interrogator

# keyword calculation for a particular word

# our aim is to use log likelihood to calculate the 'keyness' of a word. common practice.
# a normal application would be to loop through wordlists and gives every word a keyness score.
# here, we'll just get 'apple', as an example

# reference_corpus = a dictionary of words and their frequencies in a large dataset
# target_corpus = a dictionary of words and their frequencies in a smaller dataset

# our example word

interrogator

from setuptools import setup, find_packages
from setuptools.command.install import install

class install_with_nltk_extras(install):
    """Customized setuptools install command - prints a friendly greeting."""
    def run(self):
        install.run(self)
        import nltk
        nltk.download('punkt')
        nltk.download('wordnet')

interrogator

% gobble allows you to indent in your tex file
% rerun code only if it changes
\usepackage[gobble=auto,rerun=modified]{pythontex}

% a figure showing code and the image it produces

\begin{figure}[htb!]

% make a text box
\begin{mdframed}[backgroundcolor=gray!4] \footnotesize \singlespacing

interrogator

import pickle
import os
bnc = pickle.load(open('bnc.p', 'rb'))
lst = ['clinic', 'hospital', 'patient']
for w in lst:
    print '%s: %d occurrences' % ( w, bnc[w])

interrogator

LET us go then, you and I,	
When the evening is spread out against the sky	
Like a patient etherized upon a table;	
Let us go, through certain half-deserted streets,	
The muttering retreats	        5
Of restless nights in one-night cheap hotels	
And sawdust restaurants with oyster-shells:	
Streets that follow like a tedious argument	
Of insidious intent	
To lead you to an overwhelming question….	        10

interrogator

#!/usr/bin/python

def nextbus(where = 'u', walking_time = 3, nbus = 5):
    """tells you when the next bus is from home or to uni

    where: 'h'/'u'
    walking_time: don't show buses less than n mins from now
    nbus: show next n buses
    """
    walking_time = int(walking_time)

interrogator

#!/usr/bin/python

def nextbus(where = 'guess', nbus = 5, walking_time = 3):
    """
    tells you when the next bus is from home or to uni

    where: 'h'/'u'/'guess': home, uni, or try to guess based on wifi connection name
    walking_time: don't show buses less than n mins from now
    nbus: show next n buses

interrogator

# a list of ints
l = [4, 2, 6, 7, 8, 1, 50, 23, 13, 55, 12, 3]

# one line to sort them!
[l.insert(ind, l.pop(l.index(min(l[ind:])))) for ind in range(len(l))]

# see?
print(l)

# elaborated code

interrogator

from corpkit import *
corpus = corpus('corpus_name')
langmod = corpus.make_language_model('modelname')

# score string
langmod.score('Check similarity for this text to each corpus')

# score file
corpus_file = corpus.subcorpora[5].files[1]
langmod.score(corpus_file)

interrogator

%matplotlib notebook
import seaborn as sns
import numpy as np
from scipy.spatial.distance import pdist
from scipy.cluster.hierarchy import linkage, dendrogram

# pdist can be 'braycurtis', 'canberra', 'chebyshev', 'cityblock', 'correlation', 'cosine', 
# 'dice', 'euclidean', 'hamming', 'jaccard', 'kulsinski', 'mahalanobis', 'matching', 
#'minkowski', 'rogerstanimoto', 'russellrao', 'seuclidean', 'sokalmichener', 'sokalsneath', 'sqeuclidean', 'yule'