ium_487176/zad1_mlflow.py

150 lines
4.5 KiB
Python

import pandas as pd
import sklearn.model_selection
import mlflow
import mlflow.sklearn
import numpy as np
import logging
import argparse
parser = argparse.ArgumentParser(description='IUM script')
parser.add_argument('--num_epochs', type=int, default=10, help='Number of epochs')
parser.add_argument('--lr', type=float, default=0.001, help='Learning rate')
parser.add_argument('--alpha', type=float, default=0.001, help='Learning rate')
args = parser.parse_args()
logging.basicConfig(level=logging.WARN)
logger = logging.getLogger(__name__)
mlflow.set_tracking_uri("http://localhost:5000")
mlflow.set_experiment("s487176")
import requests
url = "https://huggingface.co/datasets/mstz/wine/raw/main/Wine_Quality_Data.csv"
save_path = "Wine_Quality_Data.csv"
response = requests.get(url)
response.raise_for_status()
with open(save_path, "wb") as f:
f.write(response.content)
wine_dataset = pd.read_csv("Wine_Quality_Data.csv")
wine_dataset['color'] = wine_dataset['color'].replace({'red': 1, 'white': 0})
for column in wine_dataset.columns:
wine_dataset[column] = wine_dataset[column] / wine_dataset[column].abs().max() # normalizacja
from sklearn.model_selection import train_test_split
wine_train, wine_test = sklearn.model_selection.train_test_split(wine_dataset, test_size=0.1, random_state=1, stratify=wine_dataset["color"])
wine_train["color"].value_counts()
# podzielenie na train i test
wine_test["color"].value_counts()
wine_test, wine_val = sklearn.model_selection.train_test_split(wine_test, test_size=0.5, random_state=1, stratify=wine_test["color"]) # podzielenie na test i validation
wine_test["color"].value_counts()
wine_val["color"].value_counts()
import seaborn as sns
sns.set_theme()
import torch
from torch import nn
from torch.utils.data import DataLoader, Dataset
class TabularDataset(Dataset):
def __init__(self, data):
self.data = data.values.astype('float32')
def __getitem__(self, index):
x = torch.tensor(self.data[index, :-1])
y = torch.tensor(self.data[index, -1])
return x, y
def __len__(self):
return len(self.data)
batch_size = 64
train_dataset = TabularDataset(wine_train)
train_dataloader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_dataset = TabularDataset(wine_test)
test_dataloader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)
class TabularModel(nn.Module):
def __init__(self, input_dim, hidden_dim, output_dim):
super(TabularModel, self).__init__()
self.fc1 = nn.Linear(input_dim, hidden_dim)
self.relu = nn.ReLU()
self.fc2 = nn.Linear(hidden_dim, output_dim)
self.softmax = nn.Softmax(dim=1)
def forward(self, x):
out = self.fc1(x)
out = self.relu(out)
out = self.fc2(out)
out = self.softmax(out)
return out
def predict(self, x):
with torch.no_grad():
output = self.forward(x)
_, predicted = torch.max(output, 1)
return predicted
input_dim = wine_train.shape[1] - 1
hidden_dim = 32
output_dim = 2
model = TabularModel(input_dim, hidden_dim, output_dim)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters())
num_epochs = args.num_epochs
lr = args.lr
alpha = args.alpha
model = TabularModel(input_dim=len(wine_train.columns)-1, hidden_dim=hidden_dim, output_dim=output_dim)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=alpha)
with mlflow.start_run():
mlflow.log_params({"learning rate":lr,"alpha":alpha})
for epoch in range(num_epochs):
running_loss = 0.0
for i, data in enumerate(train_dataloader, 0):
inputs, labels = data
labels = labels.type(torch.LongTensor)
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
# Print the loss every 1000 mini-batches
if (epoch%2) == 0:
print(f'Epoch {epoch + 1}, loss: {running_loss / len(train_dataloader):.4f}')
print('Finished Training')
correct = 0
total = 0
with torch.no_grad():
for data in test_dataloader:
inputs, labels = data
predicted = model.predict(inputs.float())
total += labels.size(0)
correct += (predicted == labels).sum().item()
accuracy= 100 * correct / total
print('Accuracy on test set: %d %%' % accuracy)
mlflow.log_metric("test_accuracy", accuracy)
mlflow.sklearn.log_model(model, "model")