69 lines
2.0 KiB
Plaintext
69 lines
2.0 KiB
Plaintext
import os
|
|
import pandas as pd
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.optim as optim
|
|
|
|
# Training
|
|
train_file_path = "Train1.csv"
|
|
train_data = pd.read_csv(train_file_path)
|
|
train_data = train_data.dropna(subset=['price_range'])
|
|
|
|
valid_values = {0.0, 1.0, 2.0, 3.0}
|
|
assert set(train_data['price_range'].unique()) <= valid_values, "Unexpected values in price_range"
|
|
|
|
class SimpleNN(nn.Module):
|
|
def __init__(self, input_size, hidden_size, output_size):
|
|
super(SimpleNN, self).__init__()
|
|
self.fc1 = nn.Linear(input_size, hidden_size)
|
|
self.fc2 = nn.Linear(hidden_size, output_size)
|
|
self.softmax = nn.Softmax(dim=1)
|
|
|
|
def forward(self, x):
|
|
x = torch.relu(self.fc1(x))
|
|
x = self.fc2(x)
|
|
return self.softmax(x)
|
|
|
|
input_size = len(train_data.columns) - 2
|
|
hidden_size = 50
|
|
output_size = len(valid_values)
|
|
|
|
model = SimpleNN(input_size, hidden_size, output_size)
|
|
|
|
criterion = nn.CrossEntropyLoss()
|
|
optimizer = optim.Adam(model.parameters(), lr=0.001)
|
|
|
|
epochs = 10
|
|
for epoch in range(epochs):
|
|
inputs = torch.tensor(train_data.drop(['price_range', 'ID'], axis=1).values, dtype=torch.float32)
|
|
labels = torch.tensor(train_data['price_range'].values, dtype=torch.long)
|
|
|
|
optimizer.zero_grad()
|
|
|
|
outputs = model(inputs)
|
|
loss = criterion(outputs, labels)
|
|
loss.backward()
|
|
optimizer.step()
|
|
|
|
print(f"Epoch {epoch+1}/{epochs}, Loss: {loss.item()}")
|
|
|
|
save_path = "model.pth"
|
|
torch.save(model.state_dict(), save_path)
|
|
|
|
# Testing
|
|
model.load_state_dict(torch.load("model.pth"))
|
|
model.eval()
|
|
|
|
test_file_path = "Test1.csv"
|
|
test_data = pd.read_csv(test_file_path)
|
|
|
|
inputs = torch.tensor(test_data.drop(['price_range', 'ID'], axis=1).values, dtype=torch.float32)
|
|
with torch.no_grad():
|
|
predictions = model(inputs)
|
|
predicted_classes = torch.argmax(predictions, dim=1)
|
|
|
|
predicted_classes_df = pd.DataFrame(predicted_classes.numpy(), columns=['Predicted_Price_Range'])
|
|
predicted_classes_df['Actual_Price_Range'] = test_data['price_range'].values
|
|
|
|
output_path = 'predictions.csv'
|
|
predicted_classes_df.to_csv(output_path, index=False) |