import sys
from Corpus import Corpus
corpus = Corpus()
dirr = input("Input directory of corpus:")
# dirr = "resources/corpus_mini.txt"
corpus.read(dirr)
corpus.preprocess()
corpus.ner()
corpus.train_word2vec()
import dash_bootstrap_components as dbc
import dash_html_components as html
import plotly.express as px
from dash.dependencies import Input, Output
import plotly.graph_objects as go
import plotly.figure_factory as ff
from statsmodels.graphics.gofplots import qqplot
import pandas as pd
import numpy as np
app = dash.Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
corpus = Corpus() # khởi tạo
dirr = "resources/vn_express.txt" # chọn đường dẫn corpus
corpus.read(dirr) # đọc đường dẫn
corpus.preprocess() # Tiền xử lí
corpus.read_word2vec() # Đọc model word2vec để tìm từ đồng nghĩa
corpus.read_ner() # Đọc dữ liệu đã xử lí tên thực thể và từ loại
def genResult(res):
result = [
html.P(children=sen,
style={
'backgroundColor': 'white',
'borderBottom': '2px solid #4F2992',
'margin': '30px',
'padding': '10px'
}) for sen in res
]
import dash_core_components as dcc
import dash_bootstrap_components as dbc
import dash_html_components as html
import plotly.express as px
from dash.dependencies import Input, Output
import plotly.graph_objects as go
import plotly.figure_factory as ff
from statsmodels.graphics.gofplots import qqplot
import pandas as pd
import numpy as np
app = dash.Dash(external_stylesheets=[dbc.themes.BOOTSTRAP])
corpus = Corpus()
corpus.read('resources/vn_express.txt')
corpus.preprocess()
corpus.read_ner()
# corpus.read_word2vec()
df = pd.DataFrame(corpus.data_sent_segment, columns=['sentences'])
# # đếm theo tiếng
# df['len_tieng'] = df['sentences'].str.split()
# df['len_tieng'] = df['len_tieng'].apply(len)
# so_tieng = df['len_tieng'].sum()
# cau_tu_tieng = pd.DataFrame(np.array([len(corpus.data_sent_segment), len(corpus.vocab.keys()), so_tieng]))
# print(cau_tu_tieng)
# Độ dài câu theo tiếng
