Time series with RNN in TensorFlow

Introduction

We use RNNs to understand data that changes over time, like weather or stock prices. They help predict what comes next by remembering past information.

Predicting tomorrow's temperature based on past days

Forecasting sales for the next month using previous sales data

Analyzing heart rate signals to detect irregularities

Predicting energy usage in a building over time

Understanding speech or text sequences for voice assistants

Syntax

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.SimpleRNN(units, input_shape=(time_steps, features)),
    tf.keras.layers.Dense(output_units)
])

model.compile(optimizer='adam', loss='mse')

SimpleRNN layer processes sequences step-by-step.

input_shape is (time steps, features per step).

Examples

RNN with 10 units, input sequences of length 5 with 1 feature each, output is 1 number.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.SimpleRNN(10, input_shape=(5, 1)),
    tf.keras.layers.Dense(1)
])

Stacked RNN layers: first returns full sequence, second returns last output, then dense layer.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.SimpleRNN(20, return_sequences=True, input_shape=(10, 3)),
    tf.keras.layers.SimpleRNN(10),
    tf.keras.layers.Dense(1)
])

Sample Model

This code trains a simple RNN to predict the next number in a sequence. It uses sequences of 10 numbers and tries to guess the next number. After training, it predicts the next number after 100-109.

TensorFlow

import numpy as np
import tensorflow as tf

# Create simple time series data: y = next value after sequence
np.random.seed(0)
time_steps = 10
features = 1
samples = 100

# Generate sequences
X = np.array([np.arange(i, i + time_steps) for i in range(samples)])
X = X[..., np.newaxis]  # shape (samples, time_steps, features)

# Targets are next value after sequence
Y = np.array([i + time_steps for i in range(samples)])

# Build model
model = tf.keras.Sequential([
    tf.keras.layers.SimpleRNN(20, input_shape=(time_steps, features)),
    tf.keras.layers.Dense(1)
])

model.compile(optimizer='adam', loss='mse')

# Train model
history = model.fit(X, Y, epochs=10, verbose=0)

# Predict next value for a new sequence
test_seq = np.array([np.arange(100, 110)])[..., np.newaxis]
pred = model.predict(test_seq)

print(f"Prediction for input sequence 100-109: {pred[0,0]:.2f}")
print(f"Actual next value: 110")
print(f"Final training loss: {history.history['loss'][-1]:.4f}")

Important Notes

RNNs remember past steps but can forget long ago information.

For longer sequences, consider LSTM or GRU layers instead of SimpleRNN.

Normalize your data for better training results.

Summary

RNNs help predict future values from past sequences.

Use SimpleRNN layer for basic sequence learning.

Train with sequences shaped as (samples, time steps, features).

Practice

1. What is the main purpose of using an RNN (Recurrent Neural Network) in time series prediction?

easy

A. To learn patterns from past time steps to predict future values

B. To classify images into categories

C. To reduce the size of the dataset

D. To perform arithmetic operations on numbers

Solution

1. Step 1: Understand RNN's role in time series

   RNNs are designed to process sequences by remembering past information.

2. Step 2: Connect RNN to prediction task

   They use past time steps to predict future values in a sequence.

3. Final Answer:

   To learn patterns from past time steps to predict future values -> Option A

4. Quick Check:

   RNN predicts future from past [OK]

Hint: RNNs remember past data to predict next steps [OK]

Common Mistakes:

• Confusing RNN with image classifiers
• Thinking RNN reduces data size
• Assuming RNN does simple math only

2. Which of the following is the correct way to add a SimpleRNN layer with 50 units in TensorFlow Keras?

easy

A. model.add(tf.keras.layers.SimpleRNN(input_shape=(None, 1), 50))

B. model.add(tf.keras.layers.RNN(50))

C. model.add(tf.keras.layers.SimpleRNN(activation='relu', 50))

D. model.add(tf.keras.layers.SimpleRNN(units=50))

Solution

1. Step 1: Recall SimpleRNN syntax

   The units parameter must be named or passed first as an integer.

2. Step 2: Check each option

   model.add(tf.keras.layers.SimpleRNN(units=50)) uses named parameter units=50, which is correct and clear.

