Get familiar with missing data and how it impacts your analysis! Learn about different null value operations in your dataset, how to find missing data and summarizing missingness in your data. 

Why deal with missing data?

Steps for treating missing values

Null value operations

Finding Null values

Handling missing values

Detecting missing values

Replacing missing values

Replacing hidden missing values

Analyze the amount of missingness

Analyzing missingness percentage

Visualize missingness

The Problem With Missing Data

Analyzing the type of missingness in your dataset is a very important step towards treating missing values. In this chapter, you'll learn in detail how to establish patterns in your missing and non-missing data, and how to appropriately treat the missingness using simple techniques such as listwise deletion. 

Is the data missing at random?

Guess the missingness type

Deduce MNAR

Finding patterns in missing data

Finding correlations in your data

Identify the missingness type

Visualizing missingness across a variable

Fill dummy values

Generate scatter plot with missingness

When and how to delete missing data

Delete MCAR

Will you delete?

Does Missingness Have A Pattern?

Embark on the world of data imputation! In this chapter, you will apply basic imputation techniques to fill in missing data and visualize your imputations to be able to evaluate your imputations' performance. 

Mean, median & mode imputations

Mean & median imputation

Mode and constant imputation

Visualize imputations

Imputing time-series data

Filling missing time-series data

Impute with interpolate method

Visualizing time-series imputations

Visualize forward fill imputation

Visualize backward fill imputation

Plot interpolations

Imputation Techniques

Finally, go beyond simple imputation techniques and make the most of your dataset by using advanced imputation techniques that rely on machine learning models, to be able to accurately impute and evaluate your missing data. You will be using methods such as KNN and MICE in order to get the most out of your missing data! 

Imputing using fancyimpute

KNN imputation

MICE imputation

Imputing categorical values

Ordinal encoding of a categorical column

Ordinal encoding of a DataFrame

KNN imputation of categorical values

Evaluation of different imputation techniques

Analyze the summary of linear model

Comparing and choosing the best adjusted R-squared

Comparing density plots

Conclusion

Advanced Imputation Techniques

Diabetes

Air Quality

Tired of working with messy data? Did you know that most of a data scientist's time is spent in finding, cleaning and reorganizing data?! Well turns out you can clean your data in a smart way! In this course Dealing with Missing Data in Python, you'll do just that!  You'll learn to address missing values for numerical, and categorical data as well as time-series data. You'll learn to see the patterns the missing data exhibits! While working with air quality and diabetes data, you'll also learn to analyze, impute and evaluate the effects of imputing the data.

Introduction to Data Visualization with Matplotlib

Supervised Learning with scikit-learn

Learn to address missing values for numerical, categorical, and time-series data, and to analyze, impute, and evaluate the effects of imputing the data.

Dealing with Missing Data in Python

Learn how to identify, analyze, remove and impute missing data in Python. 

Steps for treating missing values

Dealing with Missing Data in Python

Exercício interativo prático