Unit: II

Data Preparation, Summarisation and

Visualisation Using Spreadsheet
Content
◆​ Data Preparation and Cleaning
●​ Data Preparation
●​ Data Cleaning
●​ Find and Remove Duplicates
●​ Removing Duplicate Values
●​ Data Validation
●​ Identifying Outliers in Data
●​ Finding Missing Values
●​ Data Sorting
●​ Filtering Data
●​ Conditional Formatting
●​ Text to Column
◆​ Data Transformation and Analysis
●​ Data Summarization
●​ Covariance
●​ Correlation Matrix
●​ Moving Average
◆​ Data Visualization and Presentation
●​ Data Visualization
●​ Types of Data Visualizations in Excel
●​ Pivot Tables
●​ Pivot Chart
●​ Interactive Dashboard

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
Data preparation and cleaning
❖​Data Preparation
➢​ Data Preparing is a crucial step in data analysis and machine
learning, involving cleaning, transforming, and organizing raw
data for effective analysis or model training. The goal is to ensure
quality and consistency for specific tasks.
➢​Key Steps in Data Preparation

■​ Data Collection
●​ Gathering raw data from various sources (databases,
spreadsheets, APIs, sensors).
■​ Data Cleaning
●​ Detecting and correcting errors, inconsistencies, and
missing values.
●​ Handling outliers, duplicate entries, and irrelevant data
points.
■​ Data Transformation
●​ Converting data into a suitable format.
●​ Normalization, scaling numerical values, encoding
categorical variables, aggregation/disaggregation.
■​ Data Integration
●​ Merging data from multiple sources.
●​ Resolving conflicts in dataset joining.
■​ Data Reduction
●​ Reducing dataset size or complexity.
●​ Feature selection, dimensionality reduction, and
sampling.
■​ Data Formatting
●​ Standardizing formats (e.g., date formats, variable
naming conventions).
■​ Data Splitting

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
●​ Dividing data into training, validation, and test sets
for model development and evaluation.
➢​ Importance of Data Preparation
■​ Ensures data quality for generating valid and accurate
insights.
■​ Poor data preparation leads to incorrect conclusions and
unreliable models.
❖​Data Cleaning
➢​ Data cleaning (also known as data cleansing or data scrubbing) is
the process of identifying, correcting, or removing inaccurate,
incomplete, or irrelevant data to ensure high data quality for
accurate analysis, reporting, and decision-making.
➢​Steps in Data Cleaning
■​ Handling Missing Data
●​ Detection: Identify missing values (blanks, NA, null).
●​ Strategies to handle missing data:
◆​ Removal: Delete non-critical rows/columns with
missing values.
◆​ Imputation: Replace missing values with mean,
median, mode, or predictive modeling.
◆​ Placeholder: Keep missing values but flag them
for future attention.
■​ Removing Duplicate Data
●​ Identify and delete duplicate records to prevent skewed
analysis.
■​ Correcting Data Errors
●​ Fixing Inconsistencies: Standardize formatting (e.g.,
“NY” vs. “New York”).
●​ Correcting Data Entry Errors: Fix typos, misentered
values, and misspellings.
■​ Standardizing Data
●​ Normalization: Ensure uniform formats (e.g., “Male”
vs. “M”).
●​ Transformation: Convert data to a common scale or
unit (e.g., currency, weight).
■​ Outlier Detection and Treatment
●​ Identify outliers and decide whether to remove,
correct, or retain them.
■​ Validating Data Accuracy
●​ Cross-check data with reliable sources and business
rules.
●​ Ensure logical consistency (e.g., transactions should
have valid dates).
■​ Removing Irrelevant Data
●​ Filter out unnecessary data (outdated records, noise,

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
unneeded columns).
■​ Formatting and Structuring Data
●​ Ensure proper date formats, text casing, and
structure (e.g., splitting combined fields).
❖​ Find and Remove Duplicates
➢​ Duplicate data can sometimes be useful but often complicates data
analysis.
➢​ It is recommended to find, highlight, and review duplicates before
removal instead of deleting them immediately.
➢​Removing Duplicate Values (MS Excel)
■​ Steps to Remove Duplicates in Excel: (Alt + A + M)
●​ Select the data containing duplicates.
●​ Go to Data > Remove Duplicates.
●​ Uncheck columns that should not be purged.
●​ Click OK to remove duplicates

❖​Data Validation
➢​ Ensures accuracy, consistency, and integrity of data in Excel.
➢​ Helps restrict invalid data entry, reducing manual corrections.
➢​Steps to Apply Data Validation in Excel
■​ Select the cells where data validation is needed.
■​ Go to Data Tab > Data Validation to open the dialog box.
■​ Under the Settings tab, define validation criteria:
●​ Allow: Choose data type (Whole Number, Decimal,
List, Date, Time, Text Length, or Custom Formula).
●​ Data: Set conditions (e.g., between, equal to, not equal
to).

