Path: blob/main/archive/entity_ruler_v0.ipynb
744 views
Kernel: Python 3.9.7 64-bit ('spacytestenv': conda)
EntityRuler v0
This was a test ipynb to create a EntityRuler for a smaller sample, namely MRT stations.
In [1]:
In [2]:
Out[2]:
148
jurong east mrt station
bukit batok mrt station
bukit gombak mrt station
choa chu kang mrt station
yew tee mrt station
kranji mrt station
marsiling mrt station
woodlands mrt station
admiralty mrt station
sembawang mrt station
yishun mrt station
khatib mrt station
yio chu kang mrt station
ang mo kio mrt station
bishan mrt station
braddell mrt station
toa payoh mrt station
novena mrt station
newton mrt station
orchard mrt station
somerset mrt station
dhoby ghaut mrt station
city hall mrt station
raffles place mrt station
marina bay mrt station
marina south pier mrt station
pasir ris mrt station
tampines mrt station
simei mrt station
tanah merah mrt station
bedok mrt station
kembangan mrt station
eunos mrt station
paya lebar mrt station
aljunied mrt station
kallang mrt station
lavender mrt station
bugis mrt station
city hall mrt station
raffles place mrt station
tanjong pagar mrt station
outram park mrt station
tiong bahru mrt station
redhill mrt station
queenstown mrt station
commonwealth mrt station
buona vista mrt station
dover mrt station
clementi mrt station
jurong east mrt station
chinese garden mrt station
lakeside mrt station
boon lay mrt station
pioneer mrt station
joo koon mrt station
gul circle mrt station
tuas crescent mrt station
tuas west road mrt station
tuas link mrt station
expo mrt station
changi airport mrt station
harbourfront mrt station
outram park mrt station
chinatown mrt station
clarke quay mrt station
dhoby ghaut mrt station
little india mrt station
farrer park mrt station
boon keng mrt station
potong pasir mrt station
woodleigh mrt station
serangoon mrt station
kovan mrt station
hougang mrt station
buangkok mrt station
sengkang mrt station
punggol mrt station
dhoby ghaut mrt station
bras basah mrt station
esplanade mrt station
promenade mrt station
nicoll highway mrt station
stadium mrt station
mountbatten mrt station
dakota mrt station
paya lebar mrt station
macpherson mrt station
tai seng mrt station
bartley mrt station
serangoon mrt station
lorong chuan mrt station
bishan mrt station
marymount mrt station
caldecott mrt station
botanic gardens mrt station
farrer road mrt station
holland village mrt station
buona vista mrt station
one-north mrt station
kent ridge mrt station
haw par villa mrt station
pasir panjang mrt station
labrador park mrt station
telok blangah mrt station
harbourfront mrt station
bayfront mrt station
marina bay mrt station
bukit panjang mrt station
cashew mrt station
hillview mrt station
beauty world mrt station
king albert park mrt station
sixth avenue mrt station
tan kah kee mrt station
botanic gardens mrt station
stevens mrt station
newton mrt station
little india mrt station
rochor mrt station
bugis mrt station
promenade mrt station
bayfront mrt station
downtown mrt station
telok ayer mrt station
chinatown mrt station
fort canning mrt station
bencoolen mrt station
jalan besar mrt station
bendemeer mrt station
geylang bahru mrt station
mattar mrt station
macpherson mrt station
ubi mrt station
kaki bukit mrt station
bedok north mrt station
bedok reservoir mrt station
tampines west mrt station
tampines mrt station
tampines east mrt station
upper changi mrt station
expo mrt station
woodlands north mrt station
woodlands south mrt station
springleaf mrt station
lentor mrt station
