s434766/ium_434766
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

sacred

Browse Source
This commit is contained in:
s434766 2021-05-11 21:53:49 +02:00
parent e94a14e8e7
commit a5b9eb3882
2 changed files with 49 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pytorch-training-eval/Jenkinsfile-eval
View File

@ -34,7 +34,7 @@ pipeline {
stage('sendMail') {
steps{
emailext body: currentBuild.result ?: 'SUCCESS',
subject: 's434766 training',
subject: 's434766 evaluation',
to: '26ab8f35.uam.onmicrosoft.com@emea.teams.ms'
}
}

86
stroke-pytorch.py
View File

@ -9,9 +9,14 @@ from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import accuracy_score
import numpy as np
import pandas as pd
from sacred import Experiment
from sacred.observers import FileStorageObserver
np.set_printoptions(suppress=False)
ex = Experiment("stroke-pytorch", interactive=True)
ex.observers.append(FileStorageObserver('ium_s434766O_files'))
ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@localhost:27017',
db_name='sacred'))
class LogisticRegressionModel(nn.Module):
def __init__(self, input_dim, output_dim):
super(LogisticRegressionModel, self).__init__()
@ -21,49 +26,54 @@ class LogisticRegressionModel(nn.Module):
out = self.linear(x)
return self.sigmoid(out)
data_train = pd.read_csv("data_train.csv")
data_test = pd.read_csv("data_test.csv")
data_val = pd.read_csv("data_val.csv")
FEATURES = ['age','hypertension','heart_disease','ever_married', 'avg_glucose_level', 'bmi']
@ex.main
def my_main(_log):
data_train = pd.read_csv("data_train.csv")
data_test = pd.read_csv("data_test.csv")
data_val = pd.read_csv("data_val.csv")
FEATURES = ['age','hypertension','heart_disease','ever_married', 'avg_glucose_level', 'bmi']
x_train = data_train[FEATURES].astype(np.float32)
y_train = data_train['stroke'].astype(np.float32)
x_train = data_train[FEATURES].astype(np.float32)
y_train = data_train['stroke'].astype(np.float32)
x_test = data_test[FEATURES].astype(np.float32)
y_test = data_test['stroke'].astype(np.float32)
x_test = data_test[FEATURES].astype(np.float32)
y_test = data_test['stroke'].astype(np.float32)
fTrain = torch.from_numpy(x_train.values)
tTrain = torch.from_numpy(y_train.values.reshape(2945,1))
fTrain = torch.from_numpy(x_train.values)
tTrain = torch.from_numpy(y_train.values.reshape(2945,1))
fTest= torch.from_numpy(x_test.values)
tTest = torch.from_numpy(y_test.values)
fTest= torch.from_numpy(x_test.values)
tTest = torch.from_numpy(y_test.values)
batch_size = int(sys.argv[1]) if len(sys.argv) > 1 else 16
num_epochs = int(sys.argv[2]) if len(sys.argv) > 2 else 5
learning_rate = 0.001
input_dim = 6
output_dim = 1
batch_size = int(sys.argv[1]) if len(sys.argv) > 1 else 16
num_epochs = int(sys.argv[2]) if len(sys.argv) > 2 else 5
learning_rate = 0.001
input_dim = 6
output_dim = 1
info_params = "Batch size = " + str(batch_size) + " Epochs = " + str(num_epochs)
_log.info(info_params)
model = LogisticRegressionModel(input_dim, output_dim)
model = LogisticRegressionModel(input_dim, output_dim)
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)
for epoch in range(num_epochs):
# print ("Epoch #",epoch)
model.train()
optimizer.zero_grad()
# Forward pass
y_pred = model(fTrain)
# Compute Loss
loss = criterion(y_pred, tTrain)
# print(loss.item())
# Backward pass
loss.backward()
optimizer.step()
info_loss = "Last loss = " + str(loss.item())
_log.info(info_loss)
y_pred = model(fTest)
# print("predicted Y value: ", y_pred.data)
for epoch in range(num_epochs):
# print ("Epoch #",epoch)
model.train()
optimizer.zero_grad()
# Forward pass
y_pred = model(fTrain)
# Compute Loss
loss = criterion(y_pred, tTrain)
print(loss.item())
# Backward pass
loss.backward()
optimizer.step()
torch.save(model.state_dict(), 'stroke.pth')
y_pred = model(fTest)
print("predicted Y value: ", y_pred.data)
torch.save(model.state_dict(), 'stroke.pth')
ex.run()