat([raw_df, df], ignore_index=True)
raw_df.drop(['index', 'Unnamed: 0'], axis=1, inplace=True)
raw_df = raw_df.drop_duplicates()
return raw_df
def remove_xem_them(text):
text = text.replace("Xem thêm", "")
text = text.replace("xem thêm", "")
return text
# remove emojis
def remove_emojis(text):
emoj = re.compile("["
u"\U0001F600-\U0001F64F" # emoticons
u"\U0001F300-\U0001F5FF" # symbols & pictographs
u"\U0001F680-\U0001F6FF" # transport & map symbols
u"\U0001F1E0-\U0001F1FF" # flags (iOS)
u"\U00002500-\U00002BEF" # chinese char
u"\U00002702-\U000027B0"
u"\U00002702-\U000027B0"
u"\U000024C2-\U0001F251"
u"\U0001f926-\U0001f937"
u"\U00010000-\U0010ffff"
u"\u2640-\u2642"
u"\u2600-\u2B55"
u"\u200d"
u"\u23cf"
u"\u23e9"
u"\u231a"
u"\ufe0f" # dingbats
u"\u3030"
"]+", re.UNICODE)
return re.sub(emoj, ' ', text)
def remove_hastag(text):
pattern = re.compile(r'([\#]+)((\w)*)(\s*)')
matches = pattern.finditer(text + " ")
for m in matches:
text = text.replace(m.group(), '')
return text
def remove_stopwords(text):
stopwords = []
f = open('vietnamese-stopwords.txt', encoding='utf8')
for line in f:
stopwords.append(line.rstrip('\n'))
new_text = ' '.join([i for i in text.split() if i not in stopwords])
return new_text
# split word with punctuation
def format_punctuation(text):
pattern = re.compile(r'(([\!\"\#\$\%\&\,\.\-\_\+\:\;\?\^\•])+)(\w+)')
matches = pattern.finditer(text + " ")
for m in matches:
text = text.replace(m.group()[0], ' ')
return text
# remove punctuation
def remove_punctuation(text):
punc = "'!\"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~‘’“”•…‼‼‼⁃₫√≧≦–"
new_text = "".join([i for i in text if i not in punc])
return new_text
def format_price(text):
pattern = re.compile(r'([0-9]+)(\s*)(k)(?=\W)')
matches = pattern.finditer(text + " ")
prices = []
new_prices = []
for m in matches:
prices.append(m.group())
new_prices.append(m.group().replace('k', '') + " nghìn_đồng")
pattern = re.compile(r'([0-9]+)(\s*)(tr |m )(([0-9]*))')
matches = pattern.finditer(text + " ")
for m in matches:
prices.append(m.group())
for r in ["tr ", "m "]:
if r in m.group():
n_p = m.group().replace(r, " triệu ")
break
tmp = n_p.split("triệu")
if tmp[1] == " ":
n_p += "_đồng "
else :
if int(tmp[1]) < 10:
tmp[1] = int(tmp[1]) * 100
if int(tmp[1]) < 100:
tmp[1] = int(tmp[1]) * 10
n_p = tmp[0] + "_triệu " + str(tmp[1]) + " nghìn_đồng"
new_prices.append(n_p)
for i in range(len(prices)):
text = text.replace(prices[i], new_prices[i])
text = text.replace("nghìn đồng", "nghìn_đồng")
text = text.replace("triệu đồng", "triệu_đồng")
return text
def format_price_v2(text):
pattern = re.compile(r'([0-9]+)(\s*)(triệu_đồng|nghìn_đồng|nghìn)')
matches = pattern.finditer(text + " ")
old = []
new = []
for m in matches:
old.append(m.group())
new.append("_".join(m.group().split()))
for i in range(len(old)):
text = text.replace(old[i], new[i])
return text
def clean_text(text):
text = text.lower()
rp_dict = {"cty":"công ty", "\"":"", "'":"", "\n":" ", " k ":" không ", " h ":" giờ ", " ko ":" không ", " cf ":" cà phê ", " cofe ":" cà phê ", " coffee ":" cà phê ", " cofee ":" cà phê ", " cafe ":" cà phê ", " cafee ":" cà phê ",
" j ":" gì ", ".000":" nghìn", "vnd":" đồng", "vnđ":" đồng", " r ":" rồi ", " đc ":" được ", " dc ":" được ", " pv ":" phục vụ ", " pvu ":" phục vụ ", " pvụ ":" phục vụ ",
" nv ":" nhân viên ", " nvien ":" nhân viên ", " nviên ": " nhân viên ", " b ":" bạn ", " m ":" mình ", " ng ":" người ", " cx ":" cũng ", "oder":"order", "ita":"ít",
"vaie":"vải", "chie":"chỉ", "cb":"chuẩn bị", "nc":"nước", "khoog":"không", "bânh":"bánh", "lug":"lung", "nhiêm":"nhiên", "nguời":"người", "ntn":"như thế này", "nuớc":"nước",
"lẫu":"lẩu", "dẻ":"rẻ", "siu":"siêu", "ni":"này"}
for key, value in rp_dict.items():
text = text.replace(key, value)
text = re.sub('\n', '' , text)
return text
def normalize_format(text):
return unicodedata2.normalize('NFC', text)
def word_segment(text):
try:
text = word_tokenize(text, format='text')
except:
return "Lỗi"
return text |