# -*- coding: utf-8 -*- #!/usr/bin/python2.7 -S # python -m spacy.en.download python -m spacy.de.download # https://spacy.io/docs/#tutorials # CSS: http://codepen.io/explosion/pen/xEpgKz # CSS 2: https://explosion.ai/blog/displacy-ent-named-entity-visualizer import time start_time = time.time() # pip install --upgrade thinc # pip3 install suds-jurko import spacy #import base64 import json #import site import codecs import locale import shelve import gensim, logging import pprint import os.path #import sphinxapi as SP from sphinxapi import * # pip install --upgrade mysql-python import MySQLdb logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO) # pip3 install --upgrade spacy # apt-get install python3-pip # pip install --upgrade pip # pip3 install --upgrade pip3 # pip install -U textblob # python -m textblob.download_corpora # pip install --upgrade langdetect # pip install -U textblob-de # python -m textblob.download_corpora #from textblob_de import TextBlobDE as TextBlob from langdetect import detect #from textblob_de import TextBlobDE #from textblob import TextBlob from libleipzig import * # pip install --upgrade libleipzig # pip install --upgrade libleipzig # pip3 install --upgrade libleipzig # pip install --upgrade pattern import sys, time # import sys package, if not already imported reload(sys) sys.setdefaultencoding('utf-8') #sys.stdout = codecs.getwriter(locale.getpreferredencoding())(sys.stdout) path = "/home/100biere/100BIERE_model.bin" ###print ("Calculating Word2Vec for Input Word: "+ word) #model = gensim.models.Word2Vec(sentences, min_count=1, iter=300, size=500, workers=4, sorted_vocab=1, batch_words=500, alpha=0.035) model_load = gensim.models.Word2Vec.load(path) model = gensim.models.Word2Vec(model_load, hs=1, iter=1000, size=400, workers=4, sorted_vocab=1, alpha=0.055, min_count=1) model.init_sims(replace=False) # can read,write from, and also training -> more memory #model.init_sims(replace=True) # can only read from, but no more training -> less memory model.save(path) print("Script Runtime: --- %s seconds ---" % (time.time() - start_time)) sys.exit(0)