我正在尝试修改优秀书籍 Programming Collective Intelligence 提供的朴素贝叶斯分类器的代码，使其适应 GAE 数据存储（提供的代码使用 pysqlite2）。但试图做到这一点，我在这一行遇到：
update.put()
从这个块：
def incf(self,f,cat):
count=self.fcount(f,cat)
if count==0:
fc_value = fc(feature = f, category = cat, count = 1)
fc_value.put()
else:
update = db.GqlQuery("SELECT count FROM fc where feature =:feature AND category =:category", feature = f, category = cat).get()
# if update:
update.count = count + 1
update.put()
# else:
# self.con.execute(
# "update fc set count=%d where feature='%s' and category='%s'"
# % (count+1,f,cat))
这个错误：
File "C:\Users\CG\Desktop\Google Drive\Sci&Tech\projects\naivebayes\main.py", line 151, in train
self.incf(f,cat)
File "C:\Users\CG\Desktop\Google Drive\Sci&Tech\projects\naivebayes\main.py", line 88, in incf
update.put()
File "C:\Program Files (x86)\Google\google_appengine\google\appengine\ext\db\__init__.py", line 1074, in put
return datastore.Put(self._entity, **kwargs)
File "C:\Program Files (x86)\Google\google_appengine\google\appengine\api\datastore.py", line 579, in Put
return PutAsync(entities, **kwargs).get_result()
File "C:\Program Files (x86)\Google\google_appengine\google\appengine\api\datastore.py", line 529, in PutAsync
'Cannot put a partial entity: %s' % entity)
BadRequestError: Cannot put a partial entity: {u'count': 2L, 'category': None, 'feature': None}
我正在尝试做的是相当于这个 SQL：
self.con.execute(
"update fc set count=%d where feature='%s' and category='%s'"
% (count+1,f,cat))
我怎样才能做到这一点？
这里是整个代码：
import os
import random
import re
import math
from google.appengine.ext import db
import webapp2
import jinja2
from jinja2 import Environment, FileSystemLoader
jinja_environment = jinja2.Environment(autoescape=True,
loader=jinja2.FileSystemLoader(os.path.join(os.path.dirname(__file__), 'templates')))
class fc(db.Model):
feature = db.StringProperty()
category = db.StringProperty()
count = db.IntegerProperty()
fc_class = fc()
class cc(db.Model):
category = db.StringProperty()
count = db.IntegerProperty()
cc_class = cc()
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 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('db_file')
# self.con=sqlite3.connect(":memory:")
# 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:
fc_value = fc(feature = f, category = cat, count = 1)
fc_value.put()
else:
update = db.GqlQuery("SELECT count FROM fc where feature =:feature AND category =:category", feature = f, category = cat).get()
# if update:
update.count = count + 1
update.put()
# 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 = db.GqlQuery("SELECT * FROM fc WHERE feature =:feature AND category =:category", feature = f, category = cat).get()
# res=self.con.execute(
# 'select count from fc where feature="%s" and category="%s"'
# %(f,cat)).fetchone()
if res is None:
return 0
else:
return res.count
# 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))
cc_value = cc(category = cat, count = 1)
cc_value.put()
else:
update = db.GqlQuery("SELECT count FROM cc where category =:category", category = cat).get()
update.count = count + 1
update.put()
# 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()
res = db.GqlQuery("SELECT count FROM cc WHERE category =:category", category = cat).get()
if res is None: return 0
# else: return float(res[0])
else: return float(res)
def categories(self):
# cur = self.con.execute('select category from cc');
cur = db.GqlQuery("SELECT category FROM cc").fetch(999)
return [d[0] for d in cur]
def totalcount(self):
# res=self.con.execute('select sum(count) from cc').fetchone();
all_cc = db.GqlQuery("SELECT * FROM cc").fetch(999)
res = 0
for cc in all_cc:
count = cc.count
res+=count
# res = db.GqlQuery("SELECT sum(count) FROM cc").get()
# if res==None: return 0
if res == 0: return 0
# return res[0]
return res
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')
class MainHandler(webapp2.RequestHandler):
def get(self):
template_values = {"given_sentence":'put a name here'}
template = jinja_environment.get_template('index.html')
self.response.out.write(template.render(template_values))
def post(self):
nb = naivebayes(getfeatures)
sampletrain(nb)
given_sentence = self.request.get("given_sentence")
spam_result = nb.classify(given_sentence)
submit_button = self.request.get("submit_button")
if submit_button:
self.redirect('/test_result?spam_result=%s&given_sentence=%s' % (spam_result, given_sentence))
class test_resultHandler(webapp2.RequestHandler):
def get(self):
spam_result = self.request.get("spam_result")
given_sentence = self.request.get("given_sentence")
test_result_values = {"spam_result": spam_result,
"given_sentence": given_sentence}
template = jinja_environment.get_template('test_result.html')
self.response.out.write(template.render(test_result_values))
app = webapp2.WSGIApplication([('/', MainHandler), ('/test_result', test_resultHandler)],
debug=True)