Data cleaning and denoising
During the data collection process, the Parrot platform will face some common data quality problems, such as missing data, outliers, etc., and requires data cleaning and denoising operations to ensure the quality and reliability of the data.
Missing data handling: The Parrot platform detects and handles missing values in the data. For missing values, you can choose to delete missing data, use interpolation to fill missing values, or use other related data for prediction completion.
Outlier detection and processing: The Parrot platform will detect outliers in the data through statistical methods or machine learning methods. For outliers, you can choose to delete, correct or smooth them to avoid adverse effects on subsequent analysis and modeling.
Data deduplication: The Parrot platform will detect and process duplicate values in the data to avoid duplicate data from interfering with subsequent analysis and modeling. For duplicate values, you can choose to delete or merge them.
Unified data format: The Parrot platform will unify the format and data type of data to facilitate subsequent data analysis and modeling. For data of different formats and types, format conversion and data type conversion can be performed.
Abnormal data processing: The Parrot platform will process abnormal data, including but not limited to data smoothing, censoring, truncation and other methods, to eliminate the impact of abnormal data on analysis results.
Last updated