def readSamples(self, fileName, key,recalc=False,samples=None):
fn = fileName + ".pre"
try:
if recalc: raise IOError()
with open(fn): pass
print "precalculated file present"
self.mu, self.cov = hsplit(mat(fromfile(fn).reshape((3,-1))),[1])
except IOError:
if samples != None:
self._samples = samples
print "got samples: " , self._samples
else:
print "no file present, calculating..."
smpls = loadmat(fileName)[key]
print "loaded from mat file"
self._samples = mat(smpls)
print "reshaped into samples"
self.mu = sum(self._samples, axis=1) / self._samples.shape[1]
print "mu=", str(self.mu)
sampdiffmu = self._samples - self.mu
self.cov = sampdiffmu*sampdiffmu.T / self._samples.shape[1]
print"cov=", str(self.cov)
mat(hstack((self.mu,self.cov))).tofile(fn)
self._invCov = self.cov.I
self._detCov = det(self.cov)
self._multConst = 1 / sqrt((2 * pi) ** 3 * self._detCov)
def bicgstabReg(X,Y,my_Y,B):
'''
#稳定双共轭梯度下降
'''
my_Y_copy=[]
for i in my_Y:
my_Y_copy.append(i)
error = CostFunctionReg(Y,my_Y_copy,B)
R0star = Y - dot(X,B)
R0 = Y - dot(X,B)
rho0 = 1
alp0 = 1
w0 = 1
V0 =mat(zeros(len(Y)).reshape(len(Y),1))
P0 = mat(zeros(len(Y)).reshape(len(Y),1))
#print R0
while 1:
rho1 = array(dot(R0star.T, R0))[0][0]
beta = (rho1/rho0) * (alp0/w0)
P1 = R0 + beta*(P0 - w0*V0)
V1 = dot(X,P1)
alp0 = rho1/(array(dot(R0star.T,V1))[0][0])
h = B + alp0 * P1
my_Y_copy = array(dot(X,array(h).reshape(len(h),1)).reshape(1,len(Y)))[0]
new_error = CostFunctionReg(Y,my_Y_copy,h)
if abs(new_error -error) <=e:
B=h
break
#error = new_error
S = R0 - alp0*V1
t = dot(X,S)
w1 = array(dot(t.T, S))[0][0]/array(dot(t.T, t))[0][0]
B = h + w1*S
my_Y_copy = array(dot(X,array(B).reshape(len(B),1)).reshape(1,len(Y)))[0]
new_error = CostFunctionReg(Y,my_Y_copy,B)
# print abs(new_error -error)
if abs(new_error -error) <=e:
break
R0 = S - w1 * t
rho0 = rho1
P0 = P1
V0 =V1
w0 = w1
error = new_error
return dot(X,B),B
def getXmat(Xc):
X_matrix = []
for i in range(ORDER + 1):
X_matrix.append(array(Xc)**i)
X_matrix = mat(X_matrix).T
#print X_matrix
return X_matrix
def reFeature(B):
tha_ = (array(B).reshape(1, ORDER + 1))[0]
b = []
for i in range(ORDER + 1):
b.append(tha_[i] / (2.5**i))
return mat(array(b).reshape(ORDER + 1, 1))
def __calculateP__(self):
p = mat(self.p.shape)
for k in range(0,self.K):
llh = Likelihood()
llh.setParams(self.mean[k,:],self.covm[k,:,:])
for i in range(0,self.N):
p[k,i] = llh.getP(self.data[i,:])
sp = sum(p,axis=0)
for k in range(0,self.K):
for i in range(0,self.N):
self.p[k,i] = p[k,i]/sp[i]
def normalize(dataset):
for i in range(len(dataset)):
dataset[i].insert(0,'1.0')
dataset[i] = map(eval, dataset[i])
dataset = mat(dataset)
# dataset[i] = mat(dataset[i])
for i in range(dataset.shape[1] - 1):
dataset[:,i] = dataset[:,i] / dataset[:,i].max()
