def is_sanshoku_doujun(groups):
sequences = get_sequences(groups)
if len(sequences) < 3:
return False
suit_counts = get_suit_counts_groups(sequences)
if 3 in suit_counts or 4 in suit_counts:
return False
heads = [sequence.tiles[0] for sequence in sequences]
return # TODO
def is_ryanpeikou(groups):
"""
Note: Chitoitsu is implicitly excluded since it is checked as individual
tiles instead of groups; see is_chitoi().
"""
sequences = get_sequences(groups)
if len(sequences) < 4:
return False
return sum([sequences.count(sequence) == 2
for sequence in set(sequences)]) == 2
def is_ittsu(groups):
sequences = get_sequences(groups)
if len(sequences) < 3:
return False
suit_counts = get_suit_counts_groups(sequences)
if not (3 in suit_counts.values() or 4 in suit_counts.values()):
return False
suit = [suit for suit, count in suit_counts.iteritems() if count >= 3][0]
return (Sequence(suit(1)) in groups and Sequence(suit(4)) in groups
and Sequence(suit(7)) in groups)
# -*- coding: UTF-8 -*-
#Author zhang
import utils
from tensorflow.keras.preprocessing.sequence import pad_sequences
from sklearn.model_selection import train_test_split
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Embedding, Flatten, Dense, GlobalAveragePooling1D
sequences, data = utils.read_corpus("data\data.tsv")
w2v_model = utils.load_w2v("data\word2vec.model")
word2id = utils.word2id(w2v_model)
X_data = utils.get_sequences(word2id, sequences)
# 截长补短
maxlen = 20
X_pad = pad_sequences(X_data, maxlen=maxlen)
# 取得标签
Y = data.sentiment.values
# 划分数据集
X_train, X_test, Y_train, Y_test = train_test_split(
X_pad,
Y,
test_size=0.2,
random_state=42)
"""
构建分类模型
def is_iipeikou(groups):
sequences = get_sequences(groups)
return (not is_ryanpeikou(groups) and
any([sequences.count(sequence) == 2 for sequence in sequences]))