def cobraModelInit(trainNames, noiseType, imShape, patchSize=1, best=True):
"""
Initalise and train cobra mode
"""
print("Making training data ready")
trainingData, trainingData1, trainingData2, testingData = loadTrainingData(
trainNames, noiseType, patchSize)
denoisemethods = denoiseMethods()
epsilon = 0.2
machines = 3
cobra = Cobra(epsilon=epsilon, machines=machines)
print("Training model")
cobra.fit(trainingData, testingData)
for i, denoise in enumerate(denoisemethods):
cobra.load_machine(denoise, CobraMachine(denoise, patchSize))
cobra.load_machine_predictions()
# print("Predictions:", cobra.machine_predictions_)
if best:
print("Running Diagnostics")
cobra_diagnostics = Diagnostics(cobra,
trainingData,
testingData,
load_MSE=False)
print("epsilon")
epsilon, _ = cobra_diagnostics.optimal_epsilon(trainingData,
testingData,
line_points=100,
info=False)
print("machines")
machines, _ = cobra_diagnostics.optimal_alpha(trainingData,
testingData,
epsilon=epsilon,
info=False)
cobra = Cobra(epsilon=epsilon, machines=machines)
print("fit")
cobra.fit(trainingData,
testingData,
default=False,
X_k=trainingData1,
X_l=trainingData2,
y_k=testingData,
y_l=testingData)
for i, denoise in enumerate(denoisemethods):
cobra.load_machine(denoise, CobraMachine(denoise, patchSize))
cobra.load_machine_predictions()
# print("Predictions:", cobra.machine_predictions_)
return cobra, machines, epsilon
def define_cobra_model(train_names,
training_noise_kind,
patch_size=1,
optimi=True,
verbose=False):
"""
Train a cobra model for denoising task
INPUT :
train_names : list containing the name of images used to train the model
patch_size : use patch of size (2*patch_size+1)*(2*patch_size+1) as features
verbose : print or not information during the training
OUTPUT :
cobra : trained model
"""
#initial cobra parameters
Alpha = 4 #how many machines must agree
Epsilon = 0.2 # confidence parameter
print("Training cobra model...")
Xtrain, Xtrain1, Xtrain2, Ytrain = load_training_data(
train_names, training_noise_kind, patch_size)
cobra = Cobra(epsilon=Epsilon, machines=Alpha) # create a cobra machine
#cobra.fit(Xtrain, Ytrain, default=False, X_k=Xtrain1, X_l=Xtrain2, y_k=Ytrain, y_l=Ytrain) # fit the cobra machine with our data
cobra.fit(Xtrain, Ytrain) # fit the cobra machine with our data
print("Loading machines...")
cobra.load_machine('bilateral', machine('bilateral', 0, patch_size))
cobra.load_machine('nlmeans', machine('nlmeans', 1, patch_size))
cobra.load_machine('gauss', machine('gauss', 2, patch_size))
cobra.load_machine('median', machine('median', 3, patch_size))
cobra.load_machine('TVchambolle', machine('TVchambolle', 4, patch_size))
cobra.load_machine('richardson_lucy',
machine('richardson_lucy', 5, patch_size))
cobra.load_machine('inpainting', machine('inpainting', 6, patch_size))
cobra.load_machine('ksvd', machine('ksvd', 7, patch_size))
cobra.load_machine('lee', machine('lee', 8, patch_size))
# cobra.load_machine('bm3d', machine('bm3d', 9, patch_size))
print("Loading machine predictions...")
cobra.load_machine_predictions() #agregate
if verbose:
print(cobra.machine_predictions_)
if optimi:
print("Parameter optimisation")
cobra_diagnostics = Diagnostics(cobra, Xtrain, Ytrain)
Epsilon_opt, MSE = cobra_diagnostics.optimal_epsilon(Xtrain,
Ytrain,
line_points=100,
info=False)
Alpha_opt, MSE = cobra_diagnostics.optimal_alpha(Xtrain,
Ytrain,
epsilon=Epsilon_opt,
info=False)
if verbose:
print("epsilon = ", Epsilon_opt)
print("alpha = ", Alpha_opt)
print("Training cobra model again...")
