def vec2wordclustercounter(folderlist, cluster_dictionary):
"""
This is stolen from the cluster_analysis dictmaker.
The dictmaker counts the words / items contained in the files found in the folders of folderlist.
remove_stopwords uses the stopword list defined above to ignore words.
remove_punct works with string.punctuation, cf above.
This was mainly used to test how well the counting in the word2vec analysis works.
"""
with codecs.open(cluster_dictionary, "r", "utf-8") as inputjson:
clusterdict = json.load(inputjson)
result = defaultdict(int)
#this is just for qc
misses = []
for folder in folderlist:
filis = [
i for i in os.listdir(os.path.join(pathi, folder))
if not i.startswith(".")
]
print "Building vocab: we have {} files in folder {}".format(
len(filis), folder)
for fili in filis:
inputfile = codecs.open(os.path.join(pathi, folder, fili), "r",
"utf-8").read()
inputtext = ct.adtextextractor(inputfile, fili)
#pre-processing here
inputtext = ct.adcleaner(inputtext,
replace_linebreak=True,
remove_html=False)
splittext = word_tokenize(inputtext)
splittextlo = [i.lower() for i in splittext]
finaltext = [punctuationregex.sub("", i) for i in splittextlo]
finaltext = [i for i in finaltext if i and i not in ['br']]
#do we want to lemmatize or things like that
for word in finaltext:
cluster = [
k for k, v in clusterdict.items() if word in v['words']
]
if len(cluster) > 1:
print "Warning: The item {} was found in more than one clusters".format(
word)
if len(cluster) < 1:
#print "Warning: The item could not be found in a cluster"
misses.append(word)
else:
result[cluster[0]] = result[cluster[0]] + 1
print "Our vocab dictionary has {} entries".format(len(result))
ct.dictwriter(
os.path.join("~/", chapterdir[0], "outputfiles",
"fulldict_" + time.strftime("%H_%M_%m_%d")), result)
# featuredict= {key:value for key, value in vocab.items() if value > float(threshold) }
# print "Our feature dictionary has {} entries\n---------------\n".format(len(featuredict))
# print "This is our featuredict", featuredict
# ct.dictwriter(os.path.join("~/", chapterdir[0], "outputfiles", "featuredict_"+time.strftime("%H_%M_%m_%d")), featuredict)
print "misses", len(misses), set(misses)
print result
return result
def vec2wordclustercounter(folderlist, cluster_dictionary):
"""
This is stolen from the cluster_analysis dictmaker.
The dictmaker counts the words / items contained in the files found in the folders of folderlist.
remove_stopwords uses the stopword list defined above to ignore words.
remove_punct works with string.punctuation, cf above.
This was mainly used to test how well the counting in the word2vec analysis works.
"""
with codecs.open(cluster_dictionary, "r", "utf-8") as inputjson:
clusterdict=json.load(inputjson)
result=defaultdict(int)
#this is just for qc
misses=[]
for folder in folderlist:
filis=[i for i in os.listdir(os.path.join(pathi,folder)) if not i.startswith(".")]
print "Building vocab: we have {} files in folder {}".format(len(filis), folder)
for fili in filis:
inputfile=codecs.open(os.path.join(pathi, folder, fili), "r", "utf-8").read()
inputtext=ct.adtextextractor(inputfile, fili)
#pre-processing here
inputtext=ct.adcleaner(inputtext ,replace_linebreak=True, remove_html=False)
splittext=word_tokenize(inputtext)
splittextlo=[i.lower() for i in splittext]
finaltext=[punctuationregex.sub("",i) for i in splittextlo]
finaltext=[i for i in finaltext if i and i not in ['br']]
#do we want to lemmatize or things like that
for word in finaltext:
cluster= [k for k,v in clusterdict.items() if word in v['words']]
if len(cluster) > 1:
print "Warning: The item {} was found in more than one clusters".format(word)
if len(cluster) < 1:
#print "Warning: The item could not be found in a cluster"
misses.append(word)
else:
result[cluster[0]]=result[cluster[0]]+1
print "Our vocab dictionary has {} entries".format(len(result))
ct.dictwriter(os.path.join("~/", chapterdir[0], "outputfiles", "fulldict_"+time.strftime("%H_%M_%m_%d")), result)
# featuredict= {key:value for key, value in vocab.items() if value > float(threshold) }
# print "Our feature dictionary has {} entries\n---------------\n".format(len(featuredict))
# print "This is our featuredict", featuredict
# ct.dictwriter(os.path.join("~/", chapterdir[0], "outputfiles", "featuredict_"+time.strftime("%H_%M_%m_%d")), featuredict)
print "misses", len(misses), set(misses)
print result
return result
def rebusfinder_too(input_path):
"""
The rebus_too finder.
It uses a list of expressions, pre-established thru "identifying_rebus_too_1022.py", to count
instances where a writer uses "2" instead of "too".
"""
predict=defaultdict(int)
postdict=defaultdict(int)
for number in [2]:
results=[]
#this is the regular expression to identify instances of the number studied
numberregex=re.compile("\W([a-z]+)\s*("+punctuationregex+")?\s*("+unicode(number)+")(?:\s+)?("+punctuationregex+")?(?:\s+)?([a-z]+)\W")
print numberregex.pattern
#dicts to store statistics about context of number
h0dict=defaultdict(int)
h2dict=defaultdict(int)
#lists to store results and previous search patterns fed into tokenfinder to avoid duplicate output
previous_patterns=[]
results=[]
for pati in [i for i in os.listdir(input_path) if not i.startswith(".")]:
for fil in [i for i in os.listdir(os.path.join(input_path, pati)) if not i.startswith(".")]:
fili=codecs.open(os.path.join(input_path, pati, fil), "r", "utf-8")
inputad=ct.adtextextractor(fili.read(), fil)
inputad=ct.adcleaner(inputad, replace_linebreak=True)
inputad=inputad.lower()
hits=numberregex.findall(inputad)
#this weeds out all the phonenumbers.
hits=[h for h in hits if h[0] not in writtennumberdict and h[2] not in writtennumberdict]
for h in hits:
#this is needed for instance where there is no punctuation
h=[" " if i == "" else i for i in h]
"""
thus
[(u'of', 'IN'), (u'2', 'CD'), (u',', ','), (u'single', 'JJ')]
pre, "2", optional punctuation, post
"""
[pre, pre_punct, number, punct, post]=pos_tag(h)
if (
#unique items catcher
(pre[0] in ["date"])
or
(pre[0] in ["it"] and post[0] in ["i"])
or
(pre[0] in ["cook"] and post[0] in ["im"])
or
(pre[0] in ["kids"] and post[0] in ["young"])
or
(pre[0] in ["life", "way"] and post[0] in ["short"])
or
(pre[0] in ["that"] and post[0] in ["hard"])
or
(pre[0] in ["real"] and post[0] in ["hope"])
or
(pre[0] in ["me"] and post[0] in ["if"])
or
(pre[0] in ["dogs"] and post[0] in ["if"])
or
(pre[0] in ["can"] and post[0] in ["but"])
or
(pre[0] in ["kool"] and not post[0] in ["even"])
or
(pre[0] in ["on"] and punct[0] not in [" "] and inputad.split()[inputad.split().index(pre[0])-1] == "later")# and (h[h.index(pre[0])] == "later"))
or
(pre[0] in ["love"] and punct[0] not in [" "] and post[0] in ["msg"])
or
(pre[0] in ["real"] and post[0] in ["have"])
or
#BIGGER NETS
#you be too in front of punctuation catch
(pre[0] in ["be", "b", "are", "r"] and punct[0] not in [" ", "-", ")"])
or
#this is if we know the pre-word and 2 is followed by punctuation
# cf 'intellectualy ability 2. '
(pre[0] in prewords_withpunct and punct[0] not in [" ", ")", ":"])
or
#this is if we know the word to follow
# cf 'not 2 late.' collected in postwords
(post[0] in postwords)
or
#this is if we know the word to precede
(pre[0] in prewords)
):
print "\n\n***", [pre, number, punct, post], "**\n", os.path.join(input_path, pati, fil)
results.append((pre, number, punct, post, os.path.join(input_path, pati, fil)))
predict[pre[0]]=predict[pre[0]]+1
postdict[post[0]]=postdict[post[0]]+1
print "original result list is", len(results)
seti=set(results)
print "\n\n", seti
print "the set is ", len(seti)
overlap={k:results.count(k) for k in seti}
print overlap
print {k:overlap[k] for k in overlap if overlap[k] > 1}
print "PRE CONTEXT"
print "\n".join([": ".join([k, unicode(predict[k])]) for k in sorted(predict, key=predict.get, reverse=True)])
print "POST CONTEXT"
print "\n".join([": ".join([k, unicode(postdict[k])]) for k in sorted(postdict, key=postdict.get, reverse=True)])
def rebusfinder_too(input_path, number_dictionary):
"""
This finds words that are represented as numbers.