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
●​ Minimum/Maximum: Define range (e.g., 100 to 1000).

➢​Optional Features
■​ Input Message:
●​ Appears when the cell is selected.
●​ Provides instructions for valid data entry.
■​ Error Alert:
●​ Triggers when invalid data is entered.
●​ Styles: Stop (blocks entry), Warning (allows but alerts),
Information (suggests correction).
●​ Title & Message: Explains the error and suggests
correction.
❖​Identifying Outliers in Data
➢​ Outliers affect accuracy, reliability, and usability of data.
➢​ An outlier is a data point significantly different from the expected
range.
➢​ Identifying and minimizing outliers ensures accurate data analysis
and forecasting.
➢​Steps to Handle Outliers in MS Excel
■​ Review the Data
●​ Check for errors (typos, data entry mistakes) manually
or using automated tools.
■​ Sort the Data Values
●​ Arrange data in ascending/descending order for easier
analysis.
■​ Analyze Data Values
●​ Identify large discrepancies.
●​ Remove statistical anomalies instead of deleting all

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
extreme values.
■​ Identify Data Quartiles
●​ Use Excel’s QUARTILE() function:
◆​ =QUARTILE(A5:A50, 1) → First quartile (Q1,
25th percentile).
◆​ =QUARTILE(B2:B200, 3) → Third quartile
(Q3, 75th percentile).
■​ Define the Interquartile Range (IQR)
●​ IQR = Q3 - Q1 (expected range without outliers).
■​ Calculate Upper & Lower Bounds
●​ Upper Bound: = Q3 + (1.5 * IQR)
●​ Lower Bound: = Q1 - (1.5 * IQR)
■​ Remove the Outliers
●​ Identify values outside the upper and lower bounds.
●​ Delete them for more accurate analysis and
visualization.
❖​Finding Missing Values
➢​ Excel does not have a built-in function for listing missing values.
➢​ Importance of Identifying Missing Values:
■​ Data Integrity: Ensures dataset completeness.
■​ Data Reconciliation: Useful in finance and auditing.
■​ Quality Assurance: Identifies anomalies and data entry
errors.
■​ Efficient Analysis: Helps in accurate data analysis.
➢​Listing Missing Values in Excel
➢​ Using IF, ISNUMBER, and MATCH Functions
■​ IF: Returns a value based on a condition.
■​ ISNUMBER: Checks if a value is a number.
■​ MATCH: Searches for a value in a range and returns its
position.
➢​ Formula to Identify Missing Values:
■​ =IF(ISNUMBER(MATCH(ROW(A1), A:A, 0)), "",
ROW(A1))
■​ This formula checks for missing values in column A (range
1-100).
■​ Drag the formula down in column B to list missing values.
➢​ Using the Filter Feature
■​ Apply Filter on column B.
■​ Exclude blank cells to display only missing Values​

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet

❖​Data Sorting
➢​ Organizes data in a specific order for better analysis.
➢​ Types of Sorting:
■​ Text: Alphabetical (A-Z or Z-A).
■​ Numbers: Smallest to largest or vice versa.
■​ Dates & Time: Oldest to newest or newest to oldest.
■​ Example: Sorting a Column in Descending Order
■​ Select the data and press Ctrl + Shift + L (Shortcut Key).
■​ Click the down arrow on the column.
■​ Select Largest to Smallest (numbers) or Z to A (text).
❖​Filtering Data
➢​ Temporarily hides unwanted data to focus on relevant information.
➢​Filtering a Range of Data
■​ Select the column to apply the filter.
■​ Go to Data > Filter.
■​ Click the column header arrow.

■​ For text data: Uncheck values you want to hide.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet

■​ For numeric data: Use filters like "Between" to view values

in a specific range.

■​ Click OK to apply the filter.

❖​Conditional Formatting
➢​ Enhances data visualization by filling cells with colors based on
conditions.
➢​ It Helps in identifying patterns and trends in data.
➢​ Example: Highlight Cells with Values Greater than 350
■​ Select the range of cells for conditional formatting.
■​ Go to Home Tab > Styles Group > Conditional Formatting.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet

■​ Click Highlight Cells Rules > Greater Than…

■​ Enter the desired value (350) and choose a formatting style

■​ Click OK
❖​Text to Column
➢​ Splits data from a single column into multiple columns for better
readability.
➢​ Separates first name, last name, and profession stored in one
column.
➢​ Data must have a consistent delimiter (Comma, Semicolon, Space,
etc.).
➢​Steps to Split Data in MS Excel
■​ Select the cell or column containing the text to split.
■​ Go to Data > Text to Columns.
■​ In the Convert Text to Columns Wizard, select Delimited >
Next.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
■​ Choose the Delimiters (Comma, Space, etc.).
■​ Click Next, preview the split, and select Finish.

