def query_by_body(body, top_k=5):
''' query top_k most probable replies based on raw email body '''
doc = body2doc(body)
print '[doc]', doc
vec = avg_word_vec(doc)
# retrieve top-k past inquery emails.
candidates = query_by_vec_online('inbox', vec, top_k)
# get past replies.
db = EmailDB('outbox')
replies = []
for (email, score) in candidates:
reply = db.select(
where='message_id=:message_id',
data=dict(message_id=email.message_id)
)
reply = list(reply)[0].body
replies.append((reply, score))
return replies
def query_by_vec_online(table, vec, top_k=5):
init_word2vec()
db = EmailDB(table)
scores = []
for email in db.select():
if email.message_id in CACHE:
candidate_vec = CACHE[email.message_id]
else:
doc = body2doc(email.body)
print "[cache doc]", doc
candidate_vec = avg_word_vec(doc)
CACHE[email.message_id] = candidate_vec
score = np.dot(vec, candidate_vec) / npla.norm(vec) / npla.norm(candidate_vec) # cosine similarity.
score = float(score)
scores.append((email, score))
scores = [pair for pair in scores if pair[1] == pair[1]]
scores = sorted(scores, key=lambda pair: pair[1], reverse=True)
print "[matched]", scores[:top_k]
return scores[:top_k]
def sync(csv_path):
inbox_db = EmailDB("inbox")
outbox_db = EmailDB("outbox")
in_mails = []
out_mails = []
for (in_mail, out_mail) in extract(csv_path):
in_mails.append(in_mail)
out_mails.append(out_mail)
def get_in_mail():
for (mi, in_mail) in enumerate(in_mails):
print "[inbox][%d/%d]" % (mi, len(in_mails))
yield in_mail
def get_out_mail():
for (mi, out_mail) in enumerate(out_mails):
print "[outbox][%d/%d]" % (mi, len(out_mails))
yield out_mail
inbox_db.update_all("*****@*****.**", get_in_mail())
outbox_db.update_all("*****@*****.**", get_out_mail())