def edit(self, *args, **kwargs):
"""Delete or keep rows by subcorpus or by middle column text.
>>> skipped = conc.edit(skip_entries=r'to_?match')"""
from corpkit.editor import editor
return editor(self, *args, **kwargs)
def edit(self, *args, **kwargs):
"""
Delete or keep rows by subcorpus or by middle column text.
>>> skipped = conc.edit(skip_entries=r'to_?match')
"""
from corpkit.editor import editor
return editor(self, *args, **kwargs)
def edit(self, *args, **kwargs):
"""Edit each value with :func:`~corpkit.interrogation.Interrogation.edit`.
See :func:`~corpkit.interrogation.Interrogation.edit` for possible arguments.
:returns: A :class:`corpkit.interrogation.Interrodict`
"""
from corpkit.editor import editor
return editor(self, *args, **kwargs)
def edit(self, *args, **kwargs):
"""Edit each value with :func:`~corpkit.interrogation.Interrogation.edit`.
See :func:`~corpkit.interrogation.Interrogation.edit` for possible arguments.
:returns: A :class:`corpkit.interrogation.Interrodict`
"""
from corpkit.editor import editor
return editor(self, *args, **kwargs)
def multiquery(corpus, query, sort_by = 'total', quicksave = False):
"""Creates a named tuple for a list of named queries to count.
Pass in something like:
[[u'NPs in corpus', r'NP'], [u'VPs in corpus', r'VP']]"""
import collections
import os
import pandas
import pandas as pd
from time import strftime, localtime
from corpkit.interrogator import interrogator
from corpkit.editor import editor
if quicksave:
savedir = 'data/saved_interrogations'
if not quicksave.endswith('.p'):
quicksave = quicksave + '.p'
fullpath = os.path.join(savedir, quicksave)
while os.path.isfile(fullpath):
selection = raw_input("\nSave error: %s already exists in %s.\n\nPick a new name: " % (savename, savedir))
if not selection.endswith('.p'):
selection = selection + '.p'
fullpath = os.path.join(savedir, selection)
results = []
for name, pattern in query:
result = interrogator(corpus, 'count', pattern)
result.totals.name = name # rename count
results.append(result.totals)
results = pd.concat(results, axis = 1)
results = editor(results, sort_by = sort_by, print_info = False, keep_stats = False)
time = strftime("%H:%M:%S", localtime())
print '%s: Finished! %d unique results, %d total.' % (time, len(results.results.columns), results.totals.sum())
if quicksave:
from corpkit.other import save_result
save_result(results, quicksave)
return results
def interrogation_from_conclines(newdata):
"""
Make new interrogation result from its conc lines
"""
from collections import Counter
from pandas import DataFrame
from corpkit.editor import editor
results = {}
conc = newdata
subcorpora = list(set(conc['c']))
for subcorpus in subcorpora:
counted = Counter(list(conc[conc['c'] == subcorpus]['m']))
results[subcorpus] = counted
the_big_dict = {}
unique_results = set([item for sublist in list(results.values()) for item in sublist])
for word in unique_results:
the_big_dict[word] = [subcorp_result[word] for name, subcorp_result \
in sorted(results.items(), key=lambda x: x[0])]
# turn master dict into dataframe, sorted
df = DataFrame(the_big_dict, index=sorted(results.keys()))
df = editor(df, sort_by='total', print_info=False)
df.concordance = conc
return df
def interrogator(corpus,
search='w',
query='any',
show='w',
exclude=False,
excludemode='any',
searchmode='all',
case_sensitive=False,
save=False,
subcorpora=False,
just_metadata=False,
skip_metadata=False,
preserve_case=False,
lemmatag=False,
files_as_subcorpora=False,
only_unique=False,
only_format_match=True,
multiprocess=False,
spelling=False,
regex_nonword_filter=r'[A-Za-z0-9]',
gramsize=1,
conc=False,
maxconc=9999,
window=None,
no_closed=False,
no_punct=True,
discard=False,
**kwargs):
"""
Interrogate corpus, corpora, subcorpus and file objects.
See corpkit.interrogation.interrogate() for docstring
"""
conc = kwargs.get('do_concordancing', conc)
quiet = kwargs.get('quiet', False)
coref = kwargs.pop('coref', False)
show_conc_metadata = kwargs.pop('show_conc_metadata', False)
fsi_index = kwargs.pop('fsi_index', True)
dep_type = kwargs.pop('dep_type', 'collapsed-ccprocessed-dependencies')
nosubmode = subcorpora is None
#todo: temporary
#if getattr(corpus, '_dlist', False):
# subcorpora = 'file'
# store kwargs and locs
locs = locals().copy()
locs.update(kwargs)
locs.pop('kwargs', None)
import codecs
import signal
import os
from time import localtime, strftime
from collections import Counter
import pandas as pd
from pandas import DataFrame, Series
from corpkit.interrogation import Interrogation, Interrodict
from corpkit.corpus import Datalist, Corpora, Corpus, File, Subcorpus
from corpkit.process import (tregex_engine, get_deps, unsplitter, sanitise_dict,
animator, filtermaker, fix_search,
pat_format, auto_usecols, format_tregex,
make_conc_lines_from_whole_mid)
from corpkit.other import as_regex
from corpkit.dictionaries.process_types import Wordlist
from corpkit.build import check_jdk
from corpkit.conll import pipeline
from corpkit.process import delete_files_and_subcorpora
have_java = check_jdk()
# remake corpus without bad files and folders
corpus, skip_metadata, just_metadata = delete_files_and_subcorpora(corpus, skip_metadata, just_metadata)
# so you can do corpus.interrogate('features/postags/wordclasses/lexicon')
if search == 'features':
search = 'v'
query = 'any'
if search in ['postags', 'wordclasses']:
query = 'any'
preserve_case = True
show = 'p' if search == 'postags' else 'x'
# use tregex if simple because it's faster
# but use dependencies otherwise
search = 't' if not subcorpora and not just_metadata and not skip_metadata and have_java else {'w': 'any'}
if search == 'lexicon':
search = 't' if not subcorpora and not just_metadata and not skip_metadata and have_java else {'w': 'any'}
query = 'any'
show = ['w']
if not kwargs.get('cql') and isinstance(search, STRINGTYPE) and len(search) > 3:
raise ValueError('search argument not recognised.')
import re
if regex_nonword_filter:
is_a_word = re.compile(regex_nonword_filter)
else:
is_a_word = re.compile(r'.*')
from traitlets import TraitError
# convert cql-style queries---pop for the sake of multiprocessing
cql = kwargs.pop('cql', None)
if cql:
from corpkit.cql import to_corpkit
search, exclude = to_corpkit(search)
def signal_handler(signal, _):
"""
Allow pausing and restarting whn not in GUI
"""
if root:
return
import signal
import sys
from time import localtime, strftime
signal.signal(signal.SIGINT, original_sigint)
thetime = strftime("%H:%M:%S", localtime())
INPUTFUNC('\n\n%s: Paused. Press any key to resume, or ctrl+c to quit.\n' % thetime)
time = strftime("%H:%M:%S", localtime())
print('%s: Interrogation resumed.\n' % time)
signal.signal(signal.SIGINT, signal_handler)
def add_adj_for_ngram(show, gramsize):
"""
If there's a gramsize of more than 1, remake show
for ngramming
"""
if gramsize == 1:
return show
out = []
for i in show:
out.append(i)
for i in range(1, gramsize):
for bit in show:
out.append('+%d%s' % (i, bit))
return out
def fix_show_bit(show_bit):
"""
Take a single search/show_bit type, return match
"""
ends = ['w', 'l', 'i', 'n', 'f', 'p', 'x', 's', 'a', 'e', 'c']
starts = ['d', 'g', 'm', 'b', 'h', '+', '-', 'r', 'c']
show_bit = show_bit.lstrip('n')
show_bit = show_bit.lstrip('b')
show_bit = list(show_bit)
if show_bit[-1] not in ends:
show_bit.append('w')
if show_bit[0] not in starts:
show_bit.insert(0, 'm')
return ''.join(show_bit)
def fix_show(show, gramsize):
"""
Lowercase anything in show and turn into list
"""
if isinstance(show, list):
show = [i.lower() for i in show]
elif isinstance(show, STRINGTYPE):
show = show.lower()
show = [show]
show = [fix_show_bit(i) for i in show]
return add_adj_for_ngram(show, gramsize)
def is_multiquery(corpus, search, query, outname):
"""
Determine if multiprocessing is needed/possibe, and
do some retyping if need be as well
"""
is_mul = False
from collections import OrderedDict
from corpkit.dictionaries.process_types import Wordlist
if isinstance(query, Wordlist):
query = list(query)
if subcorpora and multiprocess:
is_mul = 'subcorpora'
if isinstance(subcorpora, (list, tuple)):
is_mul = 'subcorpora'
if isinstance(query, (dict, OrderedDict)):
is_mul = 'namedqueriessingle'
if isinstance(search, dict):
if all(isinstance(i, dict) for i in list(search.values())):
is_mul = 'namedqueriesmultiple'
return is_mul, corpus, search, query
def ispunct(s):
import string
return all(c in string.punctuation for c in s)
def uniquify(conc_lines):
"""get unique concordance lines"""
from collections import OrderedDict
unique_lines = []
checking = []
for index, (_, speakr, start, middle, end) in enumerate(conc_lines):
joined = ' '.join([speakr, start, 'MIDDLEHERE:', middle, ':MIDDLEHERE', end])
if joined not in checking:
unique_lines.append(conc_lines[index])
checking.append(joined)
return unique_lines
def compiler(pattern):
"""
Compile regex or fail gracefully
"""
if hasattr(pattern, 'pattern'):
return pattern
import re
try:
if case_sensitive:
comped = re.compile(pattern)
else:
comped = re.compile(pattern, re.IGNORECASE)
return comped
except:
import traceback
import sys
from time import localtime, strftime
exc_type, exc_value, exc_traceback = sys.exc_info()
lst = traceback.format_exception(exc_type, exc_value, exc_traceback)
error_message = lst[-1]
thetime = strftime("%H:%M:%S", localtime())
print('%s: Query %s' % (thetime, error_message))
if root:
return 'Bad query'
else:
raise ValueError('%s: Query %s' % (thetime, error_message))
def determine_search_func(show):
"""Figure out what search function we're using"""
simple_tregex_mode = False
statsmode = False
tree_to_text = False
search_trees = False
simp_crit = all(not i for i in [kwargs.get('tgrep'),
files_as_subcorpora,
subcorpora,
just_metadata,
skip_metadata])
if search.get('t') and simp_crit:
if have_java:
simple_tregex_mode = True
else:
search_trees = 'tgrep'
optiontext = 'Searching parse trees'
elif datatype == 'conll':
if any(i.endswith('t') for i in search.keys()):
if have_java and not kwargs.get('tgrep'):
search_trees = 'tregex'
else:
search_trees = 'tgrep'
optiontext = 'Searching parse trees'
elif any(i.endswith('v') for i in search.keys()):
# either of these searchers now seems to work
#seacher = get_stats_conll
statsmode = True
optiontext = 'General statistics'
elif any(i.endswith('r') for i in search.keys()):
optiontext = 'Distance from root'
else:
optiontext = 'Querying CONLL data'
return optiontext, simple_tregex_mode, statsmode, tree_to_text, search_trees
def get_tregex_values(show):
"""If using Tregex, set appropriate values
- Check for valid query
- Make 'any' query
- Make list query
"""
translated_option = 't'
if isinstance(search['t'], Wordlist):
search['t'] = list(search['t'])
q = tregex_engine(corpus=False,
query=search.get('t'),
options=['-t'],
check_query=True,
root=root,
preserve_case=preserve_case
)
