def create_rand(target_term, split_size, parameter_ranges, nbrTrials,
nbrEpochs, GNN, MD, MBTR):
with open("./hyper/dataset.pic", 'rb') as f:
dataset = pickle.load(f)
for trial in range(nbrTrials):
results = pd.DataFrame()
results = results.astype('object')
#print("trial =", trial)
for p in range(len(parameter_ranges)):
#print("P = ", p)
p1 = parameter_ranges[p][0]
p2 = parameter_ranges[p][1]
#print(p1,p2)
# Ignore the learning rate and randomize the others
if 0 == p:
results.loc[trial, p] = random.uniform(p1, p2)
else:
if p1 == p2:
randValue = p1
else:
randValue = random.randrange(p1, p2 + 1)
#print(randValue)
results.loc[trial, p] = int(randValue)
results[p] = results[p].astype(int)
#print(results)
#print("trial =", trial)
my_list = results.loc[trial:trial,
0:(len(parameter_ranges) - 1)].values.tolist()
my_list = my_list[0]
lr = my_list[0]
my_list = [int(x) for x in my_list]
my_list[0] = lr
train_acc, val_acc = gnn.fit_GNN(1, 0, target_term, dataset,
split_size, nbrEpochs, *my_list, GNN,
MD, MBTR)
results.at[trial, len(parameter_ranges)] = round(val_acc, 5)
print(results.loc[trial:trial, :].to_string(header=False))
# Now store the results
try:
results_old = pd.read_csv(
"../results/%s/hyper_random_results.csv" % target_term,
header=None)
#print("results_old")
#print(results_old)
all_results = pd.concat([results_old, results],
ignore_index=True,
axis=0)
all_results.to_csv("../results/%s/hyper_random_results.csv" %
target_term,
index=False,
header=False)
#subprocess.run(["mv", "./hyper_random/results_temp.csv", "./hyper_random/results.csv"])
except:
results.to_csv("../results/%s/hyper_random_results.csv" %
target_term,
index=False,
header=False)
def run_hyper_parallel(i, j, p, target_term, split_size, nbrEpochs, nbrGrid,
param_best, GNN, MD, MBTR, show):
#print(i, j, p, target_term, dataset, split_size, nbrEpochs, nbrGrid, param_best, MD, show)
with open("./hyper/dataset.pic", 'rb') as f:
dataset = pickle.load(f)
trainLoss, valLoss = gnn.fit_GNN(1, 0, target_term, dataset, split_size,
nbrEpochs, *param_best, GNN, MD, MBTR)
#print("TrainLoss_trial =", trainLoss, "ValidationLoss_trial =", valLoss)
print("param", i, "=", p, "Training loss =", round(trainLoss, 6),
"Validation loss =", round(valLoss, 6))
with open("./hyper/train_loss_%s.pic" % j, 'wb') as filehandle:
pickle.dump(trainLoss, filehandle)
with open("./hyper/val_loss_%s.pic" % j, 'wb') as filehandle:
pickle.dump(valLoss, filehandle)
def getLearningCurve(target_term, df_reduced, dataset, split_size, nbrEpochs, param_best):
df_results = pd.DataFrame(columns = ["training_size", "r2_GNN", "r2_MD", "r2_MDGNN", "MAE_GNN", "MAE_MD", "MAE_MDGNN"])
index = 0
x = 1000
while x<= len(dataset):
end = x
print("Training size =", x)
dataset_part = dataset[:end]
df_results.loc[index,"training_size"] = x
df_part = df_reduced[:end]
# GET RESULTS FOR gnn AND gnn + md
for MD in range(2):
trainData, testData = gnn.fit_GNN(0, 0, target_term, dataset_part, split_size, nbrEpochs, *param_best, MD)
#gnn.plot_results(trainData, testData, target_term, show = 1)
r2 = r2_score(testData["Target"].to_numpy(), testData["Preds"].to_numpy())
MAE = mean_absolute_error(testData["Target"].to_numpy(), testData["Preds"].to_numpy())
if (0 == MD):
print("GNN only: r2 =", r2, "MAE =", MAE)
df_results.loc[index,"r2_GNN"] = r2
df_results.loc[index,"MAE_GNN"] = MAE
trainData.to_csv("../results/%s/learning_size=%s_train_CNN=1_MD=0.csv" % (target_term, x))