cobra = Cobra(epsilon=Epsilon_opt, machines=Alpha_opt)
cobra.fit(Xtrain,
Ytrain,
default=False,
X_k=Xtrain1,
X_l=Xtrain2,
y_k=Ytrain,
y_l=Ytrain)
cobra.load_machine('bilateral', machine('bilateral', 0, patch_size))
cobra.load_machine('nlmeans', machine('nlmeans', 1, patch_size))
cobra.load_machine('gauss', machine('gauss', 2, patch_size))
cobra.load_machine('median', machine('median', 3, patch_size))
cobra.load_machine('TVchambolle', machine('TVchambolle', 4,
patch_size))
cobra.load_machine('richardson_lucy',
machine('richardson_lucy', 5, patch_size))
cobra.load_machine('inpainting', machine('inpainting', 6, patch_size))
cobra.load_machine('ksvd', machine('ksvd', 7, patch_size))
cobra.load_machine('lee', machine('lee', 8, patch_size))
# cobra.load_machine('bm3d', machine('bm3d', 9, patch_size))
cobra.load_machine_predictions()
if verbose:
print("Loading machine predictions...")
print(cobra.machine_predictions_)
return (cobra, Alpha, Epsilon)
def boxplot(self, reps=100, info=False):
"""
Plots boxplots of machines.
Parameters
----------
reps: int, optional
Number of times to repeat experiments for boxplot.
info: boolean, optional
Returns data
"""
if type(self.aggregate) is Cobra:
MSE = {k: [] for k, v in self.aggregate.machines_.items()}
MSE["COBRA"] = []
for i in range(0, reps):
cobra = Cobra(random_state=self.random_state, epsilon=self.aggregate.epsilon)
X, y = shuffle(self.aggregate.X_, self.aggregate.y_, random_state=self.aggregate.random_state)
cobra.fit(X, y, default=False)
cobra.split_data(shuffle_data=True)
for machine in self.aggregate.machines_:
self.aggregate.machines_[machine].fit(cobra.X_k_, cobra.y_k_)
cobra.load_machine(machine, self.aggregate.machines_[machine])
cobra.load_machine_predictions()
X_test, y_test = shuffle(self.X_test, self.y_test, random_state=self.aggregate.random_state)
for machine in cobra.machines_:
MSE[machine].append(mean_squared_error(y_test, cobra.machines_[machine].predict(X_test)))
MSE["COBRA"].append(mean_squared_error(y_test, cobra.predict(X_test)))
data, labels = [], []
for machine in MSE:
data.append(MSE[machine])
labels.append(machine)
if type(self.aggregate) is Ewa:
MSE = {k: [] for k, v in self.aggregate.machines_.items()}
MSE["EWA"] = []
for i in range(0, reps):
ewa = Ewa(random_state=self.random_state, beta=self.aggregate.beta)
X, y = shuffle(self.aggregate.X_, self.aggregate.y_, random_state=self.aggregate.random_state)
ewa.fit(X, y, default=False)
ewa.split_data(shuffle_data=True)
for machine in self.aggregate.machines_:
self.aggregate.machines_[machine].fit(ewa.X_k_, ewa.y_k_)
ewa.load_machine(machine, self.aggregate.machines_[machine])
ewa.load_machine_weights(self.aggregate.beta)
X_test, y_test = shuffle(self.X_test, self.y_test, random_state=self.aggregate.random_state)
for machine in ewa.machines_:
MSE[machine].append(mean_squared_error(y_test, ewa.machines_[machine].predict(X_test)))
MSE["EWA"].append(mean_squared_error(y_test, ewa.predict(X_test)))
data, labels = [], []
for machine in MSE:
data.append(MSE[machine])
labels.append(machine)
if type(self.aggregate) is ClassifierCobra:
errors = {k: [] for k, v in self.aggregate.machines_.items()}
errors["ClassifierCobra"] = []
