def setLearnerVars(self):
if self.priorsGUI:
self.priors = str(self.priorsGUI)
else:
self.priors = None
self.optAlg = int(self.optAlgGUI)
self.stopCrit = int(self.stopCritGUI) + 1
if miscUtilities.isNumber(self.stopValueGUI):
if self.stopCrit == 1: #ITER
self.maxIter = int(self.stopValueGUI)
else: #EPS
self.eps = float(self.stopValueGUI)
else:
self.warning(0, "Value for stop criteria must be a number! Using default value.")
self.maxIter = AZOC.CVANNDEFAULTDICT["maxIter"]
self.eps = AZOC.CVANNDEFAULTDICT["eps"]
self.scaleData = bool(self.scaleDataGUI)
self.scaleClass = bool(self.scaleClassGUI)
# Transform the nHidden to a list
try:
self.nHidden = string.split(str(self.nHiddenGUI),",")
self.nHidden = [int(elem.strip()) for elem in self.nHidden]
except:
self.warning(0, "Bad values for hidden neuronsi! Using default value.")
self.nHidden = AZOC.CVANNDEFAULTDICT["nHidden"]
self.setGUIVars()
def calcMahalanobis(data, testData):
"""
Calculates Mahalanobis distances.
The data should only contain attributes that are relevant for similarity. OBS data is assumed to have a response variable.
data - X matrix used to calculate the covariance matrix
testData - the examples in an ExampleTable object for which to calculate the MDs
Returns a list of Mahalanobis distances between the examples in testData and training data.
The elements of the list are dictionaries, giving the Mahalanobis distances to the average (_MD), the nearest neighbor and
an average of the 3 nearest neighbors (_train_av3nearest).
"""
# Impute any missing values
averageImputer = orange.ImputerConstructor_average(data)
data = averageImputer(data)
averageImputer = orange.ImputerConstructor_average(testData)
testData = averageImputer(testData)
# Test if there is any non-numeric value within the dataset
for ex in testData:
# It is much faster to address the ex elements by their position instead of the correpondent name
for idx in range(len(ex.domain.attributes)):
if not miscUtilities.isNumber(ex[idx].value):
raise Exception(
"Cannot calculate Mahalanobis distances. The attribute '"
+ ex.domain.attributes[idx].name
+ "' has non-numeric values. Ex: "
+ str(ex[idx].value)
)
# Create a trainingSet object.
trainingSet = getTrainingSet(data)
trainingset_descriptor_names = trainingSet.descr_names
mahalanobisCalculator = Mahalanobis.MahalanobisDistanceCalculator(trainingSet)
MDlist = []
for ex in testData:
# Create a numeric vector from the example and assure the same order as in trainingset_descriptor_names
descriptor_values = []
for name in trainingset_descriptor_names:
try:
descriptor_values.append(float(ex[name].value))
except:
raise Exception("Not possible to calculate Mahalanobis distances. Some attribute is not numeric.")
# descriptor_values = [1.5] * len(trainingset_descriptor_names)
MD = mahalanobisCalculator.calculateDistances(descriptor_values, NO_OF_NEIGHBORS)
MDlist.append(MD)
return MDlist
def updateParametersFromTable(self):
"""Updates the parameters of the optimizer with the ones present on GUI table
Returns True if all OK
Returns False if Errors occurred
"""
#self.paramsNames: ["Name","Optimize","Lower Limit","Upper Limit","Distribution","Step","Default"]
#self.comboDistItems: ["Continuous","Power2","By Step","Specific Values"]
if self.paramsTable.columnCount() < 7:
self.setErrors("Wrong number of columns in table!")
