Spaces:
Runtime error
Runtime error
Michael-Geis
commited on
Commit
•
0e1d213
1
Parent(s):
eaf77fe
removed useless notebooks
Browse files- data-exploration.ipynb +0 -516
- email-extraction.ipynb +0 -19
- library_class.py +0 -25
data-exploration.ipynb
DELETED
@@ -1,516 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"cells": [
|
3 |
-
{
|
4 |
-
"attachments": {},
|
5 |
-
"cell_type": "markdown",
|
6 |
-
"metadata": {},
|
7 |
-
"source": [
|
8 |
-
"# EDA for cleaned arXiv dataset"
|
9 |
-
]
|
10 |
-
},
|
11 |
-
{
|
12 |
-
"attachments": {},
|
13 |
-
"cell_type": "markdown",
|
14 |
-
"metadata": {},
|
15 |
-
"source": [
|
16 |
-
"## Imports"
|
17 |
-
]
|
18 |
-
},
|
19 |
-
{
|
20 |
-
"cell_type": "code",
|
21 |
-
"execution_count": 1,
|
22 |
-
"metadata": {},
|
23 |
-
"outputs": [],
|
24 |
-
"source": [
|
25 |
-
"import pandas as pd\n",
|
26 |
-
"import numpy as np"
|
27 |
-
]
|
28 |
-
},
|
29 |
-
{
|
30 |
-
"attachments": {},
|
31 |
-
"cell_type": "markdown",
|
32 |
-
"metadata": {},
|
33 |
-
"source": [
|
34 |
-
"## Which subject tag occurs the most frequently our 175k dataset?"
|
35 |
-
]
|
36 |
-
},
|
37 |
-
{
|
38 |
-
"cell_type": "code",
|
39 |
-
"execution_count": 2,
|
40 |
-
"metadata": {},
|
41 |
-
"outputs": [
|
42 |
-
{
|
43 |
-
"data": {
|
44 |
-
"text/html": [
|
45 |
-
"<div>\n",
|
46 |
-
"<style scoped>\n",
|
47 |
-
" .dataframe tbody tr th:only-of-type {\n",
|
48 |
-
" vertical-align: middle;\n",
|
49 |
-
" }\n",
|
50 |
-
"\n",
|
51 |
-
" .dataframe tbody tr th {\n",
|
52 |
-
" vertical-align: top;\n",
|
53 |
-
" }\n",
|
54 |
-
"\n",
|
55 |
-
" .dataframe thead th {\n",
|
56 |
-
" text-align: right;\n",
|
57 |
-
" }\n",
|
58 |
-
"</style>\n",
|
59 |
-
"<table border=\"1\" class=\"dataframe\">\n",
|
60 |
-
" <thead>\n",
|
61 |
-
" <tr style=\"text-align: right;\">\n",
|
62 |
-
" <th></th>\n",
|
63 |
-
" <th>Accelerator Physics</th>\n",
|
64 |
-
" <th>Adaptation and Self-Organizing Systems</th>\n",
|
65 |
-
" <th>Algebraic Geometry</th>\n",
|
66 |
-
" <th>Algebraic Topology</th>\n",
|
67 |
-
" <th>Analysis of PDEs</th>\n",
|
68 |
-
" <th>Applications</th>\n",
|
69 |
-
" <th>Applied Physics</th>\n",
|
70 |
-
" <th>Artificial Intelligence</th>\n",
|
71 |
-
" <th>Astrophysics</th>\n",
|
72 |
-
" <th>Astrophysics of Galaxies</th>\n",
|
73 |
-
" <th>...</th>\n",
|
74 |
-
" <th>Strongly Correlated Electrons</th>\n",
|
75 |
-
" <th>Subcellular Processes</th>\n",
|
76 |
-
" <th>Superconductivity</th>\n",
|
77 |
-
" <th>Symbolic Computation</th>\n",
|
78 |
-
" <th>Symplectic Geometry</th>\n",
|
79 |
-
" <th>Systems and Control</th>\n",
|
80 |
-
" <th>Theoretical Economics</th>\n",
|
81 |
-
" <th>Tissues and Organs</th>\n",
|
82 |
-
" <th>Trading and Market Microstructure</th>\n",
|
83 |
-
" <th>UNK</th>\n",
|
84 |
-
" </tr>\n",
|
85 |
-
" </thead>\n",
|
86 |
-
" <tbody>\n",
|
87 |
-
" <tr>\n",
|
88 |
-
" <th>0</th>\n",
|
89 |
-
" <td>False</td>\n",