# print "dataset dataset is:",dataset.tolist()
return dataset
def gradAscent(data,label,labelSet):
hmat = zeros((data.shape[0],len(labelSet) - 1)).tolist()
# print "hmat[2][1]",hmat[2][1]
i = 0
# print "ge zhong changdu",len(labelSet) - 1,data.shape[0]
for k in range(len(labelSet) - 1):
for j in range(data.shape[0]):
if(label[j] == labelSet[k]):
hmat[j][k] = 1
iteration = 1
error = 0.00001
m,n = shape(data)
labelNum = len(labelSet) - 1
if(labelNum >= 2):
weights = ones((n,labelNum))
else:
weights = ones((n,1))
# for i in range(iteration):
for i in range(labelNum):
diff = 1
hmat = mat(hmat)
while(diff > error):
if(labelNum == 1):
h = sigMoid(data * weights[:,i])
h = mat(h)
deri = mat(label).transpose() - h ###11*1
else:
h = fakeSigMoid(data * weights)
h = mat(h)
deri = hmat[:,i] - h[:,i] ###11*1
# cichu hai zhengchang
formal = copy.deepcopy(weights[:,i])
weights[:,i] = weights[:,i] + alpha * data.transpose() * deri ####梯度下降法目标函数取最小值，所以此处为+
diff = abs(formal.transpose() * formal - weights[:,i].transpose() * weights[:,i])
print "diff = ",diff
return weights
def TheLeastSquareMethod(X, Y):
"""
最小二乘法
"""
regula = eye(ORDER + 1)
X_matrix = []
for i in range(ORDER + 1):
X_matrix.append(array(X)**i)
X_matrix = mat(X_matrix).T
Y_matrix = array(Y).reshape((len(Y), 1))
X_matrix_T = X_matrix.T
#print dot(X_matrix_T,X_matrix)
B = dot(dot(dot(X_matrix_T, X_matrix).I, X_matrix_T), Y_matrix)
B1 = dot(dot((dot(X_matrix_T, X_matrix) + lamda * regula).I, X_matrix_T),
Y_matrix)
result = dot(X_matrix, B)
result_reg = dot(X_matrix, B1)
return X_matrix, Y_matrix, B, result, result_reg, B1
# coding:utf-8 import numpy as np from numpy.matrixlib.defmatrix import mat from numpy.core.numeric import ones, full from common_utils import typeName # 从范围【10，30) 返回以10开始，等差值为5的数列. 不包含30 print np.arange(10, 30, 5) #[10 15 20 25] result = np.arange(0, 2, 0.5) print result print type(result).__name__ # ndarray print mat(result).transpose() # 从范围[-1,0] , 5个元素组成的等差元素的数组. print np.linspace(-1, 0, 5) x = np.array([[1, 2], [3, 4]]) print mat(x) # 转化为numpy数组 print mat(x).transpose() # transpose numpy矩阵转化. 这里从1行4列，变成，4行1列. x = np.array((1, 2, 3, 4)) print mat(x) print mat(x).transpose() # transpose numpy矩阵转化. 这里从3行2列，变成，2行3列. 并且将每列的数据 合并成1行。 x = np.array([[1, 2], [3, 4], [5, 6]]) print mat(x)
def main():
'See above.'
cvs_file_abs_name_gz = os.path.join(cingDirData, 'PluginCode', 'Whatif', cvs_file_abs_name + '.gz')
gunzip(cvs_file_abs_name_gz)
reader = csv.reader(open(cvs_file_abs_name, "rb"), quoting=csv.QUOTE_NONE)
valueBySs0AndResTypes = {} # keys are SSi, RTi, RTi-1
valueBySs1AndResTypes = {} # keys are SSi-1, RTi, RTi-1
valueByResTypes = {}
valueBySs0 = {} # keys are SSi
valueBySs1 = {} # keys are SSi-1
histd1CtupleBySsAndResTypes = {}
value = [] # NB is an array without being keyed.
