class Translate:
def __init__(self):
self.tin = Translater()
self.tin.set_key("#your yandex id here")
def translate(self, text, target):
try:
self.tin.set_to_lang(target)
self.tin.set_text(text)
self.tin.set_from_lang(self.tin.detect_lang())
self.r = self.tin.translate()
return self.r
except:
print("Translate Failed.")
def __init__(self,to_lang='es',from_lang='en'):
token = "TOKEN" #get here https://translate.yandex.com/developers/keys
tr = Translater()
tr.set_key(token)
tr.set_to_lang(to_lang)
tr.set_from_lang(from_lang)
self.from_lang_default = from_lang
self.tr = tr
def init(update, context):
bot = context.bot
var_messagge = update.message.text[6:]
# Variables
currenttimestr = 'Tempo attuale a '
citynotfoundstr = 'Non ho trovato la città'
tempunit = 'celsius'
tempstr = 'C°'
lang = 'it'
# Code
try:
tr = Translater()
tr.set_key(Config.YANDEX_API)
tr.set_from_lang('en')
tr.set_to_lang(lang)
weather = pyowm.OWM(Config.OPENWEATHER_API).weather_at_place(
var_messagge.lower().capitalize()).get_weather()
status = weather.get_status()
desc = weather.get_detailed_status()
for a, b in weather.get_temperature(unit=tempunit).items():
if a == 'temp':
temp = b
if a == 'temp_min':
mintemp = b
if a == 'temp_max':
maxtemp = b
def sendweathermsg(icon):
msgtext = currenttimestr + var_messagge.lower().capitalize(
) + ':\n\n'
if icon == '':
msgtext = msgtext + desc.capitalize()
else:
msgtext = msgtext + icon + ' ' + desc.capitalize() + ' ' + icon
msgtext = msgtext + '\nHumidity: ' + str(weather.get_humidity(
)) + '%\nTemp: ' + str(temp) + tempstr + ', Min Temp: ' + str(
mintemp) + tempstr + ', Max Temp: ' + str(maxtemp) + tempstr
tr.set_text(msgtext)
bot.send_message(update.message.chat_id,
text=tr.translate(),
parse_mode='HTML')
if status == 'Clouds':
sendweathermsg('☁️')
elif status == 'Clear':
sendweathermsg('☀️')
elif status == 'Rain':
sendweathermsg('🌧')
elif status == 'Drizzle':
sendweathermsg('🌧')
elif status == 'Mist':
sendweathermsg('🌫')
else:
sendweathermsg('')
except:
bot.send_message(update.message.chat_id,
text=citynotfoundstr,
parse_mode='HTML')
def get_weather(city):
token = '<your_token>'
if city != '':
translator = Translater(token, city, 'ru', 'en')
translated = translator.translate().lower().replace(' ', '-')
else:
translated = 'moscow'
url = 'https://yandex.ru/pogoda/' + translated
response = requests.get(url)
markup = BeautifulSoup(response.content, 'html.parser')
try:
weather_in_city = markup.find_all('div', {'class': 'main-title__title-wrap'})[0].text\
+ ':'
except IndexError:
return 'Неправильный параметр команды'
temperature = markup.find('span', {'class': 'temp__value'}).text + '°'
weather_condition = markup.find('div', {'class': 'link__condition'}).text
feels_like = markup.find('dt', {'class': 'term__label'}).text
feels_like_temperature = markup.find_all(
'span', {'class': 'temp__value'})[1].text + '°'
sense = feels_like + ' ' + feels_like_temperature
humidity = 'Влажность: ' + markup.find_all(
'dd', {'class': 'term__value'})[3].text
pressure = 'Давление: ' + markup.find_all(
'dd', {'class': 'term__value'})[-2].text
try:
# может быть 'Штиль', а не направление ветра
wind_direction = markup.find('abbr', {'class': 'icon-abbr'})['title']
except TypeError:
wind_direction = 'Ветер: '
# просто красиво форматирую вывод
wind_condition = markup.find_all('dd', {'class': 'term__value'})[2].text.strip('СЮЗВ') +\
wind_direction[7:].title()
wind = wind_direction[:7] + wind_condition
return '\n'.join((weather_in_city, weather_condition, temperature, sense,
humidity, pressure, wind))
from newspaper import Article
import nltk, re, pprint
from nltk import word_tokenize
import string
from yandex.Translater import Translater
tr = Translater()
tr.set_key(
'trnsl.1.1.20190620T080928Z.059272b876400ab5.db9848757da3b1698721fef656db05d4903c4d1b'
)
tr.set_from_lang('en')
tr.set_to_lang('tr')
nltk.download('words')
nltk.download('stopwords')
nltk.download('averaged_perceptron_tagger')
#get stopwords, corpus-words
from nltk.corpus import words
from stop_words import get_stop_words
from nltk.corpus import stopwords
stop_words = list(get_stop_words('en')) #Have around 900 stopwords
nltk_words = list(stopwords.words('english')) #Have around 150 stopwords
stop_words.extend(nltk_words)
def fetch_words_from_news(url):
Generates a json from the list return by get_tryalgo_descriptions(),
and saves it in data/description.json
:param translate: boolean passed to get_tryalgo_descriptions()
"""
description_obj = get_tryalgo_descriptions(translate=translate)
description_file = os.path.join("..", "data", "description.json")
with open(description_file, "w") as f:
f.write(json.dumps(description_obj))
if __name__ == "__main__":
if len(sys.argv) > 2:
args_error()
if len(sys.argv) == 2:
if sys.argv[1] != "--no-translation":
args_error()
generate_json(translate=False)
else:
tr = Translater()
yandex_key = get_yandex_key()
tr.set_key(yandex_key)
tr.set_from_lang('en')
tr.set_to_lang('fr')
generate_json(translate=True)
import locale
from yandex.Translater import Translater
tr=Translater()
locale.setlocale(locale.LC_ALL, '') #фиксит проблему с библиотекой яндекса
api_key="trnsl.1.1.20200309T060830Z.344d9b14a5d60014.73173e69fc28c824b2288d084ca8e11617d260e1"
query='boss'
tr.set_key(api_key)
tr.set_from_lang('en')
tr.set_to_lang('ru')
tr.set_text(query)
result=tr.translate()
speak(result)
def traduceCarTec(cadenaEntrada):
apiTranslateEplan = """trnsl.1.1.20190308T091207Z.xxx"""
tr = Translater()
tr.set_key(apiTranslateEplan)
tr.set_from_lang('es')
tr.set_to_lang('en')
f.write("===> TraduceCarTec: " + str(cadenaEntrada) +
str(type(cadenaEntrada)))
tr.set_text(cadenaEntrada)
cadEng = tr.translate()
return (cadEng)
from fuzzywuzzy import process
from yandex.Translater import Translater
tr = Translater()
tr.set_key('trnsl.1.1.20191110T032857Z.5cb504ab3196bc0f.e222fb57077985f5bc174f9f7b8ff5622b83d7ed') # Api key found on https://translate.yandex.com/developers/keys
def tran(text_from_user, to_lang, tr):
tr.set_from_lang('th')
tr.set_to_lang('en')
tr.set_text(text_from_user)
text_output = tr.translate()
return (text_output)
def check_lang(Input):
corpus = {
'fr' : ['france','ฝรั่งเศส'], #90
'de' : ['german','deutsch','เยอรมันนี'], #36
'en' : ['english','อังกฤษ','อิ้ง'] #67
}
best_match = ''
highest_score = 0
for key,value in corpus.items():
out = process.extractOne(Input, value)
if out[1] > highest_score:
highest_score = out[1]
best_match = key
else :
continue
return best_match
# while True:
def translate():
tr = Translater()
tr.set_key('Insert_your_API_Key_Here') # Api key found on https://translate.yandex.com/developers/keys
