Data Preparation for RNNs

Introduction to Data Preparation for RNNs

Welcome back! In the previous lesson, we explored the basics of Recurrent Neural Networks (RNNs) and time series data. We discussed how RNNs are uniquely suited for handling sequential data due to their ability to retain information from previous inputs. We also visualized time series data to identify patterns and trends. Now, we will build on that foundation by focusing on preparing time series data specifically for RNNs. This lesson will guide you through the process of normalizing, standardizing, and converting time series data into sequences, which are essential steps for training RNN models effectively.

Why Normalize or Standardize Data?

Before feeding data into an RNN, it is crucial to normalize or standardize it. These preprocessing steps ensure that all input features are on a similar scale. If you skip normalization or standardization, your RNN may encounter several issues: Slower Training: Features with larger values can dominate the learning process, making it harder for the model to learn from features with smaller values. This can slow down convergence during training. Unstable Gradients: RNNs are sensitive to the scale of input data. Without normalization or standardization, the gradients during backpropagation can become very large or very small (exploding or vanishing gradients), making training unstable or causing the model to fail to learn. Poor Model Performance: The model may not learn the underlying patterns in the data effectively, leading to lower accuracy and worse predictions. By normalizing or standardizing your data, you help the RNN learn more efficiently and achieve better results. This is why these preprocessing steps are considered best practices when working with neural networks, especially for time series data.

Data Normalization with MinMaxScaler

X_{\text{scaled}} = \frac{X - X_{\text{min}}}{X_{\text{max}} - X_{\text{min}}}

Join the 1M+ learners on CodeSignal

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

Python

import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler

# Sample data
data = {'Passengers': [112, 118, 132, 129, 121, 135, 148, 148, 136, 119]}
df = pd.DataFrame(data)

# Normalize data
scaler = MinMaxScaler()
df['Passengers'] = scaler.fit_transform(df[['Passengers']])

Python

from sklearn.preprocessing import StandardScaler

# Standardize data
scaler = StandardScaler()
df['Passengers'] = scaler.fit_transform(df[['Passengers']])

Python

def create_sequences(data, seq_length=10):
    X, y = [], []
    for i in range(len(data) - seq_length):
        X.append(data[i:i+seq_length])
        y.append(data[i+seq_length])
    return np.array(X), np.array(y)

X, y = create_sequences(df['Passengers'].values, seq_length=10)

Python

import torch

# Reshape X for RNN
X = torch.tensor(X, dtype=torch.float32).view(X.shape[0], X.shape[1], 1)

Python

import numpy as np
import pandas as pd
import torch
from sklearn.preprocessing import MinMaxScaler, StandardScaler

# Sample data
data = {'Passengers': [112, 118, 132, 129, 121, 135, 148, 148, 136, 119]}
df = pd.DataFrame(data)

# Choose one: Normalize or Standardize data
scaler = MinMaxScaler()  # or StandardScaler()
df['Passengers'] = scaler.fit_transform(df[['Passengers']])

# Convert time series into sequences
def create_sequences(data, seq_length=10):
    X, y = [], []
    for i in range(len(data) - seq_length):
        X.append(data[i:i+seq_length])
        y.append(data[i+seq_length])
    return np.array(X), np.array(y)

X, y = create_sequences(df['Passengers'].values, seq_length=10)

# Reshape X for RNN
X = torch.tensor(X, dtype=torch.float32).view(X.shape[0], X.shape[1], 1)

Introduction to Data Preparation for RNNs

Why Normalize or Standardize Data?

Data Normalization with MinMaxScaler

Join the 1M+ learners on CodeSignal

Data Standardization with StandardScaler

Converting Time Series Data into Sequences

Reshaping Data for RNN Input

Example Walkthrough: Preparing a Sample Dataset

Summary and Next Steps