#Reading pretrained model
model = read_model(model_num, optimizer, original_models_path)
models_grid.append(model)
#Re-fit and create a new model initialized with pretrained model weights
model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size)
#saving model info with respect to threshold
file_name = "Model_" + str(model_num) + "_" + str(index)
file_path = model_path_pretrained_all
#storng max accuracy possible with this model (for shortlisting)
max_accuracy = plotMetricsWithThreshold(
models_grid[index],
X_test,
y_test,
fig_name=file_name,
fig_path=file_path,
display_info=False,
return_max_metric='accuracy')
max_accuracy_all_grid.append(max_accuracy)
#saving model and model info
saveModelandModelInfo(models_grid[index], file_name, file_path)
#Get top 5 models by max accuracy
max_accuracy_array = np.array(max_accuracy_all_grid)
top_n_by_accuracy = max_accuracy_array.argsort()[-5:][::-1]
#Copy those files in folder "grid_selected" with their rank
for rank_index in range(len(top_n_by_accuracy)):
model_index = top_n_by_accuracy[rank_index]
)
dl_fit1.train(x=x, y=y, training_frame=train)
model_name = "MLP - Feedforward Grid"
#defined_params = str(nn_params1) + ": hidden=[50,20,30,5]"
defined_params = ""
file_name = "NN_1"
training_ratio = 0.65
os.getcwd()
fig_name = file_name + "_plot"
plot_info_1_base = plotMetricsWithThreshold(dl_fit1, test, y_test, fig_name=fig_name, fig_path = None,
precision="majority", recall="minority",
fpoint5score = False, f1score=True, f2score=False, fbetascore=False,
TPR=True, FPR=True, specificity=True,
accuracy=True, misclassification=False,
display_info=True, model_type='h2o')
threshold = 0.3
report_df = report(dl_fit1, test, y , model_path, 4, report_df,
model_name, defined_params, file_name, training_ratio,
threshold=threshold, sampling=None, model_type='basic')
#NN2
dl_fit2 = H2ODeepLearningEstimator(model_id='dl_fit2',
hidden=[30,15],
seed=1,
max_categorical_features=4,
export_weights_and_biases=True,
shuffle_training_data=True,
#run 'no of models' times
filename = filenames[index]
print(filename)
json_file = open(filename + '.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
model = model_from_json(loaded_model_json)
model.load_weights(filename + ".h5")
y_pred = model.predict(X_test)
fig_name = filename + "_plot"
plot_info_one = plotMetricsWithThreshold(model,
X_test,
y_test,
fig_name=fig_name,
fig_path=None,
precision="majority",
recall="minority",
fpoint5score=False,
f1score=True,
f2score=False,
fbetascore=False,
TPR=True,
FPR=True,
specificity=True,
accuracy=True,
misclassification=False,
display_info=True)
model_plot_info.append(plot_info_one)
index += 1
model_name = "CNN"
defined_params = ""
file_name = "CNN_1"
training_ratio = 0.65
num_layers = '1+3'
fig_name = file_name + "_metrics_plot"
#plotting threshold vs metrics
model_1_plot_info = plotMetricsWithThreshold(y_test,
y_pred,
fig_name=fig_name,
fig_path=None,
precision="majority",
recall="minority",
fpoint5score=False,
f1score=True,
f2score=False,
fbetascore=False,
TPR=True,
FPR=True,
specificity=True,
accuracy=True,
misclassification=False,
display_info=True)
#report()
threshold = 0.22
report_df = report(model_1,
X_test,
y_test,
model_path,