histd1BySs0AndResTypes = {} # keys are SSi, RTi, RTi-1
histd1BySs1AndResTypes = {} # keys are SSi-1, RTi, RTi-1
histd1ByResTypes = {}
histd1BySs0 = {}
histd1BySs1 = {}
linesByEntry = {}
lineCount = 0
for row in reader:
lineCount += 1
if lineCount > lineCountMax:
break
entryId = row[0]
if not linesByEntry.has_key(entryId):
linesByEntry[ entryId ] = []
linesByEntry[ entryId ].append( row )
skippedResTypes = []
entryIdList = linesByEntry.keys()
entryIdList.sort()
# Do some pre filtering.
for entryId2 in entryIdList:
lineList = linesByEntry[ entryId2 ]
for idx,line in enumerate(lineList):
line.append(idx)
lineListSorted = NTsort(lineList,BFACTOR_COLUMN,inplace=False)
# Now throw away the worst 10 % of residues.
n = len(lineListSorted)
bad_count = int(round((n * DEFAULT_BFACTOR_PERCENTAGE_FILTER) / 100.))
to_remove_count = n-bad_count
# nTmessage("Removing at least %d from %d residues" % (bad_count,n))
badIdxList = [lineItem[IDX_COLUMN] for lineItem in lineListSorted[to_remove_count:n]]
iList = range(n)
iList.reverse()
for i in iList:
lineItem = lineList[i]
max_bfactor = float(lineItem[BFACTOR_COLUMN])
if max_bfactor > DEFAULT_MAX_BFACTOR:
# nTdebug('Skipping because max bfactor in dihedral %.3f is above %.3f %s' % (max_bfactor, DEFAULT_MAX_BFACTOR, lineItem))
del lineList[i] # TODO: check if indexing is still right or we shoot in the foot.
continue
if i in badIdxList:
# nTdebug('Skipping because bfactor worst %.3f %s' % (max_bfactor, lineItem))
del lineList[i]
continue
removed_count = n - len(lineList)
# nTdebug("Reduced list by %d" % removed_count)
if removed_count < bad_count:
nTwarning("Failed to remove at least %d residues" % bad_count)
for entryId2 in entryIdList:
prevChainId = None
prevResType = None
prevResNum = None
prevSsType = None
for _r, row in enumerate(linesByEntry[ entryId2 ]):
#1zzk,A,GLN , 17,E, 205.2, 193.6
#1zzk,A,VAL , 18,E, 193.6, 223.2
#1zzk,A,THR , 19,E, 223.2, 190.1
(entryId, chainId, resType, resNum, ssType, d1, _d2, _max_bfactor, _idx) = row
resNum = int(resNum)
ssType = to3StateDssp(ssType)[0]
resType = resType.strip()
db = NTdb.getResidueDefByName( resType )
if not db:
nTerror("resType not in db: %s" % resType)
return
resType = db.nameDict['IUPAC']
d1 = d1.strip()
d1 = floatParse(d1)
if isNaN(d1):
# nTdebug("d1 %s is a NaN on row: %s" % (d1,row))
continue
if not inRange(d1):
nTerror("d1 not in range for row: %s" % str(row))
return
if not (resType in common20AAList):
# nTmessage("Skipping uncommon residue: %s" % resType)
if not ( resType in skippedResTypes):
skippedResTypes.append( resType )
continue
if isSibling(chainId, resNum, prevChainId, prevResNum):
appendDeepByKeys(valueBySs0AndResTypes, d1, ssType, resType, prevResType)
appendDeepByKeys(valueBySs1AndResTypes, d1, prevSsType, resType, prevResType)
appendDeepByKeys(valueByResTypes, d1, resType, prevResType)
appendDeepByKeys(valueBySs0, d1, ssType)
appendDeepByKeys(valueBySs1, d1, prevSsType)
value.append( d1 )
prevResType = resType
prevResNum = resNum
prevChainId = chainId
prevSsType = ssType
os.unlink(cvs_file_abs_name)
nTmessage("Skipped skippedResTypes: %r" % skippedResTypes )
nTmessage("Got count of values: %r" % len(value) )
