Data cleaning is one of the important parts of machine learning. It plays a significant part in building a model. Data Cleaning is one of those things that everyone does but no one really talks about. It surely isn’t the fanciest part of machine learning and at the same time, there aren’t any hidden tricks or secrets to uncover. However, proper data cleaning can make or break your project. Professional data scientists usually spend a very large portion of their time on this step.
Because of the belief that, “Better data beats fancier algorithms”.
If we have a well-cleaned dataset, we can get desired results even with a very simple algorithm, which can prove very beneficial at times.
Obviously, different types of data will require different types of cleaning. However, this systematic approach can always serve as a good starting point.
Steps involved in Data Cleaning
- Removal of unwanted observations
This includes deleting duplicate/ redundant or irrelevant values from your dataset. Duplicate observations most frequently arise during data collection and Irrelevant observations are those that don’t actually fit the specific problem that you’re trying to solve.
- Redundant observations alter the efficiency by a great extent as the data repeats and may add towards the correct side or towards the incorrect side, thereby producing unfaithful results.
- Irrelevant observations are any type of data that is of no use to us and can be removed directly.
Fixing Structural errors
The errors that arise during measurement, transfer of data or other similar situations are called structural errors. Structural errors include typos in the name of features, same attribute with different name, mislabeled classes, i.e. separate classes that should really be the same or inconsistent capitalization.
- For example, the model will treat America and america as different classes or values, though they represent the same value or red, yellow and red-yellow as different classes or attributes, though one class can be included in other two classes. So, these are some structural errors that make our model inefficient and gives poor quality results.
- Managing Unwanted outliers
Outliers can cause problems with certain types of models. For example, linear regression models are less robust to outliers than decision tree models. Generally, we should not remove outliers until we have a legitimate reason to remove them. Sometimes, removing them improves performance, sometimes not. So, one must have a good reason to remove the outlier, such as suspicious measurements that are unlikely to be the part of real data.
- Handling missing data
Missing data is a deceptively tricky issue in machine learning. We cannot just ignore or remove the missing observation. They must be handled carefully as they can be an indication of something important. The two most common ways to deal with missing data are:
- Dropping observations with missing values.
Dropping missing values is sub-optimal because when you drop observations, you drop information.
- The fact that the value was missing may be informative in itself.
- Plus, in the real world, you often need to make predictions on new data even if some of the features are missing!
- Imputing the missing values from past observations.
Imputing missing values is sub-optimal because the value was originally missing but you filled it in, which always leads to a loss in information, no matter how sophisticated your imputation method is.
- Again, “missingness” is almost always informative in itself, and you should tell your algorithm if a value was missing.
- Even if you build a model to impute your values, you’re not adding any real information. You’re just reinforcing the patterns already provided by other features.
Both of these approaches are sub-optimal because dropping an observation means dropping information, thereby reducing data and imputing values also is sub-optimal as we fil the values that were not present in the actual dataset, which leads to a loss of information.
Missing data is like missing a puzzle piece. If you drop it, that’s like pretending the puzzle slot isn’t there. If you impute it, that’s like trying to squeeze in a piece from somewhere else in the puzzle.
So, missing data is always informative and indication of something important. And we must aware our algorithm of missing data by flagging it. By using this technique of flagging and filling, you are essentially allowing the algorithm to estimate the optimal constant for missingness, instead of just filling it in with the mean.
Some data cleansing tools
So, we have discussed four different steps in data cleaning to make the data more reliable and to produce good results. After properly completing the Data Cleaning steps, we’ll have a robust dataset that avoids many of the most common pitfalls. This step should not be rushed as it proves very beneficial in the further process.