def correlateRatingsTags(Ratings, Group='FullDirTrees'):
import numpy.oldnumeric.mlab as MLab
DirectionGivers = '(EDA|EMWC|KLS|KXP|TJS|WLH)'
Routes = '.*'
Envs = '.*'
Suffix = 'Dirs_\d.txt$'
Directions = DirectionCorpusReader('_'.join(
[DirectionGivers, Envs, Routes, Suffix]))
CFDist = LearnCondDist(Directions,
list(Directions.items(Group)),
Start='DIRECTIONS',
verbose=1)
TagOrder = [
tag.symbol() for tag in CFDist.conditions()
if not (tag.symbol().endswith('_P') or tag.symbol().endswith('_N')
or tag.symbol().endswith('_V'))
]
TagOrder.sort()
results = {}
for item in Directions.items(Group):
dirID = item.split('-')[1]
if not Ratings.has_key(dirID):
print 'Skipping', dirID
continue
TagCounts = {}
DirModel = LearnCondDist(Directions, [item], Start='DIRECTIONS')
for nonterm in DirModel.conditions():
tag = nonterm.symbol()
#print nonterm, [DirModel[nonterm].count(s) for s in DirModel[nonterm].samples()]
if tag in TagOrder:
TagCounts[tag] = MLab.sum([
DirModel[nonterm].count(s)
for s in DirModel[nonterm].samples()
])
TraitList = [
Ratings[dirID][2], Ratings[dirID][3], Ratings[dirID][4],
Ratings[dirID][5], Ratings[dirID][6] + Ratings[dirID][7]
]
for TagName in TagOrder:
if TagCounts.has_key(TagName):
TraitList.append(TagCounts[TagName])
else:
TraitList.append(0)
results[dirID] = TraitList
#print dirID, TraitList
for k in Ratings.keys():
if not results.has_key(k):
results[k] = [0] * (len(TagOrder) + 5) # Number of ratings used
return results, TagOrder
def correlateRatingsTags(Ratings,Group='FullDirTrees'):
import numpy.oldnumeric.mlab as MLab
DirectionGivers = '(EDA|EMWC|KLS|KXP|TJS|WLH)'
Routes = '.*'
Envs = '.*'
Suffix = 'Dirs_\d.txt$'
Directions = DirectionCorpusReader('_'.join([DirectionGivers,Envs,Routes,Suffix]))
CFDist = LearnCondDist(Directions, list(Directions.items(Group)), Start='DIRECTIONS',verbose=1)
TagOrder = [tag.symbol() for tag in CFDist.conditions()
if not (tag.symbol().endswith('_P') or tag.symbol().endswith('_N') or tag.symbol().endswith('_V'))]
TagOrder.sort()
results = {}
for item in Directions.items(Group):
dirID = item.split('-')[1]
if not Ratings.has_key(dirID):
print 'Skipping', dirID;
continue
TagCounts = {}
DirModel = LearnCondDist(Directions, [item], Start='DIRECTIONS')
for nonterm in DirModel.conditions():
tag = nonterm.symbol()
#print nonterm, [DirModel[nonterm].count(s) for s in DirModel[nonterm].samples()]
if tag in TagOrder:
TagCounts[tag] = MLab.sum([DirModel[nonterm].count(s) for s in DirModel[nonterm].samples()])
TraitList = [Ratings[dirID][2], Ratings[dirID][3], Ratings[dirID][4],
Ratings[dirID][5], Ratings[dirID][6]+Ratings[dirID][7]]
for TagName in TagOrder:
if TagCounts.has_key(TagName):
TraitList.append(TagCounts[TagName])
else: TraitList.append(0)
results[dirID] = TraitList
#print dirID, TraitList
for k in Ratings.keys():
if not results.has_key(k):
results[k] = [0] * (len(TagOrder)+5) # Number of ratings used
return results, TagOrder
def rosen(x): # The Rosenbrock function
return MLab.sum(100.0*(x[1:]-x[:-1]**2.0)**2.0 + (1-x[:-1])**2.0)