return False
RangePars,distType = [None,None]
self.nParameters = len(self.parameters)
for row in range(self.paramsTable.rowCount()):
for col in range(7):
if col == 0:#Name
name=str(self.paramsTable.item(row,col).text()).strip()
RangePars,distType = self.getRangeParsAndDistType(self.originalParameters,name)
if RangePars==None or distType==None:
self.setErrors("It was not possible to identify the range parameters")
return False
elif col == 1:#Optimize
if self.paramsTable.cellWidget(row,col).checkState()==2:
optimize=True
else:
optimize = False
self.nParameters -= 1
elif col == 2:#Lower Limit
Llimit = str(self.paramsTable.item(row,col).text()).strip()
elif col == 3:#Upper Limit
Ulimit = str(self.paramsTable.item(row,col).text()).strip()
elif col == 4:#Distribution
if "Combo" in str(type(self.paramsTable.cellWidget(row,col))):
dist = str(self.paramsTable.cellWidget(row,col).currentIndex())
else:
dist = self.comboDistItems.index(self.paramsTable.item(row,col).text())
elif col == 5:#Step
step = str(self.paramsTable.item(row,col).text()).strip()
elif col == 6:#Default
if "Combo" in str(type(self.paramsTable.cellWidget(row,col))):
default = self.paramsTable.cellWidget(row,col).currentIndex()
if len(self.parameters[name][3]) <= default: #the parameter did not have an alias, the text is the value
default = str(self.paramsTable.cellWidget(row,col).currentText()).strip()
else:
default = RangePars[default]
else:#is string
default = str(self.paramsTable.item(row,col).text()).strip()
#['types.StringType', 'values', "['kernel' , 'pls1' , 'simpls']", ['Kernel', 'PLS1', 'SimPLS'], "'simpls'", True, False]
if optimize:
self.parameters[name][5] = True
if "Combo" in str(type(self.paramsTable.cellWidget(row,4))):
comboDistType = self.paramsTable.cellWidget(row,4).currentIndex()
else:
comboDistType = self.comboDistItems.index(self.paramsTable.item(row,4).text())
if comboDistType==0: #Continuous
if not miscUtilities.isNumber(Llimit):
if "N_EX" not in Llimit and "N_ATTR" not in Llimit:
QMessageBox.warning(self,"Invalid parameter","Parameter "+name+" has invalid Lower limit",QMessageBox.Ok)
return False
if not miscUtilities.isNumber(Ulimit):
if "N_EX" not in Ulimit and "N_ATTR" not in Ulimit:
QMessageBox.warning(self,"Invalid parameter","Parameter "+name+" has invalid Upper limit",QMessageBox.Ok)
return False
self.parameters[name][1] = "interval"
self.parameters[name][2] = "[" + Llimit + " , " + Ulimit + "]"
self.parameters[name][3] = ""
self.parameters[name][4] = default
elif comboDistType==1: #Power2
if not miscUtilities.isNumber(Llimit):
if "N_EX" not in Llimit and "N_ATTR" not in Llimit:
QMessageBox.warning(self,"Invalid parameter","Parameter "+name+" has invalid Lower limit",QMessageBox.Ok)
return False
if not miscUtilities.isNumber(Ulimit):
if "N_EX" not in Ulimit and "N_ATTR" not in Ulimit:
QMessageBox.warning(self,"Invalid parameter","Parameter "+name+" has invalid Upper limit",QMessageBox.Ok)
return False
if not miscUtilities.isNumber(step):
QMessageBox.warning(self,"Invalid parameter","Parameter "+name+" has an invalid step value",QMessageBox.Ok)
return False
self.parameters[name][1] = "values"
self.parameters[name][2] = "miscUtilities.power2Range(" + Llimit + "," + Ulimit + "," + step + ")"
self.parameters[name][3] = ""
self.parameters[name][4] = default
elif comboDistType==2: #By Step
if not miscUtilities.isNumber(Llimit):
if "N_EX" not in Llimit and "N_ATTR" not in Llimit:
QMessageBox.warning(self,"Invalid parameter","Parameter "+name+" has invalid Lower limit",QMessageBox.Ok)
return False
if not miscUtilities.isNumber(Ulimit):
if "N_EX" not in Ulimit and "N_ATTR" not in Ulimit:
QMessageBox.warning(self,"Invalid parameter","Parameter "+name+" has invalid Upper limit",QMessageBox.Ok)
return False
if not miscUtilities.isNumber(step):
QMessageBox.warning(self,"Invalid parameter","Parameter "+name+" has an invalid step value",QMessageBox.Ok)
return False
self.parameters[name][1] = "values"
self.parameters[name][2] = "miscUtilities.Range(" + Llimit + "," + Ulimit + "," + step + ")"
self.parameters[name][3] = ""
self.parameters[name][4] = default
else: #Specific Values
#The 'Specific Values' refere to the parameters specified in the original AZLearnersParamsConfig.py file
self.parameters[name][1] = self.originalParameters[name][1]
self.parameters[name][2] = self.originalParameters[name][2]
self.parameters[name][3] = self.originalParameters[name][3]
self.parameters[name][4] = default
else:
self.parameters[name][5] = False
#self.parameters[name][1]='values'
if "Combo" in str(type(self.paramsTable.cellWidget(row,6))):
default = self.paramsTable.cellWidget(row,6).currentIndex()
if len(RangePars) <= default: #the parameter did not have an alias, the text is the value
#self.parameters[name][2]='[' + str(self.paramsTable.cellWidget(row,6).currentText()).strip() + ']'
self.parameters[name][4]=str(self.paramsTable.cellWidget(row,6).currentText()).strip()
else:
#self.parameters[name][2]='[' + RangePars[default] + ']'
self.parameters[name][4]= RangePars[default]
else:#is string
#self.parameters[name][2]='[' + str(self.paramsTable.item(row,6).text()).strip() + ']'
self.parameters[name][4]=str(self.paramsTable.item(row,6).text()).strip()
return True
def getNearestNeighbors(query,
n,
NNDataPath,
FPPath=None,
resPath=None,
idx=0):
""" get the n nearest neighbors
query: bin string with query fingerprint
returns an ordered list with the n top neighbors (each one in a dict):
[ {
"id" : ID,
"expVal" : ExpValues,
"similarity" : TanimotoSimilarity,
"smi" : smiles,
"imgPath" : imgPath,
"MeanInhib" : Mean Inhib. }, ... ]
It will saves the images in resPath:
NN_1.png #1 neighbor
NN_2.png #2 neighbor
...
