Preparing Data for RNNs with PyTorch

Introduction to Preparing Data for RNNs

Welcome back! In the previous lesson, we focused on understanding and preprocessing multivariate time series data using the Air Quality dataset. We cleaned the dataset by handling missing values, combining date and time columns, and setting the DateTime column as the index. Now, we will build on that foundation to prepare the data for Recurrent Neural Networks (RNNs). This preparation is crucial for multivariate time series forecasting, as it involves selecting relevant features, normalizing the data, and structuring it into sequences suitable for RNN input.

Feature Selection for RNN

Feature selection is a critical step in preparing data for RNNs. It involves choosing the most relevant features from the dataset that will be used as inputs for the model. In our case, we will focus on features that are significant for forecasting temperature, such as CO(GT), NO2(GT), PT08.S5(O3), RH, and T . By selecting these features, we ensure that the RNN model receives the most informative data for making accurate predictions. Here's how you can select these features from the dataset: Python # Select relevant features for RNN features = ['CO(GT)', 'NO2(GT)', 'PT08.S5(O3)', 'RH', 'T'] df = df[features] This code snippet extracts the specified features from the dataset, creating a new DataFrame that contains only the relevant columns. This step is essential for reducing the complexity of the model and improving its performance.

Data Normalization

Normalization is a crucial step in preparing data for RNNs, as it ensures that all features are on a similar scale. RNNs are sensitive to the scale of input data. For example, if one feature ranges from 0 to 100 and another ranges from 0 to 1, the model might prioritize the larger values just because of their magnitude—not because they’re more important. This can lead to inefficient training and poor model performance. By normalizing the data, we make sure that each feature contributes equally to the learning process. We will use the StandardScaler from the sklearn library to normalize our data. This scaler transforms each feature so that it has a mean of 0 and a standard deviation of 1. Here's how you can normalize the data: Python from sklearn.preprocessing import StandardScaler # Normalize the data scaler = StandardScaler() df_scaled = scaler.fit_transform(df) In this example, we first import the StandardScaler class from sklearn.preprocessing . We then create an instance of StandardScaler and use the fit_transform method to normalize the data. This method scales each feature to have a mean of 0 and a standard deviation of 1, ensuring that all features are on a similar scale.

Join the 1M+ learners on CodeSignal

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

Creating Sequences for Multi-Input RNN

Creating sequences is a key step in preparing data for RNNs. RNNs require input data to be structured as sequences, where each sequence consists of multiple time steps. In our case, we will create sequences of length 10, where each sequence spans 10 consecutive time steps, and each time step includes all selected features. The target variable is the temperature at the time step immediately following each sequence—that is, the next hour after the final step in the sequence.

Here's how you can create sequences for a multi-input RNN:

Python

import numpy as np

# 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 for 10 time steps
        y.append(data[i+seq_length, -1])  # Temperature at the next time step
    return np.array(X), np.array(y)

# Define sequence length
sequence_length = 10

# Create sequences
X, y = create_multivariate_sequences(df_scaled, sequence_length)

import numpy as np

# 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 for 10 time steps
        y.append(data[i+seq_length, -1])  # Temperature at the next time step
    return np.array(X), np.array(y)

# Define sequence length
sequence_length = 10

# Create sequences
X, y = create_multivariate_sequences(df_scaled, sequence_length)

In this code, we define a function create_multivariate_sequences that takes the normalized data and a sequence length as input. The function iterates over the data to create sequences of the specified length, where each sequence contains 10 consecutive time steps and all selected features at each step. For each sequence, the target value is the temperature at the time step immediately following the end of the sequence. Finally, the function returns the sequences and target values as NumPy arrays.

Example: Preparing a Dataset for RNN

Let's walk through a complete example of preparing a dataset for RNN. We will select relevant features, normalize the data, create sequences, and reshape the data. Finally, we will print the shape of the processed dataset to ensure that it is correctly prepared for RNN input.

Python

from sklearn.preprocessing import StandardScaler
import numpy as np

# Select relevant features for RNN
features = ['CO(GT)', 'NO2(GT)', 'PT08.S5(O3)', 'RH', 'T']
df = df[features]

# Normalize the data
scaler = StandardScaler()
df_scaled = scaler.fit_transform(df)

# 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)

# Print shape of the processed dataset
print(f"X shape: {X.shape}, y shape: {y.shape}")

from sklearn.preprocessing import StandardScaler
import numpy as np

# Select relevant features for RNN
features = ['CO(GT)', 'NO2(GT)', 'PT08.S5(O3)', 'RH', 'T']
df = df[features]

# Normalize the data
scaler = StandardScaler()
df_scaled = scaler.fit_transform(df)

# 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)

# Print shape of the processed dataset
print(f"X shape: {X.shape}, y shape: {y.shape}")

The output of this code will display the shape of the processed dataset, confirming that it is ready for RNN input:

X shape: (6931, 10, 5), y shape: (6931,)

X shape: (6931, 10, 5), y shape: (6931,)

This output indicates that we have 6931 samples, each with 10 timesteps and 5 features, and 6931 target values for temperature prediction.