mayflower mrt station
bright hill mrt station
upper thomson mrt station
In [3]:
Out[3]:
['jurong east mrt station', 'jurong east mrt', 'jurong east mrt stn', 'jurong east stn', 'jurong east station', 'jurong east', 'bukit batok mrt station', 'bukit batok mrt', 'bukit batok mrt stn', 'bukit batok stn', 'bukit batok station', 'bukit batok', 'bukit gombak mrt station', 'bukit gombak mrt', 'bukit gombak mrt stn', 'bukit gombak stn', 'bukit gombak station', 'bukit gombak', 'choa chu kang mrt station', 'choa chu kang mrt', 'choa chu kang mrt stn', 'choa chu kang stn', 'choa chu kang station', 'choa chu kang', 'yew tee mrt station', 'yew tee mrt', 'yew tee mrt stn', 'yew tee stn', 'yew tee station', 'yew tee', 'kranji mrt station', 'kranji mrt', 'kranji mrt stn', 'kranji stn', 'kranji station', 'kranji', 'marsiling mrt station', 'marsiling mrt', 'marsiling mrt stn', 'marsiling stn', 'marsiling station', 'marsiling', 'woodlands mrt station', 'woodlands mrt', 'woodlands mrt stn', 'woodlands stn', 'woodlands station', 'woodlands', 'admiralty mrt station', 'admiralty mrt', 'admiralty mrt stn', 'admiralty stn', 'admiralty station', 'admiralty', 'sembawang mrt station', 'sembawang mrt', 'sembawang mrt stn', 'sembawang stn', 'sembawang station', 'sembawang', 'yishun mrt station', 'yishun mrt', 'yishun mrt stn', 'yishun stn', 'yishun station', 'yishun', 'khatib mrt station', 'khatib mrt', 'khatib mrt stn', 'khatib stn', 'khatib station', 'khatib', 'yio chu kang mrt station', 'yio chu kang mrt', 'yio chu kang mrt stn', 'yio chu kang stn', 'yio chu kang station', 'yio chu kang', 'ang mo kio mrt station', 'ang mo kio mrt', 'ang mo kio mrt stn', 'ang mo kio stn', 'ang mo kio station', 'ang mo kio', 'bishan mrt station', 'bishan mrt', 'bishan mrt stn', 'bishan stn', 'bishan station', 'bishan', 'braddell mrt station', 'braddell mrt', 'braddell mrt stn', 'braddell stn', 'braddell station', 'braddell', 'toa payoh mrt station', 'toa payoh mrt', 'toa payoh mrt stn', 'toa payoh stn', 'toa payoh station', 'toa payoh', 'novena mrt station', 'novena mrt', 'novena mrt stn', 'novena stn', 'novena station', 'novena', 'newton mrt station', 'newton mrt', 'newton mrt stn', 'newton stn', 'newton station', 'newton', 'orchard mrt station', 'orchard mrt', 'orchard mrt stn', 'orchard stn', 'orchard station', 'orchard', 'somerset mrt station', 'somerset mrt', 'somerset mrt stn', 'somerset stn', 'somerset station', 'somerset', 'dhoby ghaut mrt station', 'dhoby ghaut mrt', 'dhoby ghaut mrt stn', 'dhoby ghaut stn', 'dhoby ghaut station', 'dhoby ghaut', 'city hall mrt station', 'city hall mrt', 'city hall mrt stn', 'city hall stn', 'city hall station', 'city hall', 'raffles place mrt station', 'raffles place mrt', 'raffles place mrt stn', 'raffles place stn', 'raffles place station', 'raffles place', 'marina bay mrt station', 'marina bay mrt', 'marina bay mrt stn', 'marina bay stn', 'marina bay station', 'marina bay', 'marina south pier mrt station', 'marina south pier mrt', 'marina south pier mrt stn', 'marina south pier stn', 'marina south pier station', 'marina south pier', 'pasir ris mrt station', 'pasir ris mrt', 'pasir ris mrt stn', 'pasir ris stn', 'pasir ris station', 'pasir ris', 'tampines mrt station', 'tampines mrt', 'tampines mrt stn', 'tampines stn', 'tampines station', 'tampines', 'simei mrt station', 'simei mrt', 'simei mrt stn', 'simei stn', 'simei station', 'simei', 'tanah merah mrt station', 'tanah merah mrt', 'tanah merah mrt stn', 'tanah merah stn', 'tanah merah station', 