NN_n.png #n neighbor
"""
if not query or not n or not NNDataPath or not FPPath:
return []
#if resPath and not os.path.isdir(resPath):
# os.makedirs(resPath)
# get the correct header
file = open(NNDataPath, "r")
header = file.readline().strip().split('\t')
file.close()
if "Molecule SMILES" not in header or "Compound Name" not in header:
print "NN dataset ", NNDataPath, " have not the correct header. It must contain 'Molecule SMILES' and 'Compound Name' attributes."
return []
# Index will have to be sum 1 because the TS will be prepended
idxID = header.index("Compound Name") + 1
idxExpVal = len(header)
idxSMILES = header.index("Molecule SMILES") + 1
idxSimilarity = 0
Nbits = 2048
cmdStr = 'echo "' + query + '" | fpin ' + FPPath + " " + NNDataPath + ' 0.0 ' + str(
n)
status, output = commands.getstatusoutput(cmdStr)
if status:
print status
print output
raise Exception(str(output))
# TS SMILES AZID DATE expRes
# output = "0.7117 CCCC(C)C1(C(=O)NC(=O)NC1=O)CC AZ10046012 2009-12-02 3.480007"
TS = []
for ts in output.split("\n"):
TS.append(ts.strip().split('\t'))
# in TS:
# TS[n][0] - tanimoto similarity
# TS[n][1] - SMILES
# TS[n][2] - AZID
# TS[n][-1]- expRes
res = []
timeStamp = str(time.time()).replace(".", '')
for fidx, nn in enumerate(TS):
ID = nn[idxID]
if miscUtilities.isNumber(nn[idxExpVal]):
expVal = str(round(float(nn[idxExpVal]), 2))
else:
expVal = nn[idxExpVal]
SMILES = nn[idxSMILES]
if resPath and os.path.isdir(resPath):
imgPath = os.path.join(
resPath, "NN" + str(idx) + "_" + str(fidx + 1) + "_" +
timeStamp + ".png")
mol = Chem.MolFromSmiles(SMILES)
# save the respective imgPath...
Draw.MolToImageFile(mol,
imgPath,
size=(300, 300),
kekulize=True,
wedgeBonds=True)
else:
imgPath = ""
res.append({
"id": ID,
"expVal": expVal,
"similarity": nn[idxSimilarity],
"smi": SMILES,
"imgPath": imgPath,
"MeanInhib": ''
})
return res
def calcMahalanobis(data, testData, invCovMatFile = None, centerFile = None, dataTableFile = None, domain = None, nNN = NO_OF_NEIGHBORS):
"""
Calculates Mahalanobis distances.
The data should only contain attributes that are relevant for similarity. OBS data is assumed to have a response variable.
data - X matrix used to calculate the covariance matrix
testData - the examples in an ExampleTable object for which to calculate the MDs
Returns a list of Mahalanobis distances between the examples in testData and training data.
The elements of the list are dictionaries, giving the Mahalanobis distances to the average (_MD), the nearest neighbor and
an average of the 3 nearest neighbors (_train_av3nearest).
