3_Excel Data Analysis
3_Excel Data Analysis
Excel Sort
The sort commands work for text too, using A-Z order.
Excel Filter
Filters can be applied to sort and hide data. It makes data analysis easier.
The menu is accessed in the default Ribbon view or in the Data section in the
navigation bar.
Applying Filter
Filters are applied by selecting a range and clicking the Filter command.
Excels Tables
Example:
Formatting a range into a table will give it a new form with a fixed structure.
Tables open access to new functionality such as: filtering, automations and
styling.
1. Select range A1:F22
Table Design
Converting a range into a table gives access to a menu called "Table Design".
Resize
Remove duplicates
Convert to range
Style options (Total row, Header row, Banded row etc..)
Formatting
Table Name:
Excel gives tables default names such as: Table 1, Table 2, Table 3 and so on.
The name of the table can be found in the Table Design tab
The resize table command allows you to change the size of the table by entering
a range.
Drag to Resize
Removing duplicates are helpful when cleaning a dataset and you do not want
to include copies.
The Remove Duplicate function is found in the Ribbon under the Table Design
tab.
The command allows you to specify the column where you want to find and
remove duplicates.
Once applied it will return the number of deleted values and how many unique
ones that remains.
Tables can be converted to ranges by selecting a cell in the table range and
clicking on the Convert to Range command.
The command to convert to range is found in the Table Design tab, in the Tools
group.
Excel Table Style
Excel has many ready to use styles which can be applied for tables.
Example: Blue, Table Style Medium 2, which is how the default looks like.
The conditions are rules based on specified numerical values or matching text.
The conditions are rules based on specified numerical values, matching text,
calendar dates, or duplicated and unique values.
Appearance Options:
The web browser version of Excel offers the following appearance options for
conditionally formatted cells:
Light Red Fill with Dark Red Text
Yellow Fill with Dark Yellow Text
Green Fill with Dark Green Text
Light Red Fill
Red Text
Red Border
Greater Than...
Less Than...
Between...
Equal To...
Text That Contains...
A Date Occurring...
Duplicate/Unique Values
Yesterday
Today
Tomorrow
In the last 7 days
Last Week
This Week
Next Week
Last Month
This Month
Next Month
Duplicate Values.. is one of the options for the condition, and can check for
both duplicate and unique values.
Repeat the steps, but instead choose Bottom 10 Items... in the menu and
select the "Light Red Fill with Dark Red Text" appearance option.
The "Top 10%..." and "Bottom 10%..." rules will highlight cells with one of the
appearance options based on the cell value being the top or bottom percent of
values in a range.
Let's first apply the Bottom 10%... rule to the Speed values.
Let's try the same with the top 10% Speed values.
Repeat the steps, but instead choose Top 10%... in the menu and select the "Green
Fill with Dark Green Text" appearance option.
Above and Below Average Rules are premade types of conditional formatting in
Excel used to change the appearance of cells in a range based on your
specified conditions.
Appearance Options
The web browser version of Excel offers the following appearance options for
conditionally formatted cells:
Repeat the steps, but instead choose Below Average in the menu and select
the "Light Red Fill with Dark Red Text" appearance option.
Data Bars are premade types of conditional formatting in Excel used to add
colored bars to cells in a range to indicate how large the cell values are
compared to the other values.
Example:
Let's apply the Data Bars conditional formatting to the Speed values.
Icon Sets are premade types of conditional formatting in Excel used to add
icons to cells in a range to indicate how large the cell values are compared to
the other values in the range.
Directional
Shapes
Indicators
Ratings
Example:
You can also use the Manage Rules menu option to clear conditional
formatting rules.
Let's remove the Color Scale rule applied to all the Stat values:
It will also indicate which cells the rule is applied to. Which, in this example,
is C2:H9.
Excel Charts
Pie chart
Column chart
Line chart
Clustered bar( )
Stacked bar( )
Clustered Bar charts are used when the value of data is important but the order
is not.
Example:
2. Click on the insert menu, then click on the bar menu ( ) and
The chart gives a visual overview for the "Grass", "Fire", "Water" and "Bug"
type Pokemons in generation 1.
Now let's do the same for generation 2 Pokemons and compare the results with
the last example.
2. Click on the insert menu, then click on the bar menu ( ) and
Stacked bar charts are used to highlights the total amount of contribution for
each category.
The charts are used when you have more than one data column.
Example:
We want to find out the total number of generation 1 and 2 Pokemons in each
of these type 1 categories: "Grass", "Fire", "Water" and "Bug".
2. Click on the insert menu, then click on the bar menu ( ) and
100% Stacked Bar is used to highlights the proportion of contribution for each
data column in a category.
This is done by scaling the total value of each category in a stacked bar chart
to 100.
The charts are used when you have more than one data column.
Example:
We want to find out the proportion of Pokemon types "Grass", "Fire", "Water"
and "Bug" in generation 1 and 2.
2. Click on the insert menu, then click on the bar menu ( ) and
Clustered column()
Stacked column()
100% Stacked column()
Clustered Column Chart
Clustered Column charts are used when the value of data is important but the
order is not.
Example:
2. Click on the insert menu, then click on the column menu ( ) and
Stacked Column charts are used to highlights the total amount of contribution
for each category.
The charts are used when you have more than one data column.
Example:
This is done by scaling the total value of each category in a stacked column
chart to 100.
The charts are used when you have more than one data column.
Example:
Pie charts are used for representing values of qualitative (categorical) data.
2-D pie ( )
Doughnut ( )
2-D pie charts are used when you only have one data column.
Example:
2. Click on the Insert menu, then click on the Pie menu ( ) and
Doughnut charts arrange the data as slices in a circle with hollow center.
Doughnut charts are often used when you have more than one data column.
Example:
2. Click on the Insert menu, then click on the Pie menu ( ) and
Line charts are typically used for showing trends over time.
Line charts are used with data which can be placed in an order, from low to
high.
Line
Line charts are used for showing data ordered from low to high.
Line with markers highlights data points with markers on a line chart.
Stacked Line
Example:
Excel Radar Charts
Radar charts can only show data that can be ordered from low to high.
Radar ( )
Radar charts show data as as vertices on a polygon.
The relevant distance from the center of the polygon shows the
value of the data point.
Filled radar ( )
Filled radar is similar to radar chart. The only difference is that
inside the charts are filled with color.
E.g.,
Excel Chart Customization
Excel has many options for how to customize a chart. You will learn more about
the different options in this chapter.
This doughnut chart shows the ratio of different Pokemon types in generations 1
and 2.
The "Water" type, shown in gray has the most Pokemons in both generations.
Then there are types "Bug", shown in yellow, "Grass", shown in blue and "Fire",
shown in orange.
Moving Charts:
Resizing Charts:
Resizing will scale all the elements in the chart except the text.
he default chart title in Excel is "Chart Title". This is not informative. The title
should describe the chart.
2. Find "Chart Title" text in the newly opened menu and change it