-
Notifications
You must be signed in to change notification settings - Fork 0
/
notesonlogisticregression.py
376 lines (358 loc) · 15.6 KB
/
notesonlogisticregression.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
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
Python 2.7.12 (v2.7.12:d33e0cf91556, Jun 26 2016, 12:10:39)
[GCC 4.2.1 (Apple Inc. build 5666) (dot 3)] on darwin
Type "copyright", "credits" or "license()" for more information.
>>> WARNING: The version of Tcl/Tk (8.5.9) in use may be unstable.
Visit http://www.python.org/download/mac/tcltk/ for current information.
RESTART: /Users/Ryan/github/spis16-project-planning-datamining-Jose-Ryan/youtubetitles.py
Variables: cBDict, cBData, cBTitles, cBWords, normDict, normData, normTitles, normWords
Already ran:
newDict = defaultdict(int)
for w in cBWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
for w in normWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
allWords = []
allWords = [[newDict[w],w] for w in newDict.keys()]
allWords.sort()
allWords.reverse()
words = [w[1] for w in allWords[:1500]]
wordId = dict(zip(words, range(1500)))
titleList = cBTitles + normTitles
X = [feature(d, wordId) for d in titleList]
>>> import sklearn
>>> y = [1] * len(cBTitles) + [0] * len(normTitles)
>>> from sklearn import LinearRegression
Traceback (most recent call last):
File "<pyshell#2>", line 1, in <module>
from sklearn import LinearRegression
ImportError: cannot import name LinearRegression
>>> from sklearn import LinearRegression()
SyntaxError: invalid syntax
>>> from sklearn import Linear_Regression
Traceback (most recent call last):
File "<pyshell#4>", line 1, in <module>
from sklearn import Linear_Regression
ImportError: cannot import name Linear_Regression
>>> from sklearn import LinearModel
Traceback (most recent call last):
File "<pyshell#5>", line 1, in <module>
from sklearn import LinearModel
ImportError: cannot import name LinearModel
>>> history
Traceback (most recent call last):
File "<pyshell#6>", line 1, in <module>
history
NameError: name 'history' is not defined
>>>
RESTART: /Users/Ryan/github/spis16-project-planning-datamining-Jose-Ryan/youtubetitles.py
Variables: cBDict, cBData, cBTitles, cBWords, normDict, normData, normTitles, normWords
Already ran:
newDict = defaultdict(int)
for w in cBWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
for w in normWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
allWords = []
allWords = [[newDict[w],w] for w in newDict.keys()]
allWords.sort()
allWords.reverse()
words = [w[1] for w in allWords[:1500]]
wordId = dict(zip(words, range(1500)))
titleList = cBTitles + normTitles
X = [feature(d, wordId) for d in titleList]
>>> countPunct("The. Man. Ran, over(the dog!!!")
7
>>> countPunct(titleList[34])
0
>>> titleList[34]
u'THE SADDEST MAN ON YOUTUBE FINDS LOVE'
>>>
RESTART: /Users/Ryan/github/spis16-project-planning-datamining-Jose-Ryan/youtubetitles.py
Variables: cBDict, cBData, cBTitles, cBWords, normDict, normData, normTitles, normWords
Already ran:
newDict = defaultdict(int)
for w in cBWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
for w in normWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
allWords = []
allWords = [[newDict[w],w] for w in newDict.keys()]
allWords.sort()
allWords.reverse()
words = [w[1] for w in allWords[:1500]]
wordId = dict(zip(words, range(1500)))
titleList = cBTitles + normTitles
X = [feature(d, wordId) for d in titleList]
y = [1] * len(cBTitles) + [0] * len(normTitles)
>>> cBList[24]
Traceback (most recent call last):
File "<pyshell#10>", line 1, in <module>
cBList[24]
NameError: name 'cBList' is not defined
>>> cBTitles[24]
u'HOW TO TAKE SHOWERS WITH YOUTUBERS'
>>> countCaps(cBTitles[24])
1.0
>>> test = "AbAbAb"
>>> countCaps(test)
0.5
>>> test = "AbAbAb "
>>> countCaps(test)
0.5714285714285714
>>>
RESTART: /Users/Ryan/github/spis16-project-planning-datamining-Jose-Ryan/youtubetitles.py
Variables: cBDict, cBData, cBTitles, cBWords, normDict, normData, normTitles, normWords
Already ran:
newDict = defaultdict(int)
for w in cBWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