"""
# Impute any missing valuesi
if data:
averageImputer = orange.ImputerConstructor_average(data)
data = averageImputer(data)
#If Class is continuous and all class values are unknown (and they usually are in ex to predict), the imputer cannot be created.
# Since we are only using attributes, not the class, we will assign 0 to the class values in order to impute the testData
if testData.domain.classVar and testData.domain.classVar.varType == orange.VarTypes.Continuous:
for ex in testData:
if ex.getclass().isSpecial():
ex.setclass(0)
# This can also happens when calculating a single example with missing attributes
try:
averageImputer = orange.ImputerConstructor_average(testData)
except:
for ex in testData:
for attr in [a for a in testData.domain.attributes if a.varType == orange.VarTypes.Continuous]:
if ex[attr].isSpecial():
ex[attr] = 0
averageImputer = orange.ImputerConstructor_average(testData)
testData = averageImputer(testData)
#Test if there is any non-numeric value within the dataset
for ex in testData:
#It is much faster to address the ex elements by their position instead of the correpondent name
for idx in range(len(ex.domain.attributes)):
if not miscUtilities.isNumber(ex[idx].value):
raise Exception("Cannot calculate Mahalanobis distances. The attribute '" + \
ex.domain.attributes[idx].name + "' has non-numeric values. Ex: " + \
str(ex[idx].value))
if data:
trainingSet = getTrainingSet(data)
trainingset_descriptor_names = trainingSet.descr_names
else:
trainingSet = None
trainingset_descriptor_names = [attr.name for attr in domain.attributes]
mahalanobisCalculator = Mahalanobis.MahalanobisDistanceCalculator(trainingSet,invCovMatFile,centerFile,dataTableFile)
MDlist = []
for ex in testData:
# Create a numeric vector from the example and assure the same order as in trainingset_descriptor_names
descriptor_values = []
for name in trainingset_descriptor_names:
try:
descriptor_values.append(float(ex[name].value))
except:
raise Exception("Not possible to calculate Mahalanobis distances. Some attribute is not numeric.")
#descriptor_values = [1.5] * len(trainingset_descriptor_names)
MD = mahalanobisCalculator.calculateDistances(descriptor_values, nNN)
MDlist.append(MD)
return MDlist
def __init__(self, **kwds):
self.verbose = 0
self.logFile = None
self.resultsFile = None
self.nExtFolds = 5
self.nInnerFolds = 5
self.data = None
self.learner = None
self.paramList = None
self.queueType = "NoSGE"
self.responseType = None
self.fixedParams = {}
self.testAttrFilter = None
self.testFilterVal = None
self.sampler = dataUtilities.SeedDataSampler
# Append arguments to the __dict__ member variable
self.__dict__.update(kwds)
self.learnerName = ""
self.preDefIndices = orange.LongList()
self.usePreDefFolds = False
self.useVarCtrlCV = False
if self.testAttrFilter and self.testAttrFilter in self.data.domain:
if self.testFilterVal and type(self.testFilterVal) == list and type(self.testAttrFilter) == str:
self.useVarCtrlCV = True
self.usePreDefFolds = False
for ex in self.data:
if ex[self.testAttrFilter].value in self.testFilterVal: # Compound selected to be allowed in the test set
self.preDefIndices.append(1)
else: # Compound to not include in the test set. Always to be shifted to the train
self.preDefIndices.append(0)
elif self.testFilterVal is None:
self.usePreDefFolds = True
self.useVarCtrlCV = False
#Enable pre-selected-indices ( index 0 will be set for train Bias)
foldsCounter = {}
for ex in self.data:
value = str(ex[self.testAttrFilter].value)
if not miscUtilities.isNumber(value):
self.__log("Invalid fold value:"+str(value)+". It must be str convertable to an int.")
return False
value = int(float(value))
if value not in foldsCounter:
foldsCounter[value] = 1
else:
foldsCounter[value] += 1
self.preDefIndices.append(value)
self.__log( "INFO: Pre-selected "+str(len([f for f in foldsCounter.keys() if f != 0]))+" folds for CV:")
self.__log( " Examples in data: "+str(sum(foldsCounter.values())))
self.__log( " Examples selected for validation: "+str(sum([foldsCounter[f] for f in foldsCounter if f != 0])))
self.__log( " Examples to be appended to the train set: "+ str(0 in foldsCounter.keys() and foldsCounter[0] or 0))
else:
self.__log("ERROR: Attribute Filter Ctrl was selected, but attribute is not in expected format: " + str(self.testAttrFilter))
return False
self.data = dataUtilities.attributeDeselectionData(self.data, [self.testAttrFilter])
else:
self.usePreDefFolds = False
self.useVarCtrlCV = False
self.testAttrFilter = None
self.testFilterVal = None
def calcMahalanobis(data,
testData,
invCovMatFile=None,
centerFile=None,
dataTableFile=None,
domain=None,
nNN=NO_OF_NEIGHBORS):
"""
Calculates Mahalanobis distances.
The data should only contain attributes that are relevant for similarity. OBS data is assumed to have a response variable.
data - X matrix used to calculate the covariance matrix
testData - the examples in an ExampleTable object for which to calculate the MDs
Returns a list of Mahalanobis distances between the examples in testData and training data.
The elements of the list are dictionaries, giving the Mahalanobis distances to the average (_MD), the nearest neighbor and
an average of the 3 nearest neighbors (_train_av3nearest).
"""
# Impute any missing valuesi
if data:
averageImputer = orange.ImputerConstructor_average(data)
data = averageImputer(data)
#If Class is continuous and all class values are unknown (and they usually are in ex to predict), the imputer cannot be created.
# Since we are only using attributes, not the class, we will assign 0 to the class values in order to impute the testData
if testData.domain.classVar and testData.domain.classVar.varType == orange.VarTypes.Continuous:
for ex in testData:
if ex.getclass().isSpecial():
ex.setclass(0)
# This can also happens when calculating a single example with missing attributes
try:
averageImputer = orange.ImputerConstructor_average(testData)
except:
for ex in testData:
for attr in [
a for a in testData.domain.attributes
if a.varType == orange.VarTypes.Continuous
]:
if ex[attr].isSpecial():
ex[attr] = 0
averageImputer = orange.ImputerConstructor_average(testData)
testData = averageImputer(testData)
#Test if there is any non-numeric value within the dataset
for ex in testData:
#It is much faster to address the ex elements by their position instead of the correpondent name
for idx in range(len(ex.domain.attributes)):
if not miscUtilities.isNumber(ex[idx].value):
raise Exception("Cannot calculate Mahalanobis distances. The attribute '" + \
ex.domain.attributes[idx].name + "' has non-numeric values. Ex: " + \
str(ex[idx].value))
if data:
trainingSet = getTrainingSet(data)
trainingset_descriptor_names = trainingSet.descr_names
else:
trainingSet = None
trainingset_descriptor_names = [
attr.name for attr in domain.attributes
]
mahalanobisCalculator = Mahalanobis.MahalanobisDistanceCalculator(
trainingSet, invCovMatFile, centerFile, dataTableFile)
MDlist = []
for ex in testData:
# Create a numeric vector from the example and assure the same order as in trainingset_descriptor_names
descriptor_values = []
for name in trainingset_descriptor_names:
try:
descriptor_values.append(float(ex[name].value))
except:
raise Exception(
"Not possible to calculate Mahalanobis distances. Some attribute is not numeric."
)
#descriptor_values = [1.5] * len(trainingset_descriptor_names)
MD = mahalanobisCalculator.calculateDistances(descriptor_values, nNN)
MDlist.append(MD)
return MDlist
def updateParametersFromTable(self):
"""Updates the parameters of the optimizer with the ones present on GUI table
Returns True if all OK
Returns False if Errors occurred
"""
#self.paramsNames: ["Name","Optimize","Lower Limit","Upper Limit","Distribution","Step","Default"]
#self.comboDistItems: ["Continuous","Power2","By Step","Specific Values"]
if self.paramsTable.columnCount() < 7:
self.setErrors("Wrong number of columns in table!")