# fill FOUR types of hist.
# TODO: filter differently for pro/gly
keyListSorted1 = valueBySs0AndResTypes.keys()
keyListSorted1.sort()
for isI in (True, False):
if isI:
valueBySs = valueBySs0
valueBySsAndResTypes = valueBySs0AndResTypes
histd1BySs = histd1BySs0
histd1BySsAndResTypes = histd1BySs0AndResTypes
else:
valueBySs = valueBySs1
valueBySsAndResTypes = valueBySs1AndResTypes
histd1BySs = histd1BySs1
histd1BySsAndResTypes = histd1BySs1AndResTypes
for ssType in keyListSorted1:
# keyListSorted1b = deepcopy(keyListSorted1)
# for ssTypePrev in keyListSorted1b:
d1List = valueBySs[ssType]
if not d1List:
nTerror("Expected d1List from valueBySs[%s]" % (ssType))
continue
hist1d, _bins, _patches = hist(d1List, bins=binCount, range=xRange)
nTmessage("Count %6d in valueBySs[%s]" % (sum(hist1d), ssType))
setDeepByKeys(histd1BySs, hist1d, ssType)
keyListSorted2 = valueBySsAndResTypes[ssType].keys()
keyListSorted2.sort()
for resType in keyListSorted2:
# nTmessage("Working on valueBySsAndResTypes for [%s][%s]" % (ssType, resType)) # nice for balancing output verbosity.
keyListSorted3 = valueBySsAndResTypes[ssType][resType].keys()
keyListSorted3.sort()
for prevResType in keyListSorted3:
# nTmessage("Working on valueBySsAndResTypes[%s][%s][%s]" % (ssType, resType, prevResType))
d1List = valueBySsAndResTypes[ssType][resType][prevResType]
if not d1List:
nTerror("Expected d1List from valueBySsAndResTypes[%s][%s][%s]" % (ssType, resType, prevResType))
continue
hist1d, _bins, _patches = hist(d1List, bins=binCount, range=xRange)
# nTmessage("Count %6d in valueBySsAndResTypes[%s][%s][%s]" % (sum(hist1d), ssType, resType, prevResType))
setDeepByKeys(histd1BySsAndResTypes, hist1d, ssType, resType, prevResType)
# Now that they are all in we can redo this.
# Delete the reference -not- the object.
valueBySs = None
valueBySsAndResTypes = None
histd1BySs = None
histd1BySsAndResTypes = None
for ssType in keyListSorted1:
for resType in keyListSorted2:
# nTmessage("Working on valueBySsAndResTypes for [%s][%s]" % (ssType, resType)) # nice for balancing output verbosity.
keyListSorted3 = valueBySs0AndResTypes[ssType][resType].keys()
keyListSorted3.sort()
for resTypePrev in keyListSorted3:
keyListSorted4 = keyListSorted3[:] # take a copy
for resTypeNext in keyListSorted4:
hist1 = getDeepByKeys(histd1BySs0AndResTypes, ssType, resType, resTypePrev) # x-axis
# This was bug! It needs to be hashed on the ssType of resType -not- on resTypeNext
hist2 = getDeepByKeys(histd1BySs1AndResTypes, ssType, resTypeNext, resType)
if hist1 == None:
nTdebug('skipping for hist1 is empty for [%s] [%s] [%s]' % (ssType, resTypePrev, resType))
continue
if hist2 == None:
nTdebug('skipping for hist2 is empty for [%s] [%s] [%s]' % (ssType, resType, resTypeNext))
continue
m1 = mat(hist1,dtype='float')
m2 = mat(hist2,dtype='float')
m2 = m2.transpose() # pylint: disable=E1101
hist2d = multiply(m1,m2)
cTuple = getEnsembleAverageAndSigmaHis( hist2d )
(_c_av, c_sd, _hisMin, _hisMax) = cTuple #@UnusedVariable
cTuple += tuple([str([ssType, resType, resTypePrev, resTypeNext])]) # append the hash keys as a way of id.