for i in range(0, reps):
cc = ClassifierCobra(random_state=self.random_state)
X, y = shuffle(self.aggregate.X_, self.aggregate.y_, random_state=self.aggregate.random_state)
cc.fit(X, y, default=False)
cc.split_data(shuffle_data=True)
for machine in self.aggregate.machines_:
self.aggregate.machines_[machine].fit(cc.X_k_, cc.y_k_)
cc.load_machine(machine, self.aggregate.machines_[machine])
cc.load_machine_predictions()
X_test, y_test = shuffle(self.X_test, self.y_test, random_state=self.aggregate.random_state)
for machine in cc.machines_:
errors[machine].append(1 - accuracy_score(y_test, cc.machines_[machine].predict(X_test)))
errors["ClassifierCobra"].append(1 - accuracy_score(y_test, cc.predict(X_test)))
data, labels = [], []
for machine in errors:
data.append(errors[machine])
labels.append(machine)
plt.figure(figsize=(self.plot_size, self.plot_size))
plt.boxplot(data, labels=labels)
plt.show()
if info:
return data
def boxplot(self, reps=100, info=False, dataframe=None, kind="normal"):
"""
Plots boxplots of machines.
Parameters
----------
reps: int, optional
Number of times to repeat experiments for boxplot.
info: boolean, optional
Returns data
"""
kwargs = self.kwargs
if dataframe is None:
if type(self.aggregate) is Cobra:
MSE = {k: [] for k, v in self.estimators.items()}
MSE["Cobra"] = []
for i in range(0, reps):
cobra = Cobra(epsilon=self.aggregate.epsilon)
X, y = shuffle(self.aggregate.X_, self.aggregate.y_)
cobra.fit(X, y, default=False)
cobra.split_data(shuffle_data=True)
for machine in self.aggregate.estimators_:
self.aggregate.estimators_[machine].fit(cobra.X_k_, cobra.y_k_)
cobra.load_machine(machine, self.aggregate.estimators_[machine])
cobra.load_machine_predictions()
for machine in self.estimators:
if "Cobra" in machine:
self.estimators[machine].fit(X, y)
else:
self.estimators[machine].fit(cobra.X_k_, cobra.y_k_)
try:
if type(self.estimators[machine]) == KernelCobra:
preds = self.estimators[machine].predict(self.X_test, bandwidth=kwargs["bandwidth_kernel"])
else:
preds = self.estimators[machine].predict(self.X_test)
except KeyError:
preds = self.estimators[machine].predict(self.X_test)
MSE[machine].append(mean_squared_error(self.y_test, preds))
MSE["Cobra"].append(mean_squared_error(self.y_test, cobra.predict(self.X_test)))
try:
dataframe = pd.DataFrame(data=MSE)
except ValueError:
return MSE
if type(self.aggregate) is KernelCobra:
MSE = {k: [] for k, v in self.estimators.items()}
MSE["KernalCobra"] = []
for i in range(0, reps):
kernel = KernelCobra()
X, y = shuffle(self.aggregate.X_, self.aggregate.y_)
kernel.fit(X, y, default=False)
kernel.split_data(shuffle_data=True)
for machine in self.aggregate.estimators_:
self.aggregate.estimators_[machine].fit(kernel.X_k_, kernel.y_k_)
kernel.load_machine(machine, self.aggregate.estimators_[machine])
kernel.load_machine_predictions()
for machine in self.estimators:
if "Cobra" in machine:
self.estimators[machine].fit(X, y)
else:
self.estimators[machine].fit(cobra.X_k_, cobra.y_k_)
try:
if type(self.estimators[machine]) == KernelCobra:
preds = self.estimators[machine].predict(self.X_test, bandwidth=kwargs["bandwidth_kernel"])
else:
preds = self.estimators[machine].predict(self.X_test)
