def save_to_db(vo): ''' +------------------+-------------+------+-----+---------+-------+ | Field | Type | Null | Key | Default | Extra | +------------------+-------------+------+-----+---------+-------+ | pmid | varchar(16) | YES | | NULL | | | pubdate | datetime | YES | | NULL | | | iso_abbreviation | text | YES | | NULL | | | medline_pgn | text | YES | | NULL | | | article_title | text | YES | | NULL | | | authors | text | YES | | NULL | | | abstracts | text | YES | | NULL | | | pub_types | text | YES | | NULL | | | mesh_items | text | YES | | NULL | | | substances | text | YES | | NULL | | | link_out | text | YES | | NULL | | +------------------+-------------+------+-----+---------+-------+ ''' sql = 'insert into biss_pubmed values (\'' + vo.getId() + '\', \'' + vo.getPd() + '\', \'' + vo.getIa() + '\', \'' + vo.getMp() + '\', \'' + vo.getAt() + '\', \'' + vo.getAth() + '\', \'' + vo.getAbs() + '\', \'' + vo.getPt() + '\', \'' + vo.getMi() + '\', \'' + vo.getSb() + '\', \'' + vo.getLo() + '\');' f_open = open( './logs/pubmed_sql.sql', 'a') f_open.write(sql + '\n') print 'Now inserting data into database...' print 'SQL:\n', sql try: res = MySqlConn.insert_one_by_sql(sql) print '\tData inserted into database...' except MySQLdb.DataError: print '\tData error, cannot save data...' return
def save_to_db(vo): ''' +------------+---------------+------+-----+---------+-------+ | Field | Type | Null | Key | Default | Extra | +------------+---------------+------+-----+---------+-------+ | nrsid | varchar(32) | YES | | NULL | | | locus | varchar(256) | YES | | NULL | | | definition | varchar(256) | YES | | NULL | | | accession | varchar(128) | YES | | NULL | | | version | varchar(128) | YES | | NULL | | | dblink | varchar(128) | YES | | NULL | | | keyword | varchar(32) | YES | | NULL | | | source | varchar(32) | YES | | NULL | | | organism | varchar(512) | YES | | NULL | | | comments | varchar(1024) | YES | | NULL | | | contig | varchar(128) | YES | | NULL | | +------------+---------------+------+-----+---------+-------+ ''' sql = 'insert into biss_nuccore values (\'' + vo.getId() + '\', \'' + vo.getLocus() + '\', \'' + vo.getDef() + '\', \'' + vo.getAcc() + '\', \'' + vo.getVer() + '\', \'' + vo.getDbl() + '\', \'' + vo.getKw() + '\', \'' + vo.getSrc() + '\', \'' + vo.getOrg() + '\', \'' + vo.getCmt() + '\', \'' + vo.getCtg() + '\');' f_open = open( './logs/nuccore_sql.sql', 'a') f_open.write(sql) print 'Now inserting data into database...' try: res = MySqlConn.insert_one_by_sql(sql) print '\tData inserted into database...' except MySQLdb.DataError: print '\tData error, cannot save data...' return
def save_to_db(vo): ''' +--------------+---------------+------+-----+---------+-------+ | Field | Type | Null | Key | Default | Extra | +--------------+---------------+------+-----+---------+-------+ | cid | varchar(16) | YES | | NULL | | | lib_name | varchar(128) | YES | | NULL | | | lib_abbr | varchar(16) | YES | | NULL | | | organism | varchar(32) | YES | | NULL | | | destributors | varchar(1024) | YES | | NULL | | | vetor_type | varchar(16) | YES | | NULL | | | clones_db | varchar(64) | YES | | NULL | | | end_seq_cdb | int(11) | YES | | NULL | | | isrt_seq_cdb | int(11) | YES | | NULL | | | c_end_seq | int(11) | YES | | NULL | | +--------------+---------------+------+-----+---------+-------+ ''' sql = 'insert into biss_clone values (\'' + vo.getId() + '\', \'' + vo.getLn() + '\', \'' + vo.getLa() + '\', \'' + vo.getOrg() + '\', \'' + vo.getDstr() + '\', \'' + vo.getVt() + '\', \'' + vo.getCdb() + '\', \'' + vo.getEsc() + '\', \'' + vo.getIsc() + '\', \'' + vo.getCes() + '\');' f_open = open( './logs/clone_sql.sql', 'a') f_open.write(sql + '\n') print 'Now inserting data into database...' print 'SQL:\n', sql try: res = MySqlConn.insert_one_by_sql(sql) print '\tData inserted into database...' except MySQLdb.DataError: print '\tData error, cannot save data...' return
def query_from_db( pmid): print 'Query from database, item id: ' + pmid sql = 'select pmid from biss_pubmed where pmid = ( \'' + pmid + '\');'; cds = MySqlConn.query_by_sql(sql) if len(cds) == 0: print '\tQuery result is None' # print cds return cds
def query_from_db( pid): print 'Query from database, item id: ' + pid sql = '\tCall query_protein_by_id_proc ( \'' + pid + '\');'; proc_name = 'query_protein_by_id_proc' cds = MySqlConn.query_by_sql(sql) if len(cds) == 0: print '\tQuery result is None' # print cds return cds
def query_from_db( nid): print 'Query from database, item id: ' + nid proc_name = 'query_nuc_by_id_proc' sql = 'call ' + proc_name + ' ( \'' + nid + '\');'; cds = MySqlConn.query_by_sql(sql) if len(cds) == 0: print '\tQuery result is None' # print cds return cds
def clean_table_info():
"""
清空其中的信息
:return:
"""
mysql = MySqlConn.Mysql()
try:
mysql.update(sql_template.USE_DATABASE_WORDS, ())
mysql.delete(sql_template.CLEAN_TABLE_CET6, ())
mysql.delete(sql_template.CLEAN_TABLE_CET4, ())
mysql.delete(sql_template.CLEAN_TABLE_WORDS, ())
mysql.commit()
except BaseException, arguement:
print '清空表失败,信息: ', arguement
def save_ref_to_db(vo): ''' +-------------+--------------+------+-----+---------+-------+ | Field | Type | Null | Key | Default | Extra | +-------------+--------------+------+-----+---------+-------+ | protein_id | varchar(16) | YES | | NULL | | | residues_no | int(11) | YES | | NULL | | | authors | varchar(128) | YES | | NULL | | | title | varchar(256) | YES | | NULL | | | journal | varchar(256) | YES | | NULL | | +-------------+--------------+------+-----+---------+-------+ ''' sql = 'insert into biss_protein_reference values (\'' + vo.getPid() + '\', \'' + vo.getRno() + '\', \'' + vo.getAth() + '\', \'' + vo.getTtl() + '\', \'' + vo.getJur() + '\');' f_open = open( './logs/protein_sql.sql', 'a') f_open.write(sql) print 'Now inserting data into database...\n\t\SQL:\n', sql res = MySqlConn.insert_one_by_sql(sql) print '\tData inserted into database...' return
def save_to_db(vo):
'''
|item_id | varchar(16) | NO | PRI | | |
| locus | text | YES | | NULL | |
| definition | text | YES | | NULL | |
| accession | varchar(16) | YES | | NULL | |
| keywords | varchar(16) | YES | | NULL | |
| version | varchar(32) | YES | | NULL | |
| dbsource | varchar(32) | YES | | NULL | |
| source | varchar(256) | YES | | NULL | |
| organism | text | YES | | NULL | |
| comment | text | YES | | NULL | |
| features | varchar(32) | YES | | NULL | |
| features_source | text | YES | | NULL | |
| features_protein | text | YES | | NULL | |
| features_cds | text | YES | | NULL | |
| origin
'''
'''
sql = 'insert into biss_protein values (' + vo.getId() + '\', \''
+ vo.getLocus() + '\', \''
+ vo.getDef() + '\', \''
+ vo.getAcc() + '\', \''
+ vo.getKw() + '\', \''
+ vo.getVer() + '\', \''
+ vo.getDbs() + '\', \''
+ '' + '\', \''
+ vo.getOrg() + '\', \''
+ vo.getCmt() + '\', \''
+ '' + '\', \''
+ '' + '\', \''
+ '' + '\', \''
+ '' + '\', \''
+ vo.getOri() + '\');'
'''
sql = 'insert into biss_protein values (\'' + vo.getId() + '\', \'' + vo.getLocus() + '\', \'' + vo.getDef() + '\', \'' + vo.getAcc() + '\', \'' + vo.getKw() + '\', \'' + vo.getVer() + '\', \'' + vo.getDbs() + '\', \'' + '' + '\', \'' + vo.getOrg() + '\', \'' + vo.getCmt() + '\', \'' + vo.getFtr() + '\', \'' + vo.getFtrs() + '\', \'' + vo.getFtrp() + '\', \'' + vo.getFtrc() + '\', \'' + vo.getOri() + '\');'
f_open = open( './logs/protein_sql.sql', 'a')
f_open.write(sql)
print 'Now inserting data into database...'
res = MySqlConn.insert_one_by_sql(sql)
print '\tData inserted into database...'
return
def save_word_words(json_info):
"""
保存单词数据到 mysql 中
:param json_info: json格式的单词数据
:return:
"""
mysql = MySqlConn.Mysql()
try:
json_info.pop('_id')
mysql.insert_one(
sql_template.INSERT_INTO_WORDS,
(json_info['data']['id'], json_info['data']['content'],
json_info['data']['pronunciations']['us'],
json_info['data']['pronunciations']['uk'],
json_info['data']['definition'],
json.dumps(json_info,
ensure_ascii=False), json_info['data']['audio']))
mysql.commit()
except BaseException, arguement:
print '插入信息失败,原因: ', arguement
def save_ref_to_db(vo): ''' +-------------+--------------+------+-----+---------+-------+ | Field | Type | Null | Key | Default | Extra | +-------------+--------------+------+-----+---------+-------+ | protein_id | varchar(16) | YES | | NULL | | | residues_no | int(11) | YES | | NULL | | | authors | varchar(128) | YES | | NULL | | | title | varchar(256) | YES | | NULL | | | journal | varchar(256) | YES | | NULL | | +-------------+--------------+------+-----+---------+-------+ ''' sql = 'insert into biss_nuc_ref values (\'' + vo.getNid() + '\', \'' + vo.getRno() + '\', \'' + vo.getAth() + '\', \'' + vo.getTtl() + '\', \'' + vo.getJur() + '\');' f_open = open( './logs/clo_ref.sql', 'w') f_open.write(sql) print 'Now inserting data into database...' try: print 'SQL:\n',sql res = MySqlConn.insert_one_by_sql(sql) print '\tData inserted into database...' except MySQLdb.DataError: print '\tData error, cannot save data...' return
def MainProcedure(sentence):
tokens = token_String.tokenizer(sentence)
count = 0
finalMovieList = {}
for token in tokens:
count = count + 1
if token[1] == "n":
initialVec = MySqlConn.returnMovieIdFromTag(token[0])
# print(initialVec)
else:
tagsMovieIds = MySqlConn.returnMovieIdFromTag(token[0])
#print(tagsMovieIds)
genresMovieIds = MySqlConn.returnMovieIdFromGenre(token[0])
#print(genresMovieIds)
MovieIdsTagsAndGenres = mergeArrays(tagsMovieIds, genresMovieIds)
#print(MovieIdsTagsAndGenres)
word2vecSynonims = Word2Vec.give_Word2VecSinonims(token[0])
wordNetSynonims = wordnet.wordNet(token[0])
synonims = mergeArrays(word2vecSynonims, wordNetSynonims)
movieIdList = []
for synonim in synonims:
movieIdList.extend(MySqlConn.returnMovieIdFromTag(synonim))
movieIdList = numpy.unique(movieIdList)
movieIds = mergeArrays(list(movieIdList),
list(MovieIdsTagsAndGenres))
#print(tagsMovieIds)
if count == 1:
for movie in movieIds:
finalMovieList[movie] = 1
# print(len(finalMovieList))
else:
for movie in movieIds:
if movie in finalMovieList:
finalMovieList[movie] = finalMovieList[movie] + 1
else:
finalMovieList[movie] = 1
dicDeFrec = defaultdict(list)
for movie in finalMovieList:
rating = MySqlConn.returnRatingForMovieId(movie)
dicDeFrec[finalMovieList[movie]].append({movie: rating})
max_films = 1
movielist = []
frec = len(tokens)
for i in range(len(tokens), 0, -1):
if dicDeFrec[i] != []:
for j in dicDeFrec[i]:
if max_films != 0:
movielist.append(j)
max_films = max_films - 1
else:
break
# frec = len(tokens)
# max_films = 5
# for movie in finalMovieList:
# if max_films != 0:
# if finalMovieList[movie] == frec:
# rating = MySqlConn.returnRatingForMovieId(movie)
# dicDeFrec[finalMovieList[movie]].append({movie: rating})
# max_films = max_films - 1
# else:
# pass
# print(movielist)
return movielist
