def build(*clauses,**kwargs):
priorLea = kwargs.get('priorLea',None)
# TODO: check no other args !!
# PY3: def build(*clauses,priorLea=None):
elseClauseResults = tuple(result for (cond,result) in clauses if cond is None)
if len(elseClauseResults) > 1:
raise Lea.Error("impossible to define more than one 'other' clause")
if len(elseClauseResults) == 1:
if priorLea is not None:
raise Lea.Error("impossible to define together prior probabilities and 'other' clause")
elseClauseResult = elseClauseResults[0]
else:
elseClauseResult = None
normClauseLeas = tuple((Lea.coerce(cond),Lea.coerce(result)) for (cond,result) in clauses if cond is not None)
condLeas = tuple(condLea for (condLea,resultLea) in normClauseLeas)
# check that conditions are disjoint
for (condLea1,condLea2) in genPairs(condLeas):
if (condLea1&condLea2).isFeasible():
raise Lea.Error("clause conditions are not disjoint")
# build the OR of all given conditions
orCondsLea = Lea.reduce(or_,condLeas)
isClauseSetComplete = orCondsLea.isTrue()
if priorLea is not None:
# prior distribution: determine elseClauseResult
if isClauseSetComplete:
# TODO check priorLea equivalent to self
raise Lea.Error("forbidden to define prior probabilities for complete clause set")
(pTrue,count) = orCondsLea._p(True)
pFalse = count - pTrue
priorAleaDict = dict(priorLea.getAlea().genVPs())
priorAleaCount = sum(priorAleaDict.values())
normAleaDict = dict(Mlea(*(resultLea for (condLea,resultLea) in normClauseLeas)).getAlea().genVPs())
normAleaCount = sum(normAleaDict.values())
valuesSet = frozenset(chain(priorAleaDict.keys(),normAleaDict.keys()))
vps = []
for value in valuesSet:
priorP = priorAleaDict.get(value,0)
condP = normAleaDict.get(value,0)
p = priorP*count*normAleaCount - condP*pTrue*priorAleaCount
if not(0 <= p <= pFalse*normAleaCount*priorAleaCount):
# Infeasible : probability represented by p goes outside range from 0 to 1
priorPFraction = ProbFraction(priorP,priorAleaCount)
lowerPFraction = ProbFraction(condP*pTrue,count*normAleaCount)
upperPFraction = ProbFraction(condP*pTrue+pFalse*normAleaCount,count*normAleaCount)
raise Lea.Error("prior probability of '%s' is %s, outside the range [ %s , %s ]"%(value,priorPFraction,lowerPFraction,upperPFraction))
vps.append((value,p))
elseClauseResult = Lea.fromValFreqs(*vps)
elif elseClauseResult is None:
# check that clause set is complete
if not isClauseSetComplete:
# TODO? : assume a uniform prior distribution ? ... which values ?
raise Lea.Error("incomplete clause set requires 'other' clause or prior probabilities")
if elseClauseResult is not None:
elseCondLea = ~orCondsLea
normClauseLeas += ((elseCondLea,Lea.coerce(elseClauseResult)),)
# note that orCondsLea is NOT extended with rCondsLea |= elseCondLea
# so, in case of else clause (and only in this case), orCondsLea is NOT certainly true
return Blea(*(Ilea(resultLea,condLea) for (condLea,resultLea) in normClauseLeas))
# PyBossa is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with PyBossa. If not, see <http://www.gnu.org/licenses/>.
from lea import Lea
import pandas as pd
import ngram
def lower(s):
return s.lower()
task_runs = Lea.fromValFreqs(("hola mundo", 55), ("HoLa mundos", 45), ("algo horroroso", 10))
observation = task_runs.random(30)
a = [lower(w) for w in observation]
df = pd.DataFrame({'info': a})
desc = df.describe()
top_string = desc['info']['top']
print "The top transcribed word is: %s" % top_string
G = ngram.NGram([ lower(w) for w in a])
from __future__ import division, print_function
from lea import Lea
# define coin
coin = Lea.fromValFreqs(('H', 1),
('T', 1))
print('Coin Distribution',
coin,
sep='\n')
# define six-sided die
die6 = Lea.fromValFreqs(('1', 1),
('2', 1),
('3', 1),
('4', 1),
('5', 1),
('6', 1))
print('Six-sided Die Distribution',
die6,
sep='\n')
# define four-side die
die4 = Lea.fromValFreqs(('1', 1),
('2', 1),
('3', 1),
('4', 1))
print('Four-sided Die Distribution',
from __future__ import division, print_function
from lea import Lea
# define cancer dist
cancer = Lea.fromValFreqs(('yes', 1),
('no', 99))
print('\nCancer Distribution',
'P(C)',
cancer.asPct(),
sep='\n')
# prob for mamm given cancer == yes
mamm_g_cancer = Lea.fromValFreqs(('pos', 80),
('neg', 20))
print('\nProb for mammogram given cancer',
'P(M|C=yes)',
mamm_g_cancer.asPct(),
sep='\n')
# prob for mamm given cancer == no
mamm_g_no_cancer = Lea.fromValFreqs(('pos', 96),
('neg', 1000-96))
print('\nProb for mammogram given NO cancer',
'P(M|C=no)',
mamm_g_no_cancer.asPct(),
sep='\n')
def setTermsChoices(self,*termsChoices):
self.termsChoices = Lea.fromValFreqs(*termsChoices)
from __future__ import division, print_function
from lea import Lea
# define cancer dist
cancer = Lea.fromValFreqs(('yes', 1), ('no', 99))
print('\nCancer Distribution', 'P(C)', cancer.asPct(), sep='\n')
# prob for mamm given cancer == yes
mamm_g_cancer = Lea.fromValFreqs(('pos', 80), ('neg', 20))
print('\nProb for mammogram given cancer',
'P(M|C=yes)',
mamm_g_cancer.asPct(),
sep='\n')
# prob for mamm given cancer == no
mamm_g_no_cancer = Lea.fromValFreqs(('pos', 96), ('neg', 1000 - 96))
print('\nProb for mammogram given NO cancer',
'P(M|C=no)',
mamm_g_no_cancer.asPct(),
sep='\n')
# conditional probability table
mammograms = Lea.buildCPT((cancer == 'yes', mamm_g_cancer),
(cancer == 'no', mamm_g_no_cancer))
print('\nMammograms', 'P(M)', mammograms.asPct(), sep='\n')
# get joint probs for all events