except KeyError:
preds = self.estimators[machine].predict(self.X_test)
MSE[machine].append(mean_squared_error(self.y_test, preds))
MSE["KernelCobra"].append(mean_squared_error(self.y_test, kernel.predict(self.X_test, bandwidth=kwargs[bandwidth_kernel])))
try:
dataframe = pd.DataFrame(data=MSE)
except ValueError:
return MSE
if type(self.aggregate) is Ewa:
MSE = {k: [] for k, v in self.aggregate.estimators_.items()}
MSE["EWA"] = []
for i in range(0, reps):
ewa = Ewa(random_state=self.random_state, beta=self.aggregate.beta)
X, y = shuffle(self.aggregate.X_, self.aggregate.y_, random_state=self.aggregate.random_state)
ewa.fit(X, y, default=False)
ewa.split_data(shuffle_data=True)
for machine in self.estimators:
self.aggregate.estimators_[machine].fit(ewa.X_k_, ewa.y_k_)
ewa.load_machine(machine, self.aggregate.estimators_[machine])
ewa.load_machine_weights(self.aggregate.beta)
X_test, y_test = shuffle(self.X_test, self.y_test, random_state=self.aggregate.random_state)
for machine in self.estimators:
if "EWA" in machine:
self.estimators[machine].fit(X, y)
else:
self.estimators[machine].fit(ewa.X_k_, ewa.y_k_)
try:
if type(self.estimators[machine]) == KernelCobra:
preds = self.estimators[machine].predict(self.X_test, bandwidth=kwargs["bandwidth_kernel"])
else:
preds = self.estimators[machine].predict(self.X_test)
except KeyError:
preds = self.estimators[machine].predict(self.X_test)
MSE[machine].append(mean_squared_error(y_test, preds))
MSE["EWA"].append(mean_squared_error(y_test, ewa.predict(X_test)))
try:
dataframe = pd.DataFrame(data=MSE)
except ValueError:
return MSE
if type(self.aggregate) is ClassifierCobra:
errors = {k: [] for k, v in self.aggregate.estimators_.items()}
errors["ClassifierCobra"] = []
for i in range(0, reps):
cc = ClassifierCobra(random_state=self.random_state)
X, y = shuffle(self.aggregate.X_, self.aggregate.y_, random_state=self.aggregate.random_state)
cc.fit(X, y, default=False)
cc.split_data(shuffle_data=True)
for machine in self.aggregate.estimators_:
self.aggregate.estimators_[machine].fit(cc.X_k_, cc.y_k_)
cc.load_machine(machine, self.aggregate.estimators_[machine])
cc.load_machine_predictions()
X_test, y_test = shuffle(self.X_test, self.y_test, random_state=self.aggregate.random_state)
for machine in self.estimators:
errors[machine].append(1 - accuracy_score(y_test, self.estimators[machine].predict(X_test)))
errors["ClassifierCobra"].append(1 - accuracy_score(y_test, cc.predict(X_test)))
try:
dataframe = pd.DataFrame(data=errors)
except ValueError:
return errors
# code for different boxplot styles using the python graph gallery tutorial:
# https://python-graph-gallery.com/39-hidden-data-under-boxplot/
sns.set(style="whitegrid")
if kind == "normal":
sns.boxplot(data=dataframe)
plt.title("Boxplot")
if kind == "violin":
sns.violinplot(data=dataframe)
plt.title("Violin Plot")
if kind == "jitterplot":
ax = sns.boxplot(data=dataframe)
ax = sns.stripplot(data=dataframe, color="orange", jitter=0.2, size=2.5)
plt.title("Boxplot with jitter", loc="left")
plt.ylabel("Mean Squared Errors")
plt.xlabel("Estimators")
plt.figure(figsize=(self.plot_size, self.plot_size))
plt.show()
if info:
return dataframe