Skip to content

Instantly share code, notes, and snippets.

@hchasestevens

hchasestevens/spacy-validate-pos.py

Created November 26, 2018 18:14
Show Gist options
  • Save hchasestevens/683028d7e0a02a0f2b4e91d87442dc10 to your computer and use it in GitHub Desktop.
Save hchasestevens/683028d7e0a02a0f2b4e91d87442dc10 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
spacy-validate-pos.py
In [1]: import spacy
In [2]: nlp = spacy.load('en_core_web_md')
---------------------------------------------------------------------------
OSError Traceback (most recent call last)
<ipython-input-2-614d6de0ab0f> in <module>
----> 1 nlp = spacy.load('en_core_web_md')
/usr/local/lib/python3.7/site-packages/spacy/__init__.py in load(name, **overrides)
19 if depr_path not in (True, False, None):
20 deprecation_warning(Warnings.W001.format(path=depr_path))
---> 21 return util.load_model(name, **overrides)
22
23
/usr/local/lib/python3.7/site-packages/spacy/util.py in load_model(name, **overrides)
117 elif hasattr(name, 'exists'): # Path or Path-like to model data
118 return load_model_from_path(name, **overrides)
--> 119 raise IOError(Errors.E050.format(name=name))
120
121
OSError: [E050] Can't find model 'en_core_web_md'. It doesn't seem to be a shortcut link, a Python package or a valid path to a data directory.
In [3]: nlp = spacy.load('en')
In [4]: nlp.span
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-4-a9e001ec4285> in <module>
----> 1 nlp.span
AttributeError: 'English' object has no attribute 'span'
In [5]: nlp.doc
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-5-58f524e07691> in <module>
----> 1 nlp.doc
AttributeError: 'English' object has no attribute 'doc'
In [6]: doc = nlp(u"dog toy")
In [7]: doc
Out[7]: dog toy
In [8]: doc.vector
Out[8]:
array([ 2.03829741e+00, 2.36781979e+00, 6.42098069e-01, 1.48955655e+00,
-5.62346339e-01, 1.33793569e+00, -3.09381795e+00, -6.44182622e-01,
1.25022054e+00, 2.57861495e+00, 1.38218713e+00, -5.79693139e-01,
1.82447517e+00, 1.07861161e-01, -1.72269750e+00, 1.35781884e+00,
-1.80604339e+00, -2.19296932e+00, -2.09216738e+00, -1.92655921e-02,
1.85048789e-01, 4.69555140e-01, 5.24234712e-01, 2.22291613e+00,
-2.07774997e-01, -1.86640346e+00, 9.51340437e-01, 6.01068139e-03,
-9.45809409e-02, -2.27172780e+00, -1.38216925e+00, -1.02562785e-01,
1.20026636e+00, -2.57920361e+00, 5.12370169e-01, -2.45856166e+00,
1.52551866e+00, -5.05782127e-01, 6.06138587e-01, -7.69980907e-01,
-2.88174915e+00, 1.54708731e+00, 4.56493080e-01, -1.33094585e+00,
-6.26769543e-01, 6.54031754e-01, -8.19239318e-01, -1.45735812e+00,
9.08442497e-01, -7.99261212e-01, 9.48772967e-01, -1.72847116e+00,
-1.55103135e+00, 3.27595210e+00, -3.01227808e-01, -1.87482214e+00,
3.20807981e+00, 3.96294689e+00, 1.00239944e+00, 2.04362273e-01,
-1.85942292e+00, 8.32520604e-01, 3.23689193e-01, 1.92307234e+00,
-1.82575226e-01, 1.93731260e+00, -3.16071200e+00, -3.41067839e+00,
3.50187826e+00, 3.44729042e+00, -1.31147361e+00, -1.57002985e+00,
-3.88571620e-02, 2.63054562e+00, -2.07660389e+00, -1.11394906e+00,
-1.76012826e+00, 4.40965503e-01, -1.40016389e+00, 3.38406515e+00,
