In [1]:
from nltk.corpus import wordnet
from nltk import word_tokenize, pos_tag
from nltk.stem import WordNetLemmatizer


SampleTXT='The yellow dog barked at the cat'

def get_wordnet_pos(treebank_tag):
    if treebank_tag.startswith('J'):
        return wordnet.ADJ
    elif treebank_tag.startswith('V'):
        return wordnet.VERB
    elif treebank_tag.startswith('N'):
        return wordnet.NOUN
    elif treebank_tag.startswith('R'):
        return wordnet.ADV
    else:
        return None


def lemmatize_sentence(sentence):
    res = []
    lemmatizer = WordNetLemmatizer()
    
    print word_tokenize(sentence)
    for word, pos in pos_tag(word_tokenize(sentence)):
        print word, pos
        wordnet_pos = get_wordnet_pos(pos) or wordnet.NOUN
        res.append(lemmatizer.lemmatize(word, pos=wordnet_pos))

    return res

In [8]:
import MySQLdb as mysql

In [ ]:
#connect into DB
conn = mysql.connect(host='140.116.112.164', user='iim_project', passwd='1qaz2wsx3eDC', db = "iim_project", charset="utf8")
cur = conn.cursor()

cur.execute("SELECT word FROM ES2002a_grammer")
words = cur.fetchall()

cur.execute("SELECT * FORM ES2002a_grammer")
final = cur.fetchall()

cur.close()
conn.close()

In [ ]:
final

In [38]:
words = list(words)

for i in range(len(words)):
    words[i] = list(words[i])

In [39]:
for word in words:
    word[0] = str(word[0])