# so many of these bad fixing loops!
nshow = []
for i in show:
if i == 'm':
nshow.append('w')
else:
nshow.append(i.lstrip('m'))
show = nshow
if q is False:
if root:
return 'Bad query', None
else:
return 'Bad query', None
if isinstance(search['t'], list):
regex = as_regex(search['t'], boundaries='line', case_sensitive=case_sensitive)
else:
regex = ''
# listquery, anyquery, translated_option
treg_dict = {'p': [r'__ < (/%s/ !< __)' % regex, r'__ < (/.?[A-Za-z0-9].?/ !< __)', 'u'],
'pl': [r'__ < (/%s/ !< __)' % regex, r'__ < (/.?[A-Za-z0-9].?/ !< __)', 'u'],
'x': [r'__ < (/%s/ !< __)' % regex, r'__ < (/.?[A-Za-z0-9].?/ !< __)', 'u'],
't': [r'__ < (/%s/ !< __)' % regex, r'__ < (/.?[A-Za-z0-9].?/ !< __)', 'o'],
'w': [r'/%s/ !< __' % regex, r'/.?[A-Za-z0-9].?/ !< __', 't'],
'c': [r'/%s/ !< __' % regex, r'/.?[A-Za-z0-9].?/ !< __', 'C'],
'l': [r'/%s/ !< __' % regex, r'/.?[A-Za-z0-9].?/ !< __', 't'],
'u': [r'/%s/ !< __' % regex, r'/.?[A-Za-z0-9].?/ !< __', 'v']
}
newshow = []
listq, anyq, translated_option = treg_dict.get(show[0][-1].lower())
newshow.append(translated_option)
for item in show[1:]:
_, _, noption = treg_dict.get(item.lower())
newshow.append(noption)
if isinstance(search['t'], list):
search['t'] = listq
elif search['t'] == 'any':
search['t'] = anyq
return search['t'], newshow
def correct_spelling(a_string):
"""correct spelling within a string"""
if not spelling:
return a_string
from corpkit.dictionaries.word_transforms import usa_convert
if spelling.lower() == 'uk':
usa_convert = {v: k for k, v in list(usa_convert.items())}
bits = a_string.split('/')
for index, i in enumerate(bits):
converted = usa_convert.get(i.lower(), i)
if i.islower() or preserve_case is False:
converted = converted.lower()
elif i.isupper() and preserve_case:
converted = converted.upper()
elif i.istitle() and preserve_case:
converted = converted.title()
bits[index] = converted
r = '/'.join(bits)
return r
def make_search_iterable(corpus):
"""determine how to structure the corpus for interrogation"""
# skip file definitions if they are not needed
if getattr(corpus, '_dlist', False):
return {(i.name, i.path): [i] for i in list(corpus.files)}
#return {('Sample', 'Sample'): list(corpus.files)}
if simple_tregex_mode:
if corpus.level in ['s', 'f', 'd']:
return {(corpus.name, corpus.path): False}
else:
return {(os.path.basename(i), os.path.join(corpus.path, i)): False
for i in os.listdir(corpus.path)
if os.path.isdir(os.path.join(corpus.path, i))}
if isinstance(corpus, Datalist):
to_iterate_over = {}
# it could be files or subcorpus objects
if corpus[0].level in ['s', 'd']:
if files_as_subcorpora:
for subc in corpus:
for f in subc.files:
to_iterate_over[(f.name, f.path)] = [f]
else:
for subc in corpus:
to_iterate_over[(subc.name, subc.path)] = subc.files
elif corpus[0].level == 'f':
for f in corpus:
to_iterate_over[(f.name, f.path)] = [f]
elif corpus.singlefile:
to_iterate_over = {(corpus.name, corpus.path): [corpus]}
elif not hasattr(corpus, 'subcorpora') or not corpus.subcorpora:
# just files in a directory
if files_as_subcorpora:
to_iterate_over = {}
for f in corpus.files:
to_iterate_over[(f.name, f.path)] = [f]
else:
to_iterate_over = {(corpus.name, corpus.path): corpus.files}
else:
to_iterate_over = {}
if files_as_subcorpora:
# don't know if possible: has subcorpora but also .files
if hasattr(corpus, 'files') and corpus.files is not None:
for f in corpus.files:
to_iterate_over[(f.name, f.path)] = [f]
# has subcorpora with files in those
elif hasattr(corpus, 'files') and corpus.files is None:
for subc in corpus.subcorpora:
for f in subc.files:
to_iterate_over[(f.name, f.path)] = [f]
else:
if corpus[0].level == 's':
for subcorpus in corpus:
to_iterate_over[(subcorpus.name, subcorpus.path)] = subcorpus.files
elif corpus[0].level == 'f':
for f in corpus:
to_iterate_over[(f.name, f.path)] = [f]
else:
for subcorpus in corpus.subcorpora:
to_iterate_over[(subcorpus.name, subcorpus.path)] = subcorpus.files
return to_iterate_over
def welcome_printer(return_it=False):
"""Print welcome message"""
if no_conc:
message = 'Interrogating'
else:
message = 'Interrogating and concordancing'
if only_conc:
message = 'Concordancing'
if kwargs.get('printstatus', True):
thetime = strftime("%H:%M:%S", localtime())
from corpkit.process import dictformat
sformat = dictformat(search)
welcome = ('\n%s: %s %s ...\n %s\n ' \
'Query: %s\n %s corpus ... \n' % \
(thetime, message, cname, optiontext, sformat, message))
if return_it:
return welcome
else:
print(welcome)
def goodbye_printer(return_it=False, only_conc=False):
"""Say goodbye before exiting"""
if not kwargs.get('printstatus', True):
return
thetime = strftime("%H:%M:%S", localtime())
if only_conc:
finalstring = '\n\n%s: Concordancing finished! %s results.' % (thetime, format(len(conc_df), ','))
else:
finalstring = '\n\n%s: Interrogation finished!' % thetime
if countmode:
finalstring += ' %s matches.' % format(tot, ',')
else:
finalstring += ' %s unique results, %s total occurrences.' % (format(numentries, ','), format(total_total, ','))
if return_it:
return finalstring
else:
print(finalstring)
def get_conc_colnames(corpus,
fsi_index=False,
simple_tregex_mode=False):
fields = []
base = 'c f s l m r'
if simple_tregex_mode:
base = base.replace('f ', '')
if fsi_index and not simple_tregex_mode:
base = 'i ' + base
if PYTHON_VERSION == 2:
base = base.encode('utf-8').split()
else:
base = base.split()
if show_conc_metadata:
from corpkit.build import get_all_metadata_fields
meta = get_all_metadata_fields(corpus.path)
if isinstance(show_conc_metadata, list):
meta = [i for i in meta if i in show_conc_metadata]
#elif show_conc_metadata is True:
# pass
for i in sorted(meta):
if i in ['speaker', 'sent_id', 'parse']:
continue
if PYTHON_VERSION == 2:
base.append(i.encode('utf-8'))
else:
base.append(i)
return base
def make_conc_obj_from_conclines(conc_results, fsi_index=False):
"""
Turn conclines into DataFrame
"""
from corpkit.interrogation import Concordance
#fsi_place = 2 if fsi_index else 0
all_conc_lines = []
for sc_name, resu in sorted(conc_results.items()):
if only_unique:
unique_results = uniquify(resu)
else:
unique_results = resu
#make into series
for lin in unique_results:
#spkr = str(spkr, errors = 'ignore')
#if not subcorpora:
# lin[fsi_place] = lin[fsi_place]
#lin.insert(fsi_place, sc_name)
if len(lin) < len(conc_col_names):
diff = len(conc_col_names) - len(lin)
lin.extend(['none'] * diff)
all_conc_lines.append(Series(lin, index=conc_col_names))
try:
conc_df = pd.concat(all_conc_lines, axis=1).T
except ValueError:
return
if all(x == '' for x in list(conc_df['s'].values)) or \
all(x == 'none' for x in list(conc_df['s'].values)):
conc_df.drop('s', axis=1, inplace=True)
locs['corpus'] = corpus.name
if maxconc:
conc_df = Concordance(conc_df[:maxconc])
else:
conc_df = Concordance(conc_df)
try:
conc_df.query = locs
except AttributeError:
pass
return conc_df
def lowercase_result(res):
"""
Take any result and do spelling/lowercasing if need be
todo: remove lowercase and change name
"""
if not res or statsmode:
return res
# this is likely broken, but spelling in interrogate is deprecated anyway
if spelling:
res = [correct_spelling(r) for r in res]
return res
def postprocess_concline(line, fsi_index=False, conc=False):
# todo: are these right?
if not conc:
return line
subc, star, en = 0, 2, 5
if fsi_index:
subc, star, en = 2, 4, 7
if not preserve_case:
line[star:en] = [str(x).lower() for x in line[star:en]]
if spelling:
line[star:en] = [correct_spelling(str(b)) for b in line[star:en]]
return line
def make_progress_bar():
"""generate a progress bar"""
if simple_tregex_mode:
total_files = len(list(to_iterate_over.keys()))
else:
total_files = sum(len(x) for x in list(to_iterate_over.values()))
par_args = {'printstatus': kwargs.get('printstatus', True),
'root': root,
'note': note,
'quiet': quiet,
'length': total_files,
'startnum': kwargs.get('startnum'),
'denom': kwargs.get('denominator', 1)}
term = None
if kwargs.get('paralleling', None) is not None:
from blessings import Terminal
term = Terminal()
par_args['terminal'] = term
par_args['linenum'] = kwargs.get('paralleling')
if in_notebook:
par_args['welcome_message'] = welcome_message
outn = kwargs.get('outname', '')
if outn:
outn = getattr(outn, 'name', outn)
outn = outn + ': '
tstr = '%s%d/%d' % (outn, current_iter, total_files)
p = animator(None, None, init=True, tot_string=tstr, **par_args)
tstr = '%s%d/%d' % (outn, current_iter + 1, total_files)
animator(p, current_iter, tstr, **par_args)
return p, outn, total_files, par_args
# find out if using gui
root = kwargs.get('root')
note = kwargs.get('note')
language_model = kwargs.get('language_model')
# set up pause method
original_sigint = signal.getsignal(signal.SIGINT)
if kwargs.get('paralleling', None) is None:
if not root:
original_sigint = signal.getsignal(signal.SIGINT)
signal.signal(signal.SIGINT, signal_handler)
# find out about concordancing
only_conc = False
no_conc = False
if conc is False:
no_conc = True
if isinstance(conc, str) and conc.lower() == 'only':
only_conc = True
no_conc = False
numconc = 0
# wipe non essential class attributes to not bloat query attrib
if isinstance(corpus, Corpus):
import copy
corpus = copy.copy(corpus)
for k, v in corpus.__dict__.items():
if isinstance(v, (Interrogation, Interrodict)):
corpus.__dict__.pop(k, None)
# convert path to corpus object
if not isinstance(corpus, (Corpus, Corpora, Subcorpus, File, Datalist)):
if not multiprocess and not kwargs.get('outname'):
corpus = Corpus(corpus, print_info=False)
# figure out how the user has entered the query and show, and normalise
from corpkit.process import searchfixer
search = searchfixer(search, query)
show = fix_show(show, gramsize)
locs['show'] = show
# instantiate lemmatiser if need be
lem_instance = False
if any(i.endswith('l') for i in show) and isinstance(search, dict) and search.get('t'):
from nltk.stem.wordnet import WordNetLemmatizer
lem_instance = WordNetLemmatizer()
# do multiprocessing if need be
im, corpus, search, query, = is_multiquery(corpus, search, query,
kwargs.get('outname', False))
# figure out if we can multiprocess the corpus
if hasattr(corpus, '__iter__') and im:
corpus = Corpus(corpus, print_info=False)
if hasattr(corpus, '__iter__') and not im:
im = 'datalist'
if isinstance(corpus, Corpora):
im = 'multiplecorpora'
# split corpus if the user wants multiprocessing but no other iterable
if not im and multiprocess:
im = 'datalist'
if getattr(corpus, 'subcorpora', False):
corpus = corpus[:]
else:
corpus = corpus.files
search = fix_search(search, case_sensitive=case_sensitive, root=root)
exclude = fix_search(exclude, case_sensitive=case_sensitive, root=root)
# if it's already been through pmultiquery, don't do it again
locs['search'] = search
locs['exclude'] = exclude
locs['query'] = query
locs['corpus'] = corpus
locs['multiprocess'] = multiprocess
locs['print_info'] = kwargs.get('printstatus', True)
locs['multiple'] = im
locs['subcorpora'] = subcorpora
locs['nosubmode'] = nosubmode
# send to multiprocess function
if im:
signal.signal(signal.SIGINT, original_sigint)
from corpkit.multiprocess import pmultiquery
return pmultiquery(**locs)
# get corpus metadata
cname = corpus.name
if isinstance(save, STRINGTYPE):
savename = corpus.name + '-' + save
if save is True:
raise ValueError('save must be str, not bool.')
