nazneen commited on
Commit
fdd7b58
1 Parent(s): c3153c4
data/datasets_df.parquet DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:01cb9a03e5bd4e29cecf390e5449a2cb413f9fc73daa0750b23e204397eb1ba6
3
- size 15238
 
 
 
 
data/hfid_to_pwcinfo.json DELETED
The diff for this file is too large to render. See raw diff
 
data/paper_dataset_emb.json DELETED
The diff for this file is too large to render. See raw diff
 
data/paper_emb.json DELETED
The diff for this file is too large to render. See raw diff
 
requirements.txt CHANGED
@@ -1,10 +1,319 @@
1
- beautifulsoup4==4.11.1
2
- bokeh==2.4.2
3
- datasets==2.0.0
4
- numpy==1.21.5
5
- pandas==1.4.2
6
- requests==2.27.1
7
- streamlit==1.9.0
8
- torch==1.10.2
9
- tqdm==4.64.0
10
- transformers==4.18.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # This file may be used to create an environment using:
2
+ # $ conda create --name <env> --file <this file>
3
+ # platform: osx-arm64
4
+ abseil-cpp=20210324.2=hc377ac9_0
5
+ aiohttp=3.8.1=py39h1a28f6b_1
6
+ aiosignal=1.2.0=pyhd3eb1b0_0
7
+ altair=4.1.0=py_1
8
+ appnope=0.1.2=py39hca03da5_1001
9
+ argon2-cffi=21.3.0=pyhd3eb1b0_0
10
+ argon2-cffi-bindings=21.2.0=py39h1a28f6b_0
11
+ arrow-cpp=6.0.1=py39h71c7f51_5_cpu
12
+ astor=0.8.1=pyh9f0ad1d_0
13
+ asttokens=2.0.5=pyhd3eb1b0_0
14
+ async-timeout=4.0.1=pyhd3eb1b0_0
15
+ attrs=21.4.0=pyhd3eb1b0_0
16
+ autopep8=1.6.0=pyhd3eb1b0_1
17
+ aws-c-auth=0.6.8=h77ca94e_1
18
+ aws-c-cal=0.5.12=hc1327b6_7
19
+ aws-c-common=0.6.17=h3422bc3_0
20
+ aws-c-compression=0.2.14=haaffe3e_7
21
+ aws-c-event-stream=0.2.7=hd0ff547_32
22
+ aws-c-http=0.6.10=h53b0524_3
23
+ aws-c-io=0.10.14=h3e85fa9_1
24
+ aws-c-mqtt=0.7.10=hd8b1cef_0
25
+ aws-c-s3=0.1.29=h6db2689_0
26
+ aws-c-sdkutils=0.1.1=haaffe3e_4
27
+ aws-checksums=0.1.12=haaffe3e_6
28
+ aws-crt-cpp=0.17.10=h5d9c0f4_5
29
+ aws-sdk-cpp=1.9.160=he5b1d48_0
30
+ backcall=0.2.0=pyhd3eb1b0_0
31
+ base58=2.1.1=pyhd8ed1ab_0
32
+ beautifulsoup4=4.11.1=py39hca03da5_0
33
+ blas=2.114=openblas
34
+ blas-devel=3.9.0=14_osxarm64_openblas
35
+ bleach=4.1.0=pyhd3eb1b0_0
36
+ blinker=1.4=pypi_0
37
+ blosc=1.21.0=h9f76cd9_0
38
+ bokeh=2.4.2=py39hca03da5_0
39
+ boto3=1.21.32=pyhd3eb1b0_0
40
+ botocore=1.24.32=pyhd3eb1b0_0
41
+ bottleneck=1.3.4=py39heec5a64_0
42
+ brotli=1.0.7=hc377ac9_0
43
+ brotlipy=0.7.0=py39h1a28f6b_1002
44
+ brunsli=0.1=hc377ac9_1