text_to_translate = 'شركة ذات مسؤولية محدودة'
tr.set_text(text_to_translate)
tr.set_from_lang('ar')
tr.set_to_lang('en')
translated_txt = tr.translate()
print(translated_txt)
import requests
from joblib import load
from numpy import isnan
from sklearn.ensemble import RandomForestClassifier
from yandex.Translater import Translater, TranslaterError
from gras import ROOT
from gras.base_miner import BaseMiner
from gras.errors import YandexError, YandexKeyError
from gras.identity_merging.utils import (damerau_levenshtein as dl,
gen_count_dict, gen_feature_vector,
monge_elkan, read_csv)
from gras.utils import exception_handler
logger = logging.getLogger("main")
translator = Translater()
TOTAL_TRANSLATED = 0
TERMS = [
"jr", "junior", "senior", "sr", "2nd", "ii", "iii", "iv", "v", "vi", "dr",
"mr", "mrs", "ms", "phd", "prof", "professor", "miss", "mx", "sir", "mme",
"msgr", "md", "server", "fake", "none", "null", "anonymous", "support",
"admin", "unknown", "root", "nobody", "ubuntu", "(no author)", "system",
"<blank>", "user", "noreplycom"
]
EMAIL_REGEX = r"(^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$)"
class Alias:
"""
def __init__(self):
self.tin = Translater()
self.tin.set_key("#your yandex id here")
def translate(self, text, lanFrom, lanTo):
if self.times != 0:
tr = Translater()
tr.set_key(secretKey)
if re.search(r'[А-я]', text):
tr.set_from_lang('ru')
tr.set_to_lang('en')
else:
tr.set_from_lang('en')
tr.set_to_lang('ru')
if text != "":
tr.set_text(text)
textboxR.delete('1.0', "end-1c")
textboxR.insert("1.0", tr.translate())
self.times += 1
from Sastrawi.Stemmer.StemmerFactory import StemmerFactory
from textblob import TextBlob
import re
import json
# Connection to MongoDB
myclient = pymongo.MongoClient("mongodb://localhost:27017/")
mydb = myclient["indonesia"]
mycol = mydb["test10"]
# Stemmer
factory = StemmerFactory()
stemmer = factory.create_stemmer()
# Translater
tr = Translater()
tr.set_key(
'trnsl.1.1.20191105T142939Z.b7e2df135b69d172.03f8d4635086f151f8b025984598a17b9af20ca6'
) # Api key found on https://translate.yandex.com/developers/keys
tr.set_from_lang('id')
tr.set_to_lang('en')
def _connect_mongo(host, port, username, password, db):
""" A util for making a connection to mongo """
if username and password:
mongo_uri = 'mongodb://localhost:27017/' % (username, password, host,
port, db)
conn = MongoClient(mongo_uri)
else:
def translater(self):
ru_str = self.ru_str
tr = Translater()
tr.set_key(self.token)
tr.set_from_lang("ru")
tr.set_to_lang("en")
tr.set_text(ru_str)
en_str = tr.translate()
self.result = en_str
print("Перевод:", self.result)
def init(update, context):
bot = context.bot
message_var = update.message.text[8:]
try:
tr = Translater()
tr.set_key(
Config.YANDEX_API
) # Api key found on https://translate.yandex.com/developers/keys
tr.set_text(message_var)
tr.set_from_lang('it')
tr.set_to_lang('en')
bot.send_message(update.message.chat_id, tr.translate())
except:
bot.send_message(update.message.chat_id,
text="Perfavore inserisci una frase.")
from yandex.Translater import Translater
tr = Translater()
tr.set_key(
'trnsl.1.1.20200119T075806Z.ba2fc76141b64141.3739322923782504e521bd76c8903e90835cb864'
)
tr.set_from_lang('en')
tr.set_to_lang('ta')
tr.set_text("rice crop field few weeks after sowing of seeds.")