testData.to_csv("../results/%s/learning_size=%s_test_CNN=1_MD=0.csv" % (target_term, x))
else:
print("MDGNN: r2 =", r2, "MAE =", MAE)
df_results.loc[index,"r2_MDGNN"] = r2
df_results.loc[index,"MAE_MDGNN"] = MAE
trainData.to_csv("../results/%s/learning_size=%s_train_CNN=1_MD=1.csv" % (target_term, x))
testData.to_csv("../results/%s/learning_size=%s_test_CNN=1_MD=1.csv" % (target_term, x))
# GET RESULTS FOR MD ONLY
trainData, testData, feat_importances = molecularDescriptorsOnly(df_part, split_size, target_term, 0)
r2 = r2_score(testData["Target"].to_numpy(), testData["Preds"].to_numpy())
MAE = mean_absolute_error(testData["Target"].to_numpy(), testData["Preds"].to_numpy())
print("MD only: r2 =", r2, "MAE =", MAE)
print("\n")
df_results.loc[index,"r2_MD"] = r2
df_results.loc[index,"MAE_MD"] = MAE
trainData.to_csv("../results/%s/learning_size=%s_train_CNN=0_MD=1.csv" % (target_term, x))
testData.to_csv("../results/%s/learning_size=%s_test_CNN=0_MD=1.csv" % (target_term, x))
x *= 2
index = index + 1
return(df_results)
def create_rand(parameter_ranges,nbrTrials, run, nbrEpochs):
results = pd.DataFrame()
for trial in range(nbrTrials):
#print("trial =", trial)
list = []
for p in range(len(parameter_ranges)):
#print("P = ", p)
p1 = parameter_ranges[p][0]
p2 = parameter_ranges[p][1]
#print(p1,p2)
randValue = random.randrange(p1, p2)
#print(randValue)
results.loc[trial, p] = int(randValue)
if (1 == run):
print("trial =", trial)
list = results.loc[trial:trial, 0:(len(parameter_ranges)-1)].values.tolist()
#print("list =", list)
array1 = np.asarray(list).flatten().astype(int)
array2 = np.asarray([dataset,0.75, nbrEpochs])
full_array = np.concatenate((array2, array1)).flatten()
#print(full_array)
val_acc = gnn.fit_GNN(0,*full_array)
results.at[trial, len(parameter_ranges)] = val_acc
return(results)
subprocess.run(["mkdir", "hyper"])
with open("./hyper/dataset.pic", 'wb') as filehandle:
pickle.dump(dataset, filehandle, protocol=4)
# RANDOM SEARCH
#hyper_batch_size, target_term, dataset1, split_size, parameter_ranges, nbrTrials, nbrEpochs, MD
param_best, param_best_5 = gnn.fit_hyperParameters_random(
1, target_term, 0.95, param_range, 10, 15, GNN, MD, MBTR)
with open("../results/all_hyperparameters.txt", "a") as file_object:
file_object.write("%s = %s (GNN = %s MD = %s MBTR = %s)\n" %
(target_term, param_best, GNN, MD, MBTR))
######################### FINAL OPTIMIZATION
print("########## ", target_term, " GNN =", GNN, "MD = ", MD, "MBTR =",
MBTR, "#############")
print("Molecular Descriptor used =", MD)
# getloss, verbose, target_term, dataset, split_size, num_epochs, lr, batch_size, p1, p2, numLayer, numFinalFeature, GNN, MD, MBTI
trainData, testData = gnn.fit_GNN(0, 1, target_term, dataset, 0.95,
num_epochs, *param_best, GNN, MD, MBTR)
trainData.to_csv("../results/%s/train_CNN=%s_MD=%s_MBTR=%s.csv" %
(target_term, GNN, MD, MBTR))
testData.to_csv("../results/%s/test_CNN=%s_MD=%s_MBTR=%s.csv" %
(target_term, GNN, MD, MBTR))
trainData = pd.read_csv("../results/%s/train_CNN=%s_MD=%s_MBTR=%s.csv" %
(target_term, GNN, MD, MBTR))
testData = pd.read_csv("../results/%s/test_CNN=%s_MD=%s_MBTR=%s.csv" %
(target_term, GNN, MD, MBTR))
if (1 == show_plots):
for i in range(num_epochs):
gnn.plot_losses(target_term, GNN, MD, MBTR)
time.sleep(30)
gnn.plot_results(trainData, testData, target_term, show=show_plots)
# Now store the final result