45
+ bzip2=1.0.8=h620ffc9_4
46
+ c-ares=1.18.1=h1a28f6b_0
47
+ c-blosc2=2.0.4=h0095615_1
48
+ ca-certificates=2021.10.8=h4653dfc_0
49
+ cachetools=4.2.2=pyhd3eb1b0_0
50
+ certifi=2021.10.8=py39h2804cbe_2
51
+ cffi=1.15.0=py39h22df2f2_1
52
+ cfitsio=4.0.0=h99351b2_0
53
+ charls=2.2.0=hc377ac9_0
54
+ charset-normalizer=2.0.4=pyhd3eb1b0_0
55
+ click=8.0.4=py39hca03da5_0
56
+ cloudpickle=2.0.0=pyhd3eb1b0_0
57
+ colorcet=3.0.0=py39hca03da5_0
58
+ cryptography=37.0.1=py39h834c97f_0
59
+ cycler=0.11.0=pyhd3eb1b0_0
60
+ cytoolz=0.11.0=py39h1a28f6b_0
61
+ dask=2022.2.1=pyhd3eb1b0_0
62
+ dask-core=2022.2.1=pyhd3eb1b0_0
63
+ dataclasses=0.8=pyh6d0b6a4_7
64
+ datasets=2.0.0=py_0
65
+ datasets-sql=0.1.1=pypi_0
66
+ datashader=0.13.0=pyhd3eb1b0_1
67
+ datashape=0.5.4=py39hca03da5_1
68
+ debugpy=1.5.1=py39hc377ac9_0
69
+ decorator=5.1.1=pyhd3eb1b0_0
70
+ defusedxml=0.7.1=pyhd3eb1b0_0
71
+ dill=0.3.4=pyhd3eb1b0_0
72
+ distributed=2022.2.1=pyhd3eb1b0_0
73
+ docopt=0.6.2=pypi_0
74
+ duckdb=0.3.4=pypi_0
75
+ entrypoints=0.4=py39hca03da5_0
76
+ executing=0.8.3=pyhd3eb1b0_0
77
+ filelock=3.6.0=pyhd3eb1b0_0
78
+ fonttools=4.31.2=pypi_0
79
+ freetype=2.11.0=h1192e45_0
80
+ frozenlist=1.2.0=py39h1a28f6b_0
81
+ fsspec=2022.2.0=pyhd3eb1b0_0
82
+ future=0.18.2=py39hca03da5_1
83
+ fuzzywuzzy=0.18.0=pypi_0
84
+ gflags=2.2.2=hc377ac9_0
85
+ gh=2.10.1=h75b854d_0
86
+ giflib=5.2.1=h1a28f6b_0
87
+ gitdb=4.0.7=pyhd3eb1b0_0
88
+ gitpython=3.1.18=pyhd3eb1b0_1
89
+ glog=0.5.0=hc377ac9_0
90
+ grpc-cpp=1.42.0=hedfbb7c_1
91
+ heapdict=1.0.1=pyhd3eb1b0_0
92
+ holoviews=1.14.8=pyhd3eb1b0_0
93
+ htmlmin=0.1.12=pypi_0
94
+ huggingface-hub=0.6.0=pypi_0
95
+ idna=3.3=pyhd3eb1b0_0
96
+ imagecodecs=2021.11.20=py39hcb02aed_1
97
+ imagehash=4.2.1=pypi_0
98
+ imageio=2.9.0=pyhd3eb1b0_0
99
+ importlib-metadata=4.11.3=py39hca03da5_0
100
+ importlib_metadata=4.11.3=hd3eb1b0_0
101
+ ipykernel=6.9.1=py39hca03da5_0
102
+ ipython=8.3.0=py39hca03da5_0
103
+ ipython_genutils=0.2.0=pyhd3eb1b0_1
104
+ ipywidgets=7.6.5=pyhd3eb1b0_1
105
+ jbig=2.1=h1a28f6b_0
106
+ jedi=0.18.1=py39hca03da5_1
107
+ jellyfish=0.9.0=pypi_0
108
+ jinja2=3.0.3=pyhd3eb1b0_0
109
+ jmespath=0.10.0=pyhd3eb1b0_0
110
+ joblib=1.0.1=pypi_0
111
+ jpeg=9e=h1a28f6b_0
112
+ jsonlines=3.0.0=pypi_0
113
+ jsonschema=4.4.0=py39hca03da5_0
114
+ jupyter=1.0.0=pypi_0
115
+ jupyter-console=6.4.3=pypi_0
