97 lines
3.0 KiB
Python
97 lines
3.0 KiB
Python
from sklearn.model_selection import train_test_split
|
|
import torch
|
|
import torch.nn as nn
|
|
import pandas as pd
|
|
import numpy as np
|
|
import torch.nn.functional as F
|
|
from torch.utils.data import DataLoader, TensorDataset, random_split
|
|
from sklearn import preprocessing
|
|
import sys
|
|
from sacred import Experiment
|
|
from sacred.observers import FileStorageObserver
|
|
from sklearn.metrics import accuracy_score
|
|
from sklearn.metrics import f1_score
|
|
from sklearn.metrics import mean_squared_error
|
|
|
|
np.set_printoptions(suppress=False)
|
|
|
|
ex = Experiment("ium_s440058", interactive=False, save_git_info=False)
|
|
ex.observers.append(FileStorageObserver('ium_s440058/my_runs_directory'))
|
|
|
|
@ex.config
|
|
def my_config():
|
|
num_epochs = 10
|
|
batch_size = 20
|
|
|
|
class LogisticRegressionModel(torch.nn.Module):
|
|
def __init__(self, input_dim, output_dim):
|
|
super(LogisticRegressionModel, self).__init__()
|
|
self.linear = nn.Linear(input_dim, output_dim)
|
|
self.sigmoid = nn.Sigmoid()
|
|
def forward(self, x):
|
|
out = self.linear(x)
|
|
return self.sigmoid(out)
|
|
|
|
@ex.capture
|
|
def script(num_epochs, batch_size, _run):
|
|
results = pd.read_csv('diabetes2.csv')
|
|
|
|
results.dropna()
|
|
|
|
data_train, data_valid, data_test = np.split(results.sample(frac=1), [int(.6*len(results)), int(.8*len(results))])
|
|
columns_to_train = ['Glucose', 'BloodPressure', 'Insulin', 'Age']
|
|
|
|
x_train = data_train[columns_to_train].astype(np.float32)
|
|
y_train = data_train['Outcome'].astype(np.float32)
|
|
|
|
x_test = data_test[columns_to_train].astype(np.float32)
|
|
y_test = data_test['Outcome'].astype(np.float32)
|
|
|
|
fTrain = torch.from_numpy(x_train.values)
|
|
tTrain = torch.from_numpy(y_train.values.reshape(460,1))
|
|
|
|
fTest= torch.from_numpy(x_test.values)
|
|
tTest = torch.from_numpy(y_test.values)
|
|
|
|
_run.log_scalar("Batch", str(batch_size))
|
|
_run.log_scalar("epoch", str(num_epochs))
|
|
learning_rate = 0.005
|
|
input_dim = 4
|
|
output_dim = 1
|
|
|
|
model = LogisticRegressionModel(input_dim, output_dim)
|
|
|
|
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()
|
|
|
|
_run.log_scalar("Lost", str(loss.item()))
|
|
|
|
|
|
torch.save(model.state_dict(), 'diabetes.pth')
|
|
pred = model(fTest)
|
|
accuracy = accuracy_score(tTest, np.argmax(pred.detach().numpy(), axis = 1))
|
|
f1 = f1_score(tTest, np.argmax(pred.detach().numpy(), axis = 1), average = None)
|
|
rmse = mean_squared_error(tTest, pred.detach().numpy())
|
|
_run.log_scalar("accuracy", accuracy)
|
|
_run.log_scalar("f1", f1)
|
|
_run.log_scalar("rmse", rmse)
|
|
|
|
@ex.automain
|
|
def my_main(num_epochs, batch_size, _run):
|
|
script()
|
|
|
|
ex.run()
|
|
ex.add_artifact('diabetes.pth') |