Data Summarization

★​Data Summarization Methods in Excel

○​ Excel provides multiple functions for summarizing data effectively.
○​ Descriptive Statistics
■​ Helps analyze datasets using built-in functions.
○​ Common Excel Functions for Summarization
■​ SUM, AVERAGE, MEDIAN (Total, Mean, and Median):
●​ =SUM(A2:A100) → Adds all values in the range.
●​ =AVERAGE(A2:A100) → Calculates the mean.
●​ =MEDIAN(A2:A100) → Finds the median.
■​ COUNT, COUNTA (Counting Entries):
●​ =COUNT(A2:A100) → Counts numeric values.
●​ =COUNTA(A2:A100) → Counts all non-empty cells.
■​ STDEV.P, VAR.P (Standard Deviation & Variance):
●​ =STDEV.P(A2:A100) → Computes standard
deviation.
●​ =VAR.P(A2:A100) → Computes variance.
■​ MIN, MAX (Smallest & Largest Values):
●​ =MIN(A2:A100) → Finds the smallest value.
●​ =MAX(A2:A100) → Finds the largest value.

★​Covariance
○​ Definition: Measures the joint variability between two random
variables.
○​ Use Case: Helps determine relationships between two datasets.
○​ Covariance Formula in Excel
○​ Function:

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
●​ =COVARIANCE.P(array1, array2)
■​ Array1: First dataset (range of numeric values).
■​ Array2: Second dataset (range of numeric values).
■​ Example in Excel:​
To find covariance between columns C and D (rows 1 to 10):
○​ =COVARIANCE.P(C1:C10, D1:D10)
○​ Mathematical Formula for Covariance
■​ Covariance between two variables X and Y is calculated as:
○​ COV (X, Y) = ∑[(X - x)(Y- y)]/n
■​ Where:
●​ COV (X, Y) = Covariance between X and Y variables
●​ X, Y = Individual data points in datasets X and Y
●​ x, y = Mean of datasets X and Y
●​ n = Number of data points
■​ Notes
●​ If arrays contain text or logical values, they are
ignored.
●​ Only numeric data is considered; non-numeric cells
are skipped.
●​ Both datasets must be equal in size (same number of
data points).
●​ Datasets must not be empty, and their standard
deviation should not be zero.
★​Correlation Matrix
○​ A correlation matrix is a table that displays the correlation
coefficients between multiple variables.
○​ Summarizes large datasets and helps identify patterns.
○​ Used in multiple linear regression analysis to understand
relationships between independent variables.
○​ Types of Correlation
■​ Positive Correlation: Both variables increase or decrease
together. (e.g., Height & Weight)
■​ Negative Correlation: One variable increases while the other
decreases. (e.g., Speed & Travel Time)

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet

○​ Calculating Correlation in Excel

■​ CORRELFunction =CORREL(array1, array2)
●​ Example:
○​ =CORREL(B2:B13, C2:C13) (Finds
correlation between datasets in columns B & C).
■​ PEARSON Function
●​ Performs the same function as CORREL.
●​ Syntax =PEARSON(array1, array2)
●​ Example:
○​ =PEARSON(B2:B13, C2:C13).
■​ Notes:
●​ If arrays contain text, logical values, or blanks, they
are ignored.
●​ If arrays have different lengths, an N/A error occurs.
●​ If either array is empty or has a zero standard
deviation, a divide-by-zero error occurs.

○​ Interpreting Correlation Matrix Results

■​ The diagonal values in the matrix are always 1
(self-correlation).

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
■​ Negative coefficients indicate an inverse correlation.
■​ Positive coefficients indicate a direct relationship between
variables.
★​Moving Average
○​ Also known as rolling average, running average, or moving mean.
○​ Identifies trends by averaging subsets of a dataset:
■​ Stock Trading: Analyzing security trends over time.
■​ Business Analytics: Understanding market trends using past
sales data.
■​ Weather Forecasting: Predicting seasonal temperature
patterns.

○​ Types of Moving Averages

■​ Simple Moving Average (SMA)
■​ Exponential Moving Average (EMA)
■​ Variable Moving Average (VMA)
■​ Triangular Moving Average (TMA)
■​ Weighted Moving Averages (WMA)
○​ Calculating Simple Moving Average in Excel
■​ Using the AVERAGE Function =AVERAGE(B2:B4)
●​ Computes the moving average for the first 3 months
(rows 2 to 4).
●​ Can also be calculated as:
○​ =SUM(B2:B4)/3
●​ To find Subsequent Average, the formula can be
copied in other rows.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet

○​ Visualizing Moving Average with a Trendline:

■​ Step 1: Click anywhere on the chart.
■​ Step 2: Go to Layout Tab > Analysis Group > Trendline
Option.
■​ Step 3: Select the desired trendline type.

Data Visualisation and Presentation

❖​Data Visualization
➢​ Converts raw data into visual insights for better understanding.
➢​ Helps identify trends, patterns, and relationships in data.
➢​ Enhances decision-making and communication of complex
information.
➢​ Makes data more accessible for users by summarizing large
datasets visually.
❖​Steps to Create a Chart in Excel
➢​Organize Data Properly
■​ Ensure data is structured in rows and columns with
appropriate headers.
■​ Remove duplicate or irrelevant data before visualization.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
■​ Data should be consistent and complete to avoid errors in
the chart.
➢​Select the Data for Visualization
■​ Click and drag to highlight the data range, including both
row and column headers.
■​ Ensure the selected range contains all necessary values for
accurate chart representation.

➢​Choose a Chart Type

■​ Go to the Insert Tab > Charts Section.
■​ Click on the dropdown menu and select the most suitable
chart type, such as:
●​ Column Chart – To compare different categories.
●​ Line Chart – To show trends over time.
●​ Pie Chart – To represent proportions.
●​ Bar Chart – Similar to column chart but horizontal.
●​ Scatter Plot – To display relationships between two
variables.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
➢​Insert the Chart
■​ After selecting the chart type, Excel will automatically
generate the chart.
■​ The chart will appear inside the worksheet for further
modifications.
■​ You can drag to reposition or resize the chart using the
corner handles.
➢​Customize the Chart
■​ Click on the chart to access Design & Format tabs in the
toolbar.
■​ Modify the chart title to describe the chart’s purpose clearly.
■​ Adjust axis labels to specify what the X and Y axes represent.
■​ Add or remove the legend for better clarity.
■​ Enable data labels to display exact values on the chart.
■​ Use color themes to improve visualization and distinguish
categories.

➢​Edit the Data (Optional)

■​ If the underlying data changes, Excel will automatically
update the chart to reflect new values.
■​ Modify the dataset directly in the worksheet to update the
chart dynamically.
■​ Use Chart Filters to display only selected data for analysis.
❖​Types of Data Visualization in Excel
➢​ Data visualization in Excel allows users to transform raw data into
meaningful graphical representations, helping to identify trends,
patterns, and relationships. Choosing the right type of chart
enhances data interpretation and simplifies decision-making.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
■​ Below are the commonly used types of data visualization
in Excel:
➢​Column Chart
■​ Uses vertical bars to compare values across categories.
■​ Ideal for tracking trends over time or comparing different
groups.
■​ Can be formatted as clustered, stacked, or 100% stacked for
multiple datasets.
■​ Examples:
●​ Risk/Loss Reduced over the Year

➢​Bar Chart
■​ Similar to a column chart but uses horizontal bars.
■​ Useful when category names are long or there are many
categories.
■​ Provides better readability for large datasets compared to
column charts.
■​ Example:
●​ Comparing Profit and Discount Across Products

➢​Line Chart

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
■​ Connects data points with lines to show trends and changes
over time.
■​ Best suited for continuous data such as stock prices or
revenue growth.
■​ Can display multiple data series for comparison.
■​ Example:
●​ Sales Comparison Between China, UK & US

➢​Pie Chart
■​ Represents data as slices of a circle, showing proportions of a
whole.
■​ Best for percentage-based comparisons among a few
categories.
■​ Becomes less effective when dealing with too many
categories.
■​ Example:
●​ Diet Recommendation

➢​Scatter Plot
■​ Plots individual data points to analyze relationships between
two variables.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
■​ Helps identify correlations, trends, and outliers in datasets.
■​ Can include trendlines for better interpretation.
■​ Example:
●​ Correlation Between Sales($) & Temperature(°C)

❖​Pivot Tables
➢​ Quickly sumrise large Datasets.
➢​ Analyse numerical data in detail.
➢​ Answer unexpected question about the data.
➢​ They provide a user-friendly and interactive way to query data.
■​ They can handle large datasets
■​ like the one in the figure with 6 columns and 213 rows.