-2.86365724e+00, 6.23282313e-01, -2.19943976e+00, -1.83886528e+00,
1.74480951e+00, 7.56090641e-01, -4.80079293e-01, 5.17534912e-01,
-7.56085157e-01, 2.04470336e-01, -3.48385859e+00, 4.70846319e+00,
-3.14527607e+00, 3.12757540e+00, -9.90008652e-01, 1.43748927e+00,
-1.94329762e+00, 5.87370872e-01, 1.11473751e+00, -1.49453950e+00,
-8.46697807e-01, 2.69886756e+00, 1.06683612e+00, -2.39443588e+00,
-3.64536375e-01, 1.25542951e+00, -3.53582859e-01, -1.81180298e+00,
-2.62189555e+00, -1.85188425e+00, -8.88717949e-01, -2.57389593e+00,
-2.92672610e+00, 9.19499993e-02, 3.08820343e+00, 1.79746699e+00,
2.29005292e-01, 1.87167573e+00, 4.68110561e-01, -1.58678412e+00,
1.87270045e-01, 1.91545773e+00, 2.84377813e-01, 1.47847533e+00,
1.23288643e+00, -2.31316745e-01, 5.15741825e+00, -1.37675810e+00,
-3.12431306e-01, -4.11446214e-01, 4.16860729e-02, -1.98357016e-01,
-6.19191766e-01, 1.20228127e-01, -2.80023783e-01, 3.97638291e-01,
3.86109322e-01, 8.00050735e-01, 4.71658289e-01, 1.98108479e-01,
3.10524791e-01, -1.55268759e-01, -5.09115219e-01, 2.38407571e-02,
-1.51686102e-01, 6.53552294e-01, 9.73685026e-01, -1.33638829e-01,
6.78870827e-02, 6.41373247e-02, 2.70350277e-01, 3.95080328e-01,
-8.35354552e-02, -3.53606343e-01, 1.65485635e-01, -4.55213606e-01,
-3.20883125e-01, -2.39480942e-01, 5.55148721e-03, 1.08948857e-01,
-1.25072077e-01, -6.44631758e-02, -2.84211189e-02, -1.87336117e-01,
5.43430686e-01, -3.73104922e-02, -1.40576646e-01, -1.71181068e-01,
-8.74379948e-02, 7.86384821e-01, -2.33069211e-01, -3.67068291e-01,
1.02189548e-01, 2.03321040e-01, -2.55088061e-01, -3.11571032e-01,
-1.08178802e-01, -5.19075990e-01, -5.77531219e-01, -5.11749864e-01,
-3.61509055e-01, -2.00518742e-02, 2.09935486e-01, -2.63720393e-01,
4.65391636e-01, -1.60855547e-01, 7.33086467e-01, -1.81556195e-02,
4.34110433e-01, 4.38683391e-01, -3.17823082e-01, 6.10184073e-01,
6.61699295e-01, 3.32412064e-01, -1.72873959e-01, -6.97959960e-03,
-2.78868228e-02, 3.09387475e-01, 1.08236291e-01, -2.05971599e-01,
-1.09158695e-01, 1.08477779e-01, -3.35278213e-01, 2.26818621e-01,
1.75207153e-01, -2.59554565e-01, 3.14607441e-01, 3.85165632e-01,
4.77660507e-01, -1.74006954e-01, -4.84731495e-01, 3.31658125e-01,
-1.15263537e-01, 7.54618794e-02, -8.30164552e-01, -4.90665853e-01,
-1.95597142e-01, -2.10968226e-01, 6.21919274e-01, -1.37239814e-01,
-8.06269199e-02, -8.58397186e-02, -1.66399345e-01, -1.56603038e-01,
2.27226913e-02, -3.33659649e-01, -1.82272926e-01, -4.65639383e-01,
8.36346075e-02, 9.78264809e-02, 8.56393874e-02, 8.36825728e-01,
1.88273221e-01, -3.03988039e-01, -7.27899015e-01, 6.53200299e-02,
-2.40058154e-01, -2.45316714e-01, -2.64545828e-01, -4.64284658e-01,
1.78413004e-01, -2.46938676e-01, 4.56624359e-01, -7.44943678e-01,
-5.53129315e-02, -6.11129254e-02, -1.20640695e-02, 3.28660727e-01,
1.55273408e-01, -5.32252014e-01, 3.68054807e-02, 9.02774110e-02,
-4.01241004e-01, 3.38618398e-01, 2.11462438e-01, 4.73303914e-01,
-3.87565136e-01, -1.06366068e-01, 1.31288856e-01, -1.21853352e-02,
-1.49548009e-01, -4.31959450e-01, 3.88634577e-02, -4.13253382e-02,
-2.21528277e-01, -1.96539760e-01, -5.27421534e-02, 2.04898000e-01,
