Build and visualize

Use this tool when you want to:

Use the following configuration options to configure the Aggregate tool.

Let's use the aggregate tool to return the total row count for our data set.

The Aggregate tool is commonly used in conjunction with the following tools:

Use the Aggregate tool to calculate the total amount of commission a payee is eligible for in a given period. In this example, we'll use the Aggregate tool in conjunction with the Union tool.

Let's say we had two compensation reports, one tracking commissions for new business and one for renewals, and we added a Union tool to combine these results into one compensation report. Our result likely looked something like this:

As you can see from these results, we have multiple entries for payees for the same pay period. We can add an Aggregate tool to combine these rows and calculate the total commission rate for the payee for the period.

To achieve this, we'll group by PayeeID, Period, and CompPlan, and we'll perform a SUM operation on the Commission column. Let's call our new column Total commission. The results will look like this:

Use this tool to comply with ASC 606 preparation, ASC 606 amortization standards or amortize your sales commissions.

Use when you want to label your data in a specific way.

The Case tool supports both filter and formula expressions, with the filter function as the default. You can switch between the two functions as necessary.

With the filter function, you can select a column to filter and then choose the filter category and value or text. You can use AND or OR statements to filter. For more information about the Filter functions, see Filter.

With the formula function, you can apply a formula to the data. The formula must return a value of TRUE or FALSE. For more information about the Formula functions, see Formula.

The Case tool requires one data input.

Use the following configuration options to help create your case configuration.

The Case tool can identify the following errors in your formulas:

The Case tool is commonly used in conjunction with the following tools:

Use the Case tool when you have mutually exclusive categories for elements of your business, for example eligibility for transactions, or payee eligibility. In this example, we'll use the Case tool to identify which transactions are eligible to be credited to the payee and which are ineligible.

Let's assume the following criteria: for a transaction to be eligible, we need to check that it was closed in a maximum of 30 days. In our sample data, we can see that this information is tracked in the TransClosingDays column.

We'll add a Case tool to our calculation that will add a new column called TransactionEligibility. We'll set the default value as Ineligible, which means that any transaction that does not meet our case, will be marked as ineligible.

Next, we'll create an Eligible case using a filter. For our example, the case that we want is TransClosingDay column less than or equal to 30.

After our Case tool is applied, our new column is added to our data set, with transactions marked as Eligible or Ineligible.

Use when you want to answer a question about your data.

Use when you need to add date and time information to your data set.

The Date add tool requires one data input.

Use the following configuration options to configure the Date add tool.

Date aggregation can be useful when you're preparing your data for Forecasting.

The Date aggregate tool requires one data input.

Use the following configuration options to help create your Date aggregate configuration.

Use this if you want to know how much time has passed between two dates.

The Date diff tool requires one data input.

Use the following configuration options to help create your Date diff configuration.

The Date diff tool is commonly used in conjunction with the following tools:

Use the Date diff tool to calculate the time difference between two dates. In this example, we'll use the Date diff tool to calculate the number of days it took to close a transaction. This information is important for determining transaction eligibility.

In our transaction data, we can see that we have two columns tracking dates. The LineItemEndDate column tracks the closing date of the transaction and the IncentiveDate column tracks the transaction date.

The time between these two dates represents the total number of days it took to close this transaction. To calculate it, we'll add a Date diff tool, and we'll name the new column TransClosingDays. We'll select Days as the unit of time, and then specify the IncentiveDate as the start date and the LineItemClosingDate as the end date.

The result is a new column that counts the number of days between our two dates:

The Formula tool requires one data input.

Use the following configuration options to help create your Formula configuration.

Use the Formula tool to perform calculations on your existing data. In this example, we'll add a Formula tool to calculate the total commission payout for payees. We'll do this by multiplying our sales amount by the rate.

Let's say we have the following transaction data:

To calculate commissions, we'll need to multiply the value in the SalesAmount column with the value in the Rate column.

This creates a new column called Commissions:

Sales Planning Integrations uses the following data types to construct formulas:

Incentives uses the following data types to construct formulas:

The behavior of round() for floats can be surprising because most decimal fractions cannot be represented exactly as a float.

For example, round(2.675, 2) will return 2.67 instead of the expected 2.68.

You can read Floating Point Arithmetic: Issues and Limitations for more information.

The Formula tool can find the following errors in your data set:

Combine formulas to transform data into an existing column. Sales Planning Integrations creates a new column with the output.