In [40]:
words


Out[40]:
[['Uh_huh'],
 ['select'],
 ['a'],
 ['she'],
 ['has'],
 ['produced'],
 ['a'],
 ['powerpoint'],
 ['Uh'],
 ['I'],
 ['think'],
 ['it'],
 ["'s"],
 ['already'],
 ['on'],
 ['actually'],
 ['we'],
 ["'ll"],
 ['try'],
 ['the'],
 ['main'],
 ['thing'],
 ['work'],
 ['yeah'],
 ['applies'],
 ['in'],
 ['the'],
 ['back'],
 ['but'],
 ['okay'],
 ['right'],
 ['Now'],
 ['I'],
 ['yes'],
 ['okay'],
 ['right'],
 ['well'],
 ['was'],
 ['the'],
 ['kickoff'],
 ['meeting'],
 ['for'],
 ['our'],
 ['our'],
 ['project'],
 ['and'],
 ['this'],
 ['this'],
 ['is'],
 ['just'],
 ['what'],
 ['we'],
 ['we'],
 ["'re"],
 ['gon'],
 ['na'],
 ['be'],
 ['doing'],
 ['in'],
 ['the'],
 ['next'],
 ['twenty'],
 ['five'],
 ['minutes'],
 ['Um'],
 ['so'],
 ['personal'],
 ['just'],
 ['to'],
 ['kind'],
 ['of'],
 ['make'],
 ['sure'],
 ['that'],
 ['we'],
 ['all'],
 ['know'],
 ['each'],
 ['other'],
 ['I'],
 ["'m"],
 ['your'],
 ['and'],
 ['I'],
 ["'m"],
 ['the'],
 ['project'],
 ['manager'],
 ['manager'],
 ['do'],
 ["n't"],
 ['introduce'],
 ['yourself'],
 ['again'],
 ['Um'],
 ['data'],
 ['data'],
 ['and'],
 ['I'],
 ['I'],
 ['I'],
 ["'m"],
 ['supposed'],
 ['to'],
 ['be'],
 ['industrial'],
 ['designer'],
 ['okay'],
 ['Andrew'],
 ['and'],
 ['I'],
 ['I'],
 ["'m"],
 ['the'],
 ['marketing'],
 ['an'],
 ['expert'],
 ['I'],
 ["'m"],
 ['pregnant'],
 ['agent'],
 ['great'],
 ['okay'],
 ['I'],
 ['was'],
 ['we'],
 ["'re"],
 ['designing'],
 ['any'],
 ['remote'],
 ['control'],
 ['And'],
 ['oh'],
 ['I'],
 ['I'],
 ['have'],
 ['to'],
 ['record'],
 ['he'],
 ["'s"],
 ['here'],
 ['actually'],
 ['so'],
 ['this'],
 ['this'],
 ['do'],
 ['the'],
 ['Andrew'],
 ['and'],
 ['created'],
 ['created'],
 ['and'],
 ['you'],
 ["'ll"],
 ['arrived'],
 ['on'],
 ['time'],
 ['Um'],
 ['yes'],
 ['it'],
 ['is'],
 ['a'],
 ['design'],
 ['a'],
 ['new'],
 ['remote'],
 ['control'],
 ['as'],
 ['you'],
 ['can'],
 ['see'],
 ['is'],
 ['this'],
 ['this'],
 ['be'],
 ['original'],
 ['trendy'],
 ['and'],
 ['user'],
 ['friendly'],
 ['friendly'],
 ['Um'],
 ['so'],
 ['that'],
 ["'s"],
 ['kind'],
 ['of'],
 ['our'],
 ['our'],
 ['brief'],
 ['the'],
 ['wire'],
 ['and'],
 ['so'],
 ['there'],
 ['are'],
 ['are'],
 ['three'],
 ['different'],
 ['stages'],
 ['to'],
 ['the'],
 ['design'],
 ['And'],
 ['I'],
 ["'m"],
 ['not'],
 ['sure'],
 ['what'],
 ['what'],
 ['you'],
 ['guys'],
 ['have'],
 ['already'],
 ['received'],
 ['in'],
 ['your'],
 ['emails'],
 ['emails'],
 ['what'],
 ["'d"],
 ['you'],
 ['get'],
 ['I'],
 ['just'],
 ['got'],
 ["'cause"],
 ['I'],
 ['know'],
 ['you'],
 ['had'],
 ['to'],
 ['calls'],
 ['okay'],
 ['so'],
 ['we'],
 ['we'],
 ["'re"],
 ['gon'],
 ['na'],
 ['have'],
 ['like'],
 ['individual'],
 ['work'],
 ['and'],
 ['then'],
 ['a'],
 ['meeting'],