116
+ jupyter_client=7.2.2=py39hca03da5_0
117
+ jupyter_core=4.10.0=py39hca03da5_0
118
+ jupyterlab_pygments=0.1.2=py_0
119
+ jupyterlab_widgets=1.0.0=pyhd3eb1b0_1
120
+ jxrlib=1.1=h1a28f6b_2
121
+ kaleido=0.2.1=pypi_0
122
+ kiwisolver=1.4.2=pypi_0
123
+ krb5=1.19.2=h3b8d789_0
124
+ lcms2=2.12=hba8e193_0
125
+ lerc=3.0=hc377ac9_0
126
+ libaec=1.0.6=hbdafb3b_0
127
+ libblas=3.9.0=14_osxarm64_openblas
128
+ libbrotlicommon=1.0.9=h1c322ee_7
129
+ libbrotlidec=1.0.9=h1c322ee_7
130
+ libbrotlienc=1.0.9=h1c322ee_7
131
+ libcblas=3.9.0=14_osxarm64_openblas
132
+ libcurl=7.82.0=hc6d1d07_0
133
+ libcxx=12.0.0=hf6beb65_1
134
+ libdeflate=1.8=h1a28f6b_5
135
+ libedit=3.1.20210910=h1a28f6b_0
136
+ libev=4.33=h1a28f6b_1
137
+ libevent=2.1.10=hbae9a57_4
138
+ libffi=3.4.2=hc377ac9_2
139
+ libgfortran=5.0.0=11_1_0_h6a59814_26
140
+ libgfortran5=11.1.0=h6a59814_26
141
+ liblapack=3.9.0=14_osxarm64_openblas
142
+ liblapacke=3.9.0=14_osxarm64_openblas
143
+ libllvm11=11.1.0=h12f7ac0_4
144
+ libnghttp2=1.46.0=h95c9599_0
145
+ libopenblas=0.3.20=openmp_h2209c59_0
146
+ libpng=1.6.37=hb8d0fd4_0
147
+ libprotobuf=3.19.1=h98b2900_0
148
+ libsodium=1.0.18=h1a28f6b_0
149
+ libssh2=1.10.0=hf27765b_0
150
+ libthrift=0.15.0=h28a9c34_1
151
+ libtiff=4.3.0=h74060c4_2
152
+ libutf8proc=2.6.1=h1a28f6b_0
153
+ libwebp=1.2.2=h68602c7_0
154
+ libwebp-base=1.2.2=h1a28f6b_0
155
+ libzlib=1.2.11=h90dfc92_1014
156
+ libzopfli=1.0.3=hc377ac9_0
157
+ llvm-openmp=14.0.3=hd125106_0
158
+ llvmlite=0.38.0=py39h98b2900_0
159
+ locket=0.2.1=py39hca03da5_2
160
+ lz4-c=1.9.3=hc377ac9_0
161
+ markdown=3.3.4=py39hca03da5_0
162
+ markupsafe=2.0.1=py39h1a28f6b_0
163
+ matplotlib=3.5.1=py39hca03da5_1
164
+ matplotlib-base=3.5.1=py39hc377ac9_1
165
+ matplotlib-inline=0.1.2=pyhd3eb1b0_2
166
+ missingno=0.5.1=pypi_0
167
+ mistune=0.8.4=py39h1a28f6b_1000
168
+ msgpack-python=1.0.3=py39h525c30c_0
169
+ multidict=5.2.0=py39h1a28f6b_2
170
+ multimethod=1.7=pypi_0
171
+ multipledispatch=0.6.0=py39hca03da5_0
172
+ multiprocess=0.70.12.2=py39hb18efdd_2
173
+ munkres=1.1.4=py_0
174
+ nbclient=0.5.13=py39hca03da5_0
175
+ nbconvert=6.4.4=py39hca03da5_0
176
+ nbformat=5.3.0=py39hca03da5_0
177
+ ncurses=6.3=h1a28f6b_2
178
+ nest-asyncio=1.5.5=py39hca03da5_0
179
+ networkx=2.7.1=pyhd3eb1b0_0
180
+ ninja=1.10.2=hca03da5_5
181
+ ninja-base=1.10.2=h525c30c_5