datatype = getattr(corpus, 'datatype', 'conll')
singlefile = getattr(corpus, 'singlefile', False)
level = getattr(corpus, 'level', 'c')
# store all results in here
from collections import defaultdict
results = defaultdict(Counter)
count_results = defaultdict(list)
conc_results = defaultdict(list)
# check if just counting, turn off conc if so
countmode = 'c' in show or 'mc' in show
if countmode:
no_conc = True
only_conc = False
# where we are at in interrogation
current_iter = 0
# multiprocessing progress bar
denom = kwargs.get('denominator', 1)
startnum = kwargs.get('startnum', 0)
# Determine the search function to be used #
optiontext, simple_tregex_mode, statsmode, tree_to_text, search_trees = determine_search_func(show)
# no conc for statsmode
if statsmode:
no_conc = True
only_conc = False
conc = False
# Set some Tregex-related values
translated_option = False
if search.get('t'):
query, translated_option = get_tregex_values(show)
if query == 'Bad query' and translated_option is None:
if root:
return 'Bad query'
else:
return
# more tregex options
if tree_to_text:
treg_q = r'ROOT << __'
op = ['-o', '-t', '-w', '-f']
elif simple_tregex_mode:
treg_q = search['t']
op = ['-%s' % i for i in translated_option] + ['-o', '-f']
# make iterable object for corpus interrogation
to_iterate_over = make_search_iterable(corpus)
try:
from ipywidgets import IntProgress
_ = IntProgress(min=0, max=10, value=1)
in_notebook = True
except TraitError:
in_notebook = False
except ImportError:
in_notebook = False
# caused in newest ipython
except AttributeError:
in_notebook = False
lemtag = False
if search.get('t'):
from corpkit.process import gettag
lemtag = gettag(search.get('t'), lemmatag)
usecols = auto_usecols(search, exclude, show, kwargs.pop('usecols', None), coref=coref)
# print welcome message
welcome_message = welcome_printer(return_it=in_notebook)
# create a progress bar
p, outn, total_files, par_args = make_progress_bar()
if conc:
conc_col_names = get_conc_colnames(corpus,
fsi_index=fsi_index,
simple_tregex_mode=False)
# Iterate over data, doing interrogations
for (subcorpus_name, subcorpus_path), files in sorted(to_iterate_over.items()):
if nosubmode:
subcorpus_name = 'Total'
# results for subcorpus go here
#conc_results[subcorpus_name] = []
#count_results[subcorpus_name] = []
#results[subcorpus_name] = Counter()
# get either everything (tree_to_text) or the search['t'] query
if tree_to_text or simple_tregex_mode:
result = tregex_engine(query=treg_q,
options=op,
corpus=subcorpus_path,
root=root,
preserve_case=preserve_case)
# format search results with slashes etc
if not countmode and not tree_to_text:
result = format_tregex(result, show, translated_option=translated_option,
exclude=exclude, excludemode=excludemode, lemtag=lemtag,
lem_instance=lem_instance, countmode=countmode, speaker_data=False)
# if concordancing, do the query again with 'whole' sent and fname
if not no_conc:
ops = ['-w'] + op
#ops = [i for i in ops if i != '-n']
whole_result = tregex_engine(query=search['t'],
options=ops,
corpus=subcorpus_path,
root=root,
preserve_case=preserve_case
)
# format match too depending on option
if not only_format_match:
wholeresult = format_tregex(whole_result, show, translated_option=translated_option,
exclude=exclude, excludemode=excludemode, lemtag=lemtag,
lem_instance=lem_instance, countmode=countmode, speaker_data=False, whole=True)
# make conc lines from conc results
conc_result = make_conc_lines_from_whole_mid(whole_result, result, show=show)
for lin in conc_result:
if maxconc is False or numconc < maxconc:
conc_results[subcorpus_name].append(lin)
numconc += 1
# add matches to ongoing counts
if countmode:
count_results[subcorpus_name] += [result]
else:
if result:
results[subcorpus_name] += Counter([i[-1] for i in result])
else:
results[subcorpus_name] += Counter()
# update progress bar
current_iter += 1
tstr = '%s%d/%d' % (outn, current_iter + 1, total_files)
animator(p, current_iter, tstr, **par_args)
continue
# todo: move this
kwargs.pop('by_metadata', None)
# conll querying goes by file, not subcorpus
for f in files:
slow_treg_speaker_guess = kwargs.get('outname', '') if kwargs.get('multispeaker') else ''
filepath, corefs = f.path, coref
res, conc_res = pipeline(filepath, search=search, show=show,
dep_type=dep_type,
exclude=exclude,
excludemode=excludemode,
searchmode=searchmode,
case_sensitive=case_sensitive,
conc=conc,
only_format_match=only_format_match,
speaker=slow_treg_speaker_guess,
gramsize=gramsize,
no_punct=no_punct,
no_closed=no_closed,
window=window,
filename=f.path,
coref=corefs,
countmode=countmode,
maxconc=(maxconc, numconc),
is_a_word=is_a_word,
by_metadata=subcorpora,
show_conc_metadata=show_conc_metadata,
just_metadata=just_metadata,
skip_metadata=skip_metadata,
fsi_index=fsi_index,
category=subcorpus_name,
translated_option=translated_option,
statsmode=statsmode,
preserve_case=preserve_case,
usecols=usecols,
search_trees=search_trees,
lem_instance=lem_instance,
lemtag=lemtag,
**kwargs)
if res is None and conc_res is None:
current_iter += 1
tstr = '%s%d/%d' % (outn, current_iter + 1, total_files)
animator(p, current_iter, tstr, **par_args)
continue
# deal with symbolic structures---that is, rather than adding
# results by subcorpora, add them by metadata value
# todo: sorting?
if subcorpora:
for (k, v), concl in zip(res.items(), conc_res.values()):
v = lowercase_result(v)
results[k] += Counter(v)
for line in concl:
if maxconc is False or numconc < maxconc:
line = postprocess_concline(line,
fsi_index=fsi_index, conc=conc)
conc_results[k].append(line)
numconc += 1
current_iter += 1
tstr = '%s%d/%d' % (outn, current_iter + 1, total_files)
animator(p, current_iter, tstr, **par_args)
continue
# garbage collection needed?
sents = None
corefs = None
if res == 'Bad query':
return 'Bad query'
if countmode:
count_results[subcorpus_name] += [res]
else:
# add filename and do lowercasing for conc
if not no_conc:
for line in conc_res:
line = postprocess_concline(line,
fsi_index=fsi_index, conc=conc)
if maxconc is False or numconc < maxconc:
conc_results[subcorpus_name].append(line)
numconc += 1
# do lowercasing and spelling
if not only_conc:
res = lowercase_result(res)
# discard removes low results, helping with
# curse of dimensionality
countres = Counter(res)
if isinstance(discard, float):
countres.most_common()
nkeep = len(counter) - len(counter) * discard
countres = Counter({k: v for i, (k, v) in enumerate(countres.most_common()) if i <= nkeep})
elif isinstance(discard, int):
countres = Counter({k: v for k, v in countres.most_common() if v >= discard})
results[subcorpus_name] += countres
#else:
#results[subcorpus_name] += res
# update progress bar
current_iter += 1
tstr = '%s%d/%d' % (outn, current_iter + 1, total_files)
animator(p, current_iter, tstr, **par_args)
# Get concordances into DataFrame, return if just conc
if not no_conc:
# fail on this line with typeerror if no results?
conc_df = make_conc_obj_from_conclines(conc_results, fsi_index=fsi_index)
if only_conc and conc_df is None:
return
elif only_conc:
locs = sanitise_dict(locs)
try:
conc_df.query = locs
except AttributeError:
return conc_df
if save and not kwargs.get('outname'):
if conc_df is not None:
conc_df.save(savename)
goodbye_printer(only_conc=True)
if not root:
signal.signal(signal.SIGINT, original_sigint)
return conc_df
else:
conc_df = None
# Get interrogation into DataFrame
if countmode:
df = Series({k: sum(v) for k, v in sorted(count_results.items())})
tot = df.sum()
else:
the_big_dict = {}
unique_results = set(item for sublist in list(results.values()) for item in sublist)
sortres = sorted(results.items(), key=lambda x: x[0])
for word in unique_results:
the_big_dict[word] = [subcorp_result[word] for _, subcorp_result in sortres]
# turn master dict into dataframe, sorted
df = DataFrame(the_big_dict, index=sorted(results.keys()))
# for ngrams, remove hapaxes
#if show_ngram or show_collocates:
# if not language_model:
# df = df[[i for i in list(df.columns) if df[i].sum() > 1]]
numentries = len(df.columns)
tot = df.sum(axis=1)
total_total = df.sum().sum()
# turn df into series if all conditions met
conds = [countmode,
files_as_subcorpora,
subcorpora,
kwargs.get('df1_always_df', False)]
anyxs = [level == 's',
singlefile,
nosubmode]
if all(not x for x in conds) and any(x for x in anyxs):
df = Series(df.ix[0])
df.sort_values(ascending=False, inplace=True)
tot = df.sum()
numentries = len(df.index)
total_total = tot
# turn data into DF for GUI if need be
if isinstance(df, Series) and kwargs.get('df1_always_df', False):
total_total = df.sum()
df = DataFrame(df)
tot = Series(total_total, index=['Total'])
# if we're doing files as subcorpora, we can remove the extension etc
if isinstance(df, DataFrame) and files_as_subcorpora:
cname = corpus.name.replace('-stripped', '').replace('-parsed', '')
edits = [(r'(-[0-9][0-9][0-9])?\.txt\.conllu?', ''),
(r'-%s(-stripped)?(-parsed)?' % cname, '')]
from corpkit.editor import editor
df = editor(df, replace_subcorpus_names=edits).results
tot = df.sum(axis=1)
total_total = df.sum().sum()
if conc_df is not None and conc_df is not False:
# removed 'f' from here for now
for col in ['c']:
for pat in ['.txt', '.conll', '.conllu']:
conc_df[col] = conc_df[col].str.replace(pat, '')
conc_df[col] = conc_df[col].str.replace(r'-[0-9][0-9][0-9]$', '')
#df.index = df.index.str.replace('w', 'this')
# make interrogation object
locs['corpus'] = corpus.path
locs = sanitise_dict(locs)
if nosubmode and isinstance(df, pd.DataFrame):
df = df.sum()
interro = Interrogation(results=df, totals=tot, query=locs, concordance=conc_df)
# save it
if save and not kwargs.get('outname'):
print('\n')
interro.save(savename)
goodbye = goodbye_printer(return_it=in_notebook)
if in_notebook:
try:
p.children[2].value = goodbye.replace('\n', '')
except AttributeError:
pass
if not root:
signal.signal(signal.SIGINT, original_sigint)
return interro
def edit(self, *args, **kwargs):
"""
Manipulate results of interrogations.