'tanah merah', 'bedok mrt station', 'bedok mrt', 'bedok mrt stn', 'bedok stn', 'bedok station', 'bedok', 'kembangan mrt station', 'kembangan mrt', 'kembangan mrt stn', 'kembangan stn', 'kembangan station', 'kembangan', 'eunos mrt station', 'eunos mrt', 'eunos mrt stn', 'eunos stn', 'eunos station', 'eunos', 'paya lebar mrt station', 'paya lebar mrt', 'paya lebar mrt stn', 'paya lebar stn', 'paya lebar station', 'paya lebar', 'aljunied mrt station', 'aljunied mrt', 'aljunied mrt stn', 'aljunied stn', 'aljunied station', 'aljunied', 'kallang mrt station', 'kallang mrt', 'kallang mrt stn', 'kallang stn', 'kallang station', 'kallang', 'lavender mrt station', 'lavender mrt', 'lavender mrt stn', 'lavender stn', 'lavender station', 'lavender', 'bugis mrt station', 'bugis mrt', 'bugis mrt stn', 'bugis stn', 'bugis station', 'bugis', 'city hall mrt station', 'city hall mrt', 'city hall mrt stn', 'city hall stn', 'city hall station', 'city hall', 'raffles place mrt station', 'raffles place mrt', 'raffles place mrt stn', 'raffles place stn', 'raffles place station', 'raffles place', 'tanjong pagar mrt station', 'tanjong pagar mrt', 'tanjong pagar mrt stn', 'tanjong pagar stn', 'tanjong pagar station', 'tanjong pagar', 'outram park mrt station', 'outram park mrt', 'outram park mrt stn', 'outram park stn', 'outram park station', 'outram park', 'tiong bahru mrt station', 'tiong bahru mrt', 'tiong bahru mrt stn', 'tiong bahru stn', 'tiong bahru station', 'tiong bahru', 'redhill mrt station', 'redhill mrt', 'redhill mrt stn', 'redhill stn', 'redhill station', 'redhill', 'queenstown mrt station', 'queenstown mrt', 'queenstown mrt stn', 'queenstown stn', 'queenstown station', 'queenstown', 'commonwealth mrt station', 'commonwealth mrt', 'commonwealth mrt stn', 'commonwealth stn', 'commonwealth station', 'commonwealth', 'buona vista mrt station', 'buona vista mrt', 'buona vista mrt stn', 'buona vista stn', 'buona vista station', 'buona vista', 'dover mrt station', 'dover mrt', 'dover mrt stn', 'dover stn', 'dover station', 'dover', 'clementi mrt station', 'clementi mrt', 'clementi mrt stn', 'clementi stn', 'clementi station', 'clementi', 'jurong east mrt station', 'jurong east mrt', 'jurong east mrt stn', 'jurong east stn', 'jurong east station', 'jurong east', 'chinese garden mrt station', 'chinese garden mrt', 'chinese garden mrt stn', 'chinese garden stn', 'chinese garden station', 'chinese garden', 'lakeside mrt station', 'lakeside mrt', 'lakeside mrt stn', 'lakeside stn', 'lakeside station', 'lakeside', 'boon lay mrt station', 'boon lay mrt', 'boon lay mrt stn', 'boon lay stn', 'boon lay station', 'boon lay', 'pioneer mrt station', 'pioneer mrt', 'pioneer mrt stn', 'pioneer stn', 'pioneer station', 'pioneer', 'joo koon mrt station', 'joo koon mrt', 'joo koon mrt stn', 'joo koon stn', 'joo koon station', 'joo koon', 'gul circle mrt station', 'gul circle mrt', 'gul circle mrt stn', 'gul circle stn', 'gul circle station', 'gul circle', 'tuas crescent mrt station', 'tuas crescent mrt', 'tuas crescent mrt stn', 'tuas crescent stn', 'tuas crescent station', 'tuas crescent', 'tuas west road mrt station', 'tuas west road mrt', 'tuas west road mrt stn', 'tuas west road stn', 'tuas west road station', 'tuas west road', 'tuas link mrt station', 'tuas link mrt', 'tuas link mrt stn', 'tuas link stn', 'tuas link station', 'tuas link', 'expo mrt station', 'expo mrt', 'expo mrt stn', 'expo stn', 'expo station', 'expo', 'changi airport mrt station', 'changi airport mrt', 'changi