return False
RangePars, distType = [None, None]
self.nParameters = len(self.parameters)
for row in range(self.paramsTable.rowCount()):
for col in range(7):
if col == 0: #Name
name = str(self.paramsTable.item(row, col).text()).strip()
RangePars, distType = self.getRangeParsAndDistType(
self.originalParameters, name)
if RangePars == None or distType == None:
self.setErrors(
"It was not possible to identify the range parameters"
)
return False
elif col == 1: #Optimize
if self.paramsTable.cellWidget(row, col).checkState() == 2:
optimize = True
else:
optimize = False
self.nParameters -= 1
elif col == 2: #Lower Limit
Llimit = str(self.paramsTable.item(row,
col).text()).strip()
elif col == 3: #Upper Limit
Ulimit = str(self.paramsTable.item(row,
col).text()).strip()
elif col == 4: #Distribution
if "Combo" in str(
type(self.paramsTable.cellWidget(row, col))):
dist = str(
self.paramsTable.cellWidget(row,
col).currentIndex())
else:
dist = self.comboDistItems.index(
self.paramsTable.item(row, col).text())
elif col == 5: #Step
step = str(self.paramsTable.item(row, col).text()).strip()
elif col == 6: #Default
if "Combo" in str(
type(self.paramsTable.cellWidget(row, col))):
default = self.paramsTable.cellWidget(
row, col).currentIndex()
if len(
self.parameters[name][3]
) <= default: #the parameter did not have an alias, the text is the value
default = str(
self.paramsTable.cellWidget(
row, col).currentText()).strip()
else:
default = RangePars[default]
else: #is string
default = str(self.paramsTable.item(
row, col).text()).strip()
#['types.StringType', 'values', "['kernel' , 'pls1' , 'simpls']", ['Kernel', 'PLS1', 'SimPLS'], "'simpls'", True, False]
if optimize:
self.parameters[name][5] = True
if "Combo" in str(type(self.paramsTable.cellWidget(row, 4))):
comboDistType = self.paramsTable.cellWidget(
row, 4).currentIndex()
else:
comboDistType = self.comboDistItems.index(
self.paramsTable.item(row, 4).text())
if comboDistType == 0: #Continuous
if not miscUtilities.isNumber(Llimit):
if "N_EX" not in Llimit and "N_ATTR" not in Llimit:
QMessageBox.warning(
self, "Invalid parameter", "Parameter " +
name + " has invalid Lower limit",
QMessageBox.Ok)
return False
if not miscUtilities.isNumber(Ulimit):
if "N_EX" not in Ulimit and "N_ATTR" not in Ulimit:
QMessageBox.warning(
self, "Invalid parameter", "Parameter " +
name + " has invalid Upper limit",
QMessageBox.Ok)
return False
self.parameters[name][1] = "interval"
self.parameters[name][
2] = "[" + Llimit + " , " + Ulimit + "]"
self.parameters[name][3] = ""
self.parameters[name][4] = default
elif comboDistType == 1: #Power2
if not miscUtilities.isNumber(Llimit):
if "N_EX" not in Llimit and "N_ATTR" not in Llimit:
QMessageBox.warning(
self, "Invalid parameter", "Parameter " +
name + " has invalid Lower limit",
QMessageBox.Ok)
return False
if not miscUtilities.isNumber(Ulimit):
if "N_EX" not in Ulimit and "N_ATTR" not in Ulimit:
QMessageBox.warning(
self, "Invalid parameter", "Parameter " +
name + " has invalid Upper limit",
QMessageBox.Ok)
return False
if not miscUtilities.isNumber(step):
QMessageBox.warning(
self, "Invalid parameter",
"Parameter " + name + " has an invalid step value",
QMessageBox.Ok)
return False
self.parameters[name][1] = "values"
self.parameters[name][
2] = "miscUtilities.power2Range(" + Llimit + "," + Ulimit + "," + step + ")"
self.parameters[name][3] = ""
self.parameters[name][4] = default
elif comboDistType == 2: #By Step
if not miscUtilities.isNumber(Llimit):
if "N_EX" not in Llimit and "N_ATTR" not in Llimit:
QMessageBox.warning(
self, "Invalid parameter", "Parameter " +
name + " has invalid Lower limit",
QMessageBox.Ok)
return False
if not miscUtilities.isNumber(Ulimit):
if "N_EX" not in Ulimit and "N_ATTR" not in Ulimit:
QMessageBox.warning(
self, "Invalid parameter", "Parameter " +
name + " has invalid Upper limit",
QMessageBox.Ok)
return False
if not miscUtilities.isNumber(step):
QMessageBox.warning(
self, "Invalid parameter",
"Parameter " + name + " has an invalid step value",
QMessageBox.Ok)
return False
self.parameters[name][1] = "values"
self.parameters[name][
2] = "miscUtilities.Range(" + Llimit + "," + Ulimit + "," + step + ")"
self.parameters[name][3] = ""
self.parameters[name][4] = default
else: #Specific Values
#The 'Specific Values' refere to the parameters specified in the original AZLearnersParamsConfig.py file
self.parameters[name][1] = self.originalParameters[name][1]
self.parameters[name][2] = self.originalParameters[name][2]
self.parameters[name][3] = self.originalParameters[name][3]
self.parameters[name][4] = default
else:
self.parameters[name][5] = False
#self.parameters[name][1]='values'
if "Combo" in str(type(self.paramsTable.cellWidget(row, 6))):
default = self.paramsTable.cellWidget(row,
6).currentIndex()
if len(
RangePars
) <= default: #the parameter did not have an alias, the text is the value
#self.parameters[name][2]='[' + str(self.paramsTable.cellWidget(row,6).currentText()).strip() + ']'
self.parameters[name][4] = str(
self.paramsTable.cellWidget(
row, 6).currentText()).strip()
else:
#self.parameters[name][2]='[' + RangePars[default] + ']'
self.parameters[name][4] = RangePars[default]
else: #is string
#self.parameters[name][2]='[' + str(self.paramsTable.item(row,6).text()).strip() + ']'
self.parameters[name][4] = str(
self.paramsTable.item(row, 6).text()).strip()
return True
def getExamplesAndSetTrainBias(self, data, testAttrFilter, testFilterVal):
"""
Collects and returns the examples that match the filterValue at the Attr defined
The remaining examples (that do not match the filterValue at the Attr defined) are
placed in the trainBias to be added in all train events.
"""
self.trainBias = None
if testAttrFilter is not None and testFilterVal is not None and testAttrFilter in data.domain:
if type(testFilterVal) != list:
raise Exception("Invalid Attr filter value. It must be a list of strings")
else:
allDataEx = len(data)
examples = orange.ExampleTable(data.domain)
self.trainBias = orange.ExampleTable(data.domain)
for ex in data:
inExamples = False
for Vfilter in testFilterVal:
if ex[testAttrFilter].value == Vfilter:
examples.append(ex)
inExamples = True
break
if not inExamples:
self.trainBias.append(ex)
print "INFO: Variable control validation:"
print " Examples in data: "+str(allDataEx)
print " Examples selected for validation: "+str(len(examples))
print " Examples to be appended to the train set: "+str(len(self.trainBias))
examples = dataUtilities.attributeDeselectionData(examples, [testAttrFilter])
elif testAttrFilter is not None and testFilterVal is None and testAttrFilter in data.domain:
#Enable pre-selected-indices
self.fixedIdx = orange.LongList()
allDataEx = len(data)
examples = orange.ExampleTable(data.domain)
self.trainBias = orange.ExampleTable(data.domain)
foldsCounter = {}
for ex in data:
value = str(ex[testAttrFilter].value)
if not miscUtilities.isNumber(value):
raise Exception("Invalid fold value:"+str(value)+". It must be str convertable to an int.")
value = int(float(value))
if value not in foldsCounter:
foldsCounter[value] = 1
else:
foldsCounter[value] += 1
if not miscUtilities.isNumber:
raise Exception("Invalid fold value:"+str(value)+". It must be str convertable to an int.")
if value != 0:
examples.append(ex)
self.fixedIdx.append(value - 1)
else:
self.trainBias.append(ex)
print "INFO: Pre-selected "+str(len([f for f in foldsCounter if f != 0]))+" folds for CV:"
print " Examples in data: "+str(allDataEx)
print " Examples selected for validation: "+str(len(examples))
print " Examples to be appended to the train set: "+str(len(self.trainBias))
examples = dataUtilities.attributeDeselectionData(examples, [testAttrFilter])
else:
examples = data
return examples
def getNearestNeighbors(query, n, NNDataPath, FPPath = None, resPath = None, idx = 0):
""" get the n nearest neighbors
query: bin string with query fingerprint
returns an ordered list with the n top neighbors (each one in a dict):
[ {
"id" : ID,
"expVal" : ExpValues,
"similarity" : TanimotoSimilarity,
"smi" : smiles,
"imgPath" : imgPath,
"MeanInhib" : Mean Inhib. }, ... ]
It will saves the images in resPath:
NN_1.png #1 neighbor
NN_2.png #2 neighbor
...
NN_n.png #n neighbor
"""
if not query or not n or not NNDataPath or not FPPath:
return []
#if resPath and not os.path.isdir(resPath):
# os.makedirs(resPath)
# get the correct header
file = open(NNDataPath,"r")
header = file.readline().strip().split('\t')
file.close()
if "Molecule SMILES" not in header or "Compound Name" not in header:
print "NN dataset ",NNDataPath, " have not the correct header. It must contain 'Molecule SMILES' and 'Compound Name' attributes."
return []
# Index will have to be sum 1 because the TS will be prepended
idxID = header.index("Compound Name") + 1
idxExpVal = len(header)
idxSMILES = header.index("Molecule SMILES") + 1
idxSimilarity = 0
Nbits = 2048
cmdStr = 'echo "' + query + '" | fpin ' + FPPath + " " +NNDataPath + ' 0.0 '+str(n)
status,output = commands.getstatusoutput(cmdStr)
if status:
print status
print output
raise Exception(str(output))
# TS SMILES AZID DATE expRes
# output = "0.7117 CCCC(C)C1(C(=O)NC(=O)NC1=O)CC AZ10046012 2009-12-02 3.480007"
TS=[]
for ts in output.split("\n"):
TS.append(ts.strip().split('\t'))
# in TS:
# TS[n][0] - tanimoto similarity
# TS[n][1] - SMILES
# TS[n][2] - AZID
# TS[n][-1]- expRes
res = []
timeStamp=str(time.time()).replace(".",'')
for fidx,nn in enumerate(TS):
ID= nn[idxID]
if miscUtilities.isNumber(nn[idxExpVal]):
expVal = str(round(float(nn[idxExpVal]),2))
else:
expVal = nn[idxExpVal]
SMILES = nn[idxSMILES]
if resPath and os.path.isdir(resPath):
imgPath = os.path.join(resPath,"NN"+str(idx)+"_"+str(fidx+1)+"_"+timeStamp+".png")
mol = Chem.MolFromSmiles(SMILES)
# save the respective imgPath...
Draw.MolToImageFile(mol,imgPath,size=(300, 300), kekulize=True, wedgeBonds=True)
else:
imgPath = ""
res.append( {
"id": ID,
"expVal": expVal,
"similarity": nn[idxSimilarity],
"smi": SMILES,
"imgPath": imgPath,
"MeanInhib": ''} )
return res
def __init__(self, **kwds):
self.verbose = 0
self.logFile = None
self.resultsFile = None
self.nExtFolds = 5
self.nInnerFolds = 5
self.data = None
self.learner = None
self.paramList = None
self.queueType = "NoSGE"
self.responseType = None
self.fixedParams = {}
self.testAttrFilter = None
self.testFilterVal = None
self.sampler = dataUtilities.SeedDataSampler
# Append arguments to the __dict__ member variable
self.__dict__.update(kwds)
self.learnerName = ""
self.preDefIndices = orange.LongList()
self.usePreDefFolds = False
self.useVarCtrlCV = False
if self.testAttrFilter and self.testAttrFilter in self.data.domain:
if self.testFilterVal and type(
self.testFilterVal) == list and type(
self.testAttrFilter) == str:
self.useVarCtrlCV = True
self.usePreDefFolds = False
for ex in self.data:
if ex[self.
testAttrFilter].value in self.testFilterVal: # Compound selected to be allowed in the test set
self.preDefIndices.append(1)
else: # Compound to not include in the test set. Always to be shifted to the train
self.preDefIndices.append(0)
elif self.testFilterVal is None:
self.usePreDefFolds = True
self.useVarCtrlCV = False
#Enable pre-selected-indices ( index 0 will be set for train Bias)
foldsCounter = {}
for ex in self.data:
value = str(ex[self.testAttrFilter].value)
if not miscUtilities.isNumber(value):
self.__log("Invalid fold value:" + str(value) +
". It must be str convertable to an int.")
return False
value = int(float(value))
if value not in foldsCounter:
foldsCounter[value] = 1
else:
foldsCounter[value] += 1
self.preDefIndices.append(value)
self.__log("INFO: Pre-selected " +
str(len([f
for f in foldsCounter.keys() if f != 0])) +
" folds for CV:")
self.__log(" Examples in data: " +
str(sum(foldsCounter.values())))
self.__log(
" Examples selected for validation: " +
str(sum([foldsCounter[f]
for f in foldsCounter if f != 0])))
self.__log(
" Examples to be appended to the train set: " +
str(0 in foldsCounter.keys() and foldsCounter[0] or 0))
else:
self.__log(
"ERROR: Attribute Filter Ctrl was selected, but attribute is not in expected format: "
+ str(self.testAttrFilter))
return False
self.data = dataUtilities.attributeDeselectionData(
self.data, [self.testAttrFilter])
else:
self.usePreDefFolds = False
self.useVarCtrlCV = False
self.testAttrFilter = None
self.testFilterVal = None
