®

Cheat Sheet: Building a KNIME Workflow for Beginners

Getting started with KNIME Analytics Platform EXPLORE ANALYZE
Scatter Plot: Represents Sunburst Chart: Displays Stacked Area Chart: Plots Decision Tree: The Learner node trains a C4.5

(All visualizations are interactive)

● Read through the installation guide at
101.27
Decision Tree
100.00

input data rows as points in categorical columns through multiple numerical data or a CART decision tree. The configuration
90.00

knime.com/installation
a two dimensional plot. a hierarchy of rings. Each ring columns on top of each other
80.00

70.00 window includes options for pruning, early

● Check out the 7 things you should do after installing Input dimensions (columns) is sliced according to the using the previous line as the 60.00 stopping, information measures, splitting
KNIME Analytics Platform at on the x-y axis plot and nominal values in the base reference. The areas in 50.00
values, and more. Both the Learner and the
knime.com/blog/seven-things graphical properties can be corresponding column and to between lines are colored for 40.00
Predictor node provide an interactive view
changed in the the selected hierarchy. This is easier comparison. This chart 30.00

where the decision tree is displayed together

configuration window or a powerful chart for is commonly used to visualize
20.00

● Take the E-Learning Course at 10.00

with the input data propagation.
knime.com/knime-introductory-course interactively in the node multivariate analysis. trending topics.
k-Means: Implements the k-Means clustering
0.00
k-Means
view. -10.00
-14.72
algorithm. Number of clusters must be set
● Browse the workflows on the public EXAMPLES Server
1.00 5.00 10.00 15.00 20.00 25.00 31.00

prior to node execution. This node builds the

available in the KNIME Explorer Line Plot
Line Plot: Plots numerical values in data columns Color Manager
Color Manager: Assigns a color property to each Pie Chart
Pie Chart: Visualizes one aggregated metric for clusters. The Cluster Assigner node finds the
(y-axis) against values in a reference column (x-axis). input row based on the row’s value in a selected different data partitions with colored slices on a circle closest cluster and assigns it to the input data
Understanding the traffic light system: Data points are connected via colored lines. If the column. This color property affects the graphical where the areas are proportional to the metric values. row. Being an unsupervised algorithm, this
Not configured: Node is not yet configured and reference column on the x-axis contains sorted time representation in the upcoming views. The partitions are defined by a categorical column. node pair doesn’t follow the classic Learner -
cannot be executed with its current settings values, the line plot graphically represents the Predictor scheme.
evolution of a time series.
Configured: Node has been correctly configured Logistic Regression Logistic Regression: The Learner node trains a
Data Explorer
Data Explorer: Provides an interactive view to Box Plot
Box Plot: Visualizes numeric columns using the Bar Chart Bar Chart: Visualizes one or more aggregated metrics
and may be executed at any time logistic regression model to predict categorical
summarize the statistics of the input data via quartile statistics. Watch out for the points at the for different data partitions with rectangular bars where
statistical measures and histograms - for both end of the whiskers - they might mark outliers! the heights are proportional to the metric values. The target values. The configuration window includes
Executed: Node has been successfully executed
numerical and nominal columns. partitions are defined by a categorical column. options for solver, input feature choice,
and results can be viewed and used in
regularization functions to avoid overfitting, &
downstream nodes
more.
Scorer
Scorer: Calculates a number of performance
READ measures such as accuracy, F1-score, or
File Reader File Reader: Reads all text files, Table Reader Table Reader: Reads data from a .table file. Explore Cohen’s Kappa, to quantify the quality of a
particularly character separated files, .table files are organized using a KNIME Learner Learner Nodes: Supervised algorithms in KNIME classifier.
such as CSV files. The File Reader is the proprietary format, including the full file Analytics Platform have a Learner node to train a
workhorse for reading text data. structure and are optimized for space and Predictor model on a previously labelled training set.
Numeric Scorer Numeric Scorer: Calculates a number of
speed - providing maximum performance with numerical error measures, such as root mean
minimum configuration! squared error, mean absolute error, or R^2, to
Excel Reader (XLS) Excel Reader (XLS): Reads content from Predictor Nodes: Used for applying models. The
sheets in Excel files (XLS, XLSX). Sheet two inputs are the trained model and the data to quantify the quality of a numerical predictor
and cells to be read can be defined in the Google Sheets Google Sheets Reader: Reads data from a process. The output contains the original data and model.
Reader
configuration window. Google Sheet file. Authentication occurs on the the model predictions.
Google site. Google credentials are not saved ROC Curve ROC Curve: Displays the Receiver Operating
within the KNIME workflow. Characteristic (ROC) curve of a classifier
Table Creator Table Creator: Allows users to manually working on a binary class problem. One of the
create a data table in its configuration Read Transform Analyze Deploy
two classes is arbitrarily chosen as the positive
window as a data sheet. Data cells can be class and the ROC curve is built on the
copied and pasted in the sheet. Perfect for knime:// protocol: References a file path relative to some probabilities/scores produced for that class on
generating small data sets. key location of the current KNIME installation like the input data set.
knime://knime.workflow/../<filename> or knime://<knime.-
Model Reader
Model Reader: Reads machine learning server.mountpoint>/<path>/<filename> Integrations to many open source data analytics tools are
models generated with any of the Learner also available. Some use the KNIME node GUI (H2O, Weka,
nodes. Models are usually saved after Keras, Spark MLlib). Others offer nodes with a development
training and reused in deployment. environment for scripting and debugging (R, Python, Java).

TRANSFORM DEPLOY Resources

Data to Report
Data to Report: Marks the data table to be exported to BIRT -
GroupBy GroupBy: Groups the rows of a table by the unique Math Formula Math Formula: Implements a number of math Joiner Joiner: Joins rows from two data tables based on a partially open source reporting tool integrated within ● KNIME Forum: Join our global
values in selected columns and calculates operations across multiple input columns, from common values in one or more key columns. The KNIME. When switching from KNIME to BIRT, the marked community and engage in conversations
aggregation and statistical measures for the defined simple sum and average, to logarithms and most common join types are possible: inner join, data sets are imported into BIRT. The Image To Report node at forum.knime.com
groups. Despite its simple name, it offers powerful exponentials. All Math Formula operators are also left outer join, right outer join, and full outer join. marks the input images to be exported to BIRT.
functionality and has many unsuspected usages. For available in the Column Expressions node. ● KNIME Books: More tips, ideas, and
example - row deduplication. lessons from knime.com/knimepress
Excel Writer (XLS) Excel Writer (XLS): Writes the input data table to a sheet in
an Excel file (XLS or XLSX).
Pivoting Pivoting: Extends the aggregation functionality of the String to Date&Time String to Date&Time: Converts values in a String Sorter Sorter: Sorts the table in ascending or descending ● KNIME Events: Take a course, attend a
GroupBy node by creating an output data table with column into Date&Time values. The Date&Time order based on the values of a chosen column. In workshop, or join a meetup at
columns and rows for the unique values in selected format contained in the String values can be manually addition, it is possible to sort based on multiple knime.com/events
input columns. Note: the unique values of the defined or auto guessed. columns.
grouping column become rows and the unique Table Writer
Table Writer: Writes the input data table to a file using the
● KNIME Blog: Engaging topics,
values of the pivoting column become columns. .table KNIME proprietary format. This format includes the
full file structure and is optimized for space and speed. challenges, industry news, and
Including the table structure in the file is a great advantage - knowledge nuggets at knime.com/blog
Rule Engine Rule Engine: Applies a set of rules to each row of Cell Splitter Cell Splitter: Splits values in a selected column into Concatenate Concatenate: Merges vertically two data tables, by
the input data table. All Rule Engine operators are two or more substrings, as defined by a delimiter piling up cells in columns with the same name. especially when exchanging data files among users.
also available in the Column Expressions node. match. Delimiter is a set character, such as a comma, Cells in uncommon columns are filled with missing ● Workflow Hub: Browse our example
space, or any other character or character sequence. values. The Concatenate (Optional in) node merges
CSV Writer CSV Writer: Writes the input data table to a CSV file. workflows and/or share your own
vertically up to four data tables. workflows. Show appreciation for others
by adding ratings, or comments at
workflows.knime.com
Partitioning Partitioning: Splits data into two subsets according Column Filter Column Filter: Filters columns in or out from the input Missing Value Missing Value: Defines a strategy to deal with
to a sampling strategy. This node is generally used data table according to a filtering rule. Columns to be missing values in the input data table - either Google Sheets Google Sheets Writer: Writes the input data table into a ● More Guides: Still using SAS or Excel?
to produce a training and a test set to train and retained can be manually picked or selected globally on all columns, or individually for each Writer
Google Sheet file. Authentication occurs on the Google Transition to KNIME Analytics Platform
evaluate a machine learning model. according to their type, or of a regex expression single column.
site. Google credentials are not saved within the KNIME with these handy guides at
matching their name.
workflow. knime.com/knimepress

Row Filter
Row Filter: Filters rows in or out from the input data Column Rename
Column Rename: Assigns new names and types to String Manipulation
String Manipulation: Performs operations on String Send to Tableau
Server
Connectors to Tableau: Export input data table into a ● KNIME Server: For team-based
table according to a filtering rule. The filtering rule selected columns, as configured in the dialog. values in columns, such as combining two or more Tableau file or server for reporting. collaboration, automation, management,
can match a value in a selected column or numbers Strings together, extracting one or more substrings, and deployment check out KNIME Server
in a numerical range. trimming blank spaces, and so on. All operators at knime.com/server
are also available in the Column Expressions node.

© 2018 KNIME AG. All rights reserved. The KNIME® trademark and logo and OPEN FOR INNOVATION® trademark are used by KNIME AG under license from KNIME GmbH, and are registered in the United States. KNIME® is also registered in Germany. KNIME AG Technoparkstrasse 1, 8005 Zurich, Switzerland / [email protected] / www.knime.com