Will you delete?
Before deleting missing values completely, you must consider the factors for deletion. The simplest factor to consider is the size of the missing data. More complex reasons affecting missingness may require domain knowledge. In this exercise, you will identify the reason for missingness and then perform the appropriate deletion.
You'll first use msno.matrix() and msno.heatmap() to visualize missingness and the correlation between variables with missing data. You will then determine pattern in missingness. Lastly, you'll delete depending on the type of missingness.
The diabetes DataFrame has been loaded for you.
Note that we've used a proprietary display() function instead of plt.show() to make it easier for you to view the output.
Este exercício faz parte do curso
Dealing with Missing Data in Python
Exercício interativo prático
Experimente este exercício completando este código de exemplo.
# Visualize the missingness in the data
___.___(___)
# Display nullity matrix
display("/usr/local/share/datasets/matrix_diabetes.png")