This is the initial release of the high_frequency_checks Python package, which provides a framework for performing high-frequency checks on survey data. This package is designed to help identify potential errors or inconsistencies in the data, enabling data quality assurance before further analysis.
Features
Indicator Modules: The package includes modules for calculating and validating various indicators commonly used in survey data analysis, such as:
- Food Consumption Score (FCS)
- Reduced Coping Strategy Index (rCSI)
- Household Dietary Diversity Score (HDDS)
- Household Expenditure (HHEXPF_7D, HHEXPNF_1M, HHEXPNF_6M)
- Livelihoods Coping Strategies (LCS_FS, LCS_FS_R, LCS_EN)
- Housing conditions
- Demographic information
Configurable Checks: Each indicator module includes a set of configurable checks to identify potential errors or inconsistencies in the data. These checks can be customized based on the specific requirements of the survey or data collection process.
Flagging System: The package implements a flagging system to mark records with potential issues. Flags are generated based on the configured checks, and a narrative description is provided for each flagged record, facilitating review and follow-up.
Master Sheet Generation: The package can generate a master sheet that consolidates the original data with the calculated indicators and flags. This master sheet can be used for further review and analysis.
Data Loading: The package includes utilities for loading data from various sources, such as Excel files or databases.