1.11881711e-01, -2.69103855e-01, -4.39333767e-01, 9.57148433e-01,
8.17030668e-04, -4.92422789e-01, -2.08693728e-01, -5.17838359e-01,
9.70528945e-02, -3.98110271e-01, 7.19831645e-01, -4.34794992e-01,
-3.70642155e-01, -2.50049919e-01, -3.71729404e-01, 5.27465641e-01,
2.71481752e-01, 2.58169085e-01, -2.62687981e-01, -4.46192205e-01,
-1.33499056e-01, 4.66216683e-01, 3.08755189e-02, 3.06384861e-02,
-1.54926628e-02, 9.56144810e-01, -2.29332708e-02, -3.42007220e-01,
1.74159303e-01, -1.49220452e-01, 7.78728426e-02, -5.04470170e-01,
2.53704429e-01, -2.66093612e-01, -3.96699041e-01, -4.49841380e-01,
1.70797080e-01, -3.78622413e-01, -1.80736393e-01, -3.06358218e-01,
1.99226588e-01, 2.17968091e-01, -5.80939412e-01, 4.47778165e-01,
-5.11823356e-01, 4.96672839e-01, 7.39834070e-01, -2.79730737e-01,
3.72516394e-01, 8.61741662e-01, 6.35811687e-03, 1.99798346e-02,
1.00568962e+00, 4.71090674e-01, -2.94721454e-01, 3.74424070e-01,
-3.72704506e-01, -1.29196078e-01, -3.67877662e-01, -7.91607499e-02,
1.60355985e-01, -5.84337413e-02, 4.61368501e-01, -1.69377372e-01,
-7.92818516e-03, 7.00522065e-01, -3.83161515e-01, 1.19057596e-02,
-2.18008399e-01, 6.15855306e-02, 7.38954246e-02, -3.16653430e-01,
-3.87689978e-01, -3.52238894e-01, 5.28031662e-02, -7.48071074e-02,
-2.79495150e-01, -2.00976878e-02, -3.30628753e-01, 5.13699591e-01,
9.98179555e-01, -3.44403744e-01, -3.71480882e-01, -1.02415539e-01,
-5.99051416e-01, 5.94294071e-01, -4.21366468e-02, -3.09960067e-01,
-2.04859301e-02, -1.91371664e-02, -4.82665718e-01, -6.00422740e-01,
-1.69866771e-01, 5.29779673e-01, 3.22359204e-01, 3.46182466e-01,
-8.69033873e-01, 3.93946171e-01, 8.49267393e-02, 2.04889283e-01,
2.59491652e-01, 1.59783691e-01, -6.27252936e-01, -9.77487266e-02,
1.07644260e-01, -7.85464227e-01, 1.80039316e-01, 8.61204624e-01,
1.21076196e-01, -1.30450159e-01, 4.94117200e-01, 1.70044839e-01,
-1.42732441e-01, -2.25537285e-01, 3.37821245e-01, -7.52153769e-02],
dtype=float32)
In [9]: doc
Out[9]: dog toy
In [10]: dog_tog = dog
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-10-2b4b1bda2725> in <module>
----> 1 dog_tog = dog
NameError: name 'dog' is not defined
In [11]: dog_tog = doc
In [12]: dog_toy = doc
In [13]: toy_dog = nlp(u"toy dog")
In [14]: toy_dog.vector
Out[14]:
array([ 1.97872829e+00, 2.09140491e+00, 1.96997762e+00, 8.19003224e-01,
-1.35973859e+00, 1.25479841e+00, -3.77185130e+00, -2.88658559e-01,
1.31364548e+00, 2.13239765e+00, 1.27812088e+00, -1.06135464e+00,
1.52951837e+00, -4.63982671e-02, -7.14774132e-01, 8.74460816e-01,
-1.19989741e+00, -1.97877848e+00, -1.53531671e+00, -6.45628870e-02,
-5.77156961e-01, 1.56403303e-01, 5.14393270e-01, 9.58792865e-01,
-3.34061354e-01, -1.98225856e+00, 2.95840859e-01, 5.15633345e-01,
-5.54689527e-01, -2.47388601e+00, -9.45187569e-01, 7.40396604e-02,
5.34163594e-01, -1.65874839e+00, 1.39302939e-01, -2.07191920e+00,
2.30082417e+00, 2.84077525e-02, 2.99124241e-01, -5.83031237e-01,
-2.72889781e+00, 1.73131251e+00, 3.18379343e-01, -9.64858174e-01,
-8.25401902e-01, 7.85821199e-01, -1.38636827e+00, 2.71931469e-01,
1.08307564e+00, -6.03309631e-01, 3.00979078e-01, -8.23145032e-01,