 ['meeting'],
 ['about'],
 ['it'],
 ['And'],
 ['repeat'],
 ['that'],
 ['process'],
 ['three'],
 ['times'],
 ['Um'],
 ['and'],
 ['at'],
 ['this'],
 ['point'],
 ['we'],
 ['get'],
 ['try'],
 ['the'],
 ['whiteboard'],
 ['over'],
 ['there'],
 ['I'],
 ['I'],
 ['I'],
 ['so'],
 ['you'],
 ['you'],
 ['get'],
 ['to'],
 ['draw'],
 ['your'],
 ['favourite'],
 ['animal'],
 ['and'],
 ['sum'],
 ['sum'],
 ['of'],
 ['so'],
 ['you'],
 ['you'],
 ["'d"],
 ['like'],
 ['to'],
 ['get'],
 ['more'],
 ['is'],
 ['very'],
 ['kids'],
 ['I.'],
 ['alright'],
 ['So'],
 ['this'],
 ['one'],
 ['here'],
 ['right'],
 ['okay'],
 ['I'],
 ['do'],
 ["n't"],
 ['alright'],
 ['my'],
 ['favourite'],
 ['animal'],
 ['and'],
 ['like'],
 ['ah'],
 ['ah'],
 ['a'],
 ['L'],
 ['I'],
 ['characters'],
 ['are'],
 ['about'],
 ['right'],
 ['yeah'],
 ['alright'],
 ['well'],
 ['basically'],
 ['high'],
 ['priority'],
 ['for'],
 ['any'],
 ['animal'],
 ['for'],
 ['me'],
 ['is'],
 ['that'],
 ['they'],
 ['they'],
 ['be'],
 ['willing'],
 ['to'],
 ['take'],
 ['a'],
 ['lot'],
 ['of'],
 ['physical'],
 ['affection'],
 ['from'],
 ['the'],
 ['family'],
 ['And'],
 ['just'],
 ['yeah'],
 ['they'],
 ['have'],
 ['lots'],
 ['of'],
 ['personality'],
 ['and'],
 ['this'],
 ['this'],
 ['and'],
 ['then'],
 ['robust'],
 ['good'],
 ['health'],
 ['health'],
 ['So'],
 ['this'],
 ['is'],
 ['the'],
 ['bigger'],
 ['I'],
 ['families'],
 ['be'],
 ['right'],
 ['lovely'],
 ['yeah'],
 ['no'],
 ['matter'],
 ['of'],
 ['on'],
 ['would'],
 ['be'],
 ['a'],
 ['monkey'],
 ['I'],
 ['I'],
 ['the'],
 ['smoke'],
 ['even'],
 ['for'],
 ['a'],
 ['and'],
 ['then'],
 ['one'],
 ['for'],
 ['the'],
 ['gon'],
 ['na'],
 ['real'],
 ['no'],
 ['and'],
 ['when'],
 ['when'],
 ['the'],
 ['other'],
 ['with'],
 ['them'],
 ['right'],
 ['here'],
 ['you'],
 ['can'],
 ['take'],
 ['as'],
 ['long'],
 ['over'],
 ['this'],
 ['is'],
 ['a'],
 ['like'],
 ['because'],
 ['we'],
 ['have'],
 ["n't"],
 ['got'],
 ['an'],
 ['awful'],
 ['lot'],
 ['there'],
 ["'s"],
 ['of'],
 ['day'],
 ['today'],
 ['do'],
 ["n't"],
 ['feel'],
 ['like'],
 ['your'],
 ['interaction'],
 ['anyway'],
 ['actually'],
 ['told'],
 ['me'],
 ['a'],
 ['lot'],
 ['more'],
 ['about'],
 ['the'],
 ['eagles'],
 ['it'],
 ["'s"],
 ['so'],
 ['much'],
 ['or'],
 ['what'],
 ['what'],
 ['have'],
 ['have'],
 ['to'],
 ['get'],
 ['yeah'],
 ['because'],
 ['I'],
 ['do'],
 ["n't"],
 ['know'],
 ['mine'],
 ['is'],
 ["n't"],
 ['gon'],
 ['na'],
 ['think'],
 ['on'],
 ['the'],
 ['spot'],
 ['oh'],
 ['is'],
 ['that'],
 ['a'],
 ['whale'],
 ['yeah'],
 ['yeah'],
 ['I.'],
 ['well'],
 ['like'],
 ['I'],
 ['do'],
 ["n't"],
 ['know'],
 ['it'],
 ["'s"],
 ['just'],
 ['for'],
 ['am'],
 ['I'],
 ['can'],
 ['think'],
 ['of'],
 ['the'],
 ['top'],
 ['of'],
 ['my'],