There are a few overall kinds of edit, most of which can be combined
into a single function call. It's useful to keep in mind that many are
basic wrappers around `pandas` operations---if you're comfortable with
`pandas` syntax, it may be faster at times to use its syntax instead.
:Basic mathematical operations:
First, you can do basic maths on results, optionally passing in some
data to serve as the denominator. Very commonly, you'll want to get
relative frequencies:
:Example:
>>> data = corpus.interrogate({W: r'^t'})
>>> rel = data.edit('%', SELF)
>>> rel.results
.. to that the then ... toilet tolerant tolerate ton
01 18.50 14.65 14.44 6.20 ... 0.00 0.00 0.11 0.00
02 24.10 14.34 13.73 8.80 ... 0.00 0.00 0.00 0.00
03 17.31 18.01 9.97 7.62 ... 0.00 0.00 0.00 0.00
For the operation, there are a number of possible values, each of
which is to be passed in as a `str`:
`+`, `-`, `/`, `*`, `%`: self explanatory
`k`: calculate keywords
`a`: get distance metric
`SELF` is a very useful shorthand denominator. When used, all editing
is performed on the data. The totals are then extracted from the edited
data, and used as denominator. If this is not the desired behaviour,
however, a more specific `interrogation.results` or
`interrogation.totals` attribute can be used.
In the example above, `SELF` (or `'self'`) is equivalent to:
:Example:
>>> rel = data.edit('%', data.totals)
:Keeping and skipping data:
There are four keyword arguments that can be used to keep or skip rows
or columns in the data:
* `just_entries`
* `just_subcorpora`
* `skip_entries`
* `skip_subcorpora`
Each can accept different input types:
* `str`: treated as regular expression to match
* `list`:
* of integers: indices to match
* of strings: entries/subcorpora to match
:Example:
>>> data.edit(just_entries=r'^fr',
... skip_entries=['free','freedom'],
... skip_subcorpora=r'[0-9]')
:Merging data:
There are also keyword arguments for merging entries and subcorpora:
* `merge_entries`
* `merge_subcorpora`
These take a `dict`, with the new name as key and the criteria as
value. The criteria can be a str (regex) or wordlist.
:Example:
>>> from dictionaries.wordlists import wordlists
>>> mer = {'Articles': ['the', 'an', 'a'], 'Modals': wordlists.modals}
>>> data.edit(merge_entries=mer)
:Sorting:
The `sort_by` keyword argument takes a `str`, which represents the way
the result columns should be ordered.
* `increase`: highest to lowest slope value
* `decrease`: lowest to highest slope value
* `turbulent`: most change in y axis values
* `static`: least change in y axis values
* `total/most`: largest number first
* `infreq/least`: smallest number first
* `name`: alphabetically
:Example:
>>> data.edit(sort_by='increase')
:Editing text:
Column labels, corresponding to individual interrogation results, can
also be edited with `replace_names`.
:param replace_names: Edit result names, then merge duplicate entries
:type replace_names: `str`/`list of tuples`/`dict`
If `replace_names` is a string, it is treated as a regex to delete from
each name. If `replace_names` is a dict, the value is the regex, and
the key is the replacement text. Using a list of tuples in the form
`(find, replacement)` allows duplicate substitution values.
:Example:
>>> data.edit(replace_names={r'object': r'[di]obj'})
:param replace_subcorpus_names: Edit subcorpus names, then merge duplicates.
The same as `replace_names`, but on the other axis.
:type replace_subcorpus_names: `str`/`list of tuples`/`dict`
:Other options:
There are many other miscellaneous options.
:param keep_stats: Keep/drop stats values from dataframe after sorting
:type keep_stats: `bool`
:param keep_top: After sorting, remove all but the top *keep_top* results
:type keep_top: `int`
:param just_totals: Sum each column and work with sums
:type just_totals: `bool`
:param threshold: When using results list as dataframe 2, drop values
occurring fewer than n times. If not keywording, you
can use:
`'high'`: `denominator total / 2500`
`'medium'`: `denominator total / 5000`
`'low'`: `denominator total / 10000`
If keywording, there are smaller default thresholds
:type threshold: `int`/`bool`
:param span_subcorpora: If subcorpora are numerically named, span all
from *int* to *int2*, inclusive
:type span_subcorpora: `tuple` -- `(int, int2)`
:param projection: multiply results in subcorpus by n
:type projection: tuple -- `(subcorpus_name, n)`
:param remove_above_p: Delete any result over `p`
:type remove_above_p: `bool`
:param p: set the p value
:type p: `float`
:param revert_year: When doing linear regression on years, turn annual
subcorpora into 1, 2 ...
:type revert_year: `bool`
:param print_info: Print stuff to console showing what's being edited
:type print_info: `bool`
:param spelling: Convert/normalise spelling:
:type spelling: `str` -- `'US'`/`'UK'`
:Keywording options:
If the operation is `k`, you're calculating keywords. In this case,
some other keyword arguments have an effect:
:param keyword_measure: what measure to use to calculate keywords:
`ll`: log-likelihood
`pd': percentage difference
type keyword_measure: `str`
:param selfdrop: When keywording, try to remove target corpus from
reference corpus
:type selfdrop: `bool`
:param calc_all: When keywording, calculate words that appear in either
corpus
:type calc_all: `bool`
:returns: :class:`corpkit.interrogation.Interrogation`
"""
from corpkit.editor import editor
return editor(self, *args, **kwargs)
def sort(self, way, **kwargs):
from corpkit.editor import editor
return editor(self, sort_by=way, **kwargs)
def editor(dataframe1,
operation = None,
dataframe2 = False,
sort_by = False,
keep_stats = False,
keep_top = False,
just_totals = False,
threshold = 'medium',
just_entries = False,
skip_entries = False,
merge_entries = False,
newname = 'combine',
multiple_merge = False,
just_subcorpora = False,
skip_subcorpora = False,
span_subcorpora = False,
merge_subcorpora = False,
new_subcorpus_name = False,
replace_names = False,
projection = False,
remove_above_p = False,
p = 0.05,
revert_year = True,
print_info = True,
spelling = False,
selfdrop = True,
calc_all = True,
**kwargs
):
"""Edit results of interrogations, do keywording, sort, etc.
``just/skip_entries`` and ``just/skip_subcorpora`` can take a few different kinds of input:
* str: treated as regular expression to match
* list:
* of integers: indices to match
* of strings: entries/subcorpora to match
``merge_entries`` and ``merge_subcorpora``, however, are best entered as dicts:
``{newname: criteria, newname2: criteria2}```
where criteria is a string, list, etc.
:param dataframe1: Results to edit
:type dataframe1: pandas.core.frame.DataFrame
:param operation: Kind of maths to do on inputted lists:
'+', '-', '/', '*', '%': self explanatory
'k': log likelihood (keywords)
'a': get distance metric (for use with interrogator 'a' option)
'd': get percent difference (alternative approach to keywording)
:type operation: str
:param dataframe2: List of results or totals.
If list of results, for each entry in dataframe 1, locate
entry with same name in dataframe 2, and do maths there
if 'self', do all merging/keeping operations, then use
edited dataframe1 as dataframe2
:type dataframe2: pandas.core.series.Series/pandas.core.frame.DataFrame/dict/'self'
:param sort_by: Calculate slope, stderr, r, p values, then sort by:
increase: highest to lowest slope value
decrease: lowest to highest slope value
turbulent: most change in y axis values
static: least change in y axis values
total/most: largest number first
infreq/least: smallest number first
name: alphabetically
:type sort_by: str
:param keep_stats: Keep/drop stats values from dataframe after sorting
:type keep_stats: bool
:param keep_top: After sorting, remove all but the top *keep_top* results
:type keep_top: int
:param just_totals: Sum each column and work with sums
:type just_totals: bool
:param threshold: When using results list as dataframe 2, drop values occurring
fewer than n times. If not keywording, you can use:
``'high'``: dataframe2 total / 2500
``'medium'``: dataframe2 total / 5000
``'low'``: dataframe2 total / 10000
Note: if keywording, there are smaller default thresholds
:type threshold: int/bool
:param just_entries: Keep matching entries
:type just_entries: see above
:param skip_entries: Skip matching entries
:type skip_entries: see above
:param merge_entries: Merge matching entries
:type merge_entries: see above
:param newname: New name for merged entries
:type newname: str/'combine'
:param just_subcorpora: Keep matching subcorpora
:type just_subcorpora: see above
:param skip_subcorpora: Skip matching subcorpora
:type skip_subcorpora: see above
:param span_subcorpora: If subcorpora are numerically named, span all from *int* to *int2*, inclusive
:type span_subcorpora: tuple -- ``(int, int2)``
:param merge_subcorpora: Merge matching subcorpora
:type merge_subcorpora: see above
:param new_subcorpus_name: Name for merged subcorpora
:type new_subcorpus_name: str/``'combine'``
:param replace_names: Edit result names and then merge duplicate names.
:type replace_names: dict -- ``{criteria: replacement_text}``; str -- a regex to delete from names
:param projection: a to multiply results in subcorpus by n
:type projection: tuple -- ``(subcorpus_name, n)``
:param remove_above_p: Delete any result over p
:type remove_above_p: bool
:param p: set the p value
:type p: float
:param revert_year: when doing linear regression on years, turn annual subcorpora into 1, 2 ...
