def MeasureAttribute_info(self, attr, data):
table = data.select([attr, data.domain.classVar])
table = orange.Preprocessor_dropMissing(table)
a1 = [table[k][0].value for k in range(len(table))]
a2 = [table[k][1].value for k in range(len(table))]
val, prob = statc.pearsonr(a1, a2)
return val
def MeasureAttribute_info(self, attr, data):
table = data.select([attr, data.domain.classVar])
table = orange.Preprocessor_dropMissing(table)
a1 = [table[k][0].value for k in range(len(table))]
a2 = [table[k][1].value for k in range(len(table))]
val, prob = statc.pearsonr(a1, a2)
return val
def distPearson(x, y):
"""distance corresponding to 1 - pearson's correlation coefficient for arrays x,y
returns distance: 1 - pearson_r
"""
x = MA.asarray(x)
y = MA.asarray(y)
assert MA.rank(x) == MA.rank(y) == 1
cond = MA.logical_not(MA.logical_or(MA.getmaskarray(x),
MA.getmaskarray(y)))
return 1 - statc.pearsonr(
MA.compress(cond, x).tolist(),
MA.compress(cond, y).tolist())[0]
def __call__(self, e1, e2):
X1 = []; X2 = []
for i in self.indxs:
if not(e1[i].isSpecial() or e2[i].isSpecial()):
X1.append(float(e1[i]))
X2.append(float(e2[i]))
if not X1:
return 1.0
try:
return (1.0 - statc.pearsonr(X1, X2)[0]) / 2.
except:
return 1.0
def computeCorrelation(data, attr1, attr2):
if data.domain[attr1].varType != orange.VarTypes.Continuous: return None
if data.domain[attr2].varType != orange.VarTypes.Continuous: return None
table = data.select([attr1, attr2])
table = orange.Preprocessor_dropMissing(table)
a1 = [table[k][attr1].value for k in range(len(table))]
a2 = [table[k][attr2].value for k in range(len(table))]
try:
val, prob = statc.pearsonr(a1, a2)
except:
val = 0.0 # possibly invalid a1 or a2
return val
def computeCorrelation(data, attr1, attr2):
if data.domain[attr1].varType != orange.VarTypes.Continuous: return None
if data.domain[attr2].varType != orange.VarTypes.Continuous: return None
table = data.select([attr1, attr2])
table = orange.Preprocessor_dropMissing(table)
a1 = [table[k][attr1].value for k in range(len(table))]
a2 = [table[k][attr2].value for k in range(len(table))]
try:
val, prob = statc.pearsonr(a1, a2)
except:
val = 0.0 # possibly invalid a1 or a2
return val
def computeCorrelationInsideClasses(data, attr1, attr2):
if data.domain[attr1].varType != orange.VarTypes.Continuous: return None
if data.domain[attr2].varType != orange.VarTypes.Continuous: return None
table = data.select([attr1, attr2, data.domain.classVar])
table = orange.Preprocessor_dropMissing(table)
lengths = []; corrs = []
for val in table.domain.classVar.values:
tab = table.filter({table.domain.classVar: val})
a1 = [tab[k][attr1].value for k in range(len(tab))]
a2 = [tab[k][attr2].value for k in range(len(tab))]
if len(a1) == 0: continue
val, prob = statc.pearsonr(a1, a2)
lengths.append(len(a1))
corrs.append(val)
corr = 0
for ind in range(len(corrs)): corr += abs(corrs[ind])*lengths[ind]
corr /= sum(lengths)
return corr, corrs, lengths
def pearson(ex1, ex2):
vals1 = ex1.native(0)[:-1]
vals2 = ex2.native(0)[:-1]
if check_same and vals1 == vals2:
return 10 #they are the same
#leaves undefined elements out
if not no_unknowns:
common = [ True if v1 != "?" and v2 != "?" else False \
for v1,v2 in zip(vals1,vals2) ]
vals1 = [v for v, c in zip(vals1, common) if c]
vals2 = [v for v, c in zip(vals2, common) if c]
#statc correlation is from 5-10 times faster than numpy!
try:
return statc.pearsonr(vals1, vals2)[0]
except:
return numpy.corrcoef([vals1, vals2])[0, 1]
def computeCorrelationInsideClasses(data, attr1, attr2):
if data.domain[attr1].varType != orange.VarTypes.Continuous: return None
if data.domain[attr2].varType != orange.VarTypes.Continuous: return None
table = data.select([attr1, attr2, data.domain.classVar])
table = orange.Preprocessor_dropMissing(table)
lengths = []
corrs = []
for val in table.domain.classVar.values:
tab = table.filter({table.domain.classVar: val})
a1 = [tab[k][attr1].value for k in range(len(tab))]
a2 = [tab[k][attr2].value for k in range(len(tab))]
if len(a1) == 0: continue
val, prob = statc.pearsonr(a1, a2)
lengths.append(len(a1))
corrs.append(val)
corr = 0
for ind in range(len(corrs)):
corr += abs(corrs[ind]) * lengths[ind]
corr /= sum(lengths)
return corr, corrs, lengths