182
+ nltk=3.7=pyhd3eb1b0_0
183
+ notebook=6.4.11=py39hca03da5_0
184
+ numba=0.55.1=py39h9197a36_0
185
+ numexpr=2.8.1=py39h144ceef_0
186
+ numpy=1.21.5=py39h25ab29e_2
187
+ numpy-base=1.21.5=py39h974a1f5_2
188
+ openblas=0.3.20=openmp_h745f6c2_0
189
+ openjpeg=2.4.0=h062765e_1
190
+ openssl=1.1.1o=ha287fd2_0
191
+ orc=1.7.1=hcb6706d_1
192
+ packaging=21.3=pyhd3eb1b0_0
193
+ pandas=1.4.2=py39hc377ac9_0
194
+ pandas-profiling=3.1.0=pypi_0
195
+ pandocfilters=1.5.0=pyhd3eb1b0_0
196
+ panel=0.13.0=py39hca03da5_0
197
+ param=1.12.0=pyhd3eb1b0_0
198
+ parquet-cpp=1.5.1=h34088ae_4
199
+ parso=0.8.3=pyhd3eb1b0_0
200
+ partd=1.2.0=pyhd3eb1b0_1
201
+ pexpect=4.8.0=pyhd3eb1b0_3
202
+ phik=0.12.2=pypi_0
203
+ pickleshare=0.7.5=pyhd3eb1b0_1003
204
+ pillow=9.1.0=pypi_0
205
+ pip=21.2.4=py39hca03da5_0
206
+ pipreqs=0.4.11=pypi_0
207
+ plotly=5.6.0=pyhd3eb1b0_0
208
+ progressbar=2.5=pypi_0
209
+ prometheus_client=0.13.1=pyhd3eb1b0_0
210
+ prompt-toolkit=3.0.20=pyhd3eb1b0_0
211
+ protobuf=3.20.0=pypi_0
212
+ psutil=5.8.0=py39h1a28f6b_1
213
+ ptyprocess=0.7.0=pyhd3eb1b0_2
214
+ pure_eval=0.2.2=pyhd3eb1b0_0
215
+ pyahocorasick=1.4.4=pypi_0
216
+ pyarrow=6.0.1=py39hd3b58d7_5_cpu
217
+ pyasn1=0.4.8=pypi_0
218
+ pycodestyle=2.8.0=pyhd3eb1b0_0
219
+ pycparser=2.21=pyhd3eb1b0_0
220
+ pyct=0.4.6=py39hca03da5_0
221
+ pydantic=1.9.0=pypi_0
222
+ pydeck=0.7.1=pyh6c4a22f_0
223
+ pygments=2.11.2=pyhd3eb1b0_0
224
+ pympler=1.0.1=pypi_0
225
+ pynndescent=0.5.4=pyhd3eb1b0_0
226
+ pyopenssl=22.0.0=pyhd3eb1b0_0
227
+ pyparsing=3.0.4=pyhd3eb1b0_0
228
+ pyrsistent=0.18.0=py39h1a28f6b_0
229
+ pysocks=1.7.1=py39hca03da5_0
230
+ python=3.9.12=hfc7342c_1_cpython
231
+ python-dateutil=2.8.2=pyhd3eb1b0_0
232
+ python-dotenv=0.19.2=pypi_0
233
+ python-fastjsonschema=2.15.3=pyhd8ed1ab_0
234
+ python-xxhash=3.0.0=py39hb18efdd_1
235
+ python_abi=3.9=1_cp39
236
+ pytorch=1.10.2=cpu_py39h23cb94c_0
237
+ pytz=2021.3=pyhd3eb1b0_0
238
+ pyviz_comms=2.0.2=pyhd3eb1b0_0
239
+ pywavelets=1.3.0=py39h1a28f6b_0
240
+ pyyaml=6.0=py39h1a28f6b_0
241
+ pyzmq=22.3.0=py39hc377ac9_2
242
+ qtconsole=5.3.0=pypi_0
243
+ qtpy=2.0.1=pypi_0
244
+ re2=2021.11.01=hbdafb3b_0
245
+ readline=8.1.2=h1a28f6b_1
246
+ regex=2022.3.15=py39h1a28f6b_0
247
+ requests=2.27.1=pyhd3eb1b0_0
248
+ responses=0.18.0=pypi_0
249
+ s3transfer=0.5.0=pyhd3eb1b0_0
250