All combinations \W([a-z]+)\s+("+unicode(number)+")\s+([a-z]+)\W for the number put in are identified.
The lists exclude_pre and exclude_post word for negative contexts in 4.
It prints the results and give type and token counts.
"""
for number in number_dictionary.keys():
#this is for comments to self
print "PRE"
#this is the regular expression to identify instances of the number studied
numberregex = re.compile("\W([a-z]+)\s*(" + punctuationregex +
")?\s*(" + unicode(number) + ")(?:\s+)?(" +
punctuationregex + ")?(?:\s+)?([a-z]+)\W")
print numberregex.pattern
#dicts to store statistics about context of number
h0dict = defaultdict(int)
h2dict = defaultdict(int)
#lists to store results and previous search patterns fed into tokenfinder to avoid duplicate output
previous_patterns = []
results = []
for pati in [
i for i in os.listdir(input_path) if not i.startswith(".")
]:
for fil in [
i for i in os.listdir(os.path.join(input_path, pati))
if not i.startswith(".")
]:
fili = codecs.open(os.path.join(input_path, pati, fil), "r",
"utf-8")
inputad = ct.adtextextractor(fili.read(), fil)
inputad = ct.adcleaner(inputad, replace_linebreak=True)
inputad = inputad.lower()
hits = numberregex.findall(inputad)
#this weeds out all the phonenumbers.
hits = [
h for h in hits if h[0] not in writtennumberdict
and h[2] not in writtennumberdict
]
for h in hits:
h = ["" if i == "" else i for i in h]
#print "h in hits", h
if not any(
regex.match(h[2])
for regex in exclude_post_context) and not any(
regex.match(h[0])
for regex in exclude_pre_context):
tagged = pos_tag(h)
#print tagged
#if h[2] not in [" "]:
#print tagged, os.path.join(input_path, pati, fil)
#print inputad
h0dict[h[0]] = h0dict[h[0]] + 1
h2dict[h[2]] = h2dict[h[2]] + 1
h0dict[tagged[0][1]] = h0dict[tagged[0][1]] + 1
h2dict[tagged[2][1]] = h2dict[tagged[2][1]] + 1
#taking out trash
if ((tagged[0][1] in ["DT", "JJS", "TO", "PRP$"])
or (tagged[0][1] == "IN"
and h[0] not in ["out", "like"]) or
(tagged[0][1] in ["VBG"] and h[0] not in [
"talking", "responding", "waiting", "getting",
"looking", "going", "trying"
]) or (tagged[0][1] in ["VB", "VBD", "VBP", "VBZ"]
and tagged[2][1] in ["JJ"]) or
#this is where we screw up
(tagged[2][1] in ["NNS"] and h[2] not in [
"chat", "kiss", "go", "know", "find", "do",
"c", "knees"
]) or (tagged[2][1] == "IN") or
(tagged[2][1] == "CC" and h[2] not in ["but"]) or
# #we don't need this if we are to just ignore whatever goes thru all of it
# #TEMPTEMPTEMP
(h[0] in [
"be", "other", "s", "type", "was", "work",
"im", "baths", "you", "maybe", "big", "day",
"o", "round", "ride", "avengers", "kids",
"had", "number", "have", "like", "here",
"size", "got", "are", "send", "only", "have",
"go", "is", "bedroom", "but", "beautiful",
"nice"
]) or (h[2] in [
"face", "new", "faced", "wonderful", "must",
"min", "short", "si", "br", "step", "start",
"so", "out", "story", "bdrm", "other", "out",
"story", "yr", "looking", "more", "but", "hrs",
"bedroom"
]) or
(tagged[2][1] in ["JJ", "VBD", "VBZ", "VBG"])):
#print "killed",tagged, "\n"
pass
#
# #finding the good
elif ((tagged[2][1] in ["DT", "CD", "EX", "NNS", "VB"])
or
(tagged[2][1] in ["JJ"] and h[0] in ["opposed"])
or (tagged[2][1] in ["PRP"]