# nTdebug("For ssType %s residue types %s %s %s found (av/sd/min/max) %8.0f %8.0f %8.0f %8.0f" % (
# ssType, resType, resTypePrev, resTypeNext, c_av, c_sd, hisMin, hisMax))
if c_sd == None:
nTdebug('Failed to get c_sd when testing not all residues are present in smaller sets.')
continue
if c_sd == 0.:
nTdebug('Got zero c_sd, ignoring histogram. This should only occur in smaller sets. Not setting values.')
continue
setDeepByKeys( histd1CtupleBySsAndResTypes, cTuple, ssType, resType, resTypePrev, resTypeNext)
# end for isI
keyListSorted1 = valueByResTypes.keys()
keyListSorted1.sort()
for resType in keyListSorted1:
keyListSorted2 = valueByResTypes[resType].keys()
keyListSorted2.sort()
for prevResType in keyListSorted2:
d1List = valueByResTypes[resType][prevResType]
if not d1List:
nTerror("Expected d1List from valueByResTypes[%s][%s]" % (resType, prevResType))
continue
hist1d, _bins, _patches = hist(d1List, bins=binCount, range=xRange)
# nTmessage("Count %6d in valueByResTypes[%s][%s]" % (sum(hist1d), resType, prevResType))
setDeepByKeys(histd1ByResTypes, hist1d, resType, prevResType)
histd1, _bins, _patches = hist(value, bins=binCount, range=xRange)
nTmessage("Count %6d in value" % sum(histd1))
# setDeepByKeys(histd1, hist1d, resType, prevResType)
if os.path.exists(dbase_file_abs_name):
os.unlink(dbase_file_abs_name)
output = open(dbase_file_abs_name, 'wb')
dbase = {}
dbase[ 'histd1BySs0AndResTypes' ] = histd1BySs0AndResTypes # 92 kb uncompressed in the case of ~1000 lines only
dbase[ 'histd1BySs1AndResTypes' ] = histd1BySs1AndResTypes
dbase[ 'histd1CtupleBySsAndResTypes' ] = histd1CtupleBySsAndResTypes
dbase[ 'histd1ByResTypes' ] = histd1ByResTypes # 56 kb
dbase[ 'histd1BySs0' ] = histd1BySs0 # 4 kb
dbase[ 'histd1BySs1' ] = histd1BySs1
dbase[ 'histd1' ] = histd1 # 4 kb
cPickle.dump(dbase, output, 2)
output.close()
def main():
'See above.'
cvs_file_abs_name_gz = os.path.join(cingDirData, 'PluginCode', 'Whatif',
cvs_file_abs_name + '.gz')
gunzip(cvs_file_abs_name_gz)
reader = csv.reader(open(cvs_file_abs_name, "rb"), quoting=csv.QUOTE_NONE)
valueBySs0AndResTypes = {} # keys are SSi, RTi, RTi-1
valueBySs1AndResTypes = {} # keys are SSi-1, RTi, RTi-1
valueByResTypes = {}
valueBySs0 = {} # keys are SSi
valueBySs1 = {} # keys are SSi-1
histd1CtupleBySsAndResTypes = {}
value = [] # NB is an array without being keyed.
