Part-of-speech clarifier from nltk

clarify_pos.py

from nltk import pos_tag
from nltk.tag import str2tuple

"""
Usage:
dictionary_df['Pos'] = dictionary_df['Word'].apply(pos_maker)
dictionary_df['Help Definition'] = dictionary_df['Pos'].apply(clarify_pos)
"""

def clarify_pos(pos):
    """
    From https://stackoverflow.com/questions/15388831/what-are-all-possible-pos-tags-of-nltk
    Aim is to aid in analysis, can be easily applied to pandas dataframes to create
    a new column so that pos signifiers can be read in plain English.
    Input: String (part of speech)
    Output: String (help definition from upenn corpus), possibly None
    """
    
    if pos == 'CC': 
        return 'conjunction, coordinating'
    """& 'n and both but either et for less minus neither nor or plus so
    therefore times v. versus vs. whether yet"""
    
    if pos == 'CD': 
        return 'numeral, cardinal'
    """mid-1890 nine-thirty forty-two one-tenth ten million 0.5 one forty-
    seven 1987 twenty '79 zero two 78-degrees eighty-four IX '60s .025
    fifteen 271,124 dozen quintillion DM2,000 ... """
    
    if pos == 'DT': 
        return 'determiner'
    """all an another any both del each either every half la many much nary
    neither no some such that the them these this those"""
    
    if pos == 'EX': 
        return 'existential there'
    """there"""
    
    if pos == 'IN': 
        return 'preposition or conjunction, subordinating'
    """astride among uppon whether out inside pro despite on by throughout
    below within for towards near behind atop around if like until below
    next into if beside ..."""

    if pos == 'JJ': 
        return 'adjective or numeral, ordinal'
    """third ill-mannered pre-war regrettable oiled calamitous first separable
    ectoplasmic battery-powered participatory fourth still-to-be-named
    multilingual multi-disciplinary ..."""

    if pos == 'JJR': 
        return 'adjective, comparative'
    """bleaker braver breezier briefer brighter brisker broader bumper busier
    calmer cheaper choosier cleaner clearer closer colder commoner costlier
    cozier creamier crunchier cuter ..."""

    if pos == 'JJS': 
        return 'adjective, superlative'
    """calmest cheapest choicest classiest cleanest clearest closest commonest
    corniest costliest crassest creepiest crudest cutest darkest deadliest
    dearest deepest densest dinkiest ..."""

    if pos == 'LS': 
        return 'list item marker'
    """A A. B B. C C. D E F First G H I J K One SP-44001 SP-44002 SP-44005
    SP-44007 Second Third Three Two * a b c d first five four one six three
    two"""

    if pos == 'MD': 
        return 'modal auxiliary'
    """can cannot could couldn't dare may might must need ought shall should
    shouldn't will would"""

    if pos == 'NN': 
        return 'noun, common, singular or mass'
    """common-carrier cabbage knuckle-duster Casino afghan shed thermostat
    investment slide humour falloff slick wind hyena override subhumanity
    machinist ..."""

    if pos == 'NNP': 
        return 'noun, proper, singular'
    """Motown Venneboerger Czestochwa Ranzer Conchita Trumplane Christos
    Oceanside Escobar Kreisler Sawyer Cougar Yvette Ervin ODI Darryl CTCA
    Shannon A.K.C. Meltex Liverpool ..."""

    if pos == 'NNS': 
        return 'noun, common, plural'
    """undergraduates scotches bric-a-brac products bodyguards facets coasts
    divestitures storehouses designs clubs fragrances averages
    subjectivists apprehensions muses factory-jobs ..."""

    if pos == 'PDT': 
        return 'pre-determiner'
    """all both half many quite such sure this"""

    if pos == 'POS': 
        return 'genitive marker'
    """' 's """

    if pos == 'PRP': 
        return 'pronoun, personal'
    """hers herself him himself hisself it itself me myself one oneself ours
    ourselves ownself self she thee theirs them themselves they thou thy us"""

    if pos == 'PRP$': 
        return 'pronoun, possessive'
    """her his mine my our ours their thy your"""

    if pos == 'RB': 
        return 'adverb'
    """occasionally unabatingly maddeningly adventurously professedly
    stirringly prominently technologically magisterially predominately
    swiftly fiscally pitilessly ..."""

    if pos == 'RBR': 
        return 'adverb, comparative'
    """further gloomier grander graver greater grimmer harder harsher
    healthier heavier higher however larger later leaner lengthier less-
    perfectly lesser lonelier longer louder lower more ..."""

    if pos == 'RBS': 
        return 'adverb, superlative'
    """best biggest bluntest earliest farthest first furthest hardest
    heartiest highest largest least less most nearest second tightest worst"""

    if pos == 'RP': 
        return 'particle'
    """aboard about across along apart around aside at away back before behind
    by crop down ever fast for forth from go high i.e. in into just later
    low more off on open out over per pie raising start teeth that through
    under unto up up-pp upon whole with you"""

    if pos == 'TO': 
        return '"to" as preposition or infinitive marker''
    """to"""

    if pos == 'UH': 
        return 'interjection'
    """Goodbye Goody Gosh Wow Jeepers Jee-sus Hubba Hey Kee-reist Oops amen
    huh howdy uh dammit whammo shucks heck anyways whodunnit honey golly
    man baby diddle hush sonuvabitch ..."""

    if pos == 'VB': 
        return 'verb, base form'
    """ask assemble assess assign assume atone attention avoid bake balkanize
    bank begin behold believe bend benefit bevel beware bless boil bomb
    boost brace break bring broil brush build ..."""

    if pos == 'VBD': 
        return 'verb, past tense'
    """dipped pleaded swiped regummed soaked tidied convened halted registered
    cushioned exacted snubbed strode aimed adopted belied figgered
    speculated wore appreciated contemplated ..."""

    if pos == 'VBG': 
        return 'verb, present participle or gerund'
    """telegraphing stirring focusing angering judging stalling lactating
    hankerin' alleging veering capping approaching traveling besieging
    encrypting interrupting erasing wincing ..."""

    if pos == 'VBN': 
        return 'verb, past participle'
    """multihulled dilapidated aerosolized chaired languished panelized used
    experimented flourished imitated reunifed factored condensed sheared
    unsettled primed dubbed desired ..."""

    if pos == 'VBP': 
        return 'verb, present tense, not 3rd person singular'
    """predominate wrap resort sue twist spill cure lengthen brush terminate
    appear tend stray glisten obtain comprise detest tease attract
    emphasize mold postpone sever return wag ..."""

    if pos == 'VBZ': 
        return 'verb, present tense, 3rd person singular'
    """bases reconstructs marks mixes displeases seals carps weaves snatches
    slumps stretches authorizes smolders pictures emerges stockpiles
    seduces fizzes uses bolsters slaps speaks pleads ..."""

    if pos == 'WDT': 
        return 'WH-determiner'
    """that what whatever which whichever"""

    if pos == 'WP': 
        return 'WH-pronoun'
    """that what whatever whatsoever which who whom whosoever"""

    if pos == 'WRB': 
        return 'Wh-adverb'
    """how however whence whenever where whereby whereever wherein whereof why"""
    
def pos_maker(x):
    """
    Uses pos_tag on a single word to return its part of speech
    """
    try: 
        pos =  pos_tag([x.lower()])[0][1]
    except:
        if x == 'NULL':
            #throws a 'cannot use .lower() method on float' error
            pos = 'NN'
    return pos