Functions

Sales Planning Integrations offers the following types of functions to use in your formulas:

Table 21. Formula functions

Function	Description	Example	Syntax	Notes
Abs	Returns the absolute value of a number.	If you want to show the difference between this month's sales and last month's sales as a percentage, but you do not want the percent change to be a negative value, use a formula similar to the following example: ABS(Current - Prior)/Prior In this example, the formula is subtracting last month's sales from this month's sales and dividing it by last month's sales to get the percentage difference.	Abs(Number)	Number: The number of which you want the absolute value.
Acos	Returns the arccosine of a number.		Acos(Number)	Number: The cosine of the acosine angle you want, must be from -1 to 1.
Asin	Returns the arcsine of a number.		Asin(Number)	Number: The sine of the asine angle you want, must be from -1 to 1.
Atan	Returns the arctangent of a number.		Atan(Number)	Number: The tangent of the angle you want.
Ceil	Rounds a number up to the nearest integer.		Ceil(Number)	Number: The number or column that you want to round.
Concat	Concatenates all the given text and numbers.		Concat(Texts/Numbers...)	Texts/Numbers...: Any number of columns (Text or Number), user input text or numbers to concatenate with each other.
Contains	Returns either true or false if Text contains the specified Target text.		Contains(Text,Contained text)	Text: The text containing the text you want to find. This can be a column or user input text. Contained text: The text you want to find. This can be a column or user input text.
Cos	Returns the cosine of a given angle.		Cos(Number)	Number: The angle in radians for which you want the cosine.
Date	Returns a date given the specified Year, Month, and Day.		Date(Year,Month,Day)	Year: A four digit number representing the year or column. Month: A one or two digit number representing the month or column. Day: A one or two digit number representing the day of the month or column.
Endswith	Returns either true or false if Text ends with the specified Ending text.		Endswith(Text,Ending text)	Text: The text containing the text you want to find. This can be a column or user input text. Ending text: The text you want to find. This can be a column or user input text.
Floor	Rounds a number down to the nearest integer.		Floor(Number)	Number: The number or column that you want to round.
If	Returns the first input if true and the second input if false.	If the sale amount is greater than $100, you receive a 5% commission. Otherwise, you receive a 2% commission. IF(Data.Value > 100, Data.Value * 0.05, Data.Value * 0.02) Nested IF() example: If your sale amount is greater than $100, you receive 5% commission. If your sale is greater than $50, you receive 3%; otherwise, you receive 2%: IF(Data.Value > 100, Data.Value * 0.05, IF(Data.Value > 50, Data.Value * 0.03, Data.Value * 0.02))	If(Condition,True Result,False Result)	Condition: The condition you want to test. True Result: The value to return if condition is true. False Result: The value to return if condition is false.
Isnull	Returns true for empty rows. Returns false for records that are not empty.		Isnull(Column) In general, any base operation between a real number and null results in null, such as the following examples: 1+null = null1 *null = null	Column: The column to check for empty state.
Log10	Returns the base- 10 logarithm of a number.		Log10(Number)	Number: The positive real number for which you want the base- 10 logarithm.
Log2	Returns the base-2 logarithm of a number.		Log2(Number)	Number: The positive real number for which you want the base-2 logarithm.
Max	Returns the maximum value between columns for numbers and dates.	If, for each deal, you receive a 5% commission, but there is a minimum of $5 per deal you earn, you can use the following formula to determine whether the 5% commission is higher than the $5 minimum: MAX(Data.Value*0.05, $5)	Max(Numbers/Dates...)	Numbers/Dates...: Any columns (Number or Date), or user input numbers or dates of which you want to find the maximum. If you have an If statement similar to the following example: IF(A>B,A,B), you may want to use the MAX operator.
Min	Returns the minimum value between columns for numbers and dates.	If 5% commission is paid on each deal to a maximum of $100, the following formula pays either 5% commission or $100, whichever is less: MIN(Data.Value*0.05 , 100) MIN(Data.Value)	Min(Numbers/Dates...)	Numbers/Dates...: Any columns (Number or Date), or user input numbers or dates of which you want to find the minimum. If you have an If statement similar to the following example: IF(A>B,A,B), you may want to use the M operator.
Mround	Returns a number rounded to the nearest multiple.		Mround(Number,Multiple)	Number: The value to round, either a numeric value or column. Multiple: The multiple used to round the number, either a numeric value or column.
Now	Returns the current time.		Now()
Pad	Adds leading or trailing characters to the text to meet the specified length.		Pad(Text,Text length,Pad text,Pad side)	Text: Column from data or user input. Text length: Number of characters or column that indicates the text length for each row. Pad text: User input or column, that contains single/multiple characters or whitespace. If left empty, it defaults to white space. Pad side: "left" or "right" or a column that indicates the pad direction for each record.
Pow	Returns the result of a number raised to a power.		Pow(Number,Power)	Number: The base number. Power: The exponent to which the base number is raised.
Round	Rounds a number to a specified number of digits.	If you want to round your results to the nearest cent, use a formula similar to this example: ROUND(Result, 2) In this example, the formula rounds the output to 2.	Round(Number,Number of digits)	Number: The number or column that you want to round. Number of digits: The number of digits to which you want to round to.
Sin	Returns the sine of a given angle.		Sin(Number)	Number: The angle in radians for which you want the sine.
Sqrt	Returns a square root of a number.		Sqrt(Number)	Number: The number for which you want the square root.
Startswith	Returns either true or false if Text starts with the specified Starting text.		Startswith(Text,Starting text)	Text: The text containing the text you want to find. This can be a column or user input text. Starting text: The text you want to find. This can be a column or user input text.
Tan	Returns the tangent of a given angle.		Tan(Number)	Number: The angle in radians for which you want the tangent.

