Data Parsing

Fix data parsing errors with Chat Data Prep.

Akkio works best with comma delimited, flat datasets. However, you may be able to get around this requirement with Chat Data Prep.

Remove Non-numeric Characters

Remove symbols that may impact analysis and model building.

Example Prompt: Remove all non-numeric characters, such as currency symbols, commas, apostrophes, and quotation marks, from numerical values in the dataset. Ensure that spaces and other necessary characters in non-numerical text remain unaffected.

AI Interpretation: The transform function removes all non-numeric characters from the values in each column of the dataset.

Tips:

• Useful for when symbols or punctuation in the data may be affecting analysis.

• Columns to be changed may need to be specified.

Semicolon Deiminated Data

Example Prompt: Read each ; as a delimiter.

AI Interpretation: The transform function splits a string column into multiple columns based on a delimiter. Each value in the string is separated by a semicolon (;) and is split into separate columns in the resulting dataset.

Tips:

• Akkio will always assume comma delimitation on upload.

• The delimiter is likely the issue if all of your headers are listed as a single column header.

Nested Datasets

Exapmple Prompt: Parse the column "client" as a json array. Take the first element of the array and make new columns based on the parsed json.

AI Interpretation: The transform function converts a column in the dataset from a string representation of a list of dictionaries to separate columns for each key-value pair in the dictionaries.

Tips:

• If the nested fields are consistent over rows, CDP may be used to generate a rule to unnest them into separate columns.