:type revert_year: bool
:param print_info: Print stuff to console showing what's being edited
:type print_info: bool
:param spelling: Convert/normalise spelling:
:type spelling: str -- ``'US'``/``'UK'``
:param selfdrop: When keywording, try to remove target corpus from reference corpus
:type selfdrop: bool
:param calc_all: When keywording, calculate words that appear in either corpus
:type calc_all: bool
:returns: Edited interrogation
"""
# grab arguments, in case we get dict input and have to iterate
saved_args = locals()
import corpkit
import pandas
import signal
import re
import collections
import pandas as pd
import numpy as np
from pandas import DataFrame, Series
from time import localtime, strftime
try:
get_ipython().getoutput()
except TypeError:
have_ipython = True
except NameError:
have_ipython = False
try:
from IPython.display import display, clear_output
except ImportError:
pass
# if passing a multiquery, do each result separately and return
if type(dataframe1) == dict:
outdict = {}
from corpkit.editor import editor
del saved_args['dataframe1']
for i, (k, v) in enumerate(dataframe1.items()):
# only print the first time around
if i == 0:
pass
#saved_args['print_info'] = True
else:
saved_args['print_info'] = False
# if df2 is also a dict, get the relevant entry
if type(dataframe2) == dict:
if sorted(set([i.lower() for i in dataframe1.keys()])) == \
sorted(set([i.lower() for i in dataframe2.keys()])):
saved_args['dataframe2'] = dataframe2[k]
if 'use_df2_totals' in kwargs.keys():
if kwargs['use_df2_totals'] is True:
saved_args['dataframe2'] = dataframe2[k].totals
outdict[k] = editor(v.results, **saved_args)
if print_info:
from time import localtime, strftime
thetime = strftime("%H:%M:%S", localtime())
print "\n%s: Finished! Output is a dictionary with keys:\n\n '%s'\n" % (thetime, "'\n '".join(sorted(outdict.keys())))
return outdict
the_time_started = strftime("%Y-%m-%d %H:%M:%S")
pd.options.mode.chained_assignment = None
pd.set_option('display.float_format', lambda x: '%.2f' % x)
from corpkit.tests import check_pytex
if check_pytex():
print_info = False
def combiney(df, df2, operation = '%', threshold = 'medium', prinf = True):
"""mash df and df2 together in appropriate way"""
totals = False
# delete under threshold
if just_totals:
if using_totals:
if not single_totals:
to_drop = list(df2[df2['Combined total'] < threshold].index)
df = df.drop([e for e in to_drop if e in list(df.index)])
if prinf:
to_show = []
[to_show.append(w) for w in to_drop[:5]]
if len(to_drop) > 10:
to_show.append('...')
[to_show.append(w) for w in to_drop[-5:]]
if len(to_drop) > 0:
print 'Removing %d entries below threshold:\n %s' % (len(to_drop), '\n '.join(to_show))
if len(to_drop) > 10:
print '... and %d more ... \n' % (len(to_drop) - len(to_show) + 1)
else:
print ''
else:
denom = df2
else:
denom = list(df2)
if single_totals:
if operation == '%':
totals = df.sum() * 100.0 / float(df.sum().sum())
df = df * 100.0
try:
df = df.div(denom, axis = 0)
except ValueError:
from time import localtime, strftime
thetime = strftime("%H:%M:%S", localtime())
print '%s: cannot combine DataFrame 1 and 2: different shapes' % thetime
elif operation == '+':
try:
df = df.add(denom, axis = 0)
except ValueError:
from time import localtime, strftime
thetime = strftime("%H:%M:%S", localtime())
print '%s: cannot combine DataFrame 1 and 2: different shapes' % thetime
elif operation == '-':
try:
df = df.sub(denom, axis = 0)
except ValueError:
from time import localtime, strftime
thetime = strftime("%H:%M:%S", localtime())
print '%s: cannot combine DataFrame 1 and 2: different shapes' % thetime
elif operation == '*':
totals = df.sum() * float(df.sum().sum())
try:
df = df.mul(denom, axis = 0)
except ValueError:
from time import localtime, strftime
thetime = strftime("%H:%M:%S", localtime())
print '%s: cannot combine DataFrame 1 and 2: different shapes' % thetime
elif operation == '/':
try:
totals = df.sum() / float(df.sum().sum())
df = df.div(denom, axis = 0)
except ValueError:
from time import localtime, strftime
thetime = strftime("%H:%M:%S", localtime())
print '%s: cannot combine DataFrame 1 and 2: different shapes' % thetime
elif operation == 'd':
#df.ix['Combined total'] = df.sum()
#to_drop = to_drop = list(df.T[df.T['Combined total'] < threshold].index)
to_drop = [n for n in list(df.columns) if df[n].sum() < threshold]
df = df.drop([e for e in to_drop if e in list(df.columns)], axis = 1)
#df.drop('Combined total')
if prinf:
to_show = []
[to_show.append(w) for w in to_drop[:5]]
if len(to_drop) > 10:
to_show.append('...')
[to_show.append(w) for w in to_drop[-5:]]
if len(to_drop) > 0:
print 'Removing %d entries below threshold:\n %s' % (len(to_drop), '\n '.join(to_show))
if len(to_drop) > 10:
print '... and %d more ... \n' % (len(to_drop) - len(to_show) + 1)
else:
print ''
# get normalised num in target corpus
norm_in_target = df.div(denom, axis = 0)
# get normalised num in reference corpus, with or without selfdrop
tot_in_ref = df.copy()
for c in list(tot_in_ref.index):
if selfdrop:
tot_in_ref.ix[c] = df.sum() - tot_in_ref.ix[c]
else:
tot_in_ref.ix[c] = df.sum()
norm_in_ref = tot_in_ref.div(df.sum().sum())
df = (norm_in_target - norm_in_ref) / norm_in_ref * 100.0
df = df.replace(float(-100.00), np.nan)
elif operation == 'a':
for c in [c for c in list(df.columns) if int(c) > 1]:
df[c] = df[c] * (1.0 / int(c))
df = df.sum(axis = 1) / df2
elif operation.startswith('c'):
import warnings
with warnings.catch_warnings():
warnings.simplefilter("ignore")
df = pandas.concat([df, df2], axis = 1)
return df, totals
elif not single_totals:
if not operation.startswith('a'):
# generate totals
if operation == '%':
totals = df.sum() * 100.0 / float(df2.sum().sum())
if operation == '*':
totals = df.sum() * float(df2.sum().sum())
if operation == '/':
totals = df.sum() / float(df2.sum().sum())
if operation.startswith('c'):
# add here the info that merging will not work
# with identical colnames
import warnings
with warnings.catch_warnings():
warnings.simplefilter("ignore")
d = pd.concat([df.T, df2.T]).sort()
# make index nums
d = d.reset_index()
# sum and remove duplicates
d = d.groupby('index').sum()
dx = d.reset_index('index')
dx.index = list(dx['index'])
df = dx.drop('index', axis = 1).T
for index, entry in enumerate(list(df.columns)):
#p.animate(index)
if operation == '%':
try:
df[entry] = df[entry] * 100.0 / df2[entry]
except:
continue
#df.drop(entry, axis = 1, inplace = True)
#df[entry] = maths_done
elif operation == '+':
try:
df[entry] = df[entry] + df2[entry]
except:
continue
elif operation == '-':
try:
df[entry] = df[entry] - df2[entry]
except:
continue
elif operation == '*':
try:
df[entry] = df[entry] * df2[entry]
except:
continue
elif operation == '/':
try:
df[entry] = df[entry] / df2[entry]
except:
continue
else:
for c in [c for c in list(df.columns) if int(c) > 1]:
df[c] = df[c] * (1.0 / int(c))
df = df.sum(axis = 1) / df2.T.sum()
return df, totals
def parse_input(df, the_input):
"""turn whatever has been passed in into list of words that can
be used as pandas indices---maybe a bad way to go about it"""
# FIX MERGE ERROR HERE
parsed_input = False
import re
if the_input == 'all':
the_input = r'.*'
if type(the_input) == int:
try:
the_input = str(the_input)
except:
pass
the_input = [the_input]
elif type(the_input) == str or type(the_input) == unicode:
try:
regex = re.compile(the_input)
parsed_input = [w for w in list(df) if re.search(regex, w)]
return parsed_input
except:
the_input = [the_input]
if type(the_input) == list:
if type(the_input[0]) == int:
parsed_input = [word for index, word in enumerate(list(df)) if index in the_input]
elif type(the_input[0]) == str or type(the_input[0]) == unicode:
try:
parsed_input = [word for word in the_input if word in df.columns]
except AttributeError: # if series
parsed_input = [word for word in the_input if word in df.index]
return parsed_input
def synonymise(df, pos = 'n'):
"""pass a df and a pos and convert df columns to most common synonyms"""
from nltk.corpus import wordnet as wn
#from dictionaries.taxonomies import taxonomies
from collections import Counter
fixed = []
for w in list(df.columns):
try:
syns = []
for syns in wn.synsets(w, pos = pos):
for w in syns:
synonyms.append(w)
top_syn = Counter(syns).most_common(1)[0][0]
fixed.append(top_syn)
except:
fixed.append(w)
df.columns = fixed
return df
def convert_spell(df, convert_to = 'US', print_info = print_info):
"""turn dataframes into us/uk spelling"""
from dictionaries.word_transforms import usa_convert
if print_info:
print 'Converting spelling ... \n'
if convert_to == 'UK':
usa_convert = {v: k for k, v in usa_convert.items()}
fixed = []
for val in list(df.columns):
try:
fixed.append(usa_convert[val])
except:
fixed.append(val)
df.columns = fixed
return df
def merge_duplicates(df, print_info = print_info):
if print_info:
print 'Merging duplicate entries ... \n'
# now we have to merge all duplicates
for dup in df.columns.get_duplicates():
#num_dupes = len(list(df[dup].columns))
temp = df[dup].sum(axis = 1)
#df = df.drop([dup for d in range(num_dupes)], axis = 1)
df = df.drop(dup, axis = 1)
df[dup] = temp
return df
def name_replacer(df, replace_names, print_info = print_info):
"""replace entry names and merge"""
import re
# double or single nest if need be
if type(replace_names) == str:
replace_names = [(replace_names, '')]
if type(replace_names) != dict:
if type(replace_names[0]) == str:
replace_names = [replace_names]
if type(replace_names) == dict:
replace_names = [(v, k) for k, v in replace_names.items()]
for to_find, replacement in replace_names:
if print_info:
try:
print 'Replacing "%s" with "%s" ...\n' % (to_find, replacement)
except:
print 'Deleting "%s" from entry names ...\n' % (to_find)
to_find = re.compile(to_find)
try:
replacement = replacement
except:
replacement = ''
df.columns = [re.sub(to_find, replacement, l) for l in list(df.columns)]
df = merge_duplicates(df, print_info = False)
return df
def just_these_entries(df, parsed_input, prinf = True):
entries = [word for word in list(df) if word not in parsed_input]
if prinf:
print 'Keeping %d entries:\n %s' % (len(parsed_input), '\n '.join(parsed_input[:10]))
if len(parsed_input) > 10:
print '... and %d more ... \n' % (len(parsed_input) - 10)
else:
print ''
df = df.drop(entries, axis = 1)
return df
def skip_these_entries(df, parsed_input, prinf = True):
if prinf:
print 'Skipping %d entries:\n %s' % (len(parsed_input), '\n '.join(parsed_input[:10]))
if len(parsed_input) > 10:
print '... and %d more ... \n' % (len(parsed_input) - 10)
else:
print ''
df = df.drop(parsed_input, axis = 1)
return df
def newname_getter(df, parsed_input, newname = 'combine', prinf = True, merging_subcorpora = False):
"""makes appropriate name for merged entries"""
if merging_subcorpora:
if newname is False:
newname = 'combine'
if type(newname) == int:
the_newname = list(df.columns)[newname]
elif type(newname) == str:
if newname == 'combine':
if len(parsed_input) <= 3:
the_newname = '/'.join(parsed_input)
elif len(parsed_input) > 3:
the_newname = '/'.join(parsed_input[:3]) + '...'