-1.35874128e+00, 2.62804890e+00, 1.96632862e-01, -1.76964927e+00,
3.24684858e+00, 2.58082676e+00, 1.51630080e+00, 5.98251820e-04,
-1.59698486e+00, 7.18043685e-01, 4.10933673e-01, 6.56233609e-01,
-6.52878165e-01, 1.19936168e+00, -2.63424969e+00, -2.87286806e+00,
2.62794900e+00, 2.82121372e+00, -1.01733780e+00, -1.98272228e+00,
-1.34357202e+00, 2.11052966e+00, -1.87576485e+00, -8.78736377e-01,
-1.37510610e+00, 1.05369002e-01, -1.43343079e+00, 3.57330179e+00,
-2.63137341e+00, -4.17716622e-01, -2.38248587e+00, -2.11470270e+00,
1.28494203e+00, 1.09323478e+00, 3.68604481e-01, 1.43765235e+00,
-1.11563623e+00, 2.41465569e-02, -3.20997405e+00, 4.78062057e+00,
-2.78317022e+00, 2.91067457e+00, -1.36237359e+00, 1.76743042e+00,
-1.85777855e+00, 1.73678994e-03, 1.25381958e+00, -1.86376333e+00,
-1.04236364e+00, 3.01979542e+00, 8.40868890e-01, -2.54501963e+00,
-1.98569745e-02, 1.01454139e+00, -9.80589032e-01, -2.63844728e+00,
-2.02683163e+00, -1.23001492e+00, -2.09136575e-01, -2.91424799e+00,
-1.99785066e+00, 6.45630002e-01, 3.21738768e+00, 2.69334412e+00,
4.87935245e-02, 1.30142379e+00, 3.92950088e-01, -1.12446558e+00,
4.23805118e-01, 1.71206391e+00, 3.77057612e-01, 1.64717185e+00,
2.21794868e+00, -1.44902766e-02, 4.61812210e+00, -3.78390193e-01,
-3.14961821e-01, -4.77979869e-01, 3.99229303e-02, -3.20280343e-03,
-4.17106926e-01, 1.86633199e-01, -2.18393147e-01, 2.36340061e-01,
2.82352269e-01, 6.64646506e-01, 5.29131532e-01, 7.41332620e-02,
-3.37404907e-02, -2.15202749e-01, -2.76737332e-01, 1.89453721e-01,
-3.03772539e-01, 4.45481658e-01, 9.69186366e-01, -2.42250100e-01,
1.71508074e-01, 8.24534297e-02, 2.30651528e-01, 2.35662371e-01,
4.21020985e-02, -3.40390474e-01, 5.84762767e-02, -3.92092228e-01,
1.88959956e-01, -3.15476656e-01, -5.28913081e-01, 1.99238345e-01,
-2.10105523e-01, -6.70148879e-02, 4.91015017e-02, -1.86376438e-01,
5.30448377e-01, -4.77551557e-02, 1.43514201e-01, -1.93393320e-01,
-1.63401037e-01, 8.12670112e-01, -3.98401499e-01, -2.84930706e-01,
3.14741954e-02, 1.58012748e-01, -4.86410260e-01, -1.56198859e-01,
-3.67616415e-02, -2.09563062e-01, -9.35190499e-01, -3.27200055e-01,
-3.38126004e-01, -9.71031487e-02, 1.97424755e-01, -1.24282986e-01,
4.04378921e-01, -3.22293818e-01, 8.63060534e-01, 1.26939505e-01,
3.82508785e-01, 4.43892837e-01, -8.41289759e-02, 4.58587855e-01,
7.20150173e-01, 1.69993192e-01, -2.22574919e-02, -1.27805732e-02,
1.35091059e-02, 3.78924847e-01, 2.59546816e-01, -4.07916248e-01,
4.38221693e-02, 2.29720891e-01, -1.18909940e-01, 4.25066292e-01,
2.37577751e-01, -3.10390830e-01, 1.91625103e-01, 2.90943295e-01,
4.82513398e-01, -1.61673173e-01, -2.36566454e-01, 3.35159421e-01,
-2.33257562e-01, 2.42606252e-01, -6.68886185e-01, -2.87817717e-02,
-1.84682995e-01, -2.60036856e-01, 4.81778622e-01, -1.47496492e-01,
-6.31865263e-02, -2.96359658e-02, -3.30178678e-01, -1.37477607e-01,
-4.93827462e-03, -1.93857104e-01, -2.55057573e-01, -6.07353449e-01,
5.71846813e-02, 6.56697974e-02, 6.76110387e-03, 6.69722080e-01,
1.90174311e-01, -2.11789057e-01, -6.70535564e-01, -1.39362663e-02,
-3.37960780e-01, -2.92045921e-02, -3.10446739e-01, -6.79744482e-01,