histd1BySs0AndResTypes = {} # keys are SSi, RTi, RTi-1
histd1BySs1AndResTypes = {} # keys are SSi-1, RTi, RTi-1
histd1ByResTypes = {}
histd1BySs0 = {}
histd1BySs1 = {}
linesByEntry = {}
lineCount = 0
for row in reader:
lineCount += 1
if lineCount > lineCountMax:
break
entryId = row[0]
if not linesByEntry.has_key(entryId):
linesByEntry[entryId] = []
linesByEntry[entryId].append(row)
skippedResTypes = []
entryIdList = linesByEntry.keys()
entryIdList.sort()
# Do some pre filtering.
for entryId2 in entryIdList:
lineList = linesByEntry[entryId2]
for idx, line in enumerate(lineList):
line.append(idx)
lineListSorted = NTsort(lineList, BFACTOR_COLUMN, inplace=False)
# Now throw away the worst 10 % of residues.
n = len(lineListSorted)
bad_count = int(round((n * DEFAULT_BFACTOR_PERCENTAGE_FILTER) / 100.))
to_remove_count = n - bad_count
# nTmessage("Removing at least %d from %d residues" % (bad_count,n))
badIdxList = [
lineItem[IDX_COLUMN]
for lineItem in lineListSorted[to_remove_count:n]
]
iList = range(n)
iList.reverse()
for i in iList:
lineItem = lineList[i]
max_bfactor = float(lineItem[BFACTOR_COLUMN])
if max_bfactor > DEFAULT_MAX_BFACTOR:
# nTdebug('Skipping because max bfactor in dihedral %.3f is above %.3f %s' % (max_bfactor, DEFAULT_MAX_BFACTOR, lineItem))
del lineList[
i] # TODO: check if indexing is still right or we shoot in the foot.
continue
if i in badIdxList:
# nTdebug('Skipping because bfactor worst %.3f %s' % (max_bfactor, lineItem))
del lineList[i]
continue
removed_count = n - len(lineList)
# nTdebug("Reduced list by %d" % removed_count)
if removed_count < bad_count:
nTwarning("Failed to remove at least %d residues" % bad_count)
for entryId2 in entryIdList:
prevChainId = None
prevResType = None
prevResNum = None
prevSsType = None
for _r, row in enumerate(linesByEntry[entryId2]):
#1zzk,A,GLN , 17,E, 205.2, 193.6
#1zzk,A,VAL , 18,E, 193.6, 223.2
#1zzk,A,THR , 19,E, 223.2, 190.1
(entryId, chainId, resType, resNum, ssType, d1, _d2, _max_bfactor,
_idx) = row
resNum = int(resNum)
ssType = to3StateDssp(ssType)[0]
resType = resType.strip()
db = NTdb.getResidueDefByName(resType)
if not db:
nTerror("resType not in db: %s" % resType)
return
resType = db.nameDict['IUPAC']
d1 = d1.strip()
d1 = floatParse(d1)
if isNaN(d1):
# nTdebug("d1 %s is a NaN on row: %s" % (d1,row))
continue
if not inRange(d1):
nTerror("d1 not in range for row: %s" % str(row))
return
if not (resType in common20AAList):
# nTmessage("Skipping uncommon residue: %s" % resType)
if not (resType in skippedResTypes):
skippedResTypes.append(resType)
continue
if isSibling(chainId, resNum, prevChainId, prevResNum):
appendDeepByKeys(valueBySs0AndResTypes, d1, ssType, resType,
prevResType)
appendDeepByKeys(valueBySs1AndResTypes, d1, prevSsType,
resType, prevResType)
appendDeepByKeys(valueByResTypes, d1, resType, prevResType)
appendDeepByKeys(valueBySs0, d1, ssType)
appendDeepByKeys(valueBySs1, d1, prevSsType)
value.append(d1)
prevResType = resType
prevResNum = resNum
prevChainId = chainId
prevSsType = ssType
os.unlink(cvs_file_abs_name)
nTmessage("Skipped skippedResTypes: %r" % skippedResTypes)
nTmessage("Got count of values: %r" % len(value))
