Icon

05 Data Visualization - Solution

Solution to an exercise for data visualization.

Explore statistics and relationships in data with the Data Explorer, Scatter Plot, and Table View nodes. Build an interactive view with a scatter plot and an interactive table.

CHECK YOUR ANSWERS:

Data Explorer:
1. 41 different native countries are represented in the data
2. Native-country column contains 583 missing values. Occupation column contains 1843 missing values. Workclass column contains 1836 missing values.

Scatter Plot and Table View:
1. There is a slight positive correlation between hours per week and commuting time
2. Those people in the data who work <25 hours per week and commute the most are never married from their marital status

Interactive Dashboard:
The native country of the people in the data who work <25 hours per week but commute the most is United States












Exercise: Data Explorer1) Read the adult.csv file by executing the File Reader node2) Inspect the properties of the data with the Data Explorer node- How many different native countries are represented in the data?3) In the interactive view, exclude the nominal columns that contain missing values- Which of the nominal columns contain missing values? How many missing values each? Note! The Data Explorer node is part of the KNIME JavaScript Views (Labs) Extension 41 different native countries arerepresented in the data.The columns containing missing values:- native-country, 583- occupation, 1843- workclass, 1836 Exercise: Scatter Plot and Composite View1) Read the adult_w_commute.table file by executing the Table Reader node2) Assign colors to the rows based on the marital status3) Draw a scatter plot of hours per week vs. commute time- Do you observe any particular relationship between these two columns?- What can you say about the marital status of people who work <25 hours per week andcommute the most?4) Create an interactive table that displays the data. Use the Table View node.5) Encapsulate the Scatter Plot and Table View nodes into a component. Open thecomponent's interactive view.6) Switch to the mouse mode "Select" in the scatter plot view and select the data points with<25 working hours and >120 min commuting time7) Show only selected rows in the interactive table- What is the native country of the selected data points? There is a slight positive correlationbetween hours per week and commutingtimePeople who work <25 hours per week andcommute >120 min per day have themarital status "never married"The native country of these people isUnited States Read data adult.csv Inspect theproperties of the dataColor bymarital statusRead adult_w_commute.table File Reader Data Explorer Color Manager Table Reader Component Exercise: Data Explorer1) Read the adult.csv file by executing the File Reader node2) Inspect the properties of the data with the Data Explorer node- How many different native countries are represented in the data?3) In the interactive view, exclude the nominal columns that contain missing values- Which of the nominal columns contain missing values? How many missing values each? Note! The Data Explorer node is part of the KNIME JavaScript Views (Labs) Extension 41 different native countries arerepresented in the data.The columns containing missing values:- native-country, 583- occupation, 1843- workclass, 1836 Exercise: Scatter Plot and Composite View1) Read the adult_w_commute.table file by executing the Table Reader node2) Assign colors to the rows based on the marital status3) Draw a scatter plot of hours per week vs. commute time- Do you observe any particular relationship between these two columns?- What can you say about the marital status of people who work <25 hours per week andcommute the most?4) Create an interactive table that displays the data. Use the Table View node.5) Encapsulate the Scatter Plot and Table View nodes into a component. Open thecomponent's interactive view.6) Switch to the mouse mode "Select" in the scatter plot view and select the data points with<25 working hours and >120 min commuting time7) Show only selected rows in the interactive table- What is the native country of the selected data points? There is a slight positive correlationbetween hours per week and commutingtimePeople who work <25 hours per week andcommute >120 min per day have themarital status "never married"The native country of these people isUnited States Read data adult.csv Inspect theproperties of the dataColor bymarital statusRead adult_w_commute.tableFile Reader Data Explorer Color Manager Table Reader Component

Nodes

Extensions

Links