airport mrt stn', 'changi airport stn', 'changi airport station', 'changi airport', 'harbourfront mrt station', 'harbourfront mrt', 'harbourfront mrt stn', 'harbourfront stn', 'harbourfront station', 'harbourfront', 'outram park mrt station', 'outram park mrt', 'outram park mrt stn', 'outram park stn', 'outram park station', 'outram park', 'chinatown mrt station', 'chinatown mrt', 'chinatown mrt stn', 'chinatown stn', 'chinatown station', 'chinatown', 'clarke quay mrt station', 'clarke quay mrt', 'clarke quay mrt stn', 'clarke quay stn', 'clarke quay station', 'clarke quay', 'dhoby ghaut mrt station', 'dhoby ghaut mrt', 'dhoby ghaut mrt stn', 'dhoby ghaut stn', 'dhoby ghaut station', 'dhoby ghaut', 'little india mrt station', 'little india mrt', 'little india mrt stn', 'little india stn', 'little india station', 'little india', 'farrer park mrt station', 'farrer park mrt', 'farrer park mrt stn', 'farrer park stn', 'farrer park station', 'farrer park', 'boon keng mrt station', 'boon keng mrt', 'boon keng mrt stn', 'boon keng stn', 'boon keng station', 'boon keng', 'potong pasir mrt station', 'potong pasir mrt', 'potong pasir mrt stn', 'potong pasir stn', 'potong pasir station', 'potong pasir', 'woodleigh mrt station', 'woodleigh mrt', 'woodleigh mrt stn', 'woodleigh stn', 'woodleigh station', 'woodleigh', 'serangoon mrt station', 'serangoon mrt', 'serangoon mrt stn', 'serangoon stn', 'serangoon station', 'serangoon', 'kovan mrt station', 'kovan mrt', 'kovan mrt stn', 'kovan stn', 'kovan station', 'kovan', 'hougang mrt station', 'hougang mrt', 'hougang mrt stn', 'hougang stn', 'hougang station', 'hougang', 'buangkok mrt station', 'buangkok mrt', 'buangkok mrt stn', 'buangkok stn', 'buangkok station', 'buangkok', 'sengkang mrt station', 'sengkang mrt', 'sengkang mrt stn', 'sengkang stn', 'sengkang station', 'sengkang', 'punggol mrt station', 'punggol mrt', 'punggol mrt stn', 'punggol stn', 'punggol station', 'punggol', 'dhoby ghaut mrt station', 'dhoby ghaut mrt', 'dhoby ghaut mrt stn', 'dhoby ghaut stn', 'dhoby ghaut station', 'dhoby ghaut', 'bras basah mrt station', 'bras basah mrt', 'bras basah mrt stn', 'bras basah stn', 'bras basah station', 'bras basah', 'esplanade mrt station', 'esplanade mrt', 'esplanade mrt stn', 'esplanade stn', 'esplanade station', 'esplanade', 'promenade mrt station', 'promenade mrt', 'promenade mrt stn', 'promenade stn', 'promenade station', 'promenade', 'nicoll highway mrt station', 'nicoll highway mrt', 'nicoll highway mrt stn', 'nicoll highway stn', 'nicoll highway station', 'nicoll highway', 'stadium mrt station', 'stadium mrt', 'stadium mrt stn', 'stadium stn', 'stadium station', 'stadium', 'mountbatten mrt station', 'mountbatten mrt', 'mountbatten mrt stn', 'mountbatten stn', 'mountbatten station', 'mountbatten', 'dakota mrt station', 'dakota mrt', 'dakota mrt stn', 'dakota stn', 'dakota station', 'dakota', 'paya lebar mrt station', 'paya lebar mrt', 'paya lebar mrt stn', 'paya lebar stn', 'paya lebar station', 'paya lebar', 'macpherson mrt station', 'macpherson mrt', 'macpherson mrt stn', 'macpherson stn', 'macpherson station', 'macpherson', 'tai seng mrt station', 'tai seng mrt', 'tai seng mrt stn', 'tai seng stn', 'tai seng station', 'tai seng', 'bartley mrt station', 'bartley mrt', 'bartley mrt stn', 'bartley stn', 'bartley station', 'bartley', 'serangoon mrt station', 'serangoon mrt', 'serangoon mrt stn', 'serangoon stn', 'serangoon station', 'serangoon', 'lorong chuan mrt station', 'lorong chuan mrt', 'lorong chuan