def get_assay_control(self):
control_model = modelbank.control_to_yield_model('ridge', 1)
if self.compare_test:
return control_model.model_stats[
'test_avg_loss'], control_model.model_stats['test_std_loss']
else:
return control_model.model_stats[
'cv_avg_loss'], control_model.model_stats['cv_std_loss']
def get_assay_control(self):
## Initally a control_to_yield object is created from the submodels_module.py program,
## with the model architecture of ridge and sample fraction as 1 and saved as control_model
control_model=modelbank.control_to_yield_model('ridge',1)
if self.compare_test:
## If the compare_test class variable is true then a tuple containing the average loss and standard deviation loss of the testing data
## is returned
return control_model.model_stats['test_avg_loss'],control_model.model_stats['test_std_loss']
else:
## Else the average loss and standard deviation loss of the cross validation is returned in the tuple
return control_model.model_stats['cv_avg_loss'],control_model.model_stats['cv_std_loss']
def main():
'''
compare test performances when reducing training sample size. This version is for first paper, predicting yield from assays and one-hot encoded sequence.
'''
a = int(sys.argv[1])
if a < 4:
b = 0
elif a < 8:
a = a - 4
b = 1
elif a < 12:
a = a - 8
b = 2
elif a == 12:
b = 3
a = a - 12
else:
print('incorrect toggle number')
arch_list = ['ridge', 'svm', 'forest', 'fnn']
# size_list=[0.055,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1]
size_list = [0.7, 0.8, 0.9, 1]
for size in size_list:
if b == 0:
mdl = modelbank.seqandassay_to_yield_model([1, 8, 10],
arch_list[a], size)
elif b == 1: #1,5,9,12
mdl = modelbank.assay_to_yield_model([1, 8, 10], arch_list[a],
size)
elif b == 2:
mdl = modelbank.seq_to_yield_model(arch_list[a], size)
elif b == 3:
mdl = modelbank.control_to_yield_model(arch_list[a], size)
for seed in range(9): #no seed is seed=42
mdl.change_sample_seed(seed)
mdl.cross_validate_model()
mdl.limit_test_set([1, 8, 10])
mdl.test_model()
arch, 1)
if mdl.model_stats['cv_avg_loss'] < cv_loss:
cv_loss = mdl.model_stats['cv_avg_loss']
test_loss = mdl.model_stats['test_avg_loss']
test_std = mdl.model_stats['test_std_loss']
loss_per_model.append(test_loss)
std_per_model.append(test_std)
seq_model = modelbank.seq_to_yield_model('forest', 1)
seq_loss = seq_model.model_stats['test_avg_loss']
seq_std = seq_model.model_stats['test_std_loss']
x = [-0.3, 0.8]
seq_plus = [seq_loss + seq_std] * 2
seq_min = [seq_loss - seq_std] * 2
control_model = modelbank.control_to_yield_model('ridge', 1)
control_loss = control_model.model_stats['test_avg_loss']
control_model.limit_test_set([1, 8, 10])
exploded_df, _, _ = load_format_data.explode_yield(control_model.testing_df)
exp_var = np.average(np.square(np.array(exploded_df['y_std'])))
fig, ax = plt.subplots(1, 1, figsize=[2, 2], dpi=300)
xloc = [0, 0.5]
ax.axhline(seq_loss,
-0.5,
4.5,
color='green',
linestyle='--',
label='Sequence Model')
ax.axhline(control_loss,
def main():
'''
compare test performances when reducing training sample size. This version is for first paper, predicting yield from assays and one-hot encoded sequence.
'''
## A command line input is required when running this program. The integer input
## should be between 0-12.
a=int(sys.argv[1])
if a<4:
b=0
## if the input is less than 4 then b value is set to 0
elif a<8:
a=a-4
b=1
## if a is between 4-8 then the b value is set to 1 and a is reduced by 4
elif a<12:
a=a-8
b=2
## if a is between 8-12 then the b value is set to 2 and a is reduced by 8
elif a==12:
b=3
a=a-12
## if a is equal to 12 then the b value is set to 3 and a is set to 0.
else:
print('incorrect toggle number')
## If the inout is out of bounds then an error message is printed.
arch_list=['ridge','svm','forest','fnn']
## A string list is created containing the names of the different regression models and stored as arch_list
# size_list=[0.055,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1]
size_list=[0.7,0.8,0.9,1]
## A float list is created containing varying amounts of sample fractions and stored as size_list
for size in size_list:
## each element in the size_list array, we check the value of the b value created in the above if-else
## statements and this dictates the kind of submodel_module.py object created
## if b = 0, then a seqandassay_to_yield_model object is created with an assay list of [1,8,10]
## a regression model dictated by the 'a' index of the arch_list and the size determined by the iteration of size_list
if b==0:
mdl=modelbank.seqandassay_to_yield_model([1,8,10],arch_list[a],size)
## if b = 1, then a assay_to_yield_model object is created with an assay list of [1,8,10]
## a regression model dictated by the 'a' index of the arch_list and the size determined by the iteration of size_list
elif b==1: #1,5,9,12
mdl=modelbank.assay_to_yield_model([1,8,10],arch_list[a],size)
## if b = 2, then a seq_to_yield_model object is created with a regression model dictated by
## the 'a' index of the arch_list and the size determined by the iteration of size_list
elif b==2:
mdl=modelbank.seq_to_yield_model(arch_list[a],size)
## if b = 3, then a control_to_yield_model object is created with a regression model dictated by
## the 'a' index of the arch_list and the size determined by the iteration of size_list
elif b==3:
mdl=modelbank.control_to_yield_model(arch_list[a],size)
for seed in range(9): #no seed is seed=42
## For each element in the int range [0,9). The sample_seed class int to the element
## Then the trial data, model data and plots are updated to reflect the new sample_seed size
mdl.change_sample_seed(seed)
## Then the best hyperparameters for the given model and seed size is determined using the cross_validate_model()
## function from the model object
mdl.cross_validate_model()
## Following this limit_test_set() function defined in the x_to_yield_model parent class to update the
## testing_df class dataframe to reflect the 1,8,10 assays.
mdl.limit_test_set([1,8,10])
## Finally using the test_model() function from the model parent class is run to
## train the model using the hyperparameters defined above and the training data to predict the testing dataset.
mdl.test_model()