txt = tr.translate()
def traductionChained(utt, languages):
tr = Translater()
tr.set_key(
'trnsl.1.1.20200203T095917Z.30bf7af5cf091999.513bc5df39c8c45fd3cc2baa0ee4c8af7669202a'
)
tr.set_text(utt)
originLang = tr.detect_lang()
tr.set_from_lang(originLang)
tr.set_to_lang(languages[0])
tr.set_text(utt)
utt = tr.translate()
for i, lan in enumerate(languages):
tr.set_from_lang(lan)
if i < len(languages) - 1:
tr.set_to_lang(languages[i + 1])
else:
tr.set_to_lang(originLang)
utt = tr.translate()
tr.set_text(utt)
#print(utt)
return utt
from linebot import (LineBotApi, WebhookHandler)
from linebot.exceptions import (InvalidSignatureError)
from linebot.models import *
from yandex.Translater import Translater
from fuzzywuzzy import process ## import fuzz
app = Flask(__name__)
from Config import DEVELOPEMENTCONFIG
from datetime import datetime
from Flex import Flex_output, Flex_database
line_bot_api = LineBotApi(DEVELOPEMENTCONFIG.CHANNEL_ACCESS_TOKEN)
handler = WebhookHandler(DEVELOPEMENTCONFIG.CHANNEL_SECRET)
user_session = {} #database for correct user
tr = Translater()
tr.set_key(DEVELOPEMENTCONFIG.YANDEX_KEY
) # Api key found on https://translate.yandex.com/developers/keys
List_test = []
@app.route("/callback", methods=['POST'])
def callback():
# get X-Line-Signature header value
signature = request.headers['X-Line-Signature']
# get request body as text
body = request.get_data(as_text=True)
print(body)
app.logger.info("Request body: " + body)
#setup
from yandex.Translater import Translater
import sys,os
from keys import API_KEY
clear = lambda: os.system('cls')
filePath = sys.argv[1]
#opening files
wordSet = open(filePath,'r').read().split('\n')
wordSet_trd = open('translation.txt', 'w')
#setting up the API key
tr=Translater()
tr.set_key(API_KEY)
All_num = len(wordSet)
Done_num = 0
def translation(word):
tr.set_from_lang('pl')
tr.set_to_lang('en')
tr.set_text(word)
trd = tr.translate()
return trd
#main
for word in wordSet:
clear()
print(str(Done_num) + "/" + str(All_num) + " done.")
word_trd = translation(word)
Done_num += 1
from wozzol import WozzolQuizUnit
import os
import requests
from yandex.Translater import Translater
tr = Translater()
# Api key found on https://translate.yandex.com/developers/keys
tr.set_key('trnsl.1.1.20200317T184210Z.859bd4e1e36decc9.54c5d73f715ded0f0b5e33e8f80d0eca61173b7d')
tr.set_from_lang('es')
tr.set_to_lang('en')
def translate_word(word):
tr.set_text(word)
translation = tr.translate()
return translation
def convert_word_list_to_wozzol(word_list):
with open('somefile.txt', 'a') as the_file:
the_file.write('wozzol')
the_file.write('Spanish : English')
for word in word_list:
the_file.write(f'{word.question} = {word.answer}')
def convert_wiktionary():
file_path = os.path.join('web_pages', 'spanish_1000_frequency.html')
# format from https://www.wozzol.nl/woordenlijsten
text_file = open(file_path, encoding="utf-8")
text_lines = text_file.readlines()
def sendEmail(target_email,url,tmrange,etype):
df = pd.read_csv('feedback-256010.csv')
edf = pd.read_csv('email_records.csv')
if url == "EMEA":