 ['head'],
 ['figure'],
 ['is'],
 ['in'],
 ['this'],
 ["'cause"],
 ['I'],
 ["'m"],
 ['allergic'],
 ['to'],
 ['most'],
 ['animals'],
 ['animal'],
 ['for'],
 ['so'],
 ['fish'],
 ['was'],
 ['a'],
 ['natural'],
 ['choice'],
 ['it'],
 ['was'],
 ['becoming'],
 ['ill'],
 ['I'],
 ['mean'],
 ['so'],
 ['I'],
 ['for'],
 ['a'],
 ['mess'],
 ['and'],
 ['mild'],
 ['an'],
 ['interesting'],
 ['okay'],
 ['I'],
 ['still'],
 ['did'],
 ["n't"],
 ['interaction'],
 ['with'],
 ['superb'],
 ['sketch'],
 ['by'],
 ['the'],
 ['way'],
 ['yeah'],
 ['okay'],
 ['I'],
 ['was'],
 ['gon'],
 ['na'],
 ['choose'],
 ['a'],
 ['dog'],
 ['as'],
 ['well'],
 ['But'],
 ['I'],
 ['just'],
 ['a'],
 ['different'],
 ['kind'],
 ['of'],
 ['dogs'],
 ['are'],
 ['my'],
 ['favourite'],
 ['animal'],
 ['animal'],
 ['is'],
 ['my'],
 ['dog'],
 ['dog'],
 ['at'],
 ['home'],
 ['I'],
 ['that'],
 ['that'],
 ['does'],
 ["n't"],
 ['really'],
 ['look'],
 ['like'],
 ['actually'],
 ['looks'],
 ['more'],
 ['like'],
 ['a'],
 ['pig'],
 ['actually'],
 ['oh'],
 ['right'],
 ['see'],
 ['a'],
 ['dog'],
 ['in'],
 ['there'],
 ['yeah'],
 ['yeah'],
 ['yeah'],
 ['that'],
 ["'s"],
 ['a'],
 ['good'],
 ['idea'],
 ['no'],
 ['serious'],
 ['too'],
 ['I'],
 ['what'],
 ['kind'],
 ['of'],
 ["'em"],
 ['he'],
 ["'s"],
 ['a'],
 ['mixture'],
 ['of'],
 ['of'],
 ['various'],
 ['things'],
 ['Um'],
 ['and'],
 ['what'],
 ['I'],
 ['I'],
 ['like'],
 ['about'],
 ['it'],
 ['Um'],
 ['that'],
 ["'s"],
 ['just'],
 ['as'],
 ['the'],
 ['death'],
 ['that'],
 ['his'],
 ['tail'],
 ['why'],
 ['And'],
 ['very'],
 ['friendly'],
 ['and'],
 ['teary'],
 ['and'],
 ['always'],
 ['pleased'],
 ['to'],
 ['see'],
 ['you'],
 ['and'],
 ['of'],
 ['and'],
 ['and'],
 ['it'],
 ["'s"],
 ['quite'],
 ['quite'],
 ['we'],
 ['as'],
 ['well'],
 ['so'],
 ['you'],
 ['know'],
 ['you'],
 ['can'],
 ['does'],
 ["n't"],
 ['take'],
 ['too'],
 ['much'],
 ['space'],
 ['Um'],
 ['the'],
 ['thing'],
 ['does'],
 ['a'],
 ['funny'],
 ['thing'],
 ['reaches'],
 ['detail'],
 ['That'],
 ["'s"],
 ['quite'],
 ['amusing'],
 ['yeah'],
 ['where'],
 ['this'],
 ['his'],
 ['own'],
 ['genitalia'],
 ['thing'],
 ['I'],
 ['think'],
 ['anything'],
 ['and'],
 ['it'],
 ['has'],
 ['actually'],
 ['had'],
 ['is'],
 ['dinner'],
 ['I'],
 ['and'],
 ['it'],
 ['it'],
 ['just'],
 ['all'],
 ['all'],
 ['of'],
 ['a'],
 ['sudden'],
 ['is'],
 ['get'],
 ['and'],
 ['start'],
 ['start'],
 ['chasing'],
 ['his'],
 ['tail'],
 ['pipe'],
 ['it'],
 ['around'],
 ['the'],
 ['living'],
 ['room'],
 ['yeah'],
 ['only'],
 ['when'],
 ['use'],
 ['little'],
 ['he'],
 ['got'],
 ['lots'],
 ['of'],
 ['attention'],
 ['for'],
 ['doing'],
 ['it'],
 ['and'],
 ['I'],
 ['conditioned'],
 ['maybe'],
 ['yeah'],
 ['that'],
 ['where'],
 ['did'],
 ['you'],
 ['find'],
 ['this'],
 ['just'],
 ['down'],
 ['here'],
 ['okay'],
 ['Reading'],
 ['next'],
 ['Um'],
 ['okay'],
 ['mean'],
 ['I'],
 ['I'],
 ['need'],
 ['to'],
 ['discuss'],
 ['the'],
 ['project'],
 ['fine'],
 ['now'],
 ['so'],
 ['according'],
 ['to'],
 ['the'],
 ['we'],
 ['we'],
 ["'re"],
 ['gon'],
 ['na'],
 ['be'],
 ['selling'],
 ['this'],
 ['remote'],
 ['control'],
 ['for'],
 ['twenty'],
 ['five'],
 ['euro'],
 ['Um'],
 ['Um'],
 ['and'],
 ['we'],
 ['we'],
 ['we'],
 ["'re"],
 ['aiming'],
 ['to'],
 ['make'],
 ['fifty'],
 ['million'],
 ['euro'],
 ['Um'],
 ['so'],
 ['we'],
 ['we'],
 ["'re"],
 ['gon'],
 ['na'],
 ['be'],
 ['selling'],
 ['this'],
 ['on'],
 ['an'],
 ['scale'],
 ['And'],
 ['we'],
 ['do'],
 ['want'],
 ['to'],
 ['cost'],
 ['anymore'],
 ['than'],
 ['twelve'],
 ['fifty'],
 ['euros'],
 ['so'],
 ['fifty'],
 ['percent'],
 ['to'],
 ['the'],
 ['selling'],
 ['price'],
 ['and'],
 ['we'],
 ['just'],
 ['go'],
 ['that'],
 ['again'],
 ['sure'],
 ['so'],
 ['this'],
 ['alright'],
 ['okay'],
 ['okay'],
 ['so'],
 ['cost'],
 ['like'],
 ['production'],
 ['cost'],
 ['is'],
 ['altogether'],
 ['a'],
 ['fifty'],
 ['but'],
 ['selling'],
 ['selling'],
 ['price'],
 ['is'],
 ['is'],
 ['that'],
 ['wholesale'],
 ['or'],
 ['retail'],
 ['retail'],
 ['like'],
 ['on'],
 ['the'],
 ['shelf'],
 ['I'],
 ['dunno'],
 ['I'],
 ['imagine'],
 ['That'],
 ["'s"],
 ['gross'],
 ['two'],
 ['hours'],
 ['I'],
 ['marginal'],
 ['probably'],
 ['is'],
 ['are'],
 ['still'],
 ['actually'],
 ['because'],
 ['it'],
 ["'s"],
 ['probably'],
 ['up'],
 ['to'],
 ['the'],
 ['the'],
 ['retailer'],
 ['to'],
 ['myself'],
 ['whatever'],
 ['price'],
 ['they'],
 ['want'],
 ['but'],
 ['I'],
 ['I'],
 ['do'],
 ["n't"],
 ['know'],
 ['I'],
 ['mean'],
 ['do'],
 ['you'],
 ['think'],
 ['the'],
 ['fact'],
 ['that'],
 ['it'],
 ['it'],
 ["'s"],
 ['going'],
 ['to'],
 ['be'],
 ['sold'],
 ['will'],
 ['have'],
 ['a'],
 ['bearing'],
 ['on'],
 ['how'],
 ['we'],
 ['design'],
 ['it'],
 ['at'],
 ['all'],
 ['yeah'],
 ['I'],
 ['think'],
 ['it'],
 ['will'],
 ['all'],
 ['right'],
 ['away'],
 ['I'],
 ["'m"],
 ['wondering'],
 ['if'],
 ['there'],
 ['is'],
 ['like'],
 ['the'],
 ['DVD'],
 ['players'],
 ['if'],
 ['they'],
 ['are'],
 ['zones'],
 ['oh'],
 ['yeah'],
 ['regions'],
 ['stuff'],
 ['is'],
 ['limited'],
 ['or'],
 ['something'],
 ['something'],
 ['yeah'],
 ['okay'],
 ['as'],
 ['well'],
 ['as'],
 ['characters'],
 ['different'],
 ['keypad'],
 ['styles'],
 ['and'],
 ['some'],
 ['yeah'],
 ['yeah'],
 ['well'],
 ['for'],
 ['a'],
 ['remote'],
 ['control'],
 ['do'],
 ['you'],
 ['think'],
 ['that'],
 ['would'],
 ['be'],
 ['a'],
 ['specific'],
 ['depends'],
 ['on'],
 ['how'],
 ['complicated'],
 ['a'],
 ['remote'],
 ['control'],
 ['is'],
 ['except'],
 ...]

