Introduction to RNNs for Multivariate Time Series with PyTorch

Introduction to RNNs for Multivariate Time Series

Welcome to the next step in your journey of handling multivariate time series with Recurrent Neural Networks (RNNs). In the previous lessons, you learned how to preprocess the Air Quality dataset and prepare it for RNN input. Now, we will focus on building and training an RNN model to predict Temperature (T) using multiple features from this dataset. RNNs are particularly well-suited for time series forecasting due to their ability to capture temporal dependencies in sequential data. By the end of this lesson, you will have a solid understanding of how to construct and train an RNN model for multivariate time series forecasting.

Quick Recap of Preprocessing Steps

Before building the RNN model, it's essential to preprocess the Air Quality dataset to ensure it is suitable for input into the model. Here are the preprocessing steps you should have completed: Python import pandas as pd import numpy as np from sklearn.preprocessing import StandardScaler # Load the Air Quality dataset from the URL url = "https://codesignal-staging-assets.s3.amazonaws.com/uploads/1742293523899/AirQualityUCI.csv" df = pd.read_csv(url, sep=';', decimal=',') # Replace -200 with NaN df.replace(-200, np.nan, inplace=True) # Combine 'Date' and 'Time' into a single 'DateTime' column df['DateTime'] = pd.to_datetime(df['Date'] + ' ' + df['Time'], format="%d/%m/%Y %H.%M.%S") # Drop the original 'Date' and 'Time' columns df.drop(columns=['Date', 'Time'], inplace=True) # Drop unnecessary columns df.drop(columns=['Unnamed: 15', 'Unnamed: 16'], inplace=True) # Drop rows where essential features are missing df.dropna(subset=['CO(GT)', 'NO2(GT)', 'T', 'RH'], inplace=True) # Fill missing values using forward-fill & backward-fill df.ffill(inplace=True) df.bfill(inplace=True) # Set DateTime as index df.set_index('DateTime', inplace=True) # Select relevant features for RNN features = ['CO(GT)', 'NO2(GT)', 'PT08.S5(O3)', 'RH', 'T'] df_selected = df[features] # Normalize the data scaler = StandardScaler() df_scaled = scaler.fit_transform(df_selected) # Function to create sequences for multi-input RNN def create_multivariate_sequences(data, seq_length=10): X, y = [], [] for i in range(len(data) - seq_length): X.append(data[i:i+seq_length]) # Multi-feature input y.append(data[i+seq_length, -1]) # Predicting Temperature (T) return np.array(X), np.array(y) # Define sequence length sequence_length = 10 # Create sequences X, y = create_multivariate_sequences(df_scaled, sequence_length) # Reshape input for RNN X = X.reshape((X.shape[0], sequence_length, len(features))) # (samples, timesteps, features)

Join the 1M+ learners on CodeSignal

Be a part of our community of 1M+ users who develop and demonstrate their skills on CodeSignal

Compiling and Training the RNN Model

In PyTorch, training a model involves defining a loss function, an optimizer, and manually implementing the training loop. We will use the Adam optimizer and mean squared error (MSE) as the loss function, as they are commonly used for regression tasks.

Python

import torch.optim as optim

# Define loss function and optimizer
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# Convert training data to PyTorch tensors
X_train_tensor = torch.tensor(X_train, dtype=torch.float32)
y_train_tensor = torch.tensor(y_train, dtype=torch.float32)

# Training loop
epochs = 10
batch_size = 16

for epoch in range(epochs):
    model.train()
    for i in range(0, len(X_train_tensor), batch_size):
        X_batch = X_train_tensor[i:i+batch_size]
        y_batch = y_train_tensor[i:i+batch_size]

        # Forward pass
        outputs = model(X_batch)
        loss = criterion(outputs, y_batch)

        # Backward pass and optimization
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    print(f'Epoch [{epoch+1}/{epochs}], Loss: {loss.item():.4f}')

import torch.optim as optim

# Define loss function and optimizer
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# Convert training data to PyTorch tensors
X_train_tensor = torch.tensor(X_train, dtype=torch.float32)
y_train_tensor = torch.tensor(y_train, dtype=torch.float32)

# Training loop
epochs = 10
batch_size = 16

for epoch in range(epochs):
    model.train()
    for i in range(0, len(X_train_tensor), batch_size):
        X_batch = X_train_tensor[i:i+batch_size]
        y_batch = y_train_tensor[i:i+batch_size]

        # Forward pass
        outputs = model(X_batch)
        loss = criterion(outputs, y_batch)

        # Backward pass and optimization
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    print(f'Epoch [{epoch+1}/{epochs}], Loss: {loss.item():.4f}')

In this code, we define the criterion as nn.MSELoss() and the optimizer as optim.Adam(). We convert the training data to PyTorch tensors and implement a training loop that iterates over the data in batches. For each batch, we perform a forward pass, compute the loss, perform a backward pass, and update the model parameters.