-
Notifications
You must be signed in to change notification settings - Fork 0
/
samgrams.py
258 lines (254 loc) · 8.85 KB
/
samgrams.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
class Samgrams(object):
from nltk import tokenize,tag
import cPickle
import os.path
import re
# def __len__(self,x=None):
# if x == None:
# self.len = 0
# else:
# self.len = len(x)
def grams(self,n,print_results,text=None):
""":param words: a list of words"""
if n == 0:
raise ValueError("n must be greater than 0")
else:
d = dict()
start_index = 0
end_index = n
while end_index <= (len(text)):
gram = "".join((" "+word) for word in text[start_index:(end_index)])
#print gram
if gram in d.keys():
d[gram] += 1
else:
d[gram] = 1
start_index += 1
end_index += 1
self.sorted_d = sorted(d.items(),key=lambda x: x[1],reverse=True)
#sorted_d = sorted(d.items(), key=lambda item: item[1])
#sorted_d.reverse()
if print_results == True:
print self.sorted_d
return self.sorted_d
def gramsDict(self,n,print_results,text=None):
""" :param text: the text to be analyzed for n-grams
:type text: a str or a list"""
if not text:
text = self.words
else:
if type(text) == str:
self.words = nltk.tokenize.wordpunct_tokenize(text)
elif type(text) == set:
self.words = list(text)
elif type(text) == list:
self.words = text
else:
raise TypeError("text must be str or list")
print "training model..."
self.model = dict()
i = 1
while i <= n:
self.model[i] = self.grams(i,print_results,text)
#print ngramsDict[i]
i += 1
if print_results == True:
print self.model
#return self.model
def get_model(self,fname,part,n=0):
import re
""" NOTE: to prevent misidentification of pickled components, the n-gram model and n-gram frequencies
should be pickled and retrieved separately.
:param fname: name of the file containing the pickled item to be retrieved
:type fname: str
:param part: what part of the model is being retrieved:
grams: self.model[n] (will raise a ValueError if there's no corresponding self.model[n])
model: self.model
freq: self.ngramsFreqDict[n] (will raise a ValueError if there's no corresponding self.ngramsFreqDict[n])
freqs: self.ngramsFreqDict
:type part: str
:param n: if part == grams or freq, picks out which slice is being unpickled
:type n: int"""
if re.match(fname,".pickle") == False:
fname += ".pickle"
if os.path.isfile(fname) == False:
raise IOError("no such file")
else:
f_in = open(fname,"rb")
brine = cPickle()
if part == "model":
self.model = brine.load(f_in)
elif part == "freqs":
self.ngramsFreqDict = brine.load(f_in)
elif part == "grams":
if n == 0:
raise ValueError("n must be greater than 0")
else:
if self.model:
if n in self.model.keys():
if raw_input("{0}-gram model found. Overwrite? (y/n)".format(n)) == "n":
self.model[n] = brine.load(f_in)
elif raw_input("{0}-gram model found. Overwrite? (y/n)".format(n)) == "y":
print "not overwriting {0}-gram model".format(n)
return None
else:
self.model = dict()
self.model[n] = brine.load(f_in)
elif part == "freq":
if n == 0:
raise ValueError("n must be greater than 0")
else:
if self.ngramsFreqDict:
if n in self.ngramsFreqDict.keys():
if raw_input("{0}-gram frequencies found. Overwrite? (y/n)".format(n)) == "n":
self.model[n] = brine.load(f_in)
elif raw_input("{0}-gram frequencies found. Overwrite? (y/n)".format(n)) == "y":
print "not overwriting {0}-gram frequencies".format(n)
return None
else:
self.ngramsFreqDict = dict()
self.ngramsFreqDict[n] = brine.load(f_in)
else:
raise ValueError("invalid choice. part must be grams, model, freq, or freqs")
def __init__(self,text,n=0):
"""if you want to load (parts of) a model from pre-existing .pickle files, instantiate a new Samgrams object
with text=None, then call get_model"""
if text != None:
if type(text) == str:
self.words = nltk.tokenize.wordpunct_tokenize(text)
elif type(text) == set:
self.words = list(text)
elif type(text) == list:
self.words = text
else:
try:
self.words = list(text)
except TypeError:
raise TypeError("text must be iterable")
if n != 0:
self.gramsDict(n,False,text=None)
else:
raise ValueError("n must be greater than 0")
def gramFreqs(self,print_results):
""":param ngrams: an n-gram dictionary as produced by get_gramsDict"""
self.ngramsFreqDict = dict()
for d in self.model:
total = 0
for x in self.model[d]:
total += x[1]
if total == 0:
raise ValueError("%d-gram dictionary appears to be empty" %(d))
continue
else:
fd = dict()
for x in self.model[d]:
fd[x[0]] = (x[1] * 1.0) / total
self.ngramsFreqDict[d] = fd
if print_results == True:
print self.ngramsFreqDict
def get_grams(self,n):
"""print the chosen n-gram model"""
if self.model:
if n in self.model.keys():
return self.model[n]
else:
raise IndexError("n has to be equal to a set of trained ngrams (1-{0})".format(len(self.model.keys())))
else:
raise AttributeError("""no trained model. please load a pickled model with get_model
or train a new one with gramsdict""")
def get_gramsDict(self):
"""print the n-grams model"""
if self.model:
return self.model
else:
raise AttributeError("""no trained model. please load a pickled model with get_model
or train a new one with gramsdict""")
def get_gramFreqs(self,n):
"""print the frequency dictionary for the chosen n-gram"""
if self.ngramsFreqDict:
if n in self.ngramsFreqDict.keys():
return self.ngramsFreqDict[n]
else:
raise IndexError("n has to be equal to a set of frequencies for trained ngrams (1-{0})".format(len(self.ngramsFreqDict.keys())))
else:
raise AttributeError("""no frequencies found. please load a pickled set of frequencies with get_model
or train a new one with gramFreqs""")
def get_allFreqs(self):
"""print self.ngramsFreqDict"""
if self.ngramsFreqDict:
return self.ngramsFreqDict
else:
raise AttributeError("""no frequencies found. please load a pickled set of frequencies with get_model
or train a new one with gramFreqs""")
def pickle_model(self,fname,cuke,n=0):
import re
""" NOTE: to prevent misidentification of pickled components, the n-gram model and n-gram frequencies
should be pickled and retrieved separately.
:param fname: name of the file to be output to
:param fname: str
:param cuke: what you want to pickle
:type cuke: grams: self.model[n] (will raise a ValueError if there's no corresponding self.model[n])
model: self.model
freq: self.ngramsFreqDict[n] (will raise a ValueError if there's no corresponding self.ngramsFreqDict[n])
freqs: self.ngramsFreqDict
:param n: if cuke == grams or freq, picks out which slice to pickle
:type n: int"""
if re.match(fname,".pickle") == False:
fname += ".pickle"
if os.path.isfile(fname):
if raw_input("File exists! Overwrite? (y/n)") == "n":
print "not overwriting file %s" %(str(fname))
return None
else:
pass
choice = cuke
brine = cPickle()
f_out = open(str(fname),"wb")
if choice == "model":
brine.dump(self.model,f_out,protocol=pickle.HIGHEST_PROTOCOL)
print "saved ngram model as {0}".format(fname)
elif choice == "freqs":
brine.dump(self.ngramsFreqDict,f_out,protocol=pickle.HIGHEST_PROTOCOL)
print "saved ngram frequencies as {0}".format(fname)
elif choice == "grams":
if n == 0:
raise ValueError("n must be greater than 0")
elif n in self.model.keys():
brine.dump(self.model[n],f_out,protocol=pickle.HIGHEST_PROTOCOL)
print "saved {0}-grams as {1}".format(n,fname)
else:
raise IndexError("n has to be equal to a set of trained ngrams (1-{0})".format(len(self.model.keys())))
elif choice == "freq":
if n == 0:
raise ValueError("n must be greater than 0")
elif n in self.model.keys():
brine.dump(self.ngramFreqDict[n],f_out,protocol=pickle.HIGHEST_PROTOCOL)
print "saved {0}-gram frequencies as {1}".format(n,fname)
else:
raise IndexError("n has to be equal to a set of trained ngrams (1-{0})".format(len(self.model.keys())))
else:
raise ValueError("invalid choice. options are grams, model, freq, or freqs.")
f_out.close()
# def gen_sent(self,length):
# import re
# import random
# self.str_out = ""
# self.start_p = re.compile(r'^[.?!\n]?')
# self.end_p = re.compile(r'[.?!\n]?$')
# self.starts = {}
# #self.ends = {}
# for d in self.ngramsFreqDict:
# self.starts[d] = []
# for item in d:
# if re.match(self.start_p,item[0])
# self.starts[d].append(item)
# # self.ends[d] = []
# # for item in d:
# # if re.search(self.end_p,item[0])
#
# while len(self.str_out) <= length or not re.match(self.end_p,self.str_out):
#if __name__ == "__main__":
# from nltk.corpus import brown
# t = list(brown.words(categories="adventure"))
# n = get_gramsDict(t,3,False)
# y = get_gramFreqs(n,True)