else:
the_newname = newname
if newname is False:
# revise this code
import operator
sumdict = {}
for item in parsed_input:
summed = sum(list(df[item]))
sumdict[item] = summed
the_newname = max(sumdict.iteritems(), key=operator.itemgetter(1))[0]
if type(the_newname) != unicode:
the_newname = unicode(the_newname, errors = 'ignore')
return the_newname
def merge_these_entries(df, parsed_input, the_newname, prinf = True, merging = 'entries'):
# make new entry with sum of parsed input
if len(parsed_input) == 0:
import warnings
warnings.warn('No %s could be automatically merged.\n' % merging)
else:
if prinf:
print 'Merging %d %s as "%s":\n %s' % (len(parsed_input), merging, the_newname, '\n '.join(parsed_input[:10]))
if len(parsed_input) > 10:
print '... and %d more ... \n' % (len(parsed_input) - 10)
else:
print ''
# remove old entries
temp = sum([df[i] for i in parsed_input])
if not multiple_merge:
if type(df) == pandas.core.series.Series:
df = df.drop(parsed_input)
else:
df = df.drop(parsed_input, axis = 1)
df[the_newname] = temp
return df
def just_these_subcorpora(df, lst_of_subcorpora, prinf = True):
if type(lst_of_subcorpora[0]) == int:
lst_of_subcorpora = [str(l) for l in lst_of_subcorpora]
good_years = [subcorpus for subcorpus in list(df.index) if subcorpus in lst_of_subcorpora]
if prinf:
print 'Keeping %d subcorpora:\n %s' % (len(good_years), '\n '.join(good_years[:10]))
if len(good_years) > 10:
print '... and %d more ... \n' % (len(good_years) - 10)
else:
print ''
df = df.drop([subcorpus for subcorpus in list(df.index) if subcorpus not in good_years], axis = 0)
return df
def skip_these_subcorpora(df, lst_of_subcorpora, prinf = True):
if type(lst_of_subcorpora) == int:
lst_of_subcorpora = [lst_of_subcorpora]
if type(lst_of_subcorpora[0]) == int:
lst_of_subcorpora = [str(l) for l in lst_of_subcorpora]
bad_years = [subcorpus for subcorpus in list(df.index) if subcorpus in lst_of_subcorpora]
if len(bad_years) == 0:
import warnings
warnings.warn('No subcorpora skipped.\n')
else:
if prinf:
print 'Skipping %d subcorpora:\n %s' % (len(bad_years), '\n '.join([str(i) for i in bad_years[:10]]))
if len(bad_years) > 10:
print '... and %d more ... \n' % (len(bad_years) - 10)
else:
print ''
df = df.drop([subcorpus for subcorpus in list(df.index) if subcorpus in bad_years], axis = 0)
return df
def span_these_subcorpora(df, lst_of_subcorpora, prinf = True):
"""select only a span of numerical suborpora (first, last)"""
non_totals = [subcorpus for subcorpus in list(df.index)]
good_years = [subcorpus for subcorpus in non_totals if int(subcorpus) >= int(lst_of_subcorpora[0]) and int(subcorpus) <= int(lst_of_subcorpora[-1])]
if len(lst_of_subcorpora) == 0:
import warnings
warnings.warn('Span not identified.\n')
else:
if prinf:
print 'Keeping subcorpora:\n %d--%d\n' % (int(lst_of_subcorpora[0]), int(lst_of_subcorpora[-1]))
df = df.drop([subcorpus for subcorpus in list(df.index) if subcorpus not in good_years], axis = 0)
# retotal needed here
return df
def projector(df, list_of_tuples, prinf = True):
"""project abs values"""
if type(list_of_tuples) == list:
tdict = {}
for a, b in list_of_tuples:
tdict[a] = b
list_of_tuples = tdict
for subcorpus, projection_value in list_of_tuples.items():
if type(subcorpus) == int:
subcorpus = str(subcorpus)
df.ix[subcorpus] = df.ix[subcorpus] * projection_value
if prinf:
if type(projection_value) == float:
print 'Projection: %s * %s' % (subcorpus, projection_value)
if type(projection_value) == int:
print 'Projection: %s * %d' % (subcorpus, projection_value)
if prinf:
print ''
return df
def do_stats(df):
"""do linregress and add to df"""
try:
from scipy.stats import linregress
except ImportError:
from time import localtime, strftime
thetime = strftime("%H:%M:%S", localtime())
print '%s: sort type not available in this verion of corpkit.' % thetime
return False
#from stats.stats import linregress
entries = []
slopes = []
intercepts = []
rs = []
ps = []
stderrs = []
indices = list(df.index)
first_year = list(df.index)[0]
try:
x = [int(y) - int(first_year) for y in indices]
except ValueError:
x = range(len(indices))
statfields = ['slope', 'intercept', 'r', 'p', 'stderr']
for entry in list(df.columns):
entries.append(entry)
y = list(df[entry])
slope, intercept, r, p, stderr = linregress(x, y)
slopes.append(slope)
intercepts.append(intercept)
rs.append(r)
ps.append(p)
stderrs.append(stderr)
sl = pd.DataFrame([slopes, intercepts, rs, ps, stderrs],
index = statfields,
columns = list(df.columns))
df = df.append(sl)
# drop infinites and nans
if operation != 'd':
df = df.replace([np.inf, -np.inf], np.nan)
df = df.fillna(0.0)
return df
def recalc(df, operation = '%'):
statfields = ['slope', 'intercept', 'r', 'p', 'stderr']
"""Add totals to the dataframe1"""
#df.drop('Total', axis = 0, inplace = True)
#df.drop('Total', axis = 1, inplace = True)
try:
df['temp-Total'] = df.drop(statfields).sum(axis = 1)
except:
df['temp-Total'] = df.sum(axis = 1)
df = df.T
try:
df['temp-Total'] = df.drop(statfields).sum(axis = 1)
except:
df['temp-Total'] = df.sum(axis = 1)
df = df.T
return df
def resort(df, sort_by = False, keep_stats = False):
"""sort results, potentially using scipy's linregress"""
# translate options and make sure they are parseable
options = ['total', 'name', 'infreq', 'increase', 'turbulent',
'decrease', 'static', 'most', 'least', 'none']
if sort_by is True:
sort_by = 'total'
if sort_by == 'most':
sort_by = 'total'
if sort_by == 'least':
sort_by = 'infreq'
if sort_by not in options:
raise ValueError("sort_by parameter error: '%s' not recognised. Must be True, False, %s" % (sort_by, ', '.join(options)))
if operation.startswith('k'):
if type(df) == pandas.core.series.Series:
if sort_by == 'total':
df = df.order(ascending = False)
elif sort_by == 'infreq':
df = df.order(ascending = True)
elif sort_by == 'name':
df = df.sort_index()
return df
if just_totals:
if sort_by == 'infreq':
df = df.sort(columns = 'Combined total', ascending = True)
elif sort_by == 'total':
df = df.sort(columns = 'Combined total', ascending = False)
elif sort_by == 'name':
df = df.sort_index()
return df
# this is really shitty now that i know how to sort, like in the above
if keep_stats:
df = do_stats(df)
if type(df) == bool:
if df is False:
return False
if sort_by == 'total':
if df1_istotals:
df = df.T
df = recalc(df, operation = operation)
tot = df.ix['temp-Total']
df = df[tot.argsort()[::-1]]
df = df.drop('temp-Total', axis = 0)
df = df.drop('temp-Total', axis = 1)
if df1_istotals:
df = df.T
elif sort_by == 'infreq':
if df1_istotals:
df = df.T
df = recalc(df, operation = operation)
tot = df.ix['temp-Total']
df = df[tot.argsort()]
df = df.drop('temp-Total', axis = 0)
df = df.drop('temp-Total', axis = 1)
if df1_istotals:
df = df.T
elif sort_by == 'name':
# currently case sensitive...
df = df.reindex_axis(sorted(df.columns), axis=1)
else:
statfields = ['slope', 'intercept', 'r', 'p', 'stderr']
if not keep_stats:
df = do_stats(df)
if type(df) == bool:
if df is False:
return False
slopes = df.ix['slope']
if sort_by == 'increase':
df = df[slopes.argsort()[::-1]]
elif sort_by == 'decrease':
df = df[slopes.argsort()]
elif sort_by == 'static':
df = df[slopes.abs().argsort()]
elif sort_by == 'turbulent':
df = df[slopes.abs().argsort()[::-1]]
if remove_above_p:
# the easy way to do it!
df = df.T
df = df[df['p'] <= p]
df = df.T
# remove stats field by default
if not keep_stats:
df = df.drop(statfields, axis = 0)
return df
def set_threshold(big_list, threshold, prinf = True, for_keywords = False):
if type(threshold) == str:
if threshold.startswith('l'):
denominator = 10000
if threshold.startswith('m'):
denominator = 5000
if threshold.startswith('h'):
denominator = 2500
if type(big_list) == pandas.core.frame.DataFrame:
tot = big_list.sum().sum()
if type(big_list) == pandas.core.series.Series:
tot = big_list.sum()
the_threshold = float(tot) / float(denominator)
#if for_keywords:
#the_threshold = the_threshold / 2
else:
the_threshold = threshold
if prinf:
print 'Threshold: %d\n' % the_threshold
return the_threshold
# check if we're in concordance mode
try:
if list(dataframe1.columns) == ['l', 'm', 'r']:
conc_lines = True
else:
conc_lines = False
except:
conc_lines = False
# copy dataframe to be very safe
try:
df = dataframe1.copy()
except AttributeError:
no_good_dataframe1 = True
while no_good_dataframe1:
if 'interrogation' in str(type(dataframe1)):
sel = raw_input("\nIt looks like you're trying to edit an interrogation, " \
"rather than an interrogation's .results or .totals branch. You can:\n\n a) select .results branch\n b) select .totals branch\n c) exit\n\nYour choice: ")
if sel.startswith('a'):
try:
dataframe1 = dataframe1.results
no_good_dataframe1 = False
except:
pass
elif sel.startswith('b'):
try:
dataframe1 = dataframe1.totals
no_good_dataframe1 = False
except:
pass
else:
return
else:
raise ValueError("Thing to be edited (dataframe1) needs to be a Pandas DataFrame or Series. " \
"Right now, its type is: '%s'." % type(dataframe1).__name__)
df = dataframe1.copy()
# make cols into strings
try:
df.columns = [str(c) for c in list(df.columns)]
except:
pass
if operation is None:
operation = 'None'
# do concordance work
if conc_lines:
df = dataframe1.copy()
if just_entries:
if type(just_entries) == int:
just_entries = [just_entries]
if type(just_entries) == str:
df = df[df['m'].str.contains(just_entries)]
if type(just_entries) == list:
if type(just_entries[0]) == str:
regex = re.compile(r'(?i)^(' + r'|'.join(just_entries) + r')$')
df = df[df['m'].str.contains(regex)]
else:
df = df.ix[just_entries].reset_index(drop = True)
if skip_entries:
if type(skip_entries) == int:
skip_entries = [skip_entries]
if type(skip_entries) == str:
df = df[~df['m'].str.contains(skip_entries)]
if type(skip_entries) == list:
if type(skip_entries[0]) == str:
regex = re.compile(r'(?i)^(' + r'|'.join(skip_entries) + r')$')
df = df[~df['m'].str.contains(regex)]
else:
df = df.ix[[e for e in list(df.index) if e not in skip_entries]].reset_index(drop = True)
return df
if print_info:
print '\n***Processing results***\n========================\n'
df1_istotals = False
if type(df) == pandas.core.series.Series:
df1_istotals = True
df = pandas.DataFrame(df)
# if just a single result
else:
df = pandas.DataFrame(df)
if operation.startswith('k'):
if sort_by is False:
if not df1_istotals:
sort_by = 'turbulent'
if df1_istotals:
df = df.T
# figure out if there's a second list
# copy and remove totals if there is
single_totals = True
using_totals = False
outputmode = False
try:
if dataframe2.empty is False:
df2 = dataframe2.copy()
using_totals = True
if type(df2) == pandas.core.frame.DataFrame:
if len(df2.columns) > 1:
single_totals = False
else:
df2 = pd.Series(df2)
if operation == 'd':
df2 = df2.sum(axis = 1)
single_totals = True
elif type(df2) == pandas.core.series.Series:
single_totals = True
#if operation == 'k':
#raise ValueError('Keywording requires a DataFrame for dataframe2. Use "self"?')