csites = ["cs_CZ","en_UK","nl_BE","da_DK","en_ZA","nl_NL","de_AT","es_ES","pl_PL","de_CH","fr_BE","pt_pt","de_DE","fr_CH","ru_RU","en_IE","fr_FR","sv_SE","en_IL","it_IT","tr_TR","en_MDE"]
down_df = df[df['Source URL'].str.contains('|'.join(csites))]
elif url == "North America":
csites = ["en_NA"]
down_df = df[df['Source URL'].str.contains('|'.join(csites))]
elif url == "APAC":
csites = ["zh_CN","ja_JP","zh_TW","en_SEA","ko_KR","en_AU","en_NZ","en_IN"]
down_df = df[df['Source URL'].str.contains('|'.join(csites))]
elif url == "LAR":
csites = ["en_CAR","es_CL","es_PE","es_CAR","es_CO"]
down_df = df[df['Source URL'].str.contains('|'.join(csites))]
elif url == "rockwellautomation.com/search":
csites = ['rockwellautomation.com/search','rockwellautomation.com/my/search']
down_df = df[df['Source URL'].str.contains('|'.join(csites))]
else:
down_df = df[df['Source URL'].str.contains(url)]
today = datetime.now()
timzo = pytz.timezone('US/Eastern')
today = timzo.localize(today)
week_prior = today - timedelta(weeks=tmrange)
down_df['Date Submitted'] = pd.to_datetime(down_df['Date Submitted'])
down_df['Date Submitted']=down_df['Date Submitted'].dt.tz_localize(tz='US/Eastern', nonexistent='shift_forward')
date_df = down_df.loc[down_df['Date Submitted'] >= week_prior]
#Cancel if no feedback at all in past week
#if date_df.empty == True:
#print("No data for time given, email not sent for "+str(url))
#return
testemail = MIMEMultipart()
sender_email = "*****@*****.**"
pw = "Ao1HO2RO3"
#target_email = "*****@*****.**"
testemail["From"] = sender_email
testemail["To"] = target_email
testemail["Subject"] = "Hotjar feedback from "+week_prior.strftime("%m/%d")+" to "+ today.strftime("%m/%d")+" | "+str(url)
if etype == 'Responses':
mess_df=date_df.loc[date_df["Message"].notna()]
mess_df = mess_df.drop(columns=['Number',"User","OS"])
htmlbod = '<html><body><h1>Hotjar feedback over past '+str(tmrange)+' week(s) for '+str(url)+'</h1>'
if mess_df.empty == True:
htmlbod = '<html><body><p>No feedback responses for '+str(url)+' over '+str(tmrange)+' week(s).</p>'
#Emjois: 5: 128522,1F60A 4: 128527, 1F60F 3: 128528, 1F610 2: 128530 1F612 1: 128544, 1F620
#Link : 128279, 1F517
emo = '128528'
from yandex.Translater import Translater
from langdetect import detect
for row in mess_df.itertuples():
if str(row.Email)=="nan":
email = '<b>(unknown)</b>'
else:
email = '<b>'+str(row.Email)+'</b>'
if row._7==1:
emo='128544'
elif row._7==2:
emo='128530'
elif row._7==3:
emo='128528'
elif row._7==4:
emo='128527'
elif row._7==5:
emo='128522'
try:
detlan = detect(str(row.Message))
except:
detlan = 'en'
if detlan == 'en':
htmlbod = htmlbod+'<p><q>'+str(row.Message)+'</q></p><p>&#'+emo+email+' on '+row._1.strftime("%m/%d/%Y, %H:%M:%S")+" | "+str(row.Country)+" | "+str(row.Browser)+" on "+str(row.Device)+'</p><a href='+str(row._3)+'>🔗'+str(row._3)+'</a><hr>'
else:
try:
tr = Translater()
tr.set_key('trnsl.1.1.20200326T171128Z.c6e42851517b0a0a.363c0f12f70ef655b2ea466b33e40856c53df6c8')
tr.set_text(str(row.Message))
tr.set_to_lang('en')
mtrans = tr.translate()
except:
mtrans = "Translation failed."
htmlbod = htmlbod+'<p><q>'+str(row.Message)+'</q></p><p>Translation attempt: <q>'+mtrans+'</q></p><p>&#'+emo+email+' on '+row._1.strftime("%m/%d/%Y, %H:%M:%S")+" | "+str(row.Country)+" | "+str(row.Browser)+" on "+str(row.Device)+'</p><a href='+str(row._3)+'>🔗'+str(row._3)+'</a><hr>'
htmlbod = htmlbod + '</body></html>'
testemail.attach(MIMEText(htmlbod, "html"))
if etype == 'Visualizations':
histfig = px.histogram(date_df, x='Date Submitted', color='Emotion (1-5)',
title='Feedback Responses for '+str(url),
opacity=0.8,
category_orders={'Emotion (1-5)':[1,2,3,4,5]},
color_discrete_map={1:"#e83b3a",2:"#c97d7d",3:"#BAB0AC",4:"#99bd9c",5:"#4cba76"},
nbins=20
)
histfig.update_layout(xaxis_tickformat='%d %B (%a)', xaxis=dict(dtick=86400000.0))
histfig.write_image('histfigtest.png')
counfig = px.histogram(date_df, y='Country', color='Emotion (1-5)',
title='Breakdown by Country for url given',
opacity=0.8,
orientation = 'h',
height = 1000,
category_orders={'Emotion (1-5)':[1,2,3,4,5]},
color_discrete_map={1:"#e83b3a",2:"#c97d7d",3:"#BAB0AC",4:"#99bd9c",5:"#4cba76"},
#nbins=20
).update_yaxes(categoryorder="total ascending")
counfig.write_image('counfig.png')
apdate_df=date_df
apdate_df['feedback_count']= apdate_df['Source URL'].map(apdate_df['Source URL'].value_counts())
bad_df = apdate_df.loc[(apdate_df['Emotion (1-5)'] == 1) | (apdate_df['Emotion (1-5)'] == 2)]
intr_df = bad_df[bad_df.duplicated(subset='Source URL', keep=False)]
bdap_df=intr_df
bdap_df['negative_feedbacks']= bdap_df['Source URL'].map(bdap_df['Source URL'].value_counts())
intrfig = px.scatter(bdap_df, title='Pages of interest (Which pages are getting lots of bad feedback?)', y='Source URL', x='negative_feedbacks', color='negative_feedbacks', text='feedback_count', color_continuous_scale=px.colors.sequential.YlOrRd, size='feedback_count')
intrfig.update_layout(margin=dict(l=500,r=10,t=40,b=20),xaxis=dict(dtick=1))
intrfig.layout.coloraxis.showscale = False
dd_df = bdap_df.drop_duplicates(subset='Source URL', keep='first')
nlarg_df = dd_df.nlargest(5,['negative_feedbacks'])
with open('histfigtest.png', 'rb') as f:
# set attachment mime and file name, the image type is png
mime = MIMEBase('image', 'png', filename='img1.png')
# add required header data:
mime.add_header('Content-Disposition', 'attachment', filename='img1.png')
mime.add_header('X-Attachment-Id', '0')
mime.add_header('Content-ID', '<0>')
# read attachment file content into the MIMEBase object
mime.set_payload(f.read())
# encode with base64
encoders.encode_base64(mime)
# add MIMEBase object to MIMEMultipart object
testemail.attach(mime)
with open('counfig.png', 'rb') as f:
# set attachment mime and file name, the image type is png
mime = MIMEBase('image', 'png', filename='img2.png')
# add required header data:
mime.add_header('Content-Disposition', 'attachment', filename='img2.png')
mime.add_header('X-Attachment-Id', '1')
mime.add_header('Content-ID', '<1>')
# read attachment file content into the MIMEBase object
mime.set_payload(f.read())
# encode with base64
encoders.encode_base64(mime)
# add MIMEBase object to MIMEMultipart object
testemail.attach(mime)
with open('intrfig.png', 'rb') as f:
# set attachment mime and file name, the image type is png
mime = MIMEBase('image', 'png', filename='img3.png')
# add required header data:
mime.add_header('Content-Disposition', 'attachment', filename='img3.png')
mime.add_header('X-Attachment-Id', '2')
mime.add_header('Content-ID', '<2>')
# read attachment file content into the MIMEBase object
mime.set_payload(f.read())
# encode with base64
encoders.encode_base64(mime)
# add MIMEBase object to MIMEMultipart object
testemail.attach(mime)
embimg = '<html><body><h1>HotJar Report</h1>'+'<p><img src="cid:0"></p>'+'<img src="cid:1"></p>'+'<img src="cid:2"></p>'+'</body></html>'
testemail.attach(MIMEText(embimg, 'html','utf-8'))
session = smtplib.SMTP('smtp.gmail.com', 587, None, 30)
session.starttls()
session.login(sender_email, pw)
session.set_debuglevel(1)
text = testemail.as_string()
session.sendmail(sender_email, target_email, text)
session.quit()
rec_dict = {"Date":today, "Recipient":target_email, "URL":url, "Email_type":etype}
nedf = pd.DataFrame(rec_dict, index=[0])
upd_edf = edf.append(nedf, ignore_index = True)
upd_edf.to_csv('email_records.csv', index = False)
st.write("Email for "+str(url)+" sent to "+str(target_email))
# coding=UTF-8
import pandas as pd
from yandex.Translater import Translater
import time
import requests
tr = Translater()
tr.set_key('put Yandex translator key here')
tr.set_from_lang('en')
tr.set_to_lang('ru')
dfru = pd.read_csv('Names_List/FakeNameGenerator_ru.csv')
dfen = pd.read_csv('Names_List/FakeNameGenerator_en.csv')
ru_names = pd.read_csv('Names_List/final_merged_ru_names_list.csv')
# ru_fam = pd.read_csv('Names_List/russian_surnames.csv', delimiter=';', index_col=0)
ru_male_names = set(
s.replace('ё', 'е').replace(chr(769), '').lower() for s in ru_names[ru_names['sex'] == 'male']['names'])
ru_male_surnames_endings = set(
s.replace(chr(769), '')[-2:].replace('ё', 'е').lower() for s in dfru[dfru['Gender'] == 'male']['Surname'])
ru_female_names = set(
s.replace('ё', 'е').replace(chr(769), '').lower() for s in ru_names[ru_names['sex'] == 'female']['names'])
ru_female_surnames_endings = set(
s.replace(chr(769), '')[-2:].replace('ё', 'е').lower() for s in dfru[dfru['Gender'] == 'female']['Surname'])
ru_female_surnames_endings.remove('ов')
en_male_names = set(
s.replace('ё', 'е').replace(chr(769), '').lower() for s in dfen[dfen['Gender'] == 'male']['GivenName'])
return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Thresholding
def thresholding(image):
return cv2.threshold(image, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
# Set enviroment variable with path to tesseract trained data
os.environ["TESSDATA_PREFIX"] = "data"
# Setup spellchecker
spell = SpellChecker()
# Setup translater
translater = Translater()
translater.set_key(args["apikey"])
translater.set_from_lang('en')
translater.set_to_lang('ru')
# Load the input image and grab the image dimensions
image = cv2.imread(args["image"])
orig = image.copy()
(origH, origW) = image.shape[:2]
# Set the new width and height and then determine the ratio in change
# for both the width and height
(newW, newH) = (args["width"], args["height"])
rW = origW / float(newW)
rH = origH / float(newH)
def traduceEplan(cadenaEntrada):
"""esta funcion va a devolver la cadena compuesta y traducida a partir de una cadena de entrada"""
#print "----> " + str(cadenaEntrada)
cadenaEntrada = str(cadenaEntrada)
cadEs = "es_ES@" + cadenaEntrada + ';'
#Primero traduccion al ingles
apiTranslateEplan = """trnsl.1.1.20190308T091207Z.xxx"""