and not nounregex.match(tagged[0][1]))
or (h[0] == "have" and h[2]
in ["browse", "force", "go", "send", "talk"])
or (h[0] == "like"
and h[2] not in ["furry", "cuz", "straight"])
or (h[0] in ["here"]
and nounregex.match(tagged[2][1])) or
#really what we are exluding here is anything non-Verb or Noun
# # we can consider replacing this with a regex
(h[0] in ["need", "me", "pics"]
and tagged[2][1] not in ["JJ", "JJR", "MD"])
or (h[0] in [
"momma", "women", "delighted", "tryn",
"respond", "travel", "veldkum", "happness",
"pool", "lots", "bbw", "willin", "luvz",
"place", "time", "married", "pixs", "boy",
"pictures", "brickz", "somebody", "memphis",
"cell", "fear", "hoop", "open", "goes",
"afraid", "speak", "lady", "needs",
"attracted", "doms", "bottom", "head",
"apply", "drive", "pic", "newer", "pinned",
"luvs", "sumbody", "face", "due", "tryin",
"line", "has", "close", "interested", "alot",
"oral", "talk", "new", "girl", "up",
"scared", "willing", "cam", "loves", "c**k",
"out", "u", "nice", "how", "free", "hard",
"hope", "able", "someone", "man", "woman",
"male", "down", "love", "luv", "ready",
"want", "wants"
] + [
"talking", "responding", "waiting",
"getting", "looking", "lookin", "going",
"trying"
]) or (h[2] in [
"survive", "brag", "blow", "grab", "feel",
"send", "connect", "hearing", "say", "read",
"contact", "please", "run", "host", "kno",
"talk", "just", "add", "text", "chill",
"hang", "date", "find", "chat", "show", "u",
"meet", "her", "hear", "me", "my", "b",
"know", "play", "do", "suck", "go", "get",
"f**k"
])):
print "hooked the plusloop", tagged
#print tagged
results.append(tagged)
h0dict[h[0]] = h0dict[h[0]] + 1
h2dict[h[2]] = h2dict[h[2]] + 1
else:
pass
if tagged[2][
1]: #=="VB":# in ["VBP", "VBG"]:#=="go":#:# in ['my']:#, 'know', 'my']:#["me", "need", "man"]:# == "down":#h[2] not in ["have", "and", "like", "hear"]:
#print tagged
#print "elseloop", tagged
h0dict[h[0]] = h0dict[h[0]] + 1
h2dict[h[2]] = h2dict[h[2]] + 1
h0dict[tagged[0][1]] = h0dict[tagged[0][1]] + 1
h2dict[tagged[2][1]] = h2dict[tagged[2][1]] + 1
print "We have {} items with a token count of {}".format(
len(h0dict.keys()), sum(h0dict.values()))
h0dict = {k: v for k, v in h0dict.items() if v > 0}
print "\n\n", number, "\npretext here be the results\n\n"
print "\n".join([
": ".join([
k,
unicode(h0dict[k]), ".".join(
word2vecwordfinder([
k
], '/Users/ps22344/Downloads/chapter2/current/clusters_74_19_45_07_31.json'
))
]) for k in sorted(h0dict, key=h0dict.get, reverse=True)
])
print "\n\n", number, "\nposttext here be the results\n\n"
print "\n".join([
": ".join([
k,
unicode(h2dict[k]), ".".join(
word2vecwordfinder([
k
], '/Users/ps22344/Downloads/chapter2/current/clusters_74_19_45_07_31.json'
))
]) for k in sorted(h2dict, key=h2dict.get, reverse=True)
])
print "We have {} post items with a token count of {}".format(
len(h2dict.keys()), sum(h2dict.values()))
print "We have {} pre items with a token count of {}".format(
len(h0dict.keys()), sum(h0dict.values()))
return results
def rebusfinder_too(input_path, number_dictionary):
"""
This finds words that are represented as numbers.
All combinations \W([a-z]+)\s+("+unicode(number)+")\s+([a-z]+)\W for the number put in are identified.
The lists exclude_pre and exclude_post word for negative contexts in 4.
It prints the results and give type and token counts.
"""
for number in number_dictionary.keys():
#this is for comments to self
print "PRE"
#this is the regular expression to identify instances of the number studied
numberregex=re.compile("\W([a-z]+)\s*("+punctuationregex+")?\s*("+unicode(number)+")(?:\s+)?("+punctuationregex+")?(?:\s+)?([a-z]+)\W")
print numberregex.pattern
#dicts to store statistics about context of number
h0dict=defaultdict(int)
h2dict=defaultdict(int)
#lists to store results and previous search patterns fed into tokenfinder to avoid duplicate output
previous_patterns=[]
results=[]
for pati in [i for i in os.listdir(input_path) if not i.startswith(".")]:
for fil in [i for i in os.listdir(os.path.join(input_path, pati)) if not i.startswith(".")]:
fili=codecs.open(os.path.join(input_path, pati, fil), "r", "utf-8")
inputad=ct.adtextextractor(fili.read(), fil)
inputad=ct.adcleaner(inputad, replace_linebreak=True)
inputad=inputad.lower()
hits=numberregex.findall(inputad)
#this weeds out all the phonenumbers.
hits=[h for h in hits if h[0] not in writtennumberdict and h[2] not in writtennumberdict]
for h in hits:
#this is needed for instance where there is no punctuation
h=[" " if i == "" else i for i in h]
"""
thus
[(u'of', 'IN'), (u'2', 'CD'), (u',', ','), (u'single', 'JJ')]
pre, "2", optional punctuation, post
"""
[pre, pre_punct, number, punct, post]=pos_tag(h)
if (post[1] in ["NNS"]) and (punct[0] in [" "]):
print "\n\n***", [pre, number, punct, post], "**\n", os.path.join(input_path, pati, fil)
search_pattern=[re.escape(i) for i in [pre[0],number[0], punct[0], post[0]]]
if search_pattern not in previous_patterns:
tk.tokenfinder(["\s*".join(search_pattern)], dir)
previous_patterns.append(search_pattern)
else:
print "SEE TOKENFINDER RESULTS ABOVE\n"
#error catching here
#
# for h in hits:
# if h[2]:#==".":
# print h, os.path.join(input_path, pati, fil)
# print pos_tag(h), "\n"
#if not any (regex.match(h[2]) for regex in exclude_post_context) and not any (regex.match(h[0]) for regex in exclude_pre_context):
#tagged=pos_tag(h), fil
#print tagged
#if h[2] not in [" "]:
# print tagged, os.path.join(input_path, pati, fil)
#print inputad
#h0dict[h[0]]=h0dict[h[0]]+1
#h2dict[h[2]]=h2dict[h[2]]+1
#h0dict[tagged[0][1]]=h0dict[tagged[0][1]]+1
#h2dict[tagged[2][1]]=h2dict[tagged[2][1]]+1
#taking out trash
# if (
# (tagged[0][1] in ["DT", "JJS", "TO", "PRP$"])
# or
# (tagged[0][1]=="IN" and h[0] not in ["out", "like"])
# or
# (tagged[0][1] in ["VBG"] and h[0] not in ["talking", "responding", "waiting", "getting","looking", "going", "trying"])
# or
# (tagged[0][1] in ["VB", "VBD", "VBP", "VBZ"] and tagged[2][1] in ["JJ"])
# or
# #this is where we screw up
# (tagged[2][1] in ["NNS"] and h[2] not in ["chat", "kiss", "go", "know", "find", "do", "c", "knees"])
# or
# (tagged[2][1]=="IN")
# or
# (tagged[2][1]=="CC" and h[2] not in ["but"])
# or
# #we don't need this if we are to just ignore whatever goes thru all of it
# #TEMPTEMPTEMP
# (h[0] in ["be", "other", "s", "type", "was", "work", "im", "baths", "you", "maybe", "big", "day", "o", "round", "ride", "avengers", "kids", "had", "number", "have", "like", "here", "size", "got", "are", "send", "only", "have", "go", "is", "bedroom", "but", "beautiful", "nice"])
# or
# (h[2] in ["face", "new", "faced", "wonderful", "must", "min", "short", "si", "br", "step", "start", "so", "out", "story", "bdrm", "other", "out", "story", "yr", "looking", "more", "but", "hrs", "bedroom"])
# or
# (tagged[2][1] in ["JJ", "VBD", "VBZ", "VBG"])
# ):
# #print "killed",tagged, "\n"
# pass
#
# #finding the good
# elif (
# (tagged[2][1] in ["DT", "CD", "EX", "NNS", "VB"])
# or
# (tagged[2][1] in ["JJ"] and h[0] in ["opposed"])
# or
# (tagged[2][1] in ["PRP"] and not nounregex.match(tagged[0][1]))
# or
# (h[0] == "have" and h[2] in ["browse", "force", "go", "send", "talk"])
# or
# (h[0] == "like" and h[2] not in ["furry", "cuz", "straight"])
# or
# (h[0] in ["here"] and nounregex.match(tagged[2][1]))
# or
# #really what we are exluding here is anything non-Verb or Noun
# # we can consider replacing this with a regex
# (h[0] in ["need", "me", "pics"] and tagged[2][1] not in ["JJ", "JJR", "MD"])
# or
# (h[0] in ["momma", "women", "delighted", "tryn", "respond", "travel", "veldkum", "happness", "pool", "lots", "bbw", "willin", "luvz", "place", "time", "married", "pixs", "boy", "pictures", "brickz", "somebody", "memphis", "cell", "fear", "hoop", "open", "goes", "afraid", "speak", "lady", "needs", "attracted", "doms", "bottom", "head", "apply", "drive", "pic", "newer", "pinned", "luvs", "sumbody", "face", "due", "tryin", "line", "has", "close", "interested", "alot", "oral", "talk", "new", "girl", "up", "scared", "willing", "cam", "loves", "c**k", "out", "u", "nice", "how", "free", "hard", "hope", "able", "someone", "man", "woman", "male", "down", "love", "luv", "ready", "want", "wants"]+["talking", "responding", "waiting", "getting","looking", "lookin", "going", "trying"])
# or
# (h[2] in ["survive", "brag", "blow", "grab", "feel", "send", "connect", "hearing", "say", "read", "contact", "please", "run", "host","kno", "talk", "just", "add", "text", "chill", "hang", "date", "find", "chat", "show", "u", "meet", "her", "hear", "me", "my", "b", "know", "play", "do", "suck", "go", "get", "f**k"])
# ):
# #print "hooked the plusloop", tagged
# print tagged
# results.append(tagged)
# h0dict[h[0]]=h0dict[h[0]]+1
# h2dict[h[2]]=h2dict[h[2]]+1
# else:
# pass
#if tagged[2][1]:#=="VB":# in ["VBP", "VBG"]:#=="go":#:# in ['my']:#, 'know', 'my']:#["me", "need", "man"]:# == "down":#h[2] not in ["have", "and", "like", "hear"]:
# print tagged
#print "elseloop", tagged
# h0dict[h[0]]=h0dict[h[0]]+1
# h2dict[h[2]]=h2dict[h[2]]+1
#h0dict[tagged[0][1]]=h0dict[tagged[0][1]]+1
#h2dict[tagged[2][1]]=h2dict[tagged[2][1]]+1
print "We have {} items with a token count of {}".format(len(h0dict.keys()), sum(h0dict.values()))
h0dict={k:v for k,v in h0dict.items() if v > 0}
print "\n\n", number, "\npretext here be the results\n\n"
print "\n".join([": ".join([k, unicode(h0dict[k]), ".".join(word2vecwordfinder([k], '/Users/ps22344/Downloads/chapter2/current/clusters_74_19_45_07_31.json'))]) for k in sorted(h0dict, key=h0dict.get, reverse=True)])
print "\n\n", number, "\nposttext here be the results\n\n"
print "\n".join([": ".join([k, unicode(h2dict[k]), ".".join(word2vecwordfinder([k], '/Users/ps22344/Downloads/chapter2/current/clusters_74_19_45_07_31.json'))]) for k in sorted(h2dict, key=h2dict.get, reverse=True)])
print "We have {} post items with a token count of {}".format(len(h2dict.keys()), sum(h2dict.values()))
print "We have {} pre items with a token count of {}".format(len(h0dict.keys()), sum(h0dict.values()))
return results
def rebusfinder_too(input_path):
"""
The rebus_too finder.
It uses a list of expressions, pre-established thru "identifying_rebus_too_1022.py", to count
instances where a writer uses "2" instead of "too".
"""
predict=defaultdict(int)
postdict=defaultdict(int)
for number in [2]:
results=[]
#this is the regular expression to identify instances of the number studied
numberregex=re.compile("\W([a-z]+)\s*("+punctuationregex+")?\s*("+unicode(number)+")(?:\s+)?("+punctuationregex+")?(?:\s+)?([a-z]+)\W")
print numberregex.pattern
#dicts to store statistics about context of number
h0dict=defaultdict(int)
h2dict=defaultdict(int)
#lists to store results and previous search patterns fed into tokenfinder to avoid duplicate output
previous_patterns=[]
results=[]
for pati in [i for i in os.listdir(input_path) if not i.startswith(".")]:
for fil in [i for i in os.listdir(os.path.join(input_path, pati)) if not i.startswith(".")]:
fili=codecs.open(os.path.join(input_path, pati, fil), "r", "utf-8")
inputad=ct.adtextextractor(fili.read(), fil)
inputad=ct.adcleaner(inputad, replace_linebreak=True)
inputad=inputad.lower()
hits=numberregex.findall(inputad)
#this weeds out all the phonenumbers.
hits=[h for h in hits if h[0] not in writtennumberdict and h[2] not in writtennumberdict]
for h in hits:
#this is needed for instance where there is no punctuation
h=[" " if i == "" else i for i in h]
"""
thus
[(u'of', 'IN'), (u'2', 'CD'), (u',', ','), (u'single', 'JJ')]
pre, "2", optional punctuation, post
"""
[pre, pre_punct, number, punct, post]=pos_tag(h)
if (
#unique items catcher
(pre[0] in ["date"])
or
(pre[0] in ["it"] and post[0] in ["i"])
or
(pre[0] in ["cook"] and post[0] in ["im"])
or
(pre[0] in ["kids"] and post[0] in ["young"])
or
(pre[0] in ["life", "way"] and post[0] in ["short"])
or
(pre[0] in ["that"] and post[0] in ["hard"])
or
(pre[0] in ["real"] and post[0] in ["hope"])
or
(pre[0] in ["me"] and post[0] in ["if"])
or
(pre[0] in ["dogs"] and post[0] in ["if"])
or
(pre[0] in ["can"] and post[0] in ["but"])
or
(pre[0] in ["kool"] and not post[0] in ["even"])
or
(pre[0] in ["on"] and punct[0] not in [" "] and inputad.split()[inputad.split().index(pre[0])-1] == "later")# and (h[h.index(pre[0])] == "later"))
or
(pre[0] in ["love"] and punct[0] not in [" "] and post[0] in ["msg"])
or
(pre[0] in ["real"] and post[0] in ["have"])
or
#BIGGER NETS
#you be too in front of punctuation catch
(pre[0] in ["be", "b", "are", "r"] and punct[0] not in [" ", "-", ")"])
or
#this is if we know the pre-word and 2 is followed by punctuation
# cf 'intellectualy ability 2. '
(pre[0] in prewords_withpunct and punct[0] not in [" ", ")", ":"])
or
#this is if we know the word to follow
# cf 'not 2 late.' collected in postwords
(post[0] in postwords)
or
#this is if we know the word to precede
(pre[0] in prewords)
):
print "\n\n***", [pre, number, punct, post], "**\n", os.path.join(input_path, pati, fil)
results.append((pre, number, punct, post, os.path.join(input_path, pati, fil)))
predict[pre[0]]=predict[pre[0]]+1
postdict[post[0]]=postdict[post[0]]+1
print "original result list is", len(results)
seti=set(results)
print "\n\n", seti
print "the set is ", len(seti)
overlap={k:results.count(k) for k in seti}
print overlap
print {k:overlap[k] for k in overlap if overlap[k] > 1}
print "PRE CONTEXT"
print "\n".join([": ".join([k, unicode(predict[k])]) for k in sorted(predict, key=predict.get, reverse=True)])
print "POST CONTEXT"
print "\n".join([": ".join([k, unicode(postdict[k])]) for k in sorted(postdict, key=postdict.get, reverse=True)])