|
90 |
-
" <td>False</td>\n",
|
91 |
-
" <td>False</td>\n",
|
92 |
-
" <td>False</td>\n",
|
93 |
-
" <td>False</td>\n",
|
94 |
-
" <td>False</td>\n",
|
95 |
-
" <td>False</td>\n",
|
96 |
-
" <td>False</td>\n",
|
97 |
-
" <td>False</td>\n",
|
98 |
-
" <td>False</td>\n",
|
99 |
-
" <td>...</td>\n",
|
100 |
-
" <td>False</td>\n",
|
101 |
-
" <td>False</td>\n",
|
102 |
-
" <td>False</td>\n",
|
103 |
-
" <td>False</td>\n",
|
104 |
-
" <td>False</td>\n",
|
105 |
-
" <td>False</td>\n",
|
106 |
-
" <td>False</td>\n",
|
107 |
-
" <td>False</td>\n",
|
108 |
-
" <td>False</td>\n",
|
109 |
-
" <td>False</td>\n",
|
110 |
-
" </tr>\n",
|
111 |
-
" <tr>\n",
|
112 |
-
" <th>1</th>\n",
|
113 |
-
" <td>False</td>\n",
|
114 |
-
" <td>False</td>\n",
|
115 |
-
" <td>False</td>\n",
|
116 |
-
" <td>False</td>\n",
|
117 |
-
" <td>False</td>\n",
|
118 |
-
" <td>False</td>\n",
|
119 |
-
" <td>False</td>\n",
|
120 |
-
" <td>False</td>\n",
|
121 |
-
" <td>False</td>\n",
|
122 |
-
" <td>False</td>\n",
|
123 |
-
" <td>...</td>\n",
|
124 |
-
" <td>False</td>\n",
|
125 |
-
" <td>False</td>\n",
|
126 |
-
" <td>False</td>\n",
|
127 |
-
" <td>False</td>\n",
|
128 |
-
" <td>False</td>\n",
|
129 |
-
" <td>False</td>\n",
|
130 |
-
" <td>False</td>\n",
|
131 |
-
" <td>False</td>\n",
|
132 |
-
" <td>False</td>\n",
|
133 |
-
" <td>False</td>\n",
|
134 |
-
" </tr>\n",
|
135 |
-
" <tr>\n",
|
136 |
-
" <th>2</th>\n",
|
137 |
-
" <td>False</td>\n",
|
138 |
-
" <td>False</td>\n",
|
139 |
-
" <td>False</td>\n",
|
140 |
-
" <td>False</td>\n",
|
141 |
-
" <td>False</td>\n",
|
142 |
-
" <td>False</td>\n",
|
143 |
-
" <td>False</td>\n",
|
144 |
-
" <td>False</td>\n",
|
145 |
-
" <td>False</td>\n",
|
146 |
-
" <td>False</td>\n",
|
147 |
-
" <td>...</td>\n",
|
148 |
-
" <td>False</td>\n",
|
149 |
-
" <td>False</td>\n",
|
150 |
-
" <td>False</td>\n",
|
151 |
-
" <td>False</td>\n",
|
152 |
-
" <td>False</td>\n",
|
153 |
-
" <td>False</td>\n",
|
154 |
-
" <td>False</td>\n",
|
155 |
-
" <td>False</td>\n",
|
156 |
-
" <td>False</td>\n",
|
157 |
-
" <td>False</td>\n",
|
158 |
-
" </tr>\n",
|
159 |
-
" <tr>\n",
|
160 |
-
" <th>3</th>\n",
|
161 |
-
" <td>False</td>\n",
|
162 |
-
" <td>False</td>\n",
|
163 |
-
" <td>False</td>\n",
|
164 |
-
" <td>False</td>\n",
|
165 |
-
" <td>False</td>\n",
|
166 |
-
" <td>False</td>\n",
|
167 |
-
" <td>False</td>\n",
|
168 |
-
" <td>False</td>\n",
|
169 |
-
" <td>False</td>\n",
|
170 |
-
" <td>False</td>\n",
|
171 |
-
" <td>...</td>\n",
|
172 |
-
" <td>False</td>\n",
|
173 |
-
" <td>False</td>\n",
|
174 |
-
" <td>False</td>\n",
|
175 |
-
" <td>False</td>\n",
|
176 |
-
" <td>False</td>\n",
|
177 |
-
" <td>False</td>\n",
|
178 |
-
" <td>False</td>\n",
|
179 |
-
" <td>False</td>\n",
|
180 |
-
" <td>False</td>\n",
|
181 |
-
" <td>False</td>\n",
|
182 |
-
" </tr>\n",
|
183 |
-
" <tr>\n",
|
184 |
-
" <th>4</th>\n",
|
185 |
-
" <td>False</td>\n",
|
186 |
-
" <td>False</td>\n",
|