2.45386228e-01, -1.04424179e-01, 4.99432087e-01, -8.06442738e-01,
5.16275316e-02, -9.71080959e-02, -2.59308666e-01, 3.58734071e-01,
1.02245726e-01, -6.94308877e-01, 2.93777078e-01, -4.81014401e-02,
-5.56684136e-01, 4.11021054e-01, 3.11595678e-01, 3.56597066e-01,
-3.22645932e-01, -1.79708987e-01, 8.50068778e-02, -1.27996296e-01,
-2.17480451e-01, -4.59592611e-01, -3.88390683e-02, -6.09871373e-02,
-2.34044150e-01, -2.64335126e-02, -4.15414870e-02, 2.53972143e-01,
8.67001861e-02, -1.88431099e-01, -4.57411915e-01, 9.15745735e-01,
1.20536864e-01, -5.53727269e-01, -1.74834520e-01, -4.39218163e-01,
-4.76545095e-03, -2.72112757e-01, 5.60227871e-01, -6.13190591e-01,
-6.37504458e-01, -8.70291740e-02, -4.06813473e-01, 4.47323501e-01,
2.07396626e-01, 1.91421360e-01, -2.78019667e-01, -3.70491266e-01,
4.11907583e-02, 2.55189806e-01, 1.18965074e-01, 7.19900057e-02,
8.59816968e-02, 6.92228019e-01, -4.02260125e-02, -1.80300757e-01,
1.85201168e-01, -1.51197717e-01, -5.61284870e-02, -2.42304340e-01,
3.54461968e-01, -4.18369800e-01, -3.90209794e-01, -4.31636184e-01,
2.38093451e-01, -6.56422257e-01, -3.49493027e-02, -2.31433854e-01,
3.41139942e-01, 4.75289702e-01, -5.11342883e-01, 3.38428646e-01,
-5.88092089e-01, 4.93283212e-01, 9.11664307e-01, -1.27334774e-01,
5.06749809e-01, 7.32645452e-01, -2.66283363e-01, 1.75064266e-01,
9.94869113e-01, 5.84723413e-01, -1.73752010e-01, 4.10124004e-01,
-4.65234965e-01, 1.56231463e-01, -4.35835451e-01, 9.12254006e-02,
4.41908650e-02, -8.53548050e-02, 4.06444967e-01, -1.26593620e-01,
4.70226854e-02, 6.98899388e-01, -3.53937685e-01, -6.36748970e-02,
-3.04918706e-01, 5.07794470e-02, 3.00507247e-02, -3.89267594e-01,
-4.99908924e-01, -3.30217510e-01, -3.15806866e-02, 7.25844502e-02,
-3.28597486e-01, 6.21302426e-03, -3.12173724e-01, 5.40221155e-01,
8.36312413e-01, -3.86419833e-01, -2.10191488e-01, -7.43169338e-02,
-6.50263071e-01, 4.22463685e-01, 4.21417356e-02, -5.12852609e-01,
6.54429197e-04, -1.30067900e-01, -5.55027008e-01, -5.99322498e-01,
-6.70605302e-02, 4.12243307e-01, 1.91760033e-01, 3.09636176e-01,
-7.31615603e-01, 3.70420158e-01, 2.42846869e-02, 1.29094213e-01,
2.05802530e-01, 2.35914350e-01, -6.91545129e-01, -6.47444353e-02,
1.15723908e-01, -6.71297669e-01, 1.75123394e-01, 7.74486065e-01,
3.30843806e-01, -3.01485062e-01, 4.17340279e-01, 1.89491645e-01,
7.83427060e-03, -1.60822213e-01, 3.55308652e-01, -3.12092975e-02],
dtype=float32)
In [15]: toy_dog.vector != dog_toy.vector
Out[15]:
array([ True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True, True, True, True,
True, True, True, True, True, True])
In [16]: for word in toy_dog:
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_)
...:
toy 18139153236473879070 toy 15308085513773655218 NN 91 NOUN
dog 7562983679033046312 dog 15308085513773655218 NN 91 NOUN
In [17]: for word in dog_toy:
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_)
...:
dog 7562983679033046312 dog 15308085513773655218 NN 91 NOUN
toy 18139153236473879070 toy 15308085513773655218 NN 91 NOUN
In [18]: for word in dog_toy:
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_, word.dep)
...:
...:
dog 7562983679033046312 dog 15308085513773655218 NN 91 NOUN 7037928807040764755
toy 18139153236473879070 toy 15308085513773655218 NN 91 NOUN 8206900633647566924
In [19]: for word in toy_dog:
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_, word.dep)
...:
...:
...:
toy 18139153236473879070 toy 15308085513773655218 NN 91 NOUN 7037928807040764755
dog 7562983679033046312 dog 15308085513773655218 NN 91 NOUN 8206900633647566924
In [20]: for word in toy_dog:
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_, word.dep, word.head.pos)
...:
...:
...:
toy 18139153236473879070 toy 15308085513773655218 NN 91 NOUN 7037928807040764755 91
dog 7562983679033046312 dog 15308085513773655218 NN 91 NOUN 8206900633647566924 91
In [21]: for word in dog_toy:
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_, word.dep, word.head.pos)
...:
...:
...:
dog 7562983679033046312 dog 15308085513773655218 NN 91 NOUN 7037928807040764755 91
toy 18139153236473879070 toy 15308085513773655218 NN 91 NOUN 8206900633647566924 91
In [22]: for word in dog_toy:
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_, word.dep, word.head)
...:
...:
...:
dog 7562983679033046312 dog 15308085513773655218 NN 91 NOUN 7037928807040764755 toy
toy 18139153236473879070 toy 15308085513773655218 NN 91 NOUN 8206900633647566924 toy
In [23]: for word in toy_dog:
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_, word.dep, word.head)
...:
...:
...:
toy 18139153236473879070 toy 15308085513773655218 NN 91 NOUN 7037928807040764755 dog
dog 7562983679033046312 dog 15308085513773655218 NN 91 NOUN 8206900633647566924 dog
In [24]: for word in nlp(u"best doctors"):
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_, word.dep, word.head)
...:
best 5711639017775284443 good 14753207560692742245 JJS 83 ADJ 399 doctors
doctors 18058202148154971361 doctor 783433942507015291 NNS 91 NOUN 8206900633647566924 doctors
In [25]: for word in nlp(u"doctors best"):
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_, word.dep, word.head)
...:
doctors 18058202148154971361 doctor 783433942507015291 NNS 91 NOUN 8206900633647566924 doctors
best 5711639017775284443 good 14753207560692742245 JJS 83 ADJ 397 doctors
In [26]: for word in nlp(u"mechanical gaming keyboard"):
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_, word.dep, word.head)
...:
mechanical 3798063157042786403 mechanical 10554686591937588953 JJ 83 ADJ 399 keyboard
gaming 12034845724741083696 gaming 15308085513773655218 NN 91 NOUN 7037928807040764755 keyboard
keyboard 13487348978371443426 keyboard 15308085513773655218 NN 91 NOUN 8206900633647566924 keyboard
In [27]: for word in nlp(u"gaming keyboard mechanical"):
...: print(word.text, word.lemma, word.lemma_, word.tag, word.tag_, word.pos, word.pos_, word.dep, word.head)
...:
gaming 12034845724741083696 gaming 15308085513773655218 NN 91 NOUN 7037928807040764755 keyboard
keyboard 13487348978371443426 keyboard 15308085513773655218 NN 91 NOUN 8206900633647566924 keyboard
mechanical 3798063157042786403 mechanical 10554686591937588953 JJ 83 ADJ 399 keyboard
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment