ium_444421/training_sacred.py

#!/usr/bin/env python
# coding: utf-8

# In[ ]:


import numpy as np
import pandas as pd
from sklearn.metrics import accuracy_score
import torch
from torch import nn, optim
import torch.nn.functional as F
import sys
from sacred import Experiment
from sacred.observers import FileStorageObserver, MongoObserver


# In[ ]:


ex = Experiment(save_git_info=False)
# ex.observers.append(FileStorageObserver('my_runs'))
ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password@localhost:27017', db_name='sacred'))

@ex.config
def my_config():
    epochs = 400


# In[ ]:


def prepare_data():
    X_train = pd.read_csv('X_train.csv')
    y_train = pd.read_csv('y_train.csv')
    X_train = torch.from_numpy(np.array(X_train)).float()
    y_train = torch.squeeze(torch.from_numpy(y_train.values).float())
    return X_train, y_train


# In[ ]:


class Net(nn.Module):
    def __init__(self, n_features):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(n_features, 5)
        self.fc2 = nn.Linear(5, 3)
        self.fc3 = nn.Linear(3, 1)
    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        return torch.sigmoid(self.fc3(x))


# In[ ]:


def calculate_accuracy(y_true, y_pred):
    predicted = y_pred.ge(.5).view(-1)
    return (y_true == predicted).sum().float() / len(y_true)


# In[ ]:


def round_tensor(t, decimal_places=3):
    return round(t.item(), decimal_places)

# In[ ]:


def train_model(X_train, y_train, device, epochs):
    net = Net(X_train.shape[1])
    criterion = nn.BCELoss()
    optimizer = optim.Adam(net.parameters(), lr=0.001)
    
    X_train = X_train.to(device)
    y_train = y_train.to(device)
    
    net = net.to(device)
    criterion = criterion.to(device)

    for epoch in range(epochs):
        y_pred = net(X_train)
        y_pred = torch.squeeze(y_pred)
        train_loss = criterion(y_pred, y_train)
        if epoch % 100 == 0:
            train_acc = calculate_accuracy(y_train, y_pred)
            print(
                f'''epoch {epoch}
                Train set - loss: {round_tensor(train_loss)}, accuracy: {round_tensor(train_acc)}
                ''')
    optimizer.zero_grad()
    train_loss.backward()
    optimizer.step()
    return net, round_tensor(train_loss)


# In[ ]:


@ex.automain
def my_main(epochs, _run):
    X_train, y_train = prepare_data()
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    
    model, loss = train_model(X_train, y_train, device, epochs)
    torch.save(model, 'model.pth')
    ex.add_artifact('model.pth')
    
    _run.info["epochs"] = epochs
    _run.info["loss"] = loss


    
# In[ ]:


ex.run()