What Does Data Preprocessing Mean?
Data preprocessing involves transforming raw data to well-formed data sets so that data mining analytics can be applied. Raw data is often incomplete and has inconsistent formatting. The adequacy or inadequacy of data preparation has a direct correlation with the success of any project that involve data analyics.
Preprocessing involves both data validation and data imputation. The goal of data validation is to assess whether the data in question is both complete and accurate. The goal of data imputation is to correct errors and input missing values — either manually or automatically through business process automation (BPA) programming.
Data preprocessing is used in both database-driven and rules-based applications. In machine learning (ML) processes, data preprocessing is critical for ensuring large datasets are formatted in such a way that the data they contain can be interpreted and parsed by learning algorithms.
Techopedia Explains Data Preprocessing
Data goes through a series of steps during preprocessing:
Data Cleaning: Data is cleansed through processes such as filling in missing values or deleting rows with missing data, smoothing the noisy data, or resolving the inconsistencies in the data.
Smoothing noisy data is particularly important for ML datasets, since machines cannot make use of data they cannot interpret. Data can be cleaned by dividing it into equal size segments that are thus smoothed (binning), by fitting it to a linear or multiple regression function (regression), or by grouping it into clusters of similar data (clustering).
Data inconsistencies can occur due to human errors (the information was stored in a wrong field). Duplicated values should be removed through deduplication to avoid giving that data object an advantage (bias).
Data Integration: Data with different representations are put together and conflicts within the data are resolved.
Data Transformation: Data is normalized and generalized. Normalization is a process that ensures that no data is redundant, it is all stored in a single place, and all the dependencies are logical.
Data Reduction: When the volume of data is huge, databases can become slower, costly to access, and challenging to properly store. Data reduction aims to present a reduced representation of the data in a data warehouse.
There are various methods to reduce data. For example, once a subset of relevant attributes is chosen for its significance, anything below a given level is discarded.
Encoding mechanisms can be used to reduce the size of data as well. If all original data can be recovered after compression, the operation is labeled as lossless. If some data is lost, then it’s called a lossy reduction. Aggregation can also be used to condense countless transactions into a single weekly or monthly value, significantly reducing the number of data objects.
Data Discretization: Data could also be discretized to replace raw values with interval levels. This step involves the reduction of a number of values of a continuous attribute by dividing the range of attribute intervals.
Data Sampling: Sometimes, due to time, storage or memory constraints, a dataset is too big or too complex to be worked with. Sampling techniques can be used to select and work with just a subset of the dataset, provided that it has approximately the same properties of the original one.