tekknolagi

#!/usr/bin/env python

import multiprocessing
import random
import time


class Logger:
    def __init__(self, num_lines, last_output_per_process, terminal_lock):
        self.num_lines = num_lines

BrambleXu

from collections import OrderedDict
import numpy as np
import spacy
from spacy.lang.en.stop_words import STOP_WORDS

nlp = spacy.load('en_core_web_sm')

class TextRank4Keyword():
    """Extract keywords from text"""
    

rainabba

#!/bin/bash
#
#This script assumes very little other than a fresh Ubuntu install (using the Windows store) on Win10 1709 or newer with WSL installed already
#In Powershell, run the following to install WSL and Ubuntu
#
#Enable-WindowsOptionalFeature -Online -FeatureName Microsoft-Windows-Subsystem-Linux
#Invoke-WebRequest -Uri https://aka.ms/wsl-ubuntu-1604 -OutFile ~/Ubuntu.zip -UseBasicParsing
#Expand-Archive ~/Ubuntu.zip ~/Ubuntu
#~/Ubuntu/ubuntu.exe
#

simoncos

refer to: https://stackoverflow.com/questions/39371772/how-to-install-anaconda-on-raspberry-pi-3-model-b

{USER}: pi

Install Miniconda 3:

wget http://repo.continuum.io/miniconda/Miniconda3-latest-Linux-armv7l.sh
sudo md5sum Miniconda3-latest-Linux-armv7l.sh # (optional) check md5
sudo /bin/bash Miniconda3-latest-Linux-armv7l.sh # -> change default directory to /home/pi/miniconda3

BrikerMan

from gensim.models import KeyedVectors

# Load gensim word2vec
w2v_path = '<Gensim File Path>'
w2v = KeyedVectors.load_word2vec_format(w2v_path)

import io

# Vector file, `\t` seperated the vectors and `\n` seperate the words
"""

benrules2

import random
import sys

def build_chain(text, chain = {}):
    words = text.split(' ')
    index = 1
    for word in words[index:]:
        key = words[index - 1]
        if key in chain:
            chain[key].append(word)

aneesha

from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.decomposition import NMF, LatentDirichletAllocation
import numpy as np

def display_topics(H, W, feature_names, documents, no_top_words, no_top_documents):
    for topic_idx, topic in enumerate(H):
        print "Topic %d:" % (topic_idx)
        print " ".join([feature_names[i]
                        for i in topic.argsort()[:-no_top_words - 1:-1]])
        top_doc_indices = np.argsort( W[:,topic_idx] )[::-1][0:no_top_documents]

bgusach

def multireplace(string, replacements, ignore_case=False):
    """
    Given a string and a replacement map, it returns the replaced string.

    :param str string: string to execute replacements on
    :param dict replacements: replacement dictionary {value to find: value to replace}
    :param bool ignore_case: whether the match should be case insensitive
    :rtype: str

    """

jesslilly

Cron Job Wrapper Wish List

I want a script that will give me:

1. Logging
2. Log purging!
3. Email errors!
4. Prevent duplicate processes! (flock)
5. Source an environment file!
6. Anything else?

tfoldi

# CoffeeScript version of Google Spreadsheet Driver for Tableau Data Web Connector

init = ->
  if !tableau
    alert 'init- tableau NOT defined!'
    return
  tableau.scriptVersion = '1.0'
  tableau.log 'init'
  tableau.initCallback()