else:
raise ValueError('dataframe2 not recognised.')
except AttributeError:
if operation in ['k', 'd', 'a', '%', '/', '*', '-', '+']:
dataframe2 = 'self'
if dataframe2 == 'self':
outputmode = True
if operation.startswith('a') or operation.startswith('A'):
if list(df.columns)[0] != '0' and list(df.columns)[0] != 0:
df = df.T
if using_totals:
if not single_totals:
df2 = df2.T
if projection:
# projection shouldn't do anything when working with '%', remember.
df = projector(df, projection)
if using_totals:
df2 = projector(df2, projection)
if spelling:
df = convert_spell(df, convert_to = spelling)
df = merge_duplicates(df, print_info = False)
if not single_totals:
df2 = convert_spell(df2, convert_to = spelling, print_info = False)
df2 = merge_duplicates(df2, print_info = False)
if not df1_istotals:
sort_by = 'total'
if replace_names:
df = name_replacer(df, replace_names)
df = merge_duplicates(df)
if not single_totals:
df2 = name_replacer(df2, print_info = False)
df2 = merge_duplicates(df2, print_info = False)
if not sort_by:
sort_by = 'total'
# remove old stats if they're there:
statfields = ['slope', 'intercept', 'r', 'p', 'stderr']
try:
df = df.drop(statfields, axis = 0)
except:
pass
if using_totals:
try:
df2 = df2.drop(statfields, axis = 0)
except:
pass
# remove totals and tkinter order
for name, ax in zip(['Total'] * 2 + ['tkintertable-order'] * 2, [0, 1, 0, 1]):
try:
df = df.drop(name, axis = ax, errors = 'ignore')
except:
pass
for name, ax in zip(['Total'] * 2 + ['tkintertable-order'] * 2, [0, 1, 0, 1]):
try:
df2 = df2.drop(name, axis = ax, errors = 'ignore')
except:
pass
# merging: make dicts if they aren't already, so we can iterate
if merge_entries:
if type(merge_entries) != list:
if type(merge_entries) == str or type(merge_entries) == unicode:
merge_entries = {newname: merge_entries}
# for newname, criteria
for name, the_input in sorted(merge_entries.items()):
the_newname = newname_getter(df, parse_input(df, the_input), newname = name, prinf = print_info)
df = merge_these_entries(df, parse_input(df, the_input), the_newname, prinf = print_info)
if not single_totals:
df2 = merge_these_entries(df2, parse_input(df2, the_input), the_newname, prinf = False)
else:
for i in merge_entries:
the_newname = newname_getter(df, parse_input(df, merge_entries), newname = newname, prinf = print_info)
df = merge_these_entries(df, parse_input(df, merge_entries), the_newname, prinf = print_info)
if not single_totals:
df2 = merge_these_entries(df2, parse_input(df2, merge_entries), the_newname, prinf = False)
if merge_subcorpora:
if type(merge_subcorpora) != dict:
if type(merge_subcorpora) == list:
if type(merge_subcorpora[0]) == tuple:
merge_subcorpora = {x: y for x, y in merge_subcorpora}
elif type(merge_subcorpora[0]) == str or type(merge_subcorpora[0]) == unicode:
merge_subcorpora = {new_subcorpus_name: [x for x in merge_subcorpora]}
elif type(merge_subcorpora[0]) == int:
merge_subcorpora = {new_subcorpus_name: [str(x) for x in merge_subcorpora]}
else:
merge_subcorpora = {new_subcorpus_name: merge_subcorpora}
for name, the_input in sorted(merge_subcorpora.items()):
the_newname = newname_getter(df.T, parse_input(df.T, the_input),
newname = name,
merging_subcorpora = True,
prinf = print_info)
df = merge_these_entries(df.T, parse_input(df.T, the_input), the_newname, merging = 'subcorpora', prinf = print_info).T
if using_totals:
df2 = merge_these_entries(df2.T, parse_input(df2.T, the_input), the_newname, merging = 'subcorpora', prinf = False).T
if just_subcorpora:
df = just_these_subcorpora(df, just_subcorpora, prinf = print_info)
if using_totals:
df2 = just_these_subcorpora(df2, just_subcorpora, prinf = False)
if skip_subcorpora:
df = skip_these_subcorpora(df, skip_subcorpora, prinf = print_info)
if using_totals:
df2 = skip_these_subcorpora(df2, skip_subcorpora, prinf = False)
if span_subcorpora:
df = span_these_subcorpora(df, span_subcorpora, prinf = print_info)
if using_totals:
df2 = span_these_subcorpora(df2, span_subcorpora, prinf = False)
if just_entries:
df = just_these_entries(df, parse_input(df, just_entries), prinf = print_info)
if not single_totals:
df2 = just_these_entries(df2, parse_input(df2, just_entries), prinf = False)
if skip_entries:
df = skip_these_entries(df, parse_input(df, skip_entries), prinf = print_info)
if not single_totals:
df2 = skip_these_entries(df2, parse_input(df2, skip_entries), prinf = False)
# drop infinites and nans
if operation != 'd':
df = df.replace([np.inf, -np.inf], np.nan)
df = df.fillna(0.0)
# make just_totals as dataframe
just_one_total_number = False
if just_totals:
df = pd.DataFrame(df.sum(), columns = ['Combined total'])
if using_totals:
if not single_totals:
df2 = pd.DataFrame(df2.sum(), columns = ['Combined total'])
else:
just_one_total_number = True
df2 = df2.sum()
tots = df.sum(axis = 1)
if using_totals or outputmode:
if not operation.startswith('k'):
the_threshold = 0
# set a threshold if just_totals
if outputmode is True:
df2 = df.T.sum()
if not just_totals:
df2.name = 'Total'
else:
df2.name = 'Combined total'
using_totals = True
single_totals = True
if just_totals:
if not single_totals:
the_threshold = set_threshold(df2, threshold, prinf = print_info)
if operation == 'd':
the_threshold = set_threshold(df2, threshold, prinf = print_info)
df, tots = combiney(df, df2, operation = operation, threshold = the_threshold, prinf = print_info)
# if doing keywording...
if operation.startswith('k'):
from keys import keywords
# allow saved dicts to be df2, etc
try:
if dataframe2 == 'self':
df2 = df.copy()
except TypeError:
pass
if type(dataframe2) == str:
if dataframe2 != 'self':
df2 = dataframe2
else:
the_threshold = False
df = keywords(df, df2,
selfdrop = selfdrop,
threshold = threshold,
printstatus = print_info,
editing = True,
calc_all = calc_all,
**kwargs)
# eh?
df = df.T
# drop infinites and nans
if operation != 'd':
df = df.replace([np.inf, -np.inf], np.nan)
df = df.fillna(0.0)
# resort data
if sort_by:
df = resort(df, keep_stats = keep_stats, sort_by = sort_by)
if type(df) == bool:
if df is False:
return 'linregress'
if keep_top:
if not just_totals:
df = df[list(df.columns)[:keep_top]]
else:
df = df.head(keep_top)
if just_totals:
# turn just_totals into series:
df = pd.Series(df['Combined total'], name = 'Combined total')
if df1_istotals:
if operation.startswith('k'):
try:
df = pd.Series(df.ix[dataframe1.name])
df.name = '%s: keyness' % df.name
except:
df = df.iloc[0,:]
df.name = 'keyness' % df.name
# generate totals branch if not percentage results:
# fix me
if df1_istotals or operation.startswith('k'):
if not just_totals:
try:
total = pd.Series(df['Total'], name = 'Total')
except:
pass
total = 'none'
#total = df.copy()
else:
total = 'none'
else:
# might be wrong if using division or something...
try:
total = df.T.sum(axis = 1)
except:
total = 'none'
if type(tots) != pandas.core.frame.DataFrame and type(tots) != pandas.core.series.Series:
total = df.sum(axis = 1)
else:
total = tots
if type(df) == pandas.core.frame.DataFrame:
datatype = df.ix[0].dtype
else:
datatype = df.dtype
# TURN INT COL NAMES INTO STR
try:
df.results.columns = [str(d) for d in list(df.results.columns)]
except:
pass
def add_tkt_index(df):
if type(df) != pandas.core.series.Series:
df = df.T
df = df.drop('tkintertable-order', errors = 'ignore', axis = 0)
df = df.drop('tkintertable-order', errors = 'ignore', axis = 1)
df['tkintertable-order'] = pd.Series([index for index, data in enumerate(list(df.index))], index = list(df.index))
df = df.T
return df
# while tkintertable can't sort rows
from corpkit.tests import check_t_kinter
tk = check_t_kinter()
if tk:
df = add_tkt_index(df)
if 'df1_always_df' in kwargs.keys():
if kwargs['df1_always_df'] is True:
if type(df) == pandas.core.series.Series:
df = pandas.DataFrame(df)
#make named_tuple
the_operation = 'none'
if using_totals:
the_operation = operation
the_options = {}
the_options['time_started'] = the_time_started
the_options['function'] = 'editor'
the_options['dataframe1'] = dataframe1
the_options['operation'] = the_operation
the_options['dataframe2'] = dataframe2
the_options['datatype'] = datatype
the_options['sort_by'] = sort_by
the_options['keep_stats'] = keep_stats
the_options['just_totals'] = just_totals
the_options['threshold'] = threshold # can be wrong!
the_options['just_entries'] = just_entries
the_options['just_entries'] = just_entries
the_options['skip_entries'] = skip_entries
the_options['merge_entries'] = merge_entries
the_options['newname'] = newname
the_options['just_subcorpora'] = just_subcorpora
the_options['skip_subcorpora'] = skip_subcorpora
the_options['span_subcorpora'] = span_subcorpora
the_options['merge_subcorpora'] = merge_subcorpora
the_options['new_subcorpus_name'] = new_subcorpus_name
the_options['projection'] = projection
the_options['remove_above_p'] = remove_above_p
the_options['p'] = p
the_options['revert_year'] = revert_year
the_options['print_info'] = print_info
outputnames = collections.namedtuple('edited_interrogation', ['query', 'results', 'totals'])
output = outputnames(the_options, df, total)
#print '\nResult (sample)\n'
if print_info:
#if merge_entries or merge_subcorpora or span_subcorpora or just_subcorpora or \
#just_entries or skip_entries or skip_subcorpora or printed_th or projection:
print '***Done!***\n========================\n'
#print df.head().T
#print ''
if operation.startswith('k') or just_totals or df1_istotals:
pd.set_option('display.max_rows', 30)
else:
pd.set_option('display.max_rows', 15)
pd.set_option('display.max_columns', 8)
pd.set_option('max_colwidth',70)
pd.set_option('display.width', 800)
pd.set_option('expand_frame_repr', False)
pd.set_option('display.float_format', lambda x: '%.2f' % x)
return output
def _edit(self, *args, **kwargs):
from corpkit.editor import editor
return editor(self, *args, **kwargs)
def _keyness(self, measure='ll', denominator='self', **kwargs):
from corpkit.editor import editor
return editor(self, 'k', denominator, **kwargs)
def _rel(self, denominator='self', **kwargs):
from corpkit.editor import editor
return editor(self, '%', denominator, **kwargs)
def edit(self, *args, **kwargs):
"""Manipulate results of interrogations.