187 |
-
" <td>False</td>\n",
|
188 |
-
" <td>False</td>\n",
|
189 |
-
" <td>False</td>\n",
|
190 |
-
" <td>False</td>\n",
|
191 |
-
" <td>False</td>\n",
|
192 |
-
" <td>False</td>\n",
|
193 |
-
" <td>False</td>\n",
|
194 |
-
" <td>False</td>\n",
|
195 |
-
" <td>...</td>\n",
|
196 |
-
" <td>False</td>\n",
|
197 |
-
" <td>False</td>\n",
|
198 |
-
" <td>False</td>\n",
|
199 |
-
" <td>False</td>\n",
|
200 |
-
" <td>False</td>\n",
|
201 |
-
" <td>False</td>\n",
|
202 |
-
" <td>False</td>\n",
|
203 |
-
" <td>False</td>\n",
|
204 |
-
" <td>False</td>\n",
|
205 |
-
" <td>False</td>\n",
|
206 |
-
" </tr>\n",
|
207 |
-
" </tbody>\n",
|
208 |
-
"</table>\n",
|
209 |
-
"<p>5 rows × 150 columns</p>\n",
|
210 |
-
"</div>"
|
211 |
-
],
|
212 |
-
"text/plain": [
|
213 |
-
" Accelerator Physics Adaptation and Self-Organizing Systems \\\n",
|
214 |
-
"0 False False \n",
|
215 |
-
"1 False False \n",
|
216 |
-
"2 False False \n",
|
217 |
-
"3 False False \n",
|
218 |
-
"4 False False \n",
|
219 |
-
"\n",
|
220 |
-
" Algebraic Geometry Algebraic Topology Analysis of PDEs Applications \\\n",
|
221 |
-
"0 False False False False \n",
|
222 |
-
"1 False False False False \n",
|
223 |
-
"2 False False False False \n",
|
224 |
-
"3 False False False False \n",
|
225 |
-
"4 False False False False \n",
|
226 |
-
"\n",
|
227 |
-
" Applied Physics Artificial Intelligence Astrophysics \\\n",
|
228 |
-
"0 False False False \n",
|
229 |
-
"1 False False False \n",
|
230 |
-
"2 False False False \n",
|
231 |
-
"3 False False False \n",
|
232 |
-
"4 False False False \n",
|
233 |
-
"\n",
|
234 |
-
" Astrophysics of Galaxies ... Strongly Correlated Electrons \\\n",
|
235 |
-
"0 False ... False \n",
|
236 |
-
"1 False ... False \n",
|
237 |
-
"2 False ... False \n",
|
238 |
-
"3 False ... False \n",
|
239 |
-
"4 False ... False \n",
|
240 |
-
"\n",
|
241 |
-
" Subcellular Processes Superconductivity Symbolic Computation \\\n",
|
242 |
-
"0 False False False \n",
|
243 |
-
"1 False False False \n",
|
244 |
-
"2 False False False \n",
|
245 |
-
"3 False False False \n",
|
246 |
-
"4 False False False \n",
|
247 |
-
"\n",
|
248 |
-
" Symplectic Geometry Systems and Control Theoretical Economics \\\n",
|
249 |
-
"0 False False False \n",
|
250 |
-
"1 False False False \n",
|
251 |
-
"2 False False False \n",
|
252 |
-
"3 False False False \n",
|
253 |
-
"4 False False False \n",
|
254 |
-
"\n",
|
255 |
-
" Tissues and Organs Trading and Market Microstructure UNK \n",
|
256 |
-
"0 False False False \n",
|
257 |
-
"1 False False False \n",
|
258 |
-
"2 False False False \n",
|
259 |
-
"3 False False False \n",
|
260 |
-
"4 False False False \n",
|
261 |
-
"\n",
|
262 |
-
"[5 rows x 150 columns]"
|
263 |
-
]
|
264 |
-
},
|
265 |
-
"execution_count": 2,
|
266 |
-
"metadata": {},
|
267 |
-
"output_type": "execute_result"
|
268 |
-
}
|
269 |
-
],
|
270 |
-
"source": [
|
271 |
-
"cats = pd.read_parquet('./data/arXiv_cat.parquet')\n",
|
272 |
-
"cats.head()"
|
273 |
-
]
|
274 |
-
},
|
275 |
-
{
|
276 |
-
"cell_type": "code",
|
277 |
-
"execution_count": 3,
|
278 |
-
"metadata": {},
|
279 |
-
"outputs": [
|
280 |
-
{
|
281 |
-
"data": {
|
282 |
-
"text/plain": [
|
283 |
-
"Analysis of PDEs 18944\n",
|
284 |
-
"Combinatorics 18930\n",
|
285 |
-
"Optimization and Control 18284\n",
|
286 |
-
"Mathematical Physics 16381\n",
|
287 |
-
"Probability 15343\n",
|
288 |
-
"dtype: int64"
|
289 |
-
]
|
290 |
-
},
|
291 |
-
"execution_count": 3,
|
292 |
-
"metadata": {},
|
293 |
-
"output_type": "execute_result"
|
294 |
-
}
|
295 |
-
],
|
296 |
-
"source": [
|
297 |
-
"## Calculate the number of times each tag appears\n",
|
298 |
-
"\n",
|
299 |
-
"totals = cats.sum(axis=0).sort_values(ascending=False)\n",
|
300 |
-
"totals.head()"
|
301 |
-
]
|
302 |
-
},
|
303 |
-
{
|
304 |
-
"cell_type": "code",
|
305 |
-
"execution_count": 5,
|
306 |
-
"metadata": {},
|
307 |
-
"outputs": [
|
308 |
-
{
|
309 |
-
"data": {
|
310 |
-
"text/html": [
|
311 |
-
"<div>\n",
|
312 |
-
"<style scoped>\n",
|
313 |
-
" .dataframe tbody tr th:only-of-type {\n",
|
314 |
-
" vertical-align: middle;\n",
|
315 |
-
" }\n",
|
316 |
-
"\n",
|
317 |
-
" .dataframe tbody tr th {\n",
|
318 |
-
" vertical-align: top;\n",
|
319 |
-
" }\n",
|
320 |
-
"\n",
|
321 |
-
" .dataframe thead th {\n",
|
322 |
-
" text-align: right;\n",
|
323 |
-
" }\n",
|
324 |
-
"</style>\n",
|
325 |
-
"<table border=\"1\" class=\"dataframe\">\n",
|
326 |
-
" <thead>\n",
|
327 |
-
" <tr style=\"text-align: right;\">\n",
|
328 |
-
" <th></th>\n",
|
329 |
-
" <th>raw_title</th>\n",
|
330 |
-
" <th>clean_title</th>\n",
|
331 |
-
" <th>hyph_in_title</th>\n",
|
332 |
-
" <th>raw_abstract</th>\n",
|
333 |
-
" <th>clean_abstract</th>\n",
|
334 |
-
" <th>hyph_in_abstract</th>\n",
|
335 |
-
" <th>authors_parsed</th>\n",
|
336 |
-
" <th>cat</th>\n",
|
337 |
-
" <th>update_date</th>\n",
|
338 |
-
" <th>id</th>\n",
|
339 |
-
" </tr>\n",
|
340 |
-
" </thead>\n",
|
341 |
-
" <tbody>\n",
|
342 |
-
" <tr>\n",
|
343 |
-
" <th>42</th>\n",
|
344 |
-
" <td>The Prolongation Problem for the Heavenly Equa...</td>\n",
|
345 |
-
" <td>The Prolongation Problem for the Heavenly Equa...</td>\n",
|
346 |
-
" <td>None</td>\n",
|
347 |
-
" <td>We provide an exact regular solution of an o...</td>\n",
|
348 |
-
" <td>We provide an exact regular solution of an o...</td>\n",
|
349 |
-
" <td>None</td>\n",
|
350 |
-
" <td>[['Palese', 'M.', '', 'Dept. Math. Univ. of To...</td>\n",
|
351 |
-
" <td>[math.AP, math-ph, math.MP]</td>\n",
|
352 |
-
" <td>2022-09-21</td>\n",
|
353 |
-
" <td>math/0311218</td>\n",
|
354 |
-
" </tr>\n",
|
355 |
-
" <tr>\n",
|
356 |
-
" <th>55</th>\n",
|
357 |
-
" <td>Null Controllability for a Degenerate Structur...</td>\n",
|
358 |
-
" <td>Null Controllability for a Degenerate Structur...</td>\n",
|
359 |
-
" <td>None</td>\n",
|
360 |
-
" <td>In this paper, we consider the infinite dime...</td>\n",
|
361 |
-
" <td>In this paper, we consider the infinite dime...</td>\n",
|
362 |
-
" <td>[final-state]</td>\n",
|
363 |
-
" <td>[['Simporé', 'Yacouba', ''], ['gantouh', 'Yass...</td>\n",
|
364 |
-
" <td>[math.OC, math.AP]</td>\n",
|
365 |
-
" <td>2022-09-09</td>\n",
|
366 |
-
" <td>2209.03645</td>\n",
|
367 |
-
" </tr>\n",
|
368 |
-
" <tr>\n",
|
369 |
-
" <th>59</th>\n",
|
370 |
-
" <td>Voting models and semilinear parabolic equations</td>\n",
|
371 |
-
" <td>Voting models and semilinear parabolic equations</td>\n",
|
372 |
-
" <td>None</td>\n",
|
373 |
-
" <td>We present probabilistic interpretations of ...</td>\n",
|
374 |
-
" <td>We present probabilistic interpretations of ...</td>\n",
|
375 |
-
" <td>[semi-linear, Fisher-KPP, group-based, pushmi-...</td>\n",
|
376 |
-
" <td>[['An', 'Jing', ''], ['Henderson', 'Christophe...</td>\n",
|
377 |
-
" <td>[math.AP, math.PR]</td>\n",
|
378 |
-
" <td>2022-09-09</td>\n",
|
379 |
-
" <td>2209.03435</td>\n",
|
380 |
-
" </tr>\n",
|
381 |
-
" <tr>\n",
|
382 |
-
" <th>72</th>\n",
|
383 |
-
" <td>Flows of $G_2$-Structures associated to Calabi...</td>\n",
|
384 |
-
" <td>Flows of LATEX associated to Calabi-Yau Manif...</td>\n",
|
385 |
-
" <td>[Calabi-Yau]</td>\n",
|
386 |
-
" <td>We establish a correspondence between a para...</td>\n",
|
387 |
-
" <td>We establish a correspondence between a para...</td>\n",
|
388 |
-
" <td>[Monge-Ampere, Monge-Ampere, torsion-free, Ric...</td>\n",
|
389 |
-
" <td>[['Picard', 'Sébastien', ''], ['Suan', 'Caleb'...</td>\n",
|
390 |
-
" <td>[math.DG, math.AP]</td>\n",
|
391 |
-
" <td>2022-09-09</td>\n",
|
392 |
-
" <td>2209.03411</td>\n",
|
393 |
-
" </tr>\n",
|
394 |
-
" <tr>\n",
|
395 |
-
" <th>78</th>\n",
|
396 |
-
" <td>On the dynamics of vortices in viscous 2D flows</td>\n",
|
397 |
-
" <td>On the dynamics of vortices in viscous 2D flows</td>\n",
|
398 |
-
" <td>None</td>\n",
|
399 |
-
" <td>We study the 2D Navier--Stokes solution star...</td>\n",
|
400 |
-
" <td>We study the 2D Navier--Stokes solution star...</td>\n",
|
401 |
-
" <td>None</td>\n",
|
402 |
-
" <td>[['Ceci', 'Stefano', ''], ['Seis', 'Christian'...</td>\n",
|
403 |
-
" <td>[math.AP]</td>\n",
|
404 |
-
" <td>2022-09-09</td>\n",
|
405 |
-
" <td>2203.07185</td>\n",
|
406 |
-
" </tr>\n",
|
407 |
-
" </tbody>\n",
|
408 |
-
"</table>\n",
|
409 |
-
"</div>"
|
410 |
-
],
|
411 |
-
"text/plain": [
|
412 |
-
" raw_title \\\n",
|
413 |
-
"42 The Prolongation Problem for the Heavenly Equa... \n",
|
414 |
-
"55 Null Controllability for a Degenerate Structur... \n",
|
415 |
-
"59 Voting models and semilinear parabolic equations \n",
|
416 |
-
"72 Flows of $G_2$-Structures associated to Calabi... \n",
|
417 |
-
"78 On the dynamics of vortices in viscous 2D flows \n",
|
418 |
-
"\n",
|
419 |
-
" clean_title hyph_in_title \\\n",
|
420 |
-
"42 The Prolongation Problem for the Heavenly Equa... None \n",
|
421 |
-
"55 Null Controllability for a Degenerate Structur... None \n",
|
422 |
-
"59 Voting models and semilinear parabolic equations None \n",
|
423 |
-
"72 Flows of LATEX associated to Calabi-Yau Manif... [Calabi-Yau] \n",
|
424 |
-
"78 On the dynamics of vortices in viscous 2D flows None \n",
|
425 |
-
"\n",
|
426 |
-
" raw_abstract \\\n",
|
427 |
-
"42 We provide an exact regular solution of an o... \n",
|
428 |
-
"55 In this paper, we consider the infinite dime... \n",
|
429 |
-
"59 We present probabilistic interpretations of ... \n",
|
430 |
-
"72 We establish a correspondence between a para... \n",
|
431 |
-
"78 We study the 2D Navier--Stokes solution star... \n",
|
432 |
-
"\n",
|
433 |
-
" clean_abstract \\\n",
|
434 |
-
"42 We provide an exact regular solution of an o... \n",
|
435 |
-
"55 In this paper, we consider the infinite dime... \n",
|
436 |
-
"59 We present probabilistic interpretations of ... \n",
|
437 |
-
"72 We establish a correspondence between a para... \n",
|
438 |
-
"78 We study the 2D Navier--Stokes solution star... \n",
|
439 |
-
"\n",
|
440 |
-
" hyph_in_abstract \\\n",
|
441 |
-
"42 None \n",
|
442 |
-
"55 [final-state] \n",
|
443 |
-
"59 [semi-linear, Fisher-KPP, group-based, pushmi-... \n",
|
444 |
-
"72 [Monge-Ampere, Monge-Ampere, torsion-free, Ric... \n",
|
445 |
-
"78 None \n",
|
446 |
-
"\n",
|
447 |
-
" authors_parsed \\\n",
|
448 |
-
"42 [['Palese', 'M.', '', 'Dept. Math. Univ. of To... \n",
|
449 |
-
"55 [['Simporé', 'Yacouba', ''], ['gantouh', 'Yass... \n",
|
450 |
-
"59 [['An', 'Jing', ''], ['Henderson', 'Christophe... \n",
|
451 |
-
"72 [['Picard', 'Sébastien', ''], ['Suan', 'Caleb'... \n",
|
452 |
-
"78 [['Ceci', 'Stefano', ''], ['Seis', 'Christian'... \n",
|
453 |
-
"\n",
|
454 |
-
" cat update_date id \n",
|
455 |
-
"42 [math.AP, math-ph, math.MP] 2022-09-21 math/0311218 \n",
|
456 |
-
"55 [math.OC, math.AP] 2022-09-09 2209.03645 \n",
|
457 |
-
"59 [math.AP, math.PR] 2022-09-09 2209.03435 \n",
|
458 |
-
"72 [math.DG, math.AP] 2022-09-09 2209.03411 \n",
|
459 |
-
"78 [math.AP] 2022-09-09 2203.07185 "
|
460 |
-
]
|
461 |
-
},
|
462 |
-
"execution_count": 5,
|
463 |
-
"metadata": {},
|
464 |
-
"output_type": "execute_result"
|
465 |
-
}
|
466 |
-
],
|
467 |
-
"source": [
|
468 |
-
"## Create the dataset of all pde articles\n",
|
469 |
-
"\n",
|
470 |
-
"full_data = pd.read_parquet('./data/arXiv_clean.parquet')\n",
|
471 |
-
"pde = full_data.loc[cats['Analysis of PDEs'] == True]\n",
|
472 |
-
"pde.head()"
|
473 |
-
]
|
474 |
-
},
|
475 |
-
{
|
476 |
-
"attachments": {},
|
477 |
-
"cell_type": "markdown",
|
478 |
-
"metadata": {},
|
479 |
-
"source": [
|
480 |
-
"## Next goal: Does the raw arxiv dataset contain the MSC subject information?\n",
|
481 |
-
"\n",
|
482 |
-
"No, it doesn't -- this was verified in a kaggle notebook. It has only arxiv subject tag information."
|
483 |
-
]
|
484 |
-
},
|
485 |
-
{
|
486 |
-
"attachments": {},
|
487 |
-
"cell_type": "markdown",
|
488 |
-
"metadata": {},
|
489 |
-
"source": [
|
490 |
-
"## 1. Frequently occuring author names. Discover some large subsets of the data consisting of papers who have at least one author with a given name. What are the most commonly occuring names?"
|
491 |
-
]
|
492 |
-
}
|
493 |
-
],
|
494 |
-
"metadata": {
|
495 |
-
"kernelspec": {
|
496 |
-
"display_name": "Python 3",
|
497 |
-
"language": "python",
|
498 |
-
"name": "python3"
|
499 |
-
},
|
500 |
-
"language_info": {
|
501 |
-
"codemirror_mode": {
|
502 |
-
"name": "ipython",
|
503 |
-
"version": 3
|
504 |
-
},
|
505 |
-
"file_extension": ".py",
|
506 |
-
"mimetype": "text/x-python",
|
507 |
-
"name": "python",
|
508 |
-
"nbconvert_exporter": "python",
|
509 |
-
"pygments_lexer": "ipython3",
|
510 |
-
"version": "3.10.11"
|
511 |
-
},
|
512 |
-
"orig_nbformat": 4
|
513 |
-
},
|
514 |
-
"nbformat": 4,
|
515 |
-
"nbformat_minor": 2
|
516 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
email-extraction.ipynb
DELETED
@@ -1,19 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"cells": [
|
3 |
-
{
|
4 |
-
"cell_type": "code",
|
5 |
-
"execution_count": null,
|
6 |
-
"metadata": {},
|
7 |
-
"outputs": [],
|
8 |
-
"source": []
|
9 |
-
}
|
10 |
-
],
|
11 |
-
"metadata": {
|
12 |
-
"language_info": {
|
13 |
-
"name": "python"
|
14 |
-
},
|
15 |
-
"orig_nbformat": 4
|
16 |
-
},
|
17 |
-
"nbformat": 4,
|
18 |
-
"nbformat_minor": 2
|
19 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
library_class.py
DELETED
@@ -1,25 +0,0 @@
|
|
1 |
-
import util
|
2 |
-
import pandas as pd
|
3 |
-
import os
|
4 |
-
|
5 |
-
class Library(object):
|
6 |
-
|
7 |
-
def load_from_file(self,library_name):
|
8 |
-
self.raw_lib = pd.read_parquet(os.path.join('./data',library_name))
|
9 |
-
|
10 |
-
def load_from_query(self,query_string,max_results):
|
11 |
-
self.raw_lib = util.query_to_df(query_string,max_results)
|
12 |
-
|
13 |
-
def clean_library(self):
|
14 |
-
|
15 |
-
## drop columns that we aren't going to modify
|
16 |
-
cols = ['title','summary','authors','primary_category','categories']
|
17 |
-
input_lib = self.raw_lib[cols].copy()
|
18 |
-
|
19 |
-
input_lib['title'] = input_lib['title'].apply(util.cleanse)
|
20 |
-
input_lib['summary'] = input_lib['summary'].apply(util.cleanse)
|
21 |
-
input_lib['hyph_in_summary'] = input_lib['summary'].apply(util.find_hyph)
|
22 |
-
input_lib['hyph_in_title'] = input_lib['title'].apply(util.find_hyph)
|
23 |
-
input_lib['msc_tags'] = input_lib.categories.apply(util.find_msc).apply(util.msc_to_eng)
|
24 |
-
|
25 |
-
self.clean_lib = input_lib
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|