+ sacremoses=0.0.43=pyhd3eb1b0_0
251
+ scikit-image=0.19.2=py39h9197a36_0
252
+ scikit-learn=1.0.2=py39h9197a36_1
253
+ scipy=1.7.3=py39h2f0f56f_0
254
+ seaborn=0.11.2=pyhd3eb1b0_0
255
+ segtok=1.5.11=pypi_0
256
+ semver=2.13.0=pyhd3eb1b0_0
257
+ send2trash=1.8.0=pyhd3eb1b0_1
258
+ sentence-transformers=2.2.0=pyhd8ed1ab_0
259
+ sentencepiece=0.1.95=py39h525c30c_0
260
+ setuptools=61.2.0=py39hca03da5_0
261
+ simplejson=3.17.6=pypi_0
262
+ six=1.16.0=pyhd3eb1b0_1
263
+ smmap=5.0.0=pypi_0
264
+ snappy=1.1.9=hc377ac9_0
265
+ sortedcontainers=2.4.0=pyhd3eb1b0_0
266
+ soupsieve=2.3.2=pypi_0
267
+ sql-metadata=2.5.0=pypi_0
268
+ sqlite=3.38.2=h1058600_0
269
+ sqlparse=0.4.2=pypi_0
270
+ stack_data=0.2.0=pyhd3eb1b0_0
271
+ streamlit=1.9.0=pyhd8ed1ab_0
272
+ streamlit-aggrid=0.2.3.post2=pypi_0
273
+ streamlit-vega-lite=0.1.0=pypi_0
274
+ tabulate=0.8.9=pypi_0
275
+ tangled-up-in-unicode=0.1.0=pypi_0
276
+ tbb=2021.5.0=h525c30c_0
277
+ tblib=1.7.0=pyhd3eb1b0_0
278
+ tenacity=8.0.1=py39hca03da5_0
279
+ tensorboard-plugin-wit=1.8.1=pypi_0
280
+ terminado=0.13.1=py39hca03da5_0
281
+ testpath=0.5.0=pyhd3eb1b0_0
282
+ threadpoolctl=2.2.0=pyh0d69192_0
283
+ tifffile=2021.7.2=pyhd3eb1b0_2
284
+ tk=8.6.12=he1e0b03_0
285
+ tokenizers=0.11.6=pypi_0
286
+ toml=0.10.2=pyhd3eb1b0_0
287
+ toolz=0.11.2=pyhd3eb1b0_0
288
+ torchvision=0.2.2=py_3
289
+ tornado=6.1=py39h1a28f6b_0
290
+ tqdm=4.64.0=py39hca03da5_0
291
+ traitlets=5.1.1=pyhd3eb1b0_0
292
+ transformers=4.18.0=py39hca03da5_0
293
+ typing-extensions=4.1.1=hd3eb1b0_0
294
+ typing_extensions=4.1.1=pyh06a4308_0
295
+ tzdata=2022a=hda174b7_0
296
+ tzlocal=2.1=py39hca03da5_0
297
+ umap-learn=0.5.3=py39h2804cbe_0
298
+ urllib3=1.26.9=py39hca03da5_0
299
+ validators=0.18.2=pyhd3eb1b0_0
300
+ visions=0.7.4=pypi_0
301
+ watchdog=2.1.6=py39h1a28f6b_0
302
+ wcwidth=0.2.5=pyhd3eb1b0_0
303
+ webencodings=0.5.1=pypi_0
304
+ wheel=0.37.1=pyhd3eb1b0_0
305
+ widgetsnbextension=3.5.2=py39hca03da5_0
306
+ wordcloud=1.8.1=pypi_0
307
+ xarray=0.20.1=pyhd3eb1b0_1
308
+ xxhash=0.8.0=h1a28f6b_3
309
+ xz=5.2.5=h1a28f6b_1
310
+ yake=0.4.8=pypi_0
311
+ yaml=0.2.5=h1a28f6b_0
312
+ yarg=0.1.9=pypi_0
313
+ yarl=1.6.3=py39h1a28f6b_1
314
+ zeromq=4.3.4=hc377ac9_0
315
+ zfp=0.5.5=hc377ac9_6
316
+ zict=2.0.0=pyhd3eb1b0_0
317
+ zipp=3.8.0=py39hca03da5_0
318
+ zlib=1.2.11=h90dfc92_1014
319
+ zstd=1.5.2=h861e0a7_0