#?-*-?coding:?utf-8?-*-

import?os
import?math
import?time
import?jieba
import?codecs
import?pickle
import?random
import?argparse

TIME_FORMAT?=?‘%Y-%m-%d?%H:%M:%S‘
base_FOLDER?=?os.path.abspath（os.path.dirname（__file__））.decode（‘gb2312‘）
DATA_FOLDER?=?os.path.join（base_FOLDER?‘data‘）
DEFAULT_FCOLLOCATIONS_V?=?os.path.join（DATA_FOLDER?‘collocations_v‘）
DEFAULT_FCOLLOCATIONS_H?=?os.path.join（DATA_FOLDER?‘collocations_h‘）
DEFAULT_FWORDS?=?os.path.join（DATA_FOLDER?‘words‘）
DEFAULT_FTOPIC_WORDS?=?os.path.join（DATA_FOLDER?‘topic_words‘）
DEFAULT_FSTART_WORDS?=?os.path.join（DATA_FOLDER?‘start_words.txt‘）
LOG_DELTA?=?20

def?read_dump（fin）:
????fd?=?codecs.open（fin?‘rb‘）
????data?=?pickle.load（fd）
????fd.close（）
????print（u‘Read?from?{}?done.‘.format（fin））
????return?data


def?read_txt（fin）:
????fd?=?codecs.open（fin?‘r‘?‘utf-8‘）
????data?=?[i.strip（）?for?i?in?fd]
????fd.close（）
????print（u‘Read?from?{}?done.‘.format（fin））
????return?data


def?generate_first_sentence_brute_force（start_word?sentence_len?topic_vector?words）:
????sentence?=?[start_word]
????l?=?len（start_word）
????avg?=?1e-7
????while?l?????????w2?=?random.choice（words）
????????if?len（w2）?>?2:
????????????continue
????????if?topic_vector[words.index（w2）]?????????????continue
????????sentence.append（w2）
????????l?+=?len（w2）
????return?sentence


#?topic_words?max:?3.1424917513724737
#?topic_words?min:?0.0
def?generate_first_sentence（start_word?sentence_len?topic_vector?words?collocations_h）:
????f?=?[dict（）?for?i?in?range（sentence_len?+?1）]
????p?=?[dict（）?for?i?in?range（sentence_len?+?1）]
????start_len?=?len（start_word）
????f[start_len][start_word]?=?topic_vector[words.index（start_word）]?if?start_word?in?words?else?0
????p[start_len][start_word]?=?‘‘
????for?i?in?range（start_len?sentence_len）:
????????for?j?in?f[i]:
????????????if?j?not?in?collocations_h:
????????????????continue
????????????topic_score?=?topic_vector[words.index（j）]?if?j?in?words?else?0
????????????for?k?in?collocations_h[j]:
????????????????if?i?+?k?<=?sentence_len:
????????????????????for?test_count?in?range（2）:
????????????????????????（score?w2）?=?random.choice（collocations_h[j][k]）
????????????????????????temp?=?f[i][j]?+?math.log（score）?+?LOG_DELTA?+?topic_score
????????????????????????if?w2?not?in?f[i?+?k]?or?temp?>?f[i?+?k][w2]:
????????????????????????????f[i?+?k][w2]?=?temp
????????????????????????????p[i?+?k][w2]?=?j
????ans?=?0
????last_word?=?‘‘
????if?not?f[sentence_len]:
????????return?generate_first_sentence_brute_force（start_word?sentence_len?topic_vector?words）
????for?j?in?f[sentence_len]:
????????if?f[sentence_len][j]?>?ans:
????????????ans?=?f[sentence_len][j]
????????????last_word?=?j
????if?ans?==?0:
????????return?generate_first_sentence_brute_force（start_word?sentence_len?topic_vector?words）
????sentence?=?[]
????i?=?sentence_len
????while?i?>?0:
????????sentence.append（last_word）
????????last_word?i?=?p[i][last_word]?i?-?len（last_word）
????return?se

?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2015-12-20?08:24??poem_generator\
?????文件????????2057??2015-12-20?08:24??poem_generator\preprocess.py
?????文件????????4130??2015-12-20?08:24??poem_generator\index.py
?????文件????????3576??2015-12-20?08:24??poem_generator\get_topic.py
?????文件????????2491??2015-12-20?08:24??poem_generator\get_start_words.py
?????文件????????4879??2015-12-20?08:24??poem_generator\get_collocations.py
?????文件???????10261??2015-12-20?08:24??poem_generator\generate_poem.py
?????文件?????????465??2017-05-12?08:35??poem_generator\README.md
?????文件???????11358??2015-12-20?08:24??poem_generator\LICENSE
?????文件?????????702??2015-12-20?08:24??poem_generator\.gitignore
?????目錄???????????0??2015-12-20?08:24??poem_generator\templates\
?????文件????????2285??2015-12-20?08:24??poem_generator\templates\index.htm
?????目錄???????????0??2015-12-20?08:24??poem_generator\data\
?????文件????15597926??2015-12-20?08:24??poem_generator\data\唐詩(shī)語(yǔ)料庫(kù).txt