mrt stn', 'lorong chuan stn', 'lorong chuan station', 'lorong chuan', 'bishan mrt station', 'bishan mrt', 'bishan mrt stn', 'bishan stn', 'bishan station', 'bishan', 'marymount mrt station', 'marymount mrt', 'marymount mrt stn', 'marymount stn', 'marymount station', 'marymount', 'caldecott mrt station', 'caldecott mrt', 'caldecott mrt stn', 'caldecott stn', 'caldecott station', 'caldecott', 'botanic gardens mrt station', 'botanic gardens mrt', 'botanic gardens mrt stn', 'botanic gardens stn', 'botanic gardens station', 'botanic gardens', 'farrer road mrt station', 'farrer road mrt', 'farrer road mrt stn', 'farrer road stn', 'farrer road station', 'farrer road', 'holland village mrt station', 'holland village mrt', 'holland village mrt stn', 'holland village stn', 'holland village station', 'holland village', 'buona vista mrt station', 'buona vista mrt', 'buona vista mrt stn', 'buona vista stn', 'buona vista station', 'buona vista', 'one-north mrt station', 'one-north mrt', 'one-north mrt stn', 'one-north stn', 'one-north station', 'one-north', 'kent ridge mrt station', 'kent ridge mrt', 'kent ridge mrt stn', 'kent ridge stn', 'kent ridge station', 'kent ridge', 'haw par villa mrt station', 'haw par villa mrt', 'haw par villa mrt stn', 'haw par villa stn', 'haw par villa station', 'haw par villa', 'pasir panjang mrt station', 'pasir panjang mrt', 'pasir panjang mrt stn', 'pasir panjang stn', 'pasir panjang station', 'pasir panjang', 'labrador park mrt station', 'labrador park mrt', 'labrador park mrt stn', 'labrador park stn', 'labrador park station', 'labrador park', 'telok blangah mrt station', 'telok blangah mrt', 'telok blangah mrt stn', 'telok blangah stn', 'telok blangah station', 'telok blangah', 'harbourfront mrt station', 'harbourfront mrt', 'harbourfront mrt stn', 'harbourfront stn', 'harbourfront station', 'harbourfront', 'bayfront mrt station', 'bayfront mrt', 'bayfront mrt stn', 'bayfront stn', 'bayfront station', 'bayfront', 'marina bay mrt station', 'marina bay mrt', 'marina bay mrt stn', 'marina bay stn', 'marina bay station', 'marina bay', 'bukit panjang mrt station', 'bukit panjang mrt', 'bukit panjang mrt stn', 'bukit panjang stn', 'bukit panjang station', 'bukit panjang', 'cashew mrt station', 'cashew mrt', 'cashew mrt stn', 'cashew stn', 'cashew station', 'cashew', 'hillview mrt station', 'hillview mrt', 'hillview mrt stn', 'hillview stn', 'hillview station', 'hillview', 'beauty world mrt station', 'beauty world mrt', 'beauty world mrt stn', 'beauty world stn', 'beauty world station', 'beauty world', 'king albert park mrt station', 'king albert park mrt', 'king albert park mrt stn', 'king albert park stn', 'king albert park station', 'king albert park', 'sixth avenue mrt station', 'sixth avenue mrt', 'sixth avenue mrt stn', 'sixth avenue stn', 'sixth avenue station', 'sixth avenue', 'tan kah kee mrt station', 'tan kah kee mrt', 'tan kah kee mrt stn', 'tan kah kee stn', 'tan kah kee station', 'tan kah kee', 'botanic gardens mrt station', 'botanic gardens mrt', 'botanic gardens mrt stn', 'botanic gardens stn', 'botanic gardens station', 'botanic gardens', 'stevens mrt station', 'stevens mrt', 'stevens mrt stn', 'stevens stn', 'stevens station', 'stevens', 'newton mrt station', 'newton mrt', 'newton mrt stn', 'newton stn', 'newton station', 'newton', 'little india mrt station', 'little india mrt', 'little india mrt stn', 'little india stn', 'little india station', 'little india', 'rochor mrt station', 'rochor mrt', 'rochor mrt stn', 