INTRODUCTION TO

DATA ANALYTICS

OLUWATOBI ADEOYE
 WHAT IS DATA ANALYTICS

• Data analytics is the process of examining, cleaning, transforming, and

modeling data to uncover meaningful insights, patterns, and trends that can
be used to inform decision-making and drive business outcomes.
• It involves applying statistical and computational techniques to large datasets
to extract valuable information and make data-driven decisions.
 Categories of Data

• Unstructured data: these are data that does not have a predefined format or structure.
• Examples of unstructured data include emails, social media posts, audio recordings, and text
documents.

• Semi-structured data: these are data have been partially organized but are not in a well-
defined format yet.
• Examples of semi-structured data include texts in XML files, JSON files, and NoSQL
databases
 Categories of Data

• Structured data: these are well organized and formatted data.

• Examples of structured data include data in relational databases,
spreadsheets, and CSV files.
 Data Analytics Tools
• Excel: Excel is a widely used and easy-to-use tool for data analytics,
especially for beginners. It's excellent for basic data manipulation,
calculations, and creating simple charts and graphs. Its strength lies in its
accessibility and familiarity for many users.
• Power BI: Power BI is a tool primarily used for data visualization. It allows
users to create interactive dashboards and reports, connect to various data
sources, and transform data. It's often used in business intelligence contexts
for sharing insights across an organization.
 Data Analytics Tools
• Tableau: Similar to Power BI, Tableau is another popular tool used for data
visualization. It excels at creating visually appealing and interactive data
visualizations, making complex data easier to understand. Tableau is known
for its strong community and extensive features for exploring data.
• Looker Studio: (Previously Google Data Studio) Looker Studio is a free tool
for creating interactive dashboards and reports. It integrates seamlessly with
Google's ecosystem (Google Analytics, Google Sheets, BigQuery, etc.) and
offers various connectors for other