menzenski

#! /usr/bin/env python
# -*- coding: utf-8 -*-

import nltk
from nltk.stem import SnowballStemmer
from nltk import FreqDist
import codecs

def print_list(mylist):
    '''Print a list containing unicode characters.'''

menzenski

#! /usr/bin/env python
# -*- coding: utf-8 -*-

import nltk
from nltk.stem import SnowballStemmer
from nltk import FreqDist
import codecs
import glob
from diminutivefinder_04_asclass import DiminutiveFinder
import matplotlib.pyplot as plt

menzenski

#! /usr/bin/env python
# -*- coding: utf-8 -*-

from __future__ import division
import nltk
from nltk.stem import SnowballStemmer
from nltk import FreqDist
import codecs
import glob
from diminutivefinder_04_asclass import DiminutiveFinder

menzenski

\newcommand{\trans}[1]{{\em #1}}    % RUSSIAN TRANSLITERATION
\newcommand{\engl}[1]{`#1'}         % ENGLISH TRANSLATION

menzenski

\section{Discussion}

This small-scale analysis shows that there is not a significant difference in
the durations of the relative pronoun \trans{\v{s}to} and the interrogative 
pronoun \trans{\v{s}to}, nor is there a significant difference in the durations 
of the \trans{\v{s}to} of complex conjunctions such as  \trans{potomu \v{s}to} 
\engl{because} and the \trans{\v{s}to} of the hypothetical subordinator 
\trans{\v{s}toby}. However, there is a statistically significant difference in 
the durations of these two sorts of \trans{\v{s}to}, i.e., of \trans{\v{s}to} 
as an independent pronoun and \trans{\v{s}to} as part of a complex conjunction 

menzenski

139942 tokens
20123 distinct stems
2589 diminutives
684 distinct possible diminutive stems

menzenski

лиц 202
буфетчик 72
наконец 66
ник 66
лестниц 44
аннушк 41
улиц 34
милиц 33
пок 33
маленьк 31

menzenski

def save_results(dictionary):
    """Save the list of possible diminutive stems in a text file."""
    # generate a file name for the saved list of diminutive stems
    list_of_dim_stems = 'diminutive_stems.txt'
    # write the list of diminutive stems to that file
    with codecs.open(list_of_dim_stems, "w", encoding="utf-8") as stream:
        for item in dictionary.keys():
		    word = item
		    freq = dictionary[item]
		    stream.write("%s %r\n" % (word, freq))

menzenski

dim_fd = FreqDist(diminutives)

menzenski

from nltk import FreqDist