Mastering Python for Finance - Second Edition

Preparing the target variables

We have already downloaded the JPM dataset to the pandas DataFrame, df_jpm, in a previous section, and the y variable contains the daily percentage change of JPM. Convert these values to labels with the following code:

In [ ]:    import numpy as np    y_direction = y >= 0    y_direction.head(3)Out[ ]:    date
    1998-01-05     True
    1998-01-06    False
    1998-01-07     True    Name: 5. adjusted close, dtype: bool

Using the head() command, we can see that the y_direction variable becomes a pandas Series object of Boolean values. A percentage change of zero or more classifies the value with a True label, and False otherwise. Let's extract unique values with the unique() command as column names for use later on:

In [ ]: flags = list(y_direction.unique()) ...