davidlenz

import stop_words
from langdetect import detect
import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords
import ast

davidlenz

import spacy

settings.LEMMATIZER_BATCH_SIZE = 250
settings.LEMMATIZER_N_THREADS = -1

nlp = spacy.load('de')
nlp.disable_pipes('tagger', 'ner')

def spacy_lemmatizer(text, nlp):
    """text is a list of string. nlp is a spacy nlp object. Use nlp.disable_pipes('tagger','ner') to speed up lemmatization"""

davidlenz

from textblob_de import TextBlobDE as TextBlob

def textblob_lemmatizer(doclist):
    """Takes a list of strings as input and returns a list of lemmatized strings"""
    docs=[]
    for doc in doclist:
        blob = TextBlob(doc)
        docs.append(' '.join(list(blob.words.lemmatize())))

    return docs

davidlenz

import time, os
import arxiv

QUERY = 'ECB'
NUM_RESULTS = 10 # 
SLEEPTIME = 0.1 # seconds
savedir = './arxiv_papers/{}/'.format(QUERY)

if not os.path.exists(savedir):
    os.makedirs(savedir)

davidlenz

import socket
import os, json
import pip, sys
import platform

env = {}

import aetros
env['aetros_version'] = aetros.__version__

davidlenz

from sklearn.datasets import fetch_20newsgroups
import pandas as pd

def twenty_newsgroup_to_csv():
    newsgroups_train = fetch_20newsgroups(subset='train', remove=('headers', 'footers', 'quotes'))

    df = pd.DataFrame([newsgroups_train.data, newsgroups_train.target.tolist()]).T
    df.columns = ['text', 'target']

    targets = pd.DataFrame( newsgroups_train.target_names)

davidlenz

import requests
import bs4 as bs
from bs4 import BeautifulSoup
import pandas as pd
import os

def get_timestamp():
    import time, datetime
    date_n_time = datetime.datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H-%M-%S')
    return date_n_time

davidlenz

#!/usr/bin/env python
from email.mime.text import MIMEText
from email.mime.application import MIMEApplication
from email.mime.multipart import MIMEMultipart
from smtplib import SMTP
import smtplib


subject = 'Example header'
message = 'Subject: Happy Australia Day!\nHi Everyone! Happy Australia Day! Cheers, Julian'

davidlenz

#Put this in Export-Chocolatey.ps1 file and run it:
#Export-Chocolatey.ps1 > packages.config
#You can install the packages using
#choco install packages.config -y

Write-Output "<?xml version=`"1.0`" encoding=`"utf-8`"?>"
Write-Output "<packages>"
choco list -lo -r -y | % { "   <package id=`"$($_.SubString(0, $_.IndexOf("|")))`" version=`"$($_.SubString($_.IndexOf("|") + 1))`" />" }
Write-Output "</packages>"

davidlenz

import time
import boto3

job_queue = <'job-queue-name'>

client=boto3.client("batch")
states = ['RUNNABLE','SUBMITTED','PENDING','STARTING','RUNNING']

for state in states:
    print(state)