def instance(review): # "Great book!"
# [("Great", "JJ"), ("book", "NN"), ("!", "!")]
v = tag(review)
v = [word for (word, pos) in v if pos in ("JJ", "RB") or word in ("!")]
v = [predicative(word) for word in v] # ["great", "!", "!"]
v = count(v) # {"great": 1, "!": 1}
return v
def wordvarieties(word):
lem = lemma(word)
pre = predicative(word)
att = attributive(word)
sin = singularize(word)
con = conjugate(word, PRESENT, 1, SG)
return [lem, pre, att, sin, con]
def instance(review): # "Great book!"
# [("Great", "JJ"), ("book", "NN"), ("!", "!")]
v = tag(review)
v = [word for (word, pos) in v if pos in ("JJ", "RB") or word in ("!")]
v = [predicative(word) for word in v] # ["great", "!", "!"]
v = count(v) # {"great": 1, "!": 1}
return v
def test_predicative(self):
# Assert the accuracy of the predicative algorithm ("felle" => "fel").
from pattern.db import Datasheet
i, n = 0, 0
for pred, attr, sg, pl in Datasheet.load(os.path.join(PATH, "corpora", "wordforms-nl-celex.csv")):
if nl.predicative(attr) == pred:
i += 1
n += 1
self.assertTrue(float(i) / n > 0.96)
print("pattern.nl.predicative()")
def test_predicative(self):
# Assert the accuracy of the predicative algorithm ("felle" => "fel").
from pattern.db import Datasheet
i, n = 0, 0
for pred, attr, sg, pl in Datasheet.load(os.path.join(PATH, "corpora", "wordforms-nl-celex.csv")):
if nl.predicative(attr) == pred:
i +=1
n += 1
self.assertTrue(float(i) / n > 0.96)
print "pattern.nl.predicative()"
def prepare_text_nl(row):
""" Prepares dutch text by doing the following:
* Lemmatize a word
* Singularize a word
* Predicative a word
Parameters:
-----------
row : pandas dataframe
A row of a pandas dataframe
Returns:
--------
new_message : pandas dataframe
A row of a pandas dataframe
"""
try:
message = split(parse(row.Message_Only_Text))
except:
print(row.Message_Only_Text)
new_message = ''
for sentence in message:
for word, tag in sentence.tagged:
if (tag == 'MD') | ('VB' in tag):
new_message += lemma(word) + ' '
elif tag == 'NNS':
new_message += singularize(word) + ' '
elif 'JJ' in tag:
new_message += predicative(word) + ' '
else:
new_message += word + ' '
return new_message
