Dear Group,
I am trying to write a code for pulling data from MySQL at the backend and
annotating words and trying to put the results as separated sentences with each
line. The code is generally running fine but I am feeling it may be better in
the end of giving out sentences, and for small data sets it is okay but with
50,000 news articles it is performing dead slow. I am using Python2.7.11 on
Windows 7 with 8GB RAM.
I am trying to copy the code here, for your kind review.
import MySQLdb
import nltk
def sql_connect_NewTest1():
db = MySQLdb.connect(host="localhost",
user="*****",
passwd="*****",
db="abcd_efgh")
cur = db.cursor()
#cur.execute("SELECT * FROM newsinput limit 0,50000;") #REPORTING RUNTIME
ERROR
cur.execute("SELECT * FROM newsinput limit 0,50;")
dict_open=open("/python27/NewTotalTag.txt","r") #OPENING THE DICTIONARY
FILE
dict_read=dict_open.read()
dict_word=dict_read.split()
a4=dict_word #Assignment for code.
list1=[]
flist1=[]
nlist=[]
for row in cur.fetchall():
#print row[2]
var1=row[3]
#print var1 #Printing lines
#var2=len(var1) # Length of file
var3=var1.split(".") #SPLITTING INTO LINES
#print var3 #Printing The Lines
#list1.append(var1)
var4=len(var3) #Number of all lines
#print "No",var4
for line in var3:
#print line
#flist1.append(line)
linew=line.split()
for word in linew:
if word in a4:
windex=a4.index(word)
windex1=windex+1
word1=a4[windex1]
word2=word+"/"+word1
nlist.append(word2)
#print list1
#print nlist
elif word not in a4:
word3=word+"/"+"NA"
nlist.append(word3)
#print list1
#print nlist
else:
print "None"
#print "###",flist1
#print len(flist1)
#db.close()
#print nlist
lol = lambda lst, sz: [lst[i:i+sz] for i in range(0, len(lst), sz)] #TRYING
TO SPLIT THE RESULTS AS SENTENCES
nlist1=lol(nlist,7)
#print nlist1
for i in nlist1:
string1=" ".join(i)
print i
#print string1
Thanks in Advance.
--
https://mail.python.org/mailman/listinfo/python-list
