Chapter 9: Sequential Modeling with Recurrent Neural Networks

Activity 17: Predict the Trend of Microsoft’s Stock Price Using an LSTM with 50 Units (Neurons)

Solution

1. Import the required libraries:

   import numpy as np

   import matplotlib.pyplot as plt

   import pandas as pd

2. Import the dataset:

   dataset_training = pd.read_csv(‘MSFT_train.csv’)

   dataset_training.head()

   The following figure shows the output of the preceding code:

   

   Figure 9.23: The first five rows of the dataset

3. We are going to make the prediction using the Open stock price, so we will extract this column first:

   training_data = dataset_training.iloc[:, 1:2].values

   training_data

   The following figure shows the output of the preceding code:

   

   Figure 9.24: The extracted column (the open stock price) from the dataset

4. Then, perform feature scaling by normalizing the data:

   from sklearn.preprocessing import MinMaxScaler

   sc = MinMaxScaler(feature_range = (0, 1))

   training_data_scaled = sc.fit_transform(training_data)

   training_data_scaled...