def loadLabel (self, filename, verbose=True):
''' Get the solution/truth values'''
if verbose: print("========= Reading " + filename)
start = time.time()
if self.use_pickle and os.path.exists (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle")):
with open (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"), "r") as pickle_file:
vprint (verbose, "Loading pickle file : " + os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"))
return pickle.load(pickle_file)
if 'task' not in self.info.keys():
self.getTypeProblem(filename)
# IG: Here change to accommodate the new multiclass label format
if self.info['task'] == 'multilabel.classification':
label = data_io.data(filename)
elif self.info['task'] == 'multiclass.classification':
label = data_converter.convert_to_num(data_io.data(filename))
else:
label = np.ravel(data_io.data(filename)) # get a column vector
#label = np.array([np.ravel(data_io.data(filename))]).transpose() # get a column vector
if self.use_pickle:
with open (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"), "wb") as pickle_file:
vprint (verbose, "Saving pickle file : " + os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"))
p = pickle.Pickler(pickle_file)
p.fast = True
p.dump(label)
end = time.time()
if verbose: print( "[+] Success in %5.2f sec" % (end - start))
return label
def loadLabel (self, filename, verbose=True):
''' Get the solution/truth values'''
if verbose: print("========= Reading " + filename)
start = time.time()
if self.use_pickle and os.path.exists (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle")):
with open (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"), "r") as pickle_file:
vprint (verbose, "Loading pickle file : " + os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"))
return pickle.load(pickle_file)
if 'task' not in self.info.keys():
self.getTypeProblem(filename)
# IG: Here change to accommodate the new multiclass label format
if self.info['task'] == 'multilabel.classification':
label = data_io.data(filename)
elif self.info['task'] == 'multiclass.classification':
label = data_converter.convert_to_num(data_io.data(filename))
else:
label = np.ravel(data_io.data(filename)) # get a column vector
#label = np.array([np.ravel(data_io.data(filename))]).transpose() # get a column vector
if self.use_pickle:
with open (os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"), "wb") as pickle_file:
vprint (verbose, "Saving pickle file : " + os.path.join (self.tmp_dir, os.path.basename(filename) + ".pickle"))
p = pickle.Pickler(pickle_file)
p.fast = True
p.dump(label)
end = time.time()
if verbose: print( "[+] Success in %5.2f sec" % (end - start))
return label
basename = 'Iris'
D = DataManager(basename, input_dir) # Load data
print D
mymodel = model()
# Train
Yonehot_tr = D.data['Y_train']
# Attention pour les utilisateurs de problemes multiclasse,
# mettre convert_to_num DANS la methode fit car l'ingestion program
# fournit Yonehot_tr a la methode "fit"
# Ceux qui resolvent des problemes a 2 classes ou des problemes de
# regression n'en ont pas besoin
Ytrue_tr = convert_to_num(
Yonehot_tr,
verbose=False) # For multi-class only, to be compatible with scikit-learn
mymodel = mymodel.fit(D.data['X_train'], Ytrue_tr)
# Making predictions
Ypred_tr = mymodel.predict(D.data['X_train'])
Ypred_va = mymodel.predict(D.data['X_valid'])
Ypred_te = mymodel.predict(D.data['X_test'])
# We can compute the training success rate
acc_tr = accuracy_score(Ytrue_tr, Ypred_tr)
# But it might be optimistic compared to the validation and test accuracy
# that we cannot compute (except by making submissions to Codalab)
# So, we can use cross-validation:
acc_cv = cross_val_score(mymodel,
D.data['X_train'],