'rochor stn', 'rochor station', 'rochor', 'bugis mrt station', 'bugis mrt', 'bugis mrt stn', 'bugis stn', 'bugis station', 'bugis', 'promenade mrt station', 'promenade mrt', 'promenade mrt stn', 'promenade stn', 'promenade station', 'promenade', 'bayfront mrt station', 'bayfront mrt', 'bayfront mrt stn', 'bayfront stn', 'bayfront station', 'bayfront', 'downtown mrt station', 'downtown mrt', 'downtown mrt stn', 'downtown stn', 'downtown station', 'downtown', 'telok ayer mrt station', 'telok ayer mrt', 'telok ayer mrt stn', 'telok ayer stn', 'telok ayer station', 'telok ayer', 'chinatown mrt station', 'chinatown mrt', 'chinatown mrt stn', 'chinatown stn', 'chinatown station', 'chinatown', 'fort canning mrt station', 'fort canning mrt', 'fort canning mrt stn', 'fort canning stn', 'fort canning station', 'fort canning', 'bencoolen mrt station', 'bencoolen mrt', 'bencoolen mrt stn', 'bencoolen stn', 'bencoolen station', 'bencoolen', 'jalan besar mrt station', 'jalan besar mrt', 'jalan besar mrt stn', 'jalan besar stn', 'jalan besar station', 'jalan besar', 'bendemeer mrt station', 'bendemeer mrt', 'bendemeer mrt stn', 'bendemeer stn', 'bendemeer station', 'bendemeer', 'geylang bahru mrt station', 'geylang bahru mrt', 'geylang bahru mrt stn', 'geylang bahru stn', 'geylang bahru station', 'geylang bahru', 'mattar mrt station', 'mattar mrt', 'mattar mrt stn', 'mattar stn', 'mattar station', 'mattar', 'macpherson mrt station', 'macpherson mrt', 'macpherson mrt stn', 'macpherson stn', 'macpherson station', 'macpherson', 'ubi mrt station', 'ubi mrt', 'ubi mrt stn', 'ubi stn', 'ubi station', 'ubi', 'kaki bukit mrt station', 'kaki bukit mrt', 'kaki bukit mrt stn', 'kaki bukit stn', 'kaki bukit station', 'kaki bukit', 'bedok north mrt station', 'bedok north mrt', 'bedok north mrt stn', 'bedok north stn', 'bedok north station', 'bedok north', 'bedok reservoir mrt station', 'bedok reservoir mrt', 'bedok reservoir mrt stn', 'bedok reservoir stn', 'bedok reservoir station', 'bedok reservoir', 'tampines west mrt station', 'tampines west mrt', 'tampines west mrt stn', 'tampines west stn', 'tampines west station', 'tampines west', 'tampines mrt station', 'tampines mrt', 'tampines mrt stn', 'tampines stn', 'tampines station', 'tampines', 'tampines east mrt station', 'tampines east mrt', 'tampines east mrt stn', 'tampines east stn', 'tampines east station', 'tampines east', 'upper changi mrt station', 'upper changi mrt', 'upper changi mrt stn', 'upper changi stn', 'upper changi station', 'upper changi', 'expo mrt station', 'expo mrt', 'expo mrt stn', 'expo stn', 'expo station', 'expo', 'woodlands north mrt station', 'woodlands north mrt', 'woodlands north mrt stn', 'woodlands north stn', 'woodlands north station', 'woodlands north', 'woodlands south mrt station', 'woodlands south mrt', 'woodlands south mrt stn', 'woodlands south stn', 'woodlands south station', 'woodlands south', 'springleaf mrt station', 'springleaf mrt', 'springleaf mrt stn', 'springleaf stn', 'springleaf station', 'springleaf', 'lentor mrt station', 'lentor mrt', 'lentor mrt stn', 'lentor stn', 'lentor station', 'lentor', 'mayflower mrt station', 'mayflower mrt', 'mayflower mrt stn', 'mayflower stn', 'mayflower station', 'mayflower', 'bright hill mrt station', 'bright hill mrt', 'bright hill mrt stn', 'bright hill stn', 'bright hill station', 'bright hill', 'upper thomson mrt station', 'upper thomson mrt', 'upper thomson mrt stn', 'upper thomson stn', 'upper thomson station', 'upper thomson']
In [4]:
In [5]: