def train(self,
X,
T,
nIterations=100,
verbose=False,
weightPrecision=0,
errorPrecision=0,
saveWeightsHistory=False):
if self.Xmeans is None:
self.Xmeans = X.mean(axis=0)
self.Xstds = X.std(axis=0)
self.Xconstant = self.Xstds == 0
self.XstdsFixed = copy(self.Xstds)
self.XstdsFixed[self.Xconstant] = 1
X = self._standardizeX(X)
if T.ndim == 1:
T = T.reshape((-1, 1))
if self.Tmeans is None:
self.Tmeans = T.mean(axis=0)
self.Tstds = T.std(axis=0)
self.Tconstant = self.Tstds == 0
self.TstdsFixed = copy(self.Tstds)
self.TstdsFixed[self.Tconstant] = 1
self.classes = np.unique(T)
Tindicators = ml.makeIndicatorVars(T)
startTime = time.time()
scgresult = ml.scg(self._pack(self.Vs, self.W),
self._objectiveF,
self._gradientF,
X,
Tindicators,
xPrecision=weightPrecision,
fPrecision=errorPrecision,
nIterations=nIterations,
verbose=verbose,
ftracep=True,
xtracep=saveWeightsHistory)
self._unpack(scgresult['x'])
self.reason = scgresult['reason']
self.errorTrace = scgresult[
'ftrace'] # * self.Tstds # to _unstandardize the MSEs
self.numberOfIterations = len(self.errorTrace)
self.trained = True
self.weightsHistory = scgresult[
'xtrace'] if saveWeightsHistory else None
self.trainingTime = time.time() - startTime
return self
def train(self, X, T, nIterations=100, verbose=False):
if self.Xmeans is None:
self.Xmeans = X.mean(axis=0)
self.Xstds = X.std(axis=0)
self.Xconstant = self.Xstds == 0
self.XstdsFixed = copy(self.Xstds)
self.XstdsFixed[self.Xconstant] = 1
X = self._standardizeX(X)
if T.ndim == 1:
T = T.reshape((-1, 1))
if self.Tmeans is None:
self.Tmeans = T.mean(axis=0)
self.Tstds = T.std(axis=0)
self.Tconstant = self.Tstds == 0
self.TstdsFixed = copy(self.Tstds)
self.TstdsFixed[self.Tconstant] = 1
T = self._standardizeT(T)
# Local functions used by scg()
def objectiveF(w):
self._unpack(w)
Y, _ = self._forward_pass(X)
return 0.5 * np.mean((Y - T)**2)
def gradF(w):
self._unpack(w)
Y, Z = self._forward_pass(X)
delta = (Y - T) / (X.shape[0] * T.shape[1])
dVs, dW = self._backward_pass(delta, Z)
return self._pack(dVs, dW)
scgresult = ml.scg(self._pack(self.Vs, self.W),
objectiveF,
gradF,
nIterations=nIterations,
verbose=verbose,
ftracep=True)
self._unpack(scgresult['x'])
self.reason = scgresult['reason']
self.errorTrace = np.sqrt(
scgresult['ftrace']) # * self.Tstds # to unstandardize the MSEs
self.numberOfIterations = len(self.errorTrace)
self.trained = True
return self
def train(self, X, T, nIterations=100, verbose=False):
if self.Xmeans is None:
self.Xmeans = X.mean(axis=0)
self.Xstds = X.std(axis=0)
self.Xconstant = self.Xstds == 0
self.XstdsFixed = copy(self.Xstds)
self.XstdsFixed[self.Xconstant] = 1
X = self._standardizeX(X)
self.classes, counts = np.unique(T, return_counts=True)
self.mostCommonClass = self.classes[np.argmax(counts)] # to break ties
if self.no != len(self.classes):
raise ValueError(
" In NeuralNetworkClassifier, the number of outputs must equal\n the number of classes in the training data. The given number of outputs\n is %d and number of classes is %d. Try changing the number of outputs in the\n call to NeuralNetworkClassifier()."
% (self.no, len(self.classes)))
T = makeIndicatorVars(T)
# Local functions used by gradientDescent.scg()
def objectiveF(w):
self._unpack(w)
Y, _ = self._forward_pass(X)
Y = self._multinomialize(Y)
Y[Y == 0] = sys.float_info.epsilon
return -np.mean(T * np.log(Y))
def gradF(w):
self._unpack(w)
Y, Z = self._forward_pass(X)
Y = self._multinomialize(Y)
delta = (Y - T) / (X.shape[0] * (T.shape[1]))
dVs, dW = self._backward_pass(delta, Z)
return self._pack(dVs, dW)
scgresult = ml.scg(self._pack(self.Vs, self.W),
objectiveF,
gradF,
nIterations=nIterations,
ftracep=True,
verbose=verbose)
self._unpack(scgresult['x'])
self.reason = scgresult['reason']
self.errorTrace = scgresult['ftrace']
self.numberOfIterations = len(self.errorTrace) - 1
self.trained = True
return self