In [52]:
res = []
lemmatizer = WordNetLemmatizer()


for i in range(len(words)):
    for word, pos in pos_tag(words[i]):
        wordnet_pos = get_wordnet_pos(pos) or wordnet.NOUN
        res.append(lemmatizer.lemmatize(word, pos=wordnet_pos))

In [53]:
res


Out[53]:
['Uh_huh',
 'select',
 'a',
 'she',
 u'have',
 u'produce',
 'a',
 'powerpoint',
 'Uh',
 'I',
 'think',
 'it',
 "'s",
 'already',
 'on',
 'actually',
 'we',
 "'ll",
 'try',
 'the',
 'main',
 'thing',
 'work',
 'yeah',
 'applies',
 'in',
 'the',
 'back',
 'but',
 'okay',
 'right',
 'Now',
 'I',
 'yes',
 'okay',
 'right',
 'well',
 u'be',
 'the',
 'kickoff',
 'meeting',
 'for',
 'our',
 'our',
 'project',
 'and',
 'this',
 'this',
 u'be',
 'just',
 'what',
 'we',
 'we',
 "'re",
 'gon',
 'na',
 'be',
 u'do',
 'in',
 'the',
 'next',
 'twenty',
 'five',
 u'minute',
 'Um',
 'so',
 'personal',
 'just',
 'to',
 'kind',
 'of',
 'make',
 'sure',
 'that',
 'we',
 'all',
 'know',
 'each',
 'other',
 'I',
 "'m",
 'your',
 'and',
 'I',
 "'m",
 'the',
 'project',
 'manager',
 'manager',
 'do',
 "n't",
 'introduce',
 'yourself',
 'again',
 'Um',
 'data',
 'data',
 'and',
 'I',
 'I',
 'I',
 "'m",
 u'suppose',
 'to',
 'be',
 'industrial',
 'designer',
 'okay',
 'Andrew',
 'and',
 'I',
 'I',
 "'m",
 'the',
 'marketing',
 'an',
 'expert',
 'I',
 "'m",
 'pregnant',
 'agent',
 'great',
 'okay',
 'I',
 u'be',
 'we',
 "'re",
 u'design',
 'any',
 'remote',
 'control',
 'And',
 'oh',
 'I',
 'I',
 'have',
 'to',
 'record',
 'he',
 "'s",
 'here',
 'actually',
 'so',
 'this',
 'this',
 'do',
 'the',
 'Andrew',
 'and',
 u'create',
 u'create',
 'and',
 'you',
 "'ll",
 u'arrive',
 'on',
 'time',
 'Um',
 'yes',
 'it',
 u'be',
 'a',
 'design',
 'a',
 'new',
 'remote',
 'control',
 u'a',
 'you',
 'can',
 'see',
 u'be',
 'this',
 'this',
 'be',
 'original',
 'trendy',
 'and',
 'user',
 'friendly',
 'friendly',
 'Um',
 'so',
 'that',
 "'s",
 'kind',
 'of',
 'our',
 'our',
 'brief',
 'the',
 'wire',
 'and',
 'so',
 'there',
 u'be',
 u'be',
 'three',
 'different',
 u'stage',
 'to',
 'the',
 'design',
 'And',
 'I',
 "'m",
 'not',
 'sure',
 'what',
 'what',
 'you',
 u'guy',
 'have',
 'already',
 u'receive',
 'in',
 'your',
 u'email',
 u'email',
 'what',
 "'d",
 'you',
 'get',
 'I',
 'just',
 u'get',
 "'cause",
 'I',
 'know',
 'you',
 u'have',
 'to',
 u'call',
 'okay',
 'so',
 'we',
 'we',
 "'re",
 'gon',
 'na',
 'have',
 'like',
 'individual',
 'work',
 'and',
 'then',
 'a',
 'meeting',
 'meeting',
 'about',
 'it',
 'And',
 'repeat',
 'that',
 'process',
 'three',
 u'time',
 'Um',
 'and',
 'at',
 'this',
 'point',
 'we',
 'get',
 'try',
 'the',
 'whiteboard',
 'over',
 'there',
 'I',
 'I',
 'I',
 'so',
 'you',
 'you',
 'get',
 'to',
 'draw',
 'your',
 'favourite',
 'animal',
 'and',
 'sum',
 'sum',
 'of',
 'so',
 'you',
 'you',
 "'d",
 'like',
 'to',
 'get',
 'more',
 u'be',
 'very',
 u'kid',
 'I.',
 'alright',
 'So',
 'this',
 'one',
 'here',
 'right',
 'okay',
 'I',
 'do',
 "n't",
 'alright',
 'my',
 'favourite',
 'animal',
 'and',
