def Optimization():
scan_object = ta.Scan(x=x_train,
y=y_train,
params=parameters,
model=pet_finder_model,
val_split=0,
experiment_name='pet_finder')
# Evaluate
analyze_object = ta.Analyze(scan_object)
scan_data = analyze_object.data
# heatmap correlation
analyze_object.plot_corr('val_accuracy', ['accuracy', 'loss', 'val_loss'])
# a four dimensional bar grid
ast.bargrid(scan_data,
x='lr',
y='val_accuracy',
hue='num_Nodes',
row='loss_function',
col='dropout')
list_of_parameters = analyze_object.table('val_loss',
['accuracy', 'loss', 'val_loss'],
'val_accuracy')
return list_of_parameters
def test_simple_minimal(df):
ast.corr(df)
ast.kde(data=df, x='A')
ast.hist(df, x='A')
ast.pie(df, x='other')
ast.swarm(df, x='A', y='B', hue='even')
ast.scat(df, x='A', y='B', hue='even')
ast.line(df, x='A')
ast.grid(df, x='A', y='B', col='even')
ast.box(df, x='odd', y='A', hue='even')
ast.violin(df, x='odd', y='A', hue='even')
ast.strip(df, x='odd', y='B', hue='even')
ast.count(df, x='cats')
ast.bargrid(df, x='even', y='B', hue='other', col='odd')
ast.overlap(df, x='A', y='B', label_col='other')
ast.multikde(df, x='A', label_col='even')
ast.compare(df, x='A', y=['B', 'C'], label_col='other')
ast.multicount(df, x='even', hue='odd', col='other')
def bars_full(df):
ast.bargrid(data=df,
x='cats',
y='B',
hue='odd',
row='even',
col='other',
style='astetik',
dpi=72,
title='This is a title',
sub_title='And this a subtitle',
x_label='this is x label',
y_label='and this y',
legend=False,
x_scale='log',
y_scale='symlog',
x_limit=[10, 20],
y_limit=[1, 21])
def plot_bars(self, x, y, hue, col):
'''A comparison plot with 4 axis'''
return bargrid(self.data,
x=x,
y=y,
hue=hue,
col=col,
col_wrap=4)
def plot_bars(self, x, y, hue, col):
'''A comparison plot with 4 axis'''
try:
import astetik as ast
return ast.bargrid(self.data,
x=x,
y=y,
hue=hue,
col=col,
col_wrap=4)
except RuntimeError:
print('Matplotlib Runtime Error. Plots will not work.')
y=y_train,
params=parameters,
model=pet_finder_model,
val_split=0,
experiment_name='pet_finder')
# Evaluate
analyze_object = ta.Analyze(scan_object)
scan_data = analyze_object.data
# heatmap correlation
analyze_object.plot_corr('val_accuracy', ['accuracy', 'loss', 'val_loss'])
# a four dimensional bar grid
ast.bargrid(scan_data,
x='lr',
y='val_accuracy',
hue='num_Nodes',
row='loss_function',
col='dropout')
ast.bargrid(scan_data,
x='lr',
y='val_accuracy',
hue='num_Nodes',
row='final_activation',
col='dropout')
# wrapper = KerasClassifier(build_fn=create_network, epochs=epochs)
# scorer = make_scorer(f1_score, average= 'weighted')
# grid = GridSearchCV(estimator=wrapper,param_grid=parameters,scoring=scorer,iid=False,cv=5,return_train_score=True,verbose=1)
# grid_result = grid.fit(x_train,labels_train)
best_parameters = analyze_object.table('val_loss',