Transformations for Data Prep Recipes

In CRM Analytics, Data Prep provides transformations that allow you to prepare, clean, and transform your data. For example, you can use a transformation to create a calculated column based on a formula. You add transformations inside a Transform node. You can string together multiple transformations to manipulate data sequentially.

• Bucket Transformations: Categorize Column Values
  With CRM Analytics Data Prep, you can bucket your numbers, text, and date fields to group and organize data.
• Cluster Transformation: Segment Your Data
  In CRM Analytics, use the Cluster transformation in a Data Prep recipe to segment rows of data into distinct clusters based on common characteristics. For example, you can cluster accounts based on number of employees, numerical rating, and annual revenue. Using the clusters, you can identify products and services to upsell to each account based on other accounts in the same cluster, apply different service handling or marketing campaigns based on cluster, or define different metrics and KPIs for analysis.
• Data Type Conversion Transformations: Convert Column Types
  In CRM Analytics, the data type of a dataset column determines how you can query that column’s data. For example, you can filter and group by a text or date column, or perform calculations on a number column. When you load data into a dataset, CRM Analytics sometimes tags a dataset field with the wrong type. If needed, use the column-type conversion transformations in a Data Prep recipe to convert columns to the correct types.
• Date and Time Transformations: Calculate on Date Fields
  In CRM Analytics, your date fields are key to understanding trends over time or keeping teams aware of upcoming milestones and deadlines. Use the Date and Time transformations to calculate based on dates or make them more helpful to your analysis. With the Now option, you can insert a column with the current date and time in a specified format. Use Date Difference to calculate the duration between two selected date columns as days, months, or years. And use the Add or Subtract Days or Months function to add or subtract days or months from a date column.
• Detect Sentiment Transformation: Determine the Sentiment of Text
  In CRM Analytics, text fields show valuable information such as product reviews and social media posts. Use the Detect Sentiment transformation in a Data Prep recipe to quickly categorize text into sentiments. Choose whether you want sentiment results as a decimal value on a 5-point scale, with 5 as the most positive, or as labels of Positive, Negative, and Neutral. For example, detect the sentiment of survey responses to evaluate how customers feel about your product support. If more than a certain percentage—say 30%—of the comments are negative, escalate the feedback to support management.
• Drop Columns Transformation: Drop Columns from the Recipe
  In CRM Analytics, drop unwanted columns from a Data Prep recipe. For example, you can add a Drop Columns transformation after a Formula transformation to drop input columns used for a calculated column.
• Discovery Predict Transformation: Get Einstein Discovery Predictions
  In CRM Analytics, use the Discovery Predict transformation to populate your datasets with predictive and prescriptive intelligence. When you run a Data Prep recipe with a Discovery Predict node, Einstein calculates and saves predicted outcomes on a row-by-row basis. You can optionally store descriptions of top predictors and improvements. With the Discovery Predict node, you can quickly evaluate predictions across a large set of data, assess multiple models before deploying them into production, and aggregate this information in a dashboard.
• Extract Transformation: Get a Date Component
  In CRM Analytics, use the Extract transformation in a Data Prep recipe to pull a selected component from a date field into a new field. For example, extract the hour component from the Case Created Date column to analyze case creation by hour of the day.
• Edit Attributes Transformation: Change the Column Names and Value Formats
  In CRM Analytics, to make column names more descriptive and apply consistent formats to column values, use the Edit Attributes transformation in a Data Prep recipe. You can set the labels and API names of all columns. You can also set the precision and scale for number columns, character length for text columns, and date formats for date columns.
• Flatten Transformation: Flatten Hierarchies
  In CRM Analytics, the Flatten transformation flattens hierarchical data. For example, you can flatten the Salesforce role hierarchy to implement row-level security on a dataset based on the role hierarchy.
• Format Dates Transformation: Standardize the Date Format in a Column
  In CRM Analytics, if a text column contains dates in different formats, use the Format Dates recipe transformation in a Data Prep recipe to standardize the format for all dates in the column. A consistent format enables you to correctly filter and group records by date, including filtering by date component, such as month. It also ensures you can successfully convert the column type from text to date. Optionally, you can convert the column type from Text to Date.
• Formula Transformation: Create a Calculated Column Based on an Expression
  In CRM Analytics, create a column in a Data Prep recipe that displays values based on a formula calculation. The calculation can include input from other fields in the same row or across rows. For example, you can create a Profit column based on input from Revenue and Cost columns. Enter formulas in EA-SQL format. EA-SQL is a collection of standard and custom functions for numeric, string, and date data.
• Predict Missing Values Transformation: Fill In Missing Values
  In CRM Analytic, use the Predict Missing Values transformation in a Data Prep recipe to complete your data by filling in missing values in a text column. CRM Analytics Intelligently predicts values based on values in other strongly correlated columns in your data.
• Split Transformation: Break Up Column Values
  In CRM Analytic, you can split the strings in a text column into two values by specifying a delimiter. To split column values into more than two parts, add multiple instances of the Split transformation. For instance, you can use 3 Split transformations in a Data Prep recipe to split the full address into the following components: street address, city, state, and zip code.
• Time Series Forecasting Transformation: Forecast Measures
  In CRM Analytic, make decisions today based on forecasts about tomorrow with time series forecasting. A time series forecast takes an ordered series of points and intelligently forecasts the next values. For example, estimate units sold for the next 4 quarters based on the last 5 years of sales. Use the Time Series Forecasting transformation in a Data Prep recipe to run forecasts based on historical data and seasonality.