tr = Translater()
tr.set_key(apiTranslateEplan)
tr.set_from_lang('es')
tr.set_to_lang('en')
tr.set_text(cadenaEntrada)
cadEng = "en_US@" + tr.translate() + ";"
# #Frances
tr.set_to_lang('fr')
tr.set_text(cadenaEntrada)
cadFr = "fr_FR@" + tr.translate() + ";"
cadFr = cadFr.replace("'", "''")
#Aleman
tr.set_to_lang('de')
tr.set_text(cadenaEntrada)
cadAle = "de_DE@" + tr.translate() + ";"
# #Polaco
# tr.set_to_lang('pl')
# tr.set_text(cadenaEntrada)
# cadPol = "pl_PL@" + tr.translate() + ";"
cadenaSalida = cadEs + cadEng + cadFr + cadAle #+ cadPol
return (cadenaSalida)
from tkinter import *
from tkinter import scrolledtext
import pyowm
from yandex.Translater import Translater
trans = Translater()
owm = pyowm.OWM('4613a2063bd329d8886d085321fbf742')
weather_wind_azimut = ""
def clicked():
txt.delete(1.0, END)
trans.set_key(
'trnsl.1.1.20190719T155509Z.1bbb471edc0c0bc1.0a6d2b3a0871e6a62f32efb3d559b0457b464c37'
)
trans.set_from_lang('en')
trans.set_to_lang('ru')
trans.set_default_ui('ru')
observation = owm.weather_at_place(input1.get())
w = observation.get_weather()
weather_satus = w.get_detailed_status()
weather_wind_speed = w.get_wind()['speed']
weather_wind_deg = int(w.get_wind()['deg'])
if 0 <= weather_wind_deg < 90:
weather_wind_azimut = "Северный"
elif 90 <= weather_wind_deg < 180:
weather_wind_azimut = "Восточный"
elif 180 <= weather_wind_deg < 270:
weather_wind_azimut = "Южный"
elif 270 <= weather_wind_deg < 359:
weather_wind_azimut = "Западный"
def batcher(params, batch):
import tensorflow as tf
import tensorflow_hub as hub
import re
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
import os
from yandex.Translater import Translater
tr = Translater()
tr.set_key(
'trnsl.1.1.20190129T181632Z.6ad260c3f03e55a5.ae512973f3fa9c42fec01e4218fb4efd03a61a1b'
) # Api key found on https://translate.yandex.com/developers/keys
tr.set_from_lang('ru')
tr.set_to_lang('en')
module_url = "https://tfhub.dev/google/universal-sentence-encoder/2"
embed = hub.Module(module_url)
l = len(batch)
for i in range(l):
tr.set_text(batch[i])
sentence = tr.translate()
batch[i] = sentence
messages = batch
with tf.Session() as session:
session.run(
[tf.global_variables_initializer(),
tf.tables_initializer()])
message_embeddings = session.run(embed(messages))
embeddings = format(message_embeddings)
return embeddings
def init_yandex_service():
tr = Translater()
tr.set_key(initdata.yandex_token())
tr.set_from_lang('en')
tr.set_to_lang('ru')
return tr
def detect_language(texte):
tr = Translater()
tr.set_key(parameters.yandex_api_key())
tr.set_text(texte)
tr.set_hint("fr", "en")
return tr.detect_lang()
#application = Flask(__name__)
import time
import cloudmersive_ocr_api_client
from cloudmersive_ocr_api_client.rest import ApiException
from pprint import pprint
import yake
import spacy
import pytextrank
from pymongo import MongoClient
from gensim.summarization.summarizer import summarize
from gensim.summarization import keywords
from yandex.Translater import Translater
tr = Translater()
tr.set_key(
'trnsl.1.1.20200229T030530Z.d16dc45c4ba5761f.aebee0a45aab9956dae437936242065f92ab5b0b'
)
try:
conn = MongoClient()
print("Connected successfully!!!")
except:
print("Could not connect to MongoDB")
# database
db = conn.database
collection = db.english_doc
collection.delete_many({})