 'like',
 'ah',
 'ah',
 'a',
 'L',
 'I',
 u'character',
 u'be',
 'about',
 'right',
 'yeah',
 'alright',
 'well',
 'basically',
 'high',
 'priority',
 'for',
 'any',
 'animal',
 'for',
 'me',
 u'be',
 'that',
 'they',
 'they',
 'be',
 'willing',
 'to',
 'take',
 'a',
 'lot',
 'of',
 'physical',
 'affection',
 'from',
 'the',
 'family',
 'And',
 'just',
 'yeah',
 'they',
 'have',
 u'lot',
 'of',
 'personality',
 'and',
 'this',
 'this',
 'and',
 'then',
 'robust',
 'good',
 'health',
 'health',
 'So',
 'this',
 u'be',
 'the',
 u'big',
 'I',
 u'family',
 'be',
 'right',
 'lovely',
 'yeah',
 'no',
 'matter',
 'of',
 'on',
 'would',
 'be',
 'a',
 'monkey',
 'I',
 'I',
 'the',
 'smoke',
 'even',
 'for',
 'a',
 'and',
 'then',
 'one',
 'for',
 'the',
 'gon',
 'na',
 'real',
 'no',
 'and',
 'when',
 'when',
 'the',
 'other',
 'with',
 'them',
 'right',
 'here',
 'you',
 'can',
 'take',
 u'a',
 'long',
 'over',
 'this',
 u'be',
 'a',
 'like',
 'because',
 'we',
 'have',
 "n't",
 u'get',
 'an',
 'awful',
 'lot',
 'there',
 "'s",
 'of',
 'day',
 'today',
 'do',
 "n't",
 'feel',
 'like',
 'your',
 'interaction',
 'anyway',
 'actually',
 'told',
 'me',
 'a',
 'lot',
 'more',
 'about',
 'the',
 u'eagle',
 'it',
 "'s",
 'so',
 'much',
 'or',
 'what',
 'what',
 'have',
 'have',
 'to',
 'get',
 'yeah',
 'because',
 'I',
 'do',
 "n't",
 'know',
 'mine',
 u'be',
 "n't",
 'gon',
 'na',
 'think',
 'on',
 'the',
 'spot',
 'oh',
 u'be',
 'that',
 'a',
 'whale',
 'yeah',
 'yeah',
 'I.',
 'well',
 'like',
 'I',
 'do',
 "n't",
 'know',
 'it',
 "'s",
 'just',
 'for',
 u'be',
 'I',
 'can',
 'think',
 'of',
 'the',
 'top',
 'of',
 'my',
 'head',
 'figure',
 u'be',
 'in',
 'this',
 "'cause",
 'I',
 "'m",
 'allergic',
 'to',
 'most',
 u'animal',
 'animal',
 'for',
 'so',
 'fish',
 u'be',
 'a',
 'natural',
 'choice',
 'it',
 u'be',
 u'become',
 'ill',
 'I',
 'mean',
 'so',
 'I',
 'for',
 'a',
 'mess',
 'and',
 'mild',
 'an',
 u'interest',
 'okay',
 'I',
 'still',
 u'do',
 "n't",
 'interaction',
 'with',
 'superb',
 'sketch',
 'by',
 'the',
 'way',
 'yeah',
 'okay',
 'I',
 u'be',
 'gon',
 'na',
 'choose',
 'a',
 'dog',
 u'a',
 'well',
 'But',
 'I',
 'just',
 'a',
 'different',
 'kind',
 'of',
 u'dog',
 u'be',
 'my',
 'favourite',
 'animal',
 'animal',
 u'be',
 'my',
 'dog',
 'dog',
 'at',
 'home',
 'I',
 'that',
 'that',
 u'do',
 "n't",
 'really',
 'look',
 'like',
 'actually',
 u'look',
 'more',
 'like',
 'a',
 'pig',
 'actually',
 'oh',
 'right',
 'see',
 'a',
 'dog',
 'in',
 'there',
 'yeah',
 'yeah',
 'yeah',
 'that',
 "'s",
 'a',
 'good',
 'idea',
 'no',
 'serious',
 'too',
 'I',
 'what',
 'kind',
 'of',
 "'em",
 'he',
 "'s",
 'a',
 'mixture',
 'of',
 'of',
 'various',
 u'thing',
 'Um',
 'and',
 'what',
 'I',
 'I',
 'like',
 'about',
 'it',
 'Um',
 'that',
 "'s",
 'just',
 u'a',
 'the',
 'death',
 'that',
 'his',
 'tail',
 'why',
 'And',
 'very',
 'friendly',
 'and',
 'teary',
 'and',
 'always',
 'pleased',
 'to',
 'see',
 'you',
 'and',
 'of',
 'and',
 'and',
 'it',
 "'s",
 'quite',
 'quite',
 'we',
 u'a',
 'well',
 'so',
 'you',
 'know',
 'you',
 'can',
 u'do',
 "n't",
 'take',
 'too',
 'much',
 'space',
 'Um',
 'the',
 'thing',
 u'do',
 'a',
 'funny',
 'thing',
 u'reach',
 'detail',
 'That',
 "'s",
 'quite',
 u'amuse',
 'yeah',
 'where',
 'this',
 'his',
 'own',
 'genitalia',
 'thing',
 'I',
 'think',
 'anything',
 'and',
 'it',
 u'have',
 'actually',
 u'have',
 u'be',
 'dinner',
 'I',
 'and',
 'it',
 'it',
 'just',
 'all',
 'all',
 'of',
 'a',
 'sudden',
 u'be',
 'get',
 'and',
 'start',
 'start',
 u'chase',
 'his',
 'tail',
 'pipe',
 'it',
 'around',
 'the',
 'living',
 'room',
 'yeah',
 'only',
 'when',
 'use',
 'little',
 'he',
 u'get',
 u'lot',
 'of',
 'attention',
 'for',
 u'do',
 'it',
 'and',
 'I',
 u'condition',
 'maybe',
 'yeah',
 'that',
 'where',
 u'do',
 'you',
 'find',
 'this',
 'just',
 'down',
 'here',
 'okay',
 'Reading',
 'next',
 'Um',
 'okay',
 'mean',
 'I',
 'I',
 'need',
 'to',
 u'discus',
 'the',
 'project',
 'fine',
 'now',
 'so',
 u'accord',
 'to',
 'the',
 'we',
 'we',
 "'re",
 'gon',
 'na',
 'be',
 u'sell',
 'this',
 'remote',
 'control',
 'for',
 'twenty',
 'five',
 'euro',
 'Um',
 'Um',
 'and',
 'we',
 'we',
 'we',
 "'re",
 u'aim',
 'to',
 'make',
 'fifty',
 'million',
 'euro',
 'Um',
 'so',
 'we',
 'we',
 "'re",
 'gon',
 'na',
 'be',
 u'sell',
 'this',
 'on',
 'an',
 'scale',
 'And',
 'we',
 'do',
 'want',
 'to',
 'cost',
 'anymore',
 'than',
 'twelve',
 'fifty',
 u'euro',
 'so',
 'fifty',
 'percent',
 'to',
 'the',
 u'sell',
 'price',
 'and',
 'we',
 'just',
 'go',
 'that',
 'again',
 'sure',
 'so',
 'this',
 'alright',
 'okay',
 'okay',
 'so',
 'cost',
 'like',
 'production',
 'cost',
 u'be',
 'altogether',
 'a',
 'fifty',
 'but',
 u'sell',
 u'sell',
 'price',
 u'be',
 u'be',
 'that',
 'wholesale',
 'or',
 'retail',
 'retail',
 'like',
 'on',
 'the',
 'shelf',
 'I',
 'dunno',
 'I',
 'imagine',
 'That',
 "'s",
 'gross',
 'two',
 u'hour',
 'I',
 'marginal',
 'probably',
 u'be',
 u'be',
 'still',
 'actually',
 'because',
 'it',
 "'s",
 'probably',
 'up',
 'to',
 'the',
 'the',
 'retailer',
 'to',
 'myself',
 'whatever',
 'price',
 'they',
 'want',
 'but',
 'I',
 'I',
 'do',
 "n't",
 'know',
 'I',
 'mean',
 'do',
 'you',
 'think',
 'the',
 'fact',
 'that',
 'it',
 'it',
 "'s",
 u'go',
 'to',
 'be',
 u'sell',
 'will',
 'have',
 'a',
 'bearing',
 'on',
 'how',
 'we',
 'design',
 'it',
 'at',
 'all',
 'yeah',
 'I',
 'think',
 'it',
 'will',
 'all',
 'right',
 'away',
 'I',
 "'m",
 u'wonder',
 'if',
 'there',
 u'be',
 'like',
 'the',
 'DVD',
 u'player',
 'if',
 'they',
 u'be',
 u'zone',
 'oh',
 'yeah',
 u'region',
 'stuff',
 u'be',
 'limited',
 'or',
 'something',
 'something',
 'yeah',
 'okay',
 u'a',
 'well',
 u'a',
 u'character',
 'different',
 'keypad',
 u'style',
 'and',
 'some',
 'yeah',
 'yeah',
 'well',
 'for',
 'a',
 'remote',
 'control',
 'do',
 'you',
 'think',
 'that',
 'would',
 'be',
 'a',
 'specific',
 'depends',
 'on',
 'how',
 u'complicate',
 'a',
 'remote',
 'control',
 u'be',
 'except',
 ...]

In [ ]: