當我運行(末尾整個代碼)下面的代碼,這一行:如何解決這個Python繼承AttributeError:X實例沒有屬性'con'?
res=self.con.execute(
從這個函數(其中getfeatures返回dictionary):
def fcount(self,f,cat):
res=self.con.execute(
'select count from fc where feature="%s" and category="%s"'
%(f,cat)).fetchone()
if res==None: return 0
else: return float(res[0])
可生產這樣的錯誤:
AttributeError: naivebayes instance has no attribute 'con'
首先,我以爲這是一個pysqlite2問題。但我已經安裝了pysqlite2,當我運行一個pysqlite2測試時,我確定了。我也嘗試使用內置的sqlite3的,而不是pysqlite2(做一個import sqlite3
聲明和self.con=sqlite3.connect(":memory:")
更換self.con=sqlite.connect(dbfile)
,但它也不能工作。
所以,前一個問題,我得到一個客戶留言說這是不是一個pysqlite2問題,buth繼承問題,但由於在naivebayes 初始化()被重新顯式調用超類(分類)來擴展它的行爲,這樣說:
class naivebayes(classifier):
def __init__(self,getfeatures):
classifier.__init__(self,getfeatures)
我不明白是什麼繼承問題,究竟如何解決?
PS - 代碼不是我的。它來自(優秀的)「編程集體智慧」一書。我只是從raw.github.com/cataska/programming-collective-intelligence-code/...複製它,並將代碼的一部分(fisherclassifier,因爲我只使用naivebayes分類器)。
感謝您的任何幫助。
這裏整個代碼:
from pysqlite2 import dbapi2 as sqlite
import re
import math
def getfeatures(doc):
splitter=re.compile('\\W*')
# Split the words by non-alpha characters
words=[s.lower() for s in splitter.split(doc)
if len(s)>2 and len(s)<20]
# Return the unique set of words only
# return dict([(w,1) for w in words]).iteritems()
return dict([(w,1) for w in words])
class classifier:
def __init__(self,getfeatures,filename=None):
# Counts of feature/category combinations
self.fc={}
# Counts of documents in each category
self.cc={}
self.getfeatures=getfeatures
def setdb(self,dbfile):
self.con=sqlite.connect(dbfile)
self.con.execute('create table if not exists fc(feature,category,count)')
self.con.execute('create table if not exists cc(category,count)')
def incf(self,f,cat):
count=self.fcount(f,cat)
if count==0:
self.con.execute("insert into fc values ('%s','%s',1)"
% (f,cat))
else:
self.con.execute(
"update fc set count=%d where feature='%s' and category='%s'"
% (count+1,f,cat))
def fcount(self,f,cat):
res=self.con.execute(
'select count from fc where feature="%s" and category="%s"'
%(f,cat)).fetchone()
if res==None: return 0
else: return float(res[0])
def incc(self,cat):
count=self.catcount(cat)
if count==0:
self.con.execute("insert into cc values ('%s',1)" % (cat))
else:
self.con.execute("update cc set count=%d where category='%s'"
% (count+1,cat))
def catcount(self,cat):
res=self.con.execute('select count from cc where category="%s"'
%(cat)).fetchone()
if res==None: return 0
else: return float(res[0])
def categories(self):
cur=self.con.execute('select category from cc');
return [d[0] for d in cur]
def totalcount(self):
res=self.con.execute('select sum(count) from cc').fetchone();
if res==None: return 0
return res[0]
def train(self,item,cat):
features=self.getfeatures(item)
# Increment the count for every feature with this category
for f in features.keys():
## for f in features:
self.incf(f,cat)
# Increment the count for this category
self.incc(cat)
self.con.commit()
def fprob(self,f,cat):
if self.catcount(cat)==0: return 0
# The total number of times this feature appeared in this
# category divided by the total number of items in this category
return self.fcount(f,cat)/self.catcount(cat)
def weightedprob(self,f,cat,prf,weight=1.0,ap=0.5):
# Calculate current probability
basicprob=prf(f,cat)
# Count the number of times this feature has appeared in
# all categories
totals=sum([self.fcount(f,c) for c in self.categories()])
# Calculate the weighted average
bp=((weight*ap)+(totals*basicprob))/(weight+totals)
return bp
class naivebayes(classifier):
def __init__(self,getfeatures):
classifier.__init__(self,getfeatures)
self.thresholds={}
def docprob(self,item,cat):
features=self.getfeatures(item)
# Multiply the probabilities of all the features together
p=1
for f in features: p*=self.weightedprob(f,cat,self.fprob)
return p
def prob(self,item,cat):
catprob=self.catcount(cat)/self.totalcount()
docprob=self.docprob(item,cat)
return docprob*catprob
def setthreshold(self,cat,t):
self.thresholds[cat]=t
def getthreshold(self,cat):
if cat not in self.thresholds: return 1.0
return self.thresholds[cat]
def classify(self,item,default=None):
probs={}
# Find the category with the highest probability
max=0.0
for cat in self.categories():
probs[cat]=self.prob(item,cat)
if probs[cat]>max:
max=probs[cat]
best=cat
# Make sure the probability exceeds threshold*next best
for cat in probs:
if cat==best: continue
if probs[cat]*self.getthreshold(best)>probs[best]: return default
return best
def sampletrain(cl):
cl.train('Nobody owns the water.','good')
cl.train('the quick rabbit jumps fences','good')
cl.train('buy pharmaceuticals now','bad')
cl.train('make quick money at the online casino','bad')
cl.train('the quick brown fox jumps','good')
nb = naivebayes(getfeatures)
sampletrain(nb)
#print ('\nbuy is classified as %s'%nb.classify('buy'))
#print ('\nquick is classified as %s'%nb.classify('quick'))
##print getfeatures('Nobody owns the water.')