3. Final Answer:

   model.add(tf.keras.layers.SimpleRNN(units=50)) -> Option D

4. Quick Check:

   Use named units parameter [OK]

Hint: Use named 'units' parameter for clarity [OK]

Common Mistakes:

• Passing activation before units
• Omitting units parameter name
• Missing input_shape when required

3. Given this code snippet, what will be the shape of the output from the SimpleRNN layer?

model = tf.keras.Sequential()
model.add(tf.keras.layers.SimpleRNN(10, input_shape=(5, 2)))
output = model(tf.random.uniform((3, 5, 2)))
print(output.shape)

medium

A. (3, 2, 10)

B. (3, 10)

C. (5, 10)

D. (3, 5, 10)

Solution

1. Step 1: Understand input and output shapes

   Input shape is (batch=3, time steps=5, features=2). SimpleRNN with 10 units outputs (batch, units) by default.

2. Step 2: Confirm output shape

   Since return_sequences is False by default, output shape is (3, 10).

3. Final Answer:

   (3, 10) -> Option B

4. Quick Check:

   Default SimpleRNN outputs last step shape [OK]

Hint: Default SimpleRNN outputs (batch, units) shape [OK]

Common Mistakes:

• Assuming output keeps time steps dimension
• Confusing batch size with time steps
• Misreading input_shape order

4. Identify the error in this TensorFlow RNN model code:

model = tf.keras.Sequential()
model.add(tf.keras.layers.SimpleRNN(20))
model.add(tf.keras.layers.Dense(1))
model.summary()
model.compile(optimizer='adam', loss='mse')
model.fit(x_train, y_train, epochs=5)

Assume x_train shape is (100, 10, 3).

medium

A. SimpleRNN layer missing input_shape parameter

B. Dense layer should have more units

C. Loss function 'mse' is invalid

D. Optimizer 'adam' is not supported

Solution

1. Step 1: Check input shape requirement

   First layer in Sequential must specify input_shape if no input layer is given.

2. Step 2: Verify code

   SimpleRNN(20) lacks input_shape=(10,3), so model won't know input dimensions.

3. Final Answer:

   SimpleRNN layer missing input_shape parameter -> Option A

4. Quick Check:

   First layer needs input_shape [OK]

Hint: Always specify input_shape in first RNN layer [OK]

Common Mistakes:

• Ignoring input_shape in first layer
• Changing Dense units unnecessarily
• Misunderstanding loss or optimizer names

5. You want to predict the next 3 values in a time series using an RNN. Which model setup is best to output a sequence of 3 predictions for each input sequence?

hard

A. Use SimpleRNN with return_sequences=True and a Dense layer with 3 units

B. Use SimpleRNN with return_sequences=False and a Dense layer with 3 units

C. Use SimpleRNN with return_sequences=True and a TimeDistributed Dense layer with 1 unit

D. Use SimpleRNN with return_sequences=False and a TimeDistributed Dense layer with 1 unit

Solution

1. Step 1: Understand output requirements

   Predicting next 3 values means outputting a sequence of length 3, one prediction per time step.

2. Step 2: Choose correct RNN and output layer

   return_sequences=True outputs a sequence (batch, time steps, units). A Dense layer with 3 units applied at each time step (via TimeDistributed) or a Dense layer with 3 units on the last step can be used depending on output shape.

3. Step 3: Analyze options

   Use SimpleRNN with return_sequences=True and a Dense layer with 3 units outputs only the last time step's output with 3 units, which is not a sequence of 3 predictions. Use SimpleRNN with return_sequences=True and a TimeDistributed Dense layer with 1 unit uses return_sequences=True and TimeDistributed Dense(1), producing a sequence output of shape (batch, time steps, 1), which can be adjusted to 3 time steps for 3 predictions.

4. Final Answer:

   Use SimpleRNN with return_sequences=True and a TimeDistributed Dense layer with 1 unit -> Option C

5. Quick Check:

   return_sequences=True + TimeDistributed Dense(1) outputs sequence predictions [OK]

Hint: return_sequences=True + TimeDistributed Dense(1) for sequence output [OK]

Common Mistakes:

• Using return_sequences=False for sequence output
• Using Dense without TimeDistributed for sequence output
• Misunderstanding output shapes