def documents2feature_vectors(documents):
vectorizer = PolitenessFeatureVectorizer()
fks = False
X, y = [], []
for d in documents:
fs = vectorizer.features(d)
if not fks:
fks = sorted(fs.keys())
fv = [fs[f] for f in fks]
# If politeness score > 0.0,
# the doc is polite, class=1
l = 1 if d['score'] > 0.0 else 0
X.append(fv)
y.append(l)
X = csr_matrix(np.asarray(X))
y = np.asarray(y)
return X, y
% (name, expected_v, package.__version__))
####
from features.vectorizer import PolitenessFeatureVectorizer
####
# Serialized model filename
MODEL_FILENAME = os.path.join(os.path.split(__file__)[0], 'politeness-svm.p')
####
# Load model, initialize vectorizer
clf = cPickle.load(open(MODEL_FILENAME))
vectorizer = PolitenessFeatureVectorizer()
def score(request):
"""
:param request - The request document to score
:type request - dict with 'sentences' and 'parses' field
sample (taken from test2.py)--
{
'sentences': [
"Have you found the answer for your question?",
"If yes would you please share it?"
],
'parses': [
["csubj(found-3, Have-1)", "dobj(Have-1, you-2)", "root(ROOT-0, found-3)", "det(answer-5, the-4)", "dobj(found-3, answer-5)", "poss(question-8, your-7)", "prep_for(found-3, question-8)"],
["prep_if(would-3, yes-2)", "root(ROOT-0, would-3)", "nsubj(would-3, you-4)", "ccomp(would-3, please-5)", "nsubj(it-7, share-6)", "xcomp(please-5, it-7)"]
