Akkio Docs
  • Akkio Documentation
    • Akkio FAQ
  • Account and Settings
    • Team Settings
    • Organization Settings
    • Account Settings
    • Role Based Access Control
  • Demo Models
    • Demo Models
      • Lead Scoring
      • Retail Sales Forecasting
      • Predict Credit Card Fraud
      • Identify Customer Churn
  • Setting up Integrations
    • Connecting Data
    • Airtable (Beta)
    • Google Ads (Beta)
    • Google Analytics 4 (Beta)
    • Google BigQuery
    • Google BigQuery (Service Account)
    • Google Sheets
    • HubSpot (Beta)
    • MariaDB (Beta)
    • MongoDB (Beta)
    • MySQL (Beta)
    • PostgreSQL (Beta)
    • Redshift (Beta)
    • Salesforce
    • Akkio Data Chat for Slack
    • Snowflake (Username / Password) (Beta)
    • Zapier
  • Prepare your Data
    • Prepare
      • Chat Data Prep
      • Clean
      • Merge & Fuzzy Merge
      • Table View
      • Pivot View
      • Deploying Chat Data Prep
  • Explore
    • Chat Explore
    • Chart Types
  • Building a Model
    • Predict
      • Insights Report - Classification
      • Insights Report - Regression
    • Forecasting
      • Insights Report - Forecasting
    • Model Types
  • Deploying a Model
    • Deploy
      • Google BigQuery
      • Google Sheets
      • HubSpot (Beta)
      • PostgreSQL (Beta)
      • Salesforce
      • Snowflake (Beta)
      • Web App
      • Zapier
  • REPORTING AND SHARING
    • Reports
    • Dashboards
  • REST API
    • API Introduction
      • Quickstart
  • Concepts
    • Asynchronous Endpoints
    • Authentication
    • Code Generation
    • Terminology
  • Endpoints and Schemas
    • API Specifications
    • Endpoints
      • Chat Explore
      • Projects
      • Training
      • Models
      • Datasets
    • Schemas
    • Additional Libraries
      • Python Library
      • Node.js Library
Powered by GitBook
On this page

Was this helpful?

  1. Akkio Documentation
  2. Prompt Library

Data Parsing

Fix data parsing errors with Chat Data Prep.

Last updated 8 months ago

Was this helpful?

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.