wolframalpha

# this should work - confirm it !!
def get_lists(filename='evaluation3_without\n.txt')
    with open(filename, 'r') as outfile:
        # filename of the file w/o '\n'
        lines = outfile.readlines()
        data_list = [eval(lists.strip('\n')) for index, lists in enumerate(lines) if (index+1)%2 == 0]
    return data_list

wolframalpha

# coding: utf-8

import pickle
import re
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
import numpy as np
import pandas as pd
from nltk.tag import pos_tag, pos_tag_sents
from nltk.tokenize import word_tokenize
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer

wolframalpha

dateextractor

Basic Example is given in the DateFinder.py file itself!

from DateExtractor import DateFinder

df = DateFinder()

# This `find_dates(text)` returns a list of datetime objects taking a string/buffer as a parameter 
date_list = df.find_dates('<foobar> (oct 2013 to december 2014) </foobar>')

wolframalpha

http://stackoverflow.com/questions/23322674/how-to-improve-speed-with-stanford-nlp-tagger-and-nltk

wolframalpha

{% load staticfiles %}<!-- 
<script type="text/javascript" src="http://google-maps-utility-library-v3.googlecode.com/svn/trunk/markerwithlabel/src/markerwithlabel.js"></script> -->
<script type="text/javascript">
 
function inherits(childCtor, parentCtor) {
  /** @constructor */
  function tempCtor() {};
  tempCtor.prototype = parentCtor.prototype;
  childCtor.superClass_ = parentCtor.prototype;
  childCtor.prototype = new tempCtor();

wolframalpha

> Official Google news API - depreciated 
Alternative: 
  - https://newsapi.org/
    - Free to use while not clearly mentioned when the limit is breached
    - Mulitple&Huge news sources - can explicit select one of those https://newsapi.org/sources
    - Key/Pair auth
    - response type: JSON
    
> Google finance API - depriciated/ Yahoo finance API - depreciated
Alternative:

wolframalpha

import itertools
import pandas as pd
from pyspark.ml.linalg import Vectors
from pyspark.ml.feature import VectorAssembler
from pyspark.ml import Pipeline
from pyspark.ml.regression import LinearRegression

results = []
# START ----- VARIABLES
mandatory_columns = set(['Log_Price'])

wolframalpha

from pyspark.sql.functions import udf
from pyspark.sql.types import *

schema = StructType([
    StructField("foo", FloatType(), False),
    StructField("bar", FloatType(), False)
])
udf(function(), schema)

wolframalpha

from pyspark import SparkConf,SparkContext
from pyspark.sql.functions import *
from pyspark.sql import *
from pyspark.sql.types import *

configs = [('spark.eventLog.enabled', 'true'),
 ('spark.dynamicAllocation.minExecutors', '8'),
 ('spark.executor.instances', '1000'),
 ('spark.driver.host', '10.142.0.3'),
 ('spark.yarn.am.memory', '640m'),

wolframalpha

#!/bin/bash
VM=$1
OPS=$2
NODES=$4
ZONE=$3

vms=($VM-m)

for (( i=0 ; i<$NODES-1; i++ ))
do