cigrainger

i <- seq(1, numberguesses)
result <- apply(i, function(x){
        a = random(1,10000000)
        b = random(a,10000001)
        cond_exp <- CONEXP(a,b)
        cond_exp <- cond_exp[cond_exp is within .1% of actual expected value]
        return (cond_exp)
  }
)

cigrainger

library(readr)
library(dplyr)
df <- read_csv('~/desktop/guns.csv')

library(ggplot2)
library(ggthemes)
df %>%
  arrange(desc(guns_per_100_people)) %>% 
  top_n(n = 20, wt = guns_per_100_people) %>% 
  ggplot(aes(x = country, 

cigrainger

library(quanteda)
library(dplyr)
library(tidyr)
library(networkD3)

load(url("http://www.kenbenoit.net/files/presDebateCorpus2016seg.RData"))
candidates <- subset(presDebateCorpus2016seg, speakertype == 'candidate')
dfm <- dfm(candidates, groups = c("tag"), ngrams = 1:3,
           ignoredFeatures = c('people','go','going','will','know','think',
                               'country','get','applause','want','need',

cigrainger

temp_precip = []
for i,p in enumerate(correct_precip):
    if i % 6 == 0:
        temp_precip.append(p)
    else:
        temp_precip.append(p-correct_precip[i-1])
    if i % 10000 == 0:
        print i

cigrainger

correct_precip = []
for t in df.DateTime:
    if t.hour not in [0,6,12,18]:
        precip_1 = df.precip[df.DateTime==t]-df.precip[df.DateTime==t-relativedelta(hours=1)]
        dat = {'DateTime' : t, 'precipitation' : precip_1}
        correct_precip.append(dat)
    else:
        dat = {'DateTime' : t, 'precipitation' : df.precip[df.DateTime==t]}
        correct_precip.append(dat)

cigrainger

# head(postcodes)
#  postcode latitude longitude
#1     SK17 53.24400 -1.879000
#2     OX15 52.05515 -1.429983
#3      BA8 51.01226 -2.411274
#4     CB21 52.12717  0.272036
#5     CA13 54.66000 -3.366000
#6      CH7 53.6900  -3.133000
#
# head(latlon)

cigrainger

test

cigrainger

val documents: RDD[(Long, Vector)] =
  tokenized.zipWithIndex.map { case (tokens, id) =>
    val counts = new mutable.HashMap[Int, Double]()
    tokens.foreach { term =>
      if (vocab.contains(term)) {
        val idx = vocab(term)
        counts(idx) = counts.getOrElse(idx, 0.0) + 1.0
      }
    }
    (id, Vectors.sparse(vocab.size, counts.toSeq))

cigrainger

from nltk.corpus import stopwords
from nltk import wordpunct_tokenize
from nltk.tokenize import RegexpTokenizer
from nltk.stem import WordNetLemmatizer
import nltk.data
import re

tagger = nltk.data.load("trained_brill.pickle")
tokenizer = RegexpTokenizer(r'\w+')
quoted = re.compile('"[^"]*"')

cigrainger

try:
    features_list = driver.find_elements_by_class_name('detail_attrs')
except:
    i = 1
    while i < 10:
        sleep(5)
        try:
            features_list = driver.find_elements_by_class_name('detail_attrs')
        except:
            i += 1