for w in normWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
allWords = []
allWords = [[newDict[w],w] for w in newDict.keys()]
allWords.sort()
allWords.reverse()
words = [w[1] for w in allWords[:1500]]
wordId = dict(zip(words, range(1500)))
titleList = cBTitles + normTitles
X = [feature(d, wordId) for d in titleList]
y = [1] * len(cBTitles) + [0] * len(normTitles)
>>> test = "AbAbAb "
>>> countCaps(test)
0.5
>>> countPunct(test)
0
>>> titleList[34]
u'THE SADDEST MAN ON YOUTUBE FINDS LOVE'
>>> titleList[100]
u'6 MORE OF THE MOST ANNOYING PEOPLE IN CS:GO'
>>> titleList[500]
u'Little Shop Of Horrors - Feed Me (Git It)'
>>> countCaps(titleList[500])
0.3333333333333333
>>>
RESTART: /Users/Ryan/github/spis16-project-planning-datamining-Jose-Ryan/youtubetitles.py
Variables: cBDict, cBData, cBTitles, cBWords, normDict, normData, normTitles, normWords
Already ran:
newDict = defaultdict(int)
for w in cBWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
for w in normWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
allWords = []
allWords = [[newDict[w],w] for w in newDict.keys()]
allWords.sort()
allWords.reverse()
words = [w[1] for w in allWords[:1500]]
wordId = dict(zip(words, range(1500)))
titleList = cBTitles + normTitles
X = [feature(d, wordId) for d in titleList]
y = [1] * len(cBTitles) + [0] * len(normTitles)
>>> y[-2:]
[1, 3]
>>> y[-5:]
[0, 0, 0, 1, 3]
>>> len(x)
Traceback (most recent call last):
File "<pyshell#26>", line 1, in <module>
len(x)
NameError: name 'x' is not defined
>>> len(X)
972
>>> len(y)
974
>>> 3 + 2
5
>>> test = feature(titleList[3], wordId)
>>> len(test)
703
>>>
RESTART: /Users/Ryan/github/spis16-project-planning-datamining-Jose-Ryan/youtubetitles.py
Variables: cBDict, cBData, cBTitles, cBWords, normDict, normData, normTitles, normWords
Already ran:
newDict = defaultdict(int)
for w in cBWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
for w in normWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
allWords = []
allWords = [[newDict[w],w] for w in newDict.keys()]
allWords.sort()
allWords.reverse()
words = [w[1] for w in allWords[:1500]]
wordId = dict(zip(words, range(1500)))
titleList = cBTitles + normTitles
X = [feature(d, wordId) for d in titleList]
y = [1] * len(cBTitles) + [0] * len(normTitles)
>>> len(X)
971
>>> len(y)
971
>>> import sklearn
>>> from sklearn.linear_model import LogisticRegression
>>> logistic = LogisticRegression()
>>> lr = linear_model.logistic
Traceback (most recent call last):
File "<pyshell#41>", line 1, in <module>
lr = linear_model.logistic
NameError: name 'linear_model' is not defined
>>> lr = linear_model.LogisticRegression
Traceback (most recent call last):
File "<pyshell#42>", line 1, in <module>
lr = linear_model.LogisticRegression
NameError: name 'linear_model' is not defined
>>> import sklearn
>>> from sklearn.linear_model import LogisticRegression
>>> logistic = LogisticRegression()
>>> lr = logistic.fit(X, y)
>>> yhat =lr.predict(X)
>>> from sklearn.metrics import accuracy_score
>>> accuracy_score(y, yhat)
0.97528321318228628
>>>
RESTART: /Users/Ryan/github/spis16-project-planning-datamining-Jose-Ryan/youtubetitles.py
Traceback (most recent call last):
File "/Users/Ryan/github/spis16-project-planning-datamining-Jose-Ryan/youtubetitles.py", line 257, in <module>
X = [feature2(d, wordId) for d in titleList]
File "/Users/Ryan/github/spis16-project-planning-datamining-Jose-Ryan/youtubetitles.py", line 226, in feature2
feat.append(countCaps(datum))
NameError: global name 'feat' is not defined
>>>
RESTART: /Users/Ryan/github/spis16-project-planning-datamining-Jose-Ryan/youtubetitles.py
Variables: cBDict, cBData, cBTitles, cBWords, normDict, normData, normTitles, normWords
Already ran:
newDict = defaultdict(int)
for w in cBWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
for w in normWords:
newDict[w[1].lower()] = newDict[w[1].lower()] + w[0]
allWords = []
allWords = [[newDict[w],w] for w in newDict.keys()]
allWords.sort()
allWords.reverse()
words = [w[1] for w in allWords[:1500]]
wordId = dict(zip(words, range(1500)))
titleList = cBTitles + normTitles
X = [feature(d, wordId) for d in titleList]
y = [1] * len(cBTitles) + [0] * len(normTitles)
>>> import sklearn
>>> from sklearn.linear_model import LogisticRegression
>>> logistic = LogisticRegression()
>>> lr = logistic.fit(X, y)
>>> yhat =lr.predict(X)
>>> yhat
array([1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0,
1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,
0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 0, 0, 0])
>>> from sklearn.metrics import accuracy_score
>>> accuracy_score(y, yhat)
0.95056642636457256
>>> lr.predict([cBTitles[2]])
Warning (from warnings module):
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/utils/validation.py", line 386
DeprecationWarning)
DeprecationWarning: Passing 1d arrays as data is deprecated in 0.17 and willraise ValueError in 0.19. Reshape your data either using X.reshape(-1, 1) if your data has a single feature or X.reshape(1, -1) if it contains a single sample.
Traceback (most recent call last):
File "<pyshell#58>", line 1, in <module>
lr.predict([cBTitles[2]])
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/linear_model/base.py", line 268, in predict
scores = self.decision_function(X)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/linear_model/base.py", line 249, in decision_function
% (X.shape[1], n_features))
ValueError: X has 1 features per sample; expecting 2
>>> type(yhat)
<type 'numpy.ndarray'>
>>> yhat =lr.predict(titleList[24])
Traceback (most recent call last):
File "<pyshell#60>", line 1, in <module>
yhat =lr.predict(titleList[24])
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/linear_model/base.py", line 268, in predict
scores = self.decision_function(X)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/linear_model/base.py", line 249, in decision_function
% (X.shape[1], n_features))
ValueError: X has 1 features per sample; expecting 2
>>> yhat =lr.predict(X)
>>> accuracy_score([titleList[24]], yhat)
Traceback (most recent call last):
File "<pyshell#62>", line 1, in <module>
accuracy_score([titleList[24]], yhat)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/metrics/classification.py", line 172, in accuracy_score
y_type, y_true, y_pred = _check_targets(y_true, y_pred)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/metrics/classification.py", line 72, in _check_targets
check_consistent_length(y_true, y_pred)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/utils/validation.py", line 176, in check_consistent_length
"%s" % str(uniques))
ValueError: Found arrays with inconsistent numbers of samples: [ 1 971]
>>> yhat =lr.predict([titleList[24]])
Warning (from warnings module):
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/utils/validation.py", line 386
DeprecationWarning)
DeprecationWarning: Passing 1d arrays as data is deprecated in 0.17 and willraise ValueError in 0.19. Reshape your data either using X.reshape(-1, 1) if your data has a single feature or X.reshape(1, -1) if it contains a single sample.
Traceback (most recent call last):
File "<pyshell#63>", line 1, in <module>
yhat =lr.predict([titleList[24]])
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/linear_model/base.py", line 268, in predict
scores = self.decision_function(X)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/linear_model/base.py", line 249, in decision_function
% (X.shape[1], n_features))
ValueError: X has 1 features per sample; expecting 2
>>> title = titleList[24]
>>> titleFeat = feature(title, wordId)
>>> lr.predict([titleFeat])
Traceback (most recent call last):
File "<pyshell#66>", line 1, in <module>
lr.predict([titleFeat])
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/linear_model/base.py", line 268, in predict
scores = self.decision_function(X)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/linear_model/base.py", line 249, in decision_function
% (X.shape[1], n_features))
ValueError: X has 703 features per sample; expecting 2
>>> predict([titleFeat])
Traceback (most recent call last):
File "<pyshell#67>", line 1, in <module>
predict([titleFeat])
NameError: name 'predict' is not defined
>>> titleFeat = feature2(title, wordId)
>>> lr.predict([titleFeat])
array([1])
>>>