➢​Steps to Insert a Pivot Table in Excel

■​ Step 1: Click any single cell inside the dataset.
■​ Step 2: Click on the Insert tab → Select PivotTable in the
Tables group.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet

■​ Step 3: In the PivotTable dialog box, Excel automatically:

●​ Selects the data range.
●​ Sets the default location to New Worksheet.

■​ Step 4: Click OK to create the Pivot Table.

■​ Step 5: Drag fields into the Pivot Table areas:

●​ Rows area:

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
◆​ Example – Drag Product to list product names.
●​ Values area:
◆​ Example – Drag Amount to show total amount.
●​ Filters area:
◆​ Example – Drag Country to filter by country.
❖​Pivot Charts
➢​ A Pivot Chart is a dynamic visualization tool that helps summarize
and analyze large datasets interactively. It updates automatically
when changes are made in the pivot table, making data exploration
easier.
➢​Steps to Insert a Pivot Chart:
■​ Step 1: Click any cell inside the Pivot Table.
■​ Step 2: Go to PivotTable Analyze → Click PivotChart under
Tools.

■​ Step 3: Click OK in the Insert Chart dialog box.

■​ Step 4: The Pivot Chart appears and updates with the Pivot
Table.

❖​Interactive Dashboard
➢​ An Interactive Dashboard in Excel is a one-page report that allows
businesses to track and measure crucial KPIs and metrics. It
provides a visual representation of data using charts, figures, and
tables, making it easier to analyze and interpret complex information.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
With interactive features like slicers and timelines, users can filter
and explore data dynamically without modifying the original dataset.
➢​ Steps to Create an Interactive Dashboard in Excel
■​ Step 1: Define the Purpose of the Dashboard
●​ Clearly define why the dashboard is being created and
who will use it.
●​ Different stakeholders require different insights:
◆​ CFOs focus on financial metrics like revenue
and profit.
◆​ Investors look for a summarized dashboard
covering all departments.
●​ Understanding the audience ensures that only relevant
data is collected for decision-making.
■​ Step 2: Gather and Convert Data into a Pivot Table
●​ Organize data in a structured table format before
creating a Pivot Table.
●​ Steps to create a Pivot Table:
◆​ Select the dataset containing relevant business
metrics.
◆​ Go to Insert Tab > PivotTable.
◆​ Click OK to insert the Pivot Table into a new
worksheet.
●​ If multiple Pivot Charts are needed, duplicate the Pivot
Table sheet for each chart.
■​ Step 3: Create Charts Using the Pivot Table
●​ To visualize sales performance, create a Pivot
Table-based chart:
◆​ Drag Month to the Rows area to display sales
data by month.
◆​ Drag Product to the Columns area to compare
different products.
◆​ Drag Sales to the Values area to calculate total
sales.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet

■​ Step 4: Insert a Pivot Chart

●​ Select the Pivot Table, then go to PivotTable Analyze
> PivotChart.
●​ Choose a suitable chart type (e.g., Column Chart for
sales comparison).
●​ Click OK, and the chart will be inserted into the
worksheet.
■​ Step 5: Format and Customize the Chart
●​ Click on the chart to access formatting options and
enhance visualization.
●​ Use the + sign (Chart Elements) to add:

◆​ Chart Title – Rename for better clarity.

◆​ Legend – Enable or disable to improve
readability.
◆​ Axes – Edit X and Y-axis labels.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
◆​ Data Table – Display numerical values below the
chart.

●​ Move the chart to the Interactive Dashboard Sheet for

better presentation.
●​ Repeat these steps to create additional Pivot Charts
as needed.
■​ Step 6: Add Interactive Features
●​ Select any Pivot Chart and go to PivotChart Analyze
to enable interactive elements.
■​ Step 7: Insert a Timeline for Date-Based Filtering
●​ Click on Insert Timeline to add a date-based filter to
the dashboard.

●​ Ensure that the dataset contains a Date column, and

select it when prompted.
●​ Click OK to insert the Timeline, allowing users to filter
data by specific time periods.
■​ Step 8: Add a Slicer for Filtering Data
●​ Click on a Pivot Chart, then go to Insert > Slicer.
●​ Select the variables to filter data dynamically.
●​ To apply the slicer to multiple charts, follow these steps:
◆​ Click on the Slicer to activate it.
◆​ Go to Slicer Tab > Report Connections.

CWB: Class With Brother

 Unit: II
Data Preparation, Summarisation and
Visualisation Using Spreadsheet
◆​ Select all the relevant Pivot Tables to ensure
they sync with the slicer.

CWB: Class With Brother