Use the Lag tool when you want to see the trends and patterns that emerge from the transformed data. For example, you can use the Lag tool to view your revenue month over month. The Lag tool gives you a row over row comparison.

Use when you have inconsistent text columns and want to combine them into a single column.

The Merge columns tool requires one data input.

Use the following configuration options to help create your Merge columns configuration.

Use when you want to scale values so they fall between a given range.

If you want to scale values without giving a range, use the standard scaler.

Use when you want to find values in your data that might be outliers. You can then investigate why these values are outliers and, optionally, remove them.

Use when you want to calculate a running average for a column.

Use when you want to calculate an accumulating total for a column.

The Running total tool requires one data input.

Use the following configuration options to help create your Running total configuration.

Use the Running total tool to see how a total accumulates. For example, a payee might have multiple transactions within the same period. Their compensation for each transaction may not depend solely on the total for the month, but on where the total stood as the transaction came in. In this example, we'll add a Running total tool that groups transactions and adds the sales ACV for each transaction within that group to the total. This lets us track how that total builds up transaction by transaction. This is an important reporting requirement, as it lets us identify which transaction pushes the total past a threshold or cap.

Let's say we have the following transaction data:

To see a running total of SalesACV, we'll add a Running total tool that specifies SalesACV as the value column and groups transactions by PayeeID, BusinessType, and TransactionPeriod. This adds a new column called SalesACV Running Total.

As you can see, with the Running total tool, you get a line for each transaction, which calculates the cumulative total within that transaction group. In contrast, if you were to use the Aggregate tool instead, each transaction group would contain one line with the total sales ACV. For example, for payeeID 303485, you would only see the final row with the total of 37317.32 sales ACV.

Use when you want to scale values without specifying a range.

If you want to scale values between a given range, use the min max scaler.

Use when you want to know the total length of a text column.

Use when you want to know the average of two numeric columns.

Use the Word Frequency tool to perform a word or phrase frequency count in a particular column across your data set.

The Word Frequency tool requires two data inputs. The first one is the data source where the tool will look for specific words or phrases. The second is a data source containing the words or phrases.

Use the following configuration options to help create your rules.

Use this tool to find how many times each word is showing up in a specified column. Then, the tool sums up how many instances of each word for you.

For example, if you want to find out how many times the words Apple, Peach and Orange are listed in a particular column. Enter the target column and run the tool for the sums:

Use when you want to categorize values.

Use the following configuration to use the Category encoder.

There is a case where the Category encoder will encode two values to one number. When you build the pipe, the encoder learns the unique values in the column, and assigns a numeric value to each column. When you export the pipe, the encoder assigns the same numeric value for the values it already knows about. If there’s a value that the Category encoder did not learn in the build, it assigns it a particular value, such as max value + 1.

For example, if the Category encoder learns about A, B and C in the build, then the Category encoder sees A, D and E in the export. The encoder will assign A to 0, D to 3 and E to 3.

A blank empty string or text value in the build and in the export gets assigned to that particular value. If in the build there’s A, B and blank, the encoder assigns A to 0, B to 1, and blank to 2. Then, in export, if there’s A, blank, D and E, it will assign A to 0, blank to 2, D to 2 and E to 2.