There are a few overall kinds of edit, most of which can be combined
into a single function call. It's useful to keep in mind that many are
basic wrappers around `pandas` operations---if you're comfortable with
`pandas` syntax, it may be faster at times to use its syntax instead.
:Basic mathematical operations:
First, you can do basic maths on results, optionally passing in some
data to serve as the denominator. Very commonly, you'll want to get
relative frequencies:
:Example:
>>> data = corpus.interrogate({W: r'^t'})
>>> rel = data.edit('%', SELF)
>>> rel.results
.. to that the then ... toilet tolerant tolerate ton
01 18.50 14.65 14.44 6.20 ... 0.00 0.00 0.11 0.00
02 24.10 14.34 13.73 8.80 ... 0.00 0.00 0.00 0.00
03 17.31 18.01 9.97 7.62 ... 0.00 0.00 0.00 0.00
For the operation, there are a number of possible values, each of
which is to be passed in as a `str`:
`+`, `-`, `/`, `*`, `%`: self explanatory
`k`: calculate keywords
`a`: get distance metric
`SELF` is a very useful shorthand denominator. When used, all editing
is performed on the data. The totals are then extracted from the edited
data, and used as denominator. If this is not the desired behaviour,
however, a more specific `interrogation.results` or
`interrogation.totals` attribute can be used.
In the example above, `SELF` (or `'self'`) is equivalent to:
:Example:
>>> rel = data.edit('%', data.totals)
:Keeping and skipping data:
There are four keyword arguments that can be used to keep or skip rows
or columns in the data:
* `just_entries`
* `just_subcorpora`
* `skip_entries`
* `skip_subcorpora`
Each can accept different input types:
* `str`: treated as regular expression to match
* `list`:
* of integers: indices to match
* of strings: entries/subcorpora to match
:Example:
>>> data.edit(just_entries=r'^fr',
... skip_entries=['free','freedom'],
... skip_subcorpora=r'[0-9]')
:Merging data:
There are also keyword arguments for merging entries and subcorpora:
* `merge_entries`
* `merge_subcorpora`
These take a `dict`, with the new name as key and the criteria as
value. The criteria can be a str (regex) or wordlist.
:Example:
>>> from dictionaries.wordlists import wordlists
>>> mer = {'Articles': ['the', 'an', 'a'], 'Modals': wordlists.modals}
>>> data.edit(merge_entries=mer)
:Sorting:
The `sort_by` keyword argument takes a `str`, which represents the way
the result columns should be ordered.
* `increase`: highest to lowest slope value
* `decrease`: lowest to highest slope value
* `turbulent`: most change in y axis values
* `static`: least change in y axis values
* `total/most`: largest number first
* `infreq/least`: smallest number first
* `name`: alphabetically
:Example:
>>> data.edit(sort_by='increase')
:Editing text:
Column labels, corresponding to individual interrogation results, can
also be edited with `replace_names`.
:param replace_names: Edit result names, then merge duplicate entries
:type replace_names: `str`/`list of tuples`/`dict`
If `replace_names` is a string, it is treated as a regex to delete from
each name. If `replace_names` is a dict, the value is the regex, and
the key is the replacement text. Using a list of tuples in the form
`(find, replacement)` allows duplicate substitution values.
:Example:
>>> data.edit(replace_names={r'object': r'[di]obj'})
:param replace_subcorpus_names: Edit subcorpus names, then merge duplicates.
The same as `replace_names`, but on the other axis.
:type replace_subcorpus_names: `str`/`list of tuples`/`dict`
:Other options:
There are many other miscellaneous options.
:param keep_stats: Keep/drop stats values from dataframe after sorting
:type keep_stats: `bool`
:param keep_top: After sorting, remove all but the top *keep_top* results
:type keep_top: `int`
:param just_totals: Sum each column and work with sums
:type just_totals: `bool`
:param threshold: When using results list as dataframe 2, drop values
occurring fewer than n times. If not keywording, you
can use:
`'high'`: `denominator total / 2500`
`'medium'`: `denominator total / 5000`
`'low'`: `denominator total / 10000`
If keywording, there are smaller default thresholds
:type threshold: `int`/`bool`
:param span_subcorpora: If subcorpora are numerically named, span all
from *int* to *int2*, inclusive
:type span_subcorpora: `tuple` -- `(int, int2)`
:param projection: multiply results in subcorpus by n
:type projection: tuple -- `(subcorpus_name, n)`
:param remove_above_p: Delete any result over `p`
:type remove_above_p: `bool`
:param p: set the p value
:type p: `float`
:param revert_year: When doing linear regression on years, turn annual
subcorpora into 1, 2 ...
:type revert_year: `bool`
:param print_info: Print stuff to console showing what's being edited
:type print_info: `bool`
:param spelling: Convert/normalise spelling:
:type spelling: `str` -- `'US'`/`'UK'`
:Keywording options:
If the operation is `k`, you're calculating keywords. In this case,
some other keyword arguments have an effect:
:param keyword_measure: what measure to use to calculate keywords:
`ll`: log-likelihood
`pd': percentage difference
type keyword_measure: `str`
:param selfdrop: When keywording, try to remove target corpus from
reference corpus
:type selfdrop: `bool`
:param calc_all: When keywording, calculate words that appear in either
corpus
:type calc_all: `bool`
:returns: :class:`corpkit.interrogation.Interrogation`
"""
from corpkit.editor import editor
return editor(self, *args, **kwargs)
def pmultiquery(path,
option = 'c',
query = 'any',
sort_by = 'total',
quicksave = False,
num_proc = 'default',
function_filter = False,
**kwargs):
"""Parallel process multiple queries or corpora.
This function is used by interrogator if:
a) path is a list of paths
b) query is a dict of named queries.
This function needs joblib 0.8.4 or above in order to run properly."""
import collections
import os
import pandas
import pandas as pd
from collections import namedtuple
from time import strftime, localtime
from corpkit.interrogator import interrogator
from corpkit.editor import editor
from corpkit.other import save_result
try:
from joblib import Parallel, delayed
except:
raise ValueError('joblib, the module used for multiprocessing, cannot be found. ' \
'Install with:\n\n pip install joblib')
import multiprocessing
num_cores = multiprocessing.cpu_count()
def best_num_parallel(num_cores, num_queries):
"""decide how many parallel processes to run
the idea, more or less, is to """
if num_queries <= num_cores:
return num_queries
if num_queries > num_cores:
if (num_queries / num_cores) == num_cores:
return int(num_cores)
if num_queries % num_cores == 0:
return max([int(num_queries / n) for n in range(2, num_cores) if int(num_queries / n) <= num_cores])
else:
import math
if (float(math.sqrt(num_queries))).is_integer():
square_root = math.sqrt(num_queries)
if square_root <= num_queries / num_cores:
return int(square_root)
return num_queries / ((num_queries / num_cores) + 1)
# are we processing multiple queries or corpora?
# find out optimal number of cores to use.
multiple_option = False
multiple_corpora = False
if type(path) != str:
multiple_corpora = True
num_cores = best_num_parallel(num_cores, len(path))
elif type(query) != str:
multiple_corpora = False
num_cores = best_num_parallel(num_cores, len(query))
elif type(function_filter) != str:
multiple_option = True
num_cores = best_num_parallel(num_cores, len(function_filter.keys()))
if num_proc != 'default':
num_cores = num_proc
# make sure quicksaves are right type
if quicksave is True:
raise ValueError('quicksave must be string when using pmultiquery.')
# the options that don't change
d = {'option': option,
'paralleling': True,
'function': 'interrogator'}
# add kwargs to query
for k, v in kwargs.items():
d[k] = v
# make a list of dicts to pass to interrogator,
# with the iterable unique in every one
ds = []
if multiple_corpora and not multiple_option:
path = sorted(path)
for index, p in enumerate(path):
name = os.path.basename(p)
a_dict = dict(d)
a_dict['path'] = p
a_dict['query'] = query
a_dict['outname'] = name
a_dict['printstatus'] = False
ds.append(a_dict)
elif not multiple_corpora and not multiple_option:
import collections
for index, (name, q) in enumerate(query.items()):
a_dict = dict(d)
a_dict['path'] = path
a_dict['query'] = q
a_dict['outname'] = name
a_dict['printstatus'] = False
ds.append(a_dict)
elif multiple_option:
import collections
for index, (name, q) in enumerate(function_filter.items()):
a_dict = dict(d)
a_dict['path'] = path
a_dict['query'] = query
a_dict['outname'] = name
a_dict['function_filter'] = q
a_dict['printstatus'] = False
ds.append(a_dict)
time = strftime("%H:%M:%S", localtime())
if multiple_corpora and not multiple_option:
print ("\n%s: Beginning %d parallel corpus interrogations:\n %s" \
"\n Query: '%s'" \
"\n Interrogating corpus ... \n" % (time, num_cores, "\n ".join(path), query) )
elif not multiple_corpora and not multiple_option:
print ("\n%s: Beginning %d parallel corpus interrogations: %s" \
"\n Queries: '%s'" \
"\n Interrogating corpus ... \n" % (time, num_cores, path, "', '".join(query.values())) )
elif multiple_option:
print ("\n%s: Beginning %d parallel corpus interrogations (multiple options): %s" \
"\n Query: '%s'" \
"\n Interrogating corpus ... \n" % (time, num_cores, path, query) )
# run in parallel, get either a list of tuples (non-c option)
# or a dataframe (c option)
res = Parallel(n_jobs=num_cores)(delayed(interrogator)(**x) for x in ds)
res = sorted(res)
# turn list into dict of results, make query and total branches,
# save and return
if not option.startswith('c'):
out = {}
print ''
for (name, data), d in zip(res, ds):
if not option.startswith('k'):
outputnames = collections.namedtuple('interrogation', ['query', 'results', 'totals'])
stotal = data.sum(axis = 1)
stotal.name = u'Total'
output = outputnames(d, data, stotal)
else:
outputnames = collections.namedtuple('interrogation', ['query', 'results'])
output = outputnames(d, data)
out[name] = output
# could be wrong for unstructured corpora?
num_diff_results = len(data)
time = strftime("%H:%M:%S", localtime())
print "\n%s: Finished! Output is a dictionary with keys:\n\n '%s'\n" % (time, "'\n '".join(sorted(out.keys())))
if quicksave:
for k, v in out.items():
save_result(v, k, savedir = 'data/saved_interrogations/%s' % quicksave)
return out
# make query and total branch, save, return
else:
out = pd.concat(res, axis = 1)
out = editor(out, sort_by = sort_by, print_info = False, keep_stats = False)
time = strftime("%H:%M:%S", localtime())
print '\n%s: Finished! %d unique results, %d total.' % (time, len(out.results.columns), out.totals.sum())
if quicksave:
from corpkit.other import save_result
save_result(out, quicksave)
return out
def interroplot(path, query):
"""Interrogates path with Tregex query, gets relative frequencies, and plots the top seven results"""
from corpkit import interrogator, editor, plotter
quickstart = interrogator(path, 'words', query)
edited = editor(quickstart.results, '%', quickstart.totals, print_info = False)
plotter(str(path), edited.results)
