def graph_conv_training():
graph_featurizer = dc.feat.graph_features.ConvMolFeaturizer()
loader = dc.data.data_loader.CSVLoader(tasks=[t_task.get()],
smiles_field=t_smiles.get(),
id_field=t_id.get(),
featurizer=graph_featurizer)
dataset = loader.featurize(t_csv.get())
splitter = dc.splits.splitters.RandomSplitter()
trainset, testset = splitter.train_test_split(dataset)
hp = dc.molnet.preset_hyper_parameters
param = hp.hps['graphconvreg']
print(param)
batch_size = 48
from deepchem.models.tensorgraph.models.graph_models import GraphConvModel
model = GraphConvModel(n_tasks=1,
batch_size=64,
uncertainty=False,
mode='regression')
model = dc.models.GraphConvTensorGraph(1,
batch_size=batch_size,
learning_rate=1e-3,
use_queue=False,
mode='regression',
model_dir=t_savename.get())
np.random.seed(1)
random.seed(1)
model.fit(dataset, nb_epoch=max(1, int(t_epochs.get())))
#model.fit(trainset, nb_epoch=max(1, int(t_epochs.get())))
metric = dc.metrics.Metric(dc.metrics.r2_score)
print('epoch: ', t_epochs.get())
print("Evaluating model")
train_score = model.evaluate(trainset, [metric])
test_score = model.evaluate(testset, [metric])
model.save()
pred_train = model.predict(trainset)
pred_test = model.predict(testset)
y_train = np.array(trainset.y, dtype=np.float32)
y_test = np.array(testset.y, dtype=np.float32)
import matplotlib.pyplot as plt
plt.figure()
plt.figure(figsize=(5, 5))
plt.scatter(y_train, pred_train, label='Train', c='blue')
plt.title('Graph Convolution')
plt.xlabel('Measured value')
plt.ylabel('Predicted value')
plt.scatter(y_test, pred_test, c='lightgreen', label='Test', alpha=0.8)
plt.legend(loc=4)
#plt.show()
plt.savefig('score-tmp.png')
from PIL import Image
img = Image.open('score-tmp.png')
img_resize = img.resize((400, 400), Image.LANCZOS)
img_resize.save('score-tmp.png')
global image_score
image_score_open = Image.open('score-tmp.png')
image_score = ImageTk.PhotoImage(image_score_open, master=frame1)
canvas.create_image(200, 200, image=image_score)
#Calculate R2 score
print("Train score")
print(train_score)
t_train_r2.set(train_score)
print("Test scores")
print(test_score)
t_test_r2.set(test_score)
#Calculate RMSE
train_rmse = 1
test_rmse = 1
'''
print("Train RMSE")
print(train_rmse)
t_train_rmse.set(train_rmse)
print("Test RMSE")
print(test_rmse)
t_test_rmse.set(test_rmse)
'''
df_save = pd.DataFrame({'pred_train': pred_train, 'meas_train': y_train})
df_save.to_csv('pred_and_meas_train.csv')
print('finish!')
# Load Tox21 dataset
tox21_tasks, tox21_datasets, transformers = load_tox21(featurizer='GraphConv')
train_dataset, valid_dataset, test_dataset = tox21_datasets
print(train_dataset.data_dir)
print(valid_dataset.data_dir)
# Fit models
metric = dc.metrics.Metric(dc.metrics.roc_auc_score,
np.mean,
mode="classification")
# Batch size of models
batch_size = 50
model = GraphConvModel(len(tox21_tasks),
batch_size=batch_size,
mode='classification')
model.fit(train_dataset, nb_epoch=10)
print("Evaluating model")
train_scores = model.evaluate(train_dataset, [metric], transformers)
valid_scores = model.evaluate(valid_dataset, [metric], transformers)
print("Train scores")
print(train_scores)
print("Validation scores")
print(valid_scores)
loader_test = dc.data.data_loader.CSVLoader(tasks=['ACTIVITY'],
smiles_field="smiles",
featurizer=graph_featurizer)
dataset_test = loader_test.featurize('./test.csv')
# In[9]:
model = GraphConvModel(n_tasks=1, mode='regression', dropout=0.2)
model.fit(dataset_train, nb_epoch=1000)
# In[10]:
metric = dc.metrics.Metric(dc.metrics.pearson_r2_score)
print(model.evaluate(dataset_train, [metric]))
print(model.evaluate(dataset_test, [metric]))
# In[11]:
test_preds = model.predict(dataset_test)
# In[12]:
import pandas as pd
# In[13]:
print(test_preds)