Use the Clean Character tool to select text columns to clean the non-ASCII characters. All non-text columns are disabled in the column drop-down.

The default is to replace the existing column. However, if you choose add new column, the new output column is appended with the suffix _cleaned. For example, the new column could be named column_cleaned.

After you add your data source to your pipe, you can add and configure the Clean Character tool to clean your data set.

Use when your data set contains a general date column, and you want to break it down further.

The Date part tool requires one data input.

Use the following configuration options to help create your Date part configuration.

If you don't need a column, you can remove it.

If you want to remove the majority of columns from your data set, use the Select tool.

We start with this data set:

In the Columns to drop field, select or type ColumnA.

As a result, the data set now looks like this:

Use when you want to extract text in specific ways using regular expressions.

You can also use the text part tool to extract text.

Use when you need sample or placeholder data, or when you need to provide default values for empty values in a column.

Use when you want to explore a subset of your data.

The Filter tool requires one data input.

Use the following configuration options to help create your Filter configuration.

In this example, we have a data set that contains customer IDs and an NPS score.

Let's say we want to explore data only for customers considered "detractors" (a score of 6 or less). We can remove the rows we don't need by using the Filter tool:

As a result, the data set now looks like this:

Use the Filter tool to narrow down your data based on rules. In this example, lets assume we're creating a calculation to determine payout rates for monthly commissions. As a first step, we would need to filter our rate table to only show monthly commissions.

Our rate table may look like this:

Since we're only interested in the MONTHLY COMMISSION component, we'll add our Filter tool and set up our rule.

This creates the rule: Component equals MONTHLY COMMISSION. To meet the criteria of your rule, your new data set only includes rows with a MONTHLY COMMISSION component.

Use this tool to identify errors that can break your hierarchy. Build your pipe and then clean the invalid rows prior to uploading your data to Varicent Sales Planning.

When the tool runs, two columns are added to the output:

Select the applicable columns in your data set from the drop down in each field to configure this tool:

The Hierarchy validator finds and displays errors in a separate column in the row viewer. The following errors could be found in your data set:

Use when you want to categorize values.

Use when you want to remove blank values.

Use when you want to clean up your data so it doesn't contain any extreme values that could affect your analysis.

Use when you want to repeat rows in your data set.

The Repeat tool requires one data input.

Use the following configuration options to help replicate your data.

Use the Repeat tool to repeat your data a specified number of times. This repeated data can be used to test different logic and and choose the most effective approach. Combine the Repeat tool with the Random number generator tool to support forecasting through simulations.

For example, use the Repeat tool to repeat the dataset 100 times. Then, add the Random number generator tool to the pipe. The Random number generator tool will generate 100 simulations based on these repeats, which can be used to forecast different outcomes. You will need to specify the original dataset in the Random number generator tool, so it can partition by the repeat ID and learn the distribution from the original data.

Use when you want to replace values in your data.

In this example, we have two values in the VoicemailPlan column that mean the same thing.

Let's clean this up so we have consistent values.

As a result, the data set now looks like this:

The Select tool requires one data input.

Use the following configuration options to help create your Select configuration.

The Select tool is commonly used in conjunction with the following tools:

Use the Select tool to streamline your data to only include necessary information. In this example, we'll use Select in conjunction with the Join tool.

Say we've calculated the year-to-date attainment for payees at the end of each quarter. The results for this calculation may contain the following columns:

Now we want to look up the bonus amounts that each payee qualifies for. To do this we'll join our YTD attainment calculation with an effective-dated table that contains bonus amounts based on attainment. This table may contain the following columns:

We'll perform a join to combine the following columns:

Our new data set will now match the payees with the bonus amounts that they qualify for each quarter. It may look something like this:

We have a lot of data that we don't need. We can use the Select tool to clean up our data and keep only the columns needed to calculate bonus amounts.

We'll add a Select tool and configure it to keep the Payee, Quarter, CompPlan, and IncrementalBonus columns. Now our output shows us only the relevant information:

Use when you want to extract a specific word part of the sentence. If you just want to return part of a sentence irrespective of the word count, use the Text part tool.

Use when you want to return a specific part of a text value.

To use this tool, you need a text column.

When you run this tool, it replaces the data in the text column with the part you specify.

Use when you want to extract part of a text column.

Use when you want to remove extra spaces from text columns.

If you have have a text column written in HTML, you can use this tool to remove tags from those values.

Use when you want to find out how many unique rows are in your data.

You can either use your entire data set or choose a subset. To use the whole data set, select the Use all columns checkbox. To use a subset of columns, choose the columns from the Columns to include drop down. Any columns that aren't chosen are ignored.

The Unique tool requires one data input.

Use the following configuration options to help create your Unique tool configuration.

This tool takes two data sets. You can select the data source with the combinations to be used for matching, and this is the data Sales Planning Integrations will use to match and join the two data sets.

When configuring the tool, you can choose which Match type you want to use:

The output contains all records from the data set, plus an additional column indicating if one record matches any combination. The value will be "True" or "False".

When the ID Column is selected, an additional column will display the combination ID when a record matches a combination. If the record does not match any combination, the value will be empty.

Use this tool when you want to compare two data sets to find matching values.

Let's say you have two data sets. The first contains a list of online t-shirt orders, and the other contains the collections available for the season.

Using Combination Matcher, you can identify the orders you can fulfill based on the matched values between the two data sets, such as the t-shirt color and size.

This tool takes two data sets. You can select the data source to be used for matching, and this is the data Sales Planning Integrations will use to match and join the two data sets. One input is the "messy" imperfect data containing multiple rows that you want to match to a single row in the other data source. The other input is the data set that contains unique IDs, and serves as an "answer key".

When configuring the tool, the Source column is used to match the "messy" data to the "answer key" data. The Match column helps train the tool to correctly match the rows.

This tool joins the two data sets using a many-to-one method. Each row from the first input is mapped to, at most, one row from the second input. The output also adds a Similarity Measure column that shows the likelihood of the match being correct.

Use this tool when you want to detect matching data between two data sets.

Let's say you have two data sets. The first contains transaction data of purchases made by customers. This information is entered manually, so there are some misspellings or missing information in some rows. The second data set contains customer or account information. This data set is the "answer key" where each row represents a unique customer ID with no missing or incorrect information.

Without cleaning up the transaction data set, Sales Planning Integrations would treat a misspelled name and a correctly-spelled name as 2 different customers. We want to use the Fuzzy Matcher to fuzzy-match those rows to the same customer ID. When you run the tool, it fuzzy-matches each row in one data set to a maximum of one row in the other data set.

Use when you need to combine two data sets.

If you want to combine data sets but restrict it to only matching columns, use the Union tool instead.

Select the join type to combine columns:

Learn more about the join types...

In the advanced settings, you can select different comparison operators. Equal is the default operator. You can choose from the following operators to filter:

Note: If you select the Like operator, the pattern type appears.

To use this tool, you need two data sets.

When you run this tool, it appends columns to the primary data set based on the secondary data set. The data type must be the same in both key columns.

Use the following configuration options to configure the Join tool.

You have two data sets. The Universe column from the top and bottom data sets are the related columns that will allow us to merge the top and bottom nodes together.

The Join tool is commonly used in conjunction with the following tools:

Use the Join tool to combine two data sets. This lets you match data based on selected key columns. For example, we can use a Join tool to match payee bonus amounts to payees based on their year-to-date attainment for the quarter.

Say we've calculated the year-to-date attainment for payees at the end of each quarter. Our data may look something like this:

We want to look up the bonus amounts that each payee qualifies for. To do this, we'll join our YTD attainment calculation to an effective-dated table that contains bonus amounts based on attainment. This table may look like this:

To combine these two data sets, we'll add a Join tool and then configure the tool to combine the following columns:

This matches the payee with their bonus amount for the quarter. The results look like this:

The Join tool gives you a breakdown of your data sources and offers suggestions within the Row viewer to help you merge your data and get the results that you want:

To use this tool, you will need two sets of data, a main data set and a lookup data set. There are three fields to configure for the input:

Use when you want to look for a specified value in your data set.

You want to match the Region code in the top and bottom data sets, and add the corresponding Chair of board and Number of schools columns. Here is an example of the top and bottom data sets and the output:

Here is the output from the Lookup tool:

This tool takes two data sets. The top input is the imperfect data containing multiple rows that you want to match to a single row in the bottom data source. You can replace the top data set in later exports. The bottom input is the data set that contains unique IDs. This is the data used to match and join the two data sets. In practical terms, the top input is "messy" data that has incorrect or missing information in some columns. The bottom input is the data set that serves as an "answer key".

When configuring the tool, the Target column is used to match the "messy" data to the "answer key" data. The Matching columns help train the tool to correctly match the rows.

This tool joins the two data sets using a many-to-one method. Each row from the top input is mapped to, at most, one row from the bottom input. The output also adds a Probability column that shows the likelihood of the match being correct.