# fill FOUR types of hist.
# TODO: filter differently for pro/gly
keyListSorted1 = valueBySs0AndResTypes.keys()
keyListSorted1.sort()
for isI in (True, False):
if isI:
valueBySs = valueBySs0
valueBySsAndResTypes = valueBySs0AndResTypes
histd1BySs = histd1BySs0
histd1BySsAndResTypes = histd1BySs0AndResTypes
else:
valueBySs = valueBySs1
valueBySsAndResTypes = valueBySs1AndResTypes
histd1BySs = histd1BySs1
histd1BySsAndResTypes = histd1BySs1AndResTypes
for ssType in keyListSorted1:
# keyListSorted1b = deepcopy(keyListSorted1)
# for ssTypePrev in keyListSorted1b:
d1List = valueBySs[ssType]
if not d1List:
nTerror("Expected d1List from valueBySs[%s]" % (ssType))
continue
hist1d, _bins, _patches = hist(d1List, bins=binCount, range=xRange)
nTmessage("Count %6d in valueBySs[%s]" % (sum(hist1d), ssType))
setDeepByKeys(histd1BySs, hist1d, ssType)
keyListSorted2 = valueBySsAndResTypes[ssType].keys()
keyListSorted2.sort()
for resType in keyListSorted2:
# nTmessage("Working on valueBySsAndResTypes for [%s][%s]" % (ssType, resType)) # nice for balancing output verbosity.
keyListSorted3 = valueBySsAndResTypes[ssType][resType].keys()
keyListSorted3.sort()
for prevResType in keyListSorted3:
# nTmessage("Working on valueBySsAndResTypes[%s][%s][%s]" % (ssType, resType, prevResType))
d1List = valueBySsAndResTypes[ssType][resType][prevResType]
if not d1List:
nTerror(
"Expected d1List from valueBySsAndResTypes[%s][%s][%s]"
% (ssType, resType, prevResType))
continue
hist1d, _bins, _patches = hist(d1List,
bins=binCount,
range=xRange)
# nTmessage("Count %6d in valueBySsAndResTypes[%s][%s][%s]" % (sum(hist1d), ssType, resType, prevResType))
setDeepByKeys(histd1BySsAndResTypes, hist1d, ssType,
resType, prevResType)
# Now that they are all in we can redo this.
# Delete the reference -not- the object.
valueBySs = None
valueBySsAndResTypes = None
histd1BySs = None
histd1BySsAndResTypes = None
for ssType in keyListSorted1:
for resType in keyListSorted2:
# nTmessage("Working on valueBySsAndResTypes for [%s][%s]" % (ssType, resType)) # nice for balancing output verbosity.
keyListSorted3 = valueBySs0AndResTypes[ssType][resType].keys()
keyListSorted3.sort()
for resTypePrev in keyListSorted3:
keyListSorted4 = keyListSorted3[:] # take a copy
for resTypeNext in keyListSorted4:
hist1 = getDeepByKeys(histd1BySs0AndResTypes, ssType,
resType, resTypePrev) # x-axis
# This was bug! It needs to be hashed on the ssType of resType -not- on resTypeNext
hist2 = getDeepByKeys(histd1BySs1AndResTypes, ssType,
resTypeNext, resType)
if hist1 == None:
nTdebug(
'skipping for hist1 is empty for [%s] [%s] [%s]' %
(ssType, resTypePrev, resType))
continue
if hist2 == None:
nTdebug(
'skipping for hist2 is empty for [%s] [%s] [%s]' %
(ssType, resType, resTypeNext))
continue
m1 = mat(hist1, dtype='float')
m2 = mat(hist2, dtype='float')
m2 = m2.transpose() # pylint: disable=E1101
hist2d = multiply(m1, m2)
cTuple = getEnsembleAverageAndSigmaHis(hist2d)
(_c_av, c_sd, _hisMin, _hisMax) = cTuple #@UnusedVariable
cTuple += tuple([
str([ssType, resType, resTypePrev, resTypeNext])
]) # append the hash keys as a way of id.
# nTdebug("For ssType %s residue types %s %s %s found (av/sd/min/max) %8.0f %8.0f %8.0f %8.0f" % (
# ssType, resType, resTypePrev, resTypeNext, c_av, c_sd, hisMin, hisMax))
if c_sd == None:
nTdebug(
'Failed to get c_sd when testing not all residues are present in smaller sets.'
)
continue
if c_sd == 0.:
nTdebug(
'Got zero c_sd, ignoring histogram. This should only occur in smaller sets. Not setting values.'
)
continue
setDeepByKeys(histd1CtupleBySsAndResTypes, cTuple, ssType,
resType, resTypePrev, resTypeNext)
# end for isI
keyListSorted1 = valueByResTypes.keys()
keyListSorted1.sort()
for resType in keyListSorted1:
keyListSorted2 = valueByResTypes[resType].keys()
keyListSorted2.sort()
for prevResType in keyListSorted2:
d1List = valueByResTypes[resType][prevResType]
if not d1List:
nTerror("Expected d1List from valueByResTypes[%s][%s]" %
(resType, prevResType))
continue
hist1d, _bins, _patches = hist(d1List, bins=binCount, range=xRange)
# nTmessage("Count %6d in valueByResTypes[%s][%s]" % (sum(hist1d), resType, prevResType))
setDeepByKeys(histd1ByResTypes, hist1d, resType, prevResType)
histd1, _bins, _patches = hist(value, bins=binCount, range=xRange)
nTmessage("Count %6d in value" % sum(histd1))
# setDeepByKeys(histd1, hist1d, resType, prevResType)
if os.path.exists(dbase_file_abs_name):
os.unlink(dbase_file_abs_name)
output = open(dbase_file_abs_name, 'wb')
dbase = {}
dbase[
'histd1BySs0AndResTypes'] = histd1BySs0AndResTypes # 92 kb uncompressed in the case of ~1000 lines only
dbase['histd1BySs1AndResTypes'] = histd1BySs1AndResTypes
dbase['histd1CtupleBySsAndResTypes'] = histd1CtupleBySsAndResTypes
dbase['histd1ByResTypes'] = histd1ByResTypes # 56 kb
dbase['histd1BySs0'] = histd1BySs0 # 4 kb
dbase['histd1BySs1'] = histd1BySs1
dbase['histd1'] = histd1 # 4 kb
cPickle.dump(dbase, output, 2)
output.close()
B = reFeature(thata)
return my_copy, B
if __name__ == "__main__":
X, Y, Xc, Yc, ALLX, ALLY = CreatData()
Xc_ = getXmat(Xc)
'''
#批量梯度下降
#初始的系数矩阵取B（即thata）
'''
X_lemad = array(X) / 2.5 #特征收缩
X_mat_ = []
for i in range(ORDER + 1):
X_mat_.append(X_lemad**i)
X_mat_ = mat(X_mat_).T
#thata = array(B.reshape(1,len(B)))[0] +uniform(0,0.1)
X_matrix = getXmat(X)
thata_ = []
for i in range(10):
thata_.append(uniform(-1, 1))
thata0 = mat(array(thata_).reshape(ORDER + 1, 1))
thata1 = mat([1, 1])
thata1 = thata0
my_Y = array(dot(X_matrix, thata0).reshape(1, len(Y)))[0]
thata = array(thata0.reshape(1, ORDER + 1))[0]
Y_bgd, B = BatchGradientDescent(my_Y, Y, X_mat_, thata)
thata = array(thata0.reshape(1, len(B)))[0]
#coding:utf-8 # ------------------------------------------------------------ # 简介 : 机器学习基础 numpy # # 更新 : 2015年1月7日@ # ------------------------------------------------------------ from numpy import random from numpy.matrixlib.defmatrix import mat from numpy.lib.twodim_base import eye #4*4随机数组 random.rand(4, 4) #数组转矩阵 randmat = mat(random.rand(4, 4)) print(randmat) #.I专为逆矩阵 print(randmat.I) randmatv = randmat.I #矩阵和逆矩阵相乘，对角为1 其他为0 -eye(4)为单位矩阵 相减后看到有误差 print(randmat * randmatv - eye(4))