Use this tool when you want to train a model to fuzzy-match data sets. The tool gets better at matching as you add more data and build the pipe.

Let's say you have two data sets. The first contains transaction data of purchases made by customers. This information is entered manually, so there are some misspellings or missing information in some rows. The second data set contains customer or account information. This data set is the "answer key" where each row represents a unique customer ID with no missing or incorrect information.

Without cleaning up the transaction data set, Sales Planning Integrations would treat a misspelled name and a correctly-spelled name as 2 different customers. We want to use the Smart Matcher to fuzzy-match those rows to the same customer ID. When you run the tool, it fuzzy-matches each row in the top data set to, at most, one row in the bottom data set.

Add two or more data sets to the Union tool. To use this tool, you need at least one matching column shared by both data sets.

When you build this tool, it appends matching columns from the second data set to the end of the first data set.

Use when you want to combine data sets, but limit the number of columns to only those relevant to the first data set.

When you want to combine data sets without restrictions, use the Join tool instead.

Use the following configuration options to help create your unions.

The Union tool is commonly used in conjunction with the following tools:

Use the Union tool when you have multiple data sets with the same columns and you want to combine them into one source. In this example, we'll use the Union tool to merge two compensation reports into a single report for comprehensive analysis.

Say we've calculated commissions for payees using two pay measures, one for new business and one for renewals, and we want to combine these results into one data set.

We'll start with data from our two calculation outputs:

To merge these two compensation reports into one source, we'll add a Union tool.

We have two calculation results with three rows each. Since our column names match exactly, our Union tool will append all rows to one data set, leaving us with one source that contains all payee commissions.

This is often the first step in building a new pipe if you're not using a connector.

In some cases, you can use this tool to bring in placeholder data until you can bring in data from another pipe using the Pipe tool.

There are two scenarios where you'll need to use Export:

Use when you want to work with a sub-set of your data.

Use to generate more data or to address classification problems in your data.

The number of inputs feeding into the Pipe tool must be the same, and you can bring in any data sources of your choice. Ensure that you connect all of your data sources in the Pipe tool. Automatic column mapping is based on column names.

If the column names or column types are different, you must manually map the columns in a provided form.

Use when you want to bring in data from another pipe or re-use a portion of pipe logic in more than one workbench.

Let's say you want to bring an output from pipe "Function" into your current pipe, "Sandbox". There are three things you need to make sure of:

If you are using an older version of the pipe tool, you may be prompted to upgrade to the latest version. Upgrading can enhance your experience and unlock new features.

However, there is a warning when you are prompted to upgrade. Some of your existing configurations may not transfer over to the latest pipe tool version. These configurations could be lost in the process.

Use when you want to work with a smaller sample of your data.

Use when you want to explore the pipe builder and aren't ready to use your own data set.

Use when you want to keep a historical record of your data.

You can also use this as a way to save a data set state before you transform the data.

Use to address classification problems in your data.

Use when you want to add income data to your data set.

Use when you want to add population information to your data set.

To use this tool, you need two data sets. The top node is the main data source, containing the items to be assigned, such as account IDs. The bottom node is the supporting data source containing the assignees, such as seller names.

Use this tool to identify a way to distribute data from one set of data to another. For example, you want to assign sellers to sales accounts. Each account has a specific number of potential sales. You want to distribute the accounts in a way that each seller receives a fair amount of potential sales.

Enter the following information to configure the tool:

From the Row viewer, you can access the Data profile link to open the column details and compare column visuals. The results are available when you select one of the Classifier, Predictor or Regressor tools.

Use when you want to predict values.

Following a successful build using the Classifier tool, Smart exclude identifies and automatically excludes columns that don’t help predict the target column. Smart exclude will only consider columns not already manually excluded. If you want to disable this setting to troubleshoot, test, or run a calculation that is taking too long, go to the Advanced settings under the Configure tab.

In the row viewer, there are three tabs: Data, Stats and Tool.

The Data tab consists of your imported data. View all of the imported data in one spot.

The Stats tab consists of the statistics for your data. View all of the top values for each column.

The Tool tab is a visualization of additional insight into the tool and the data. The following columns are available:

A confusion matrix can help you understand how your model is performing.

To use this tool, you must include:

The results will forecast for that number of periods according to the frequency you select.

You can opt to use the Automatic feature in the Advanced configuration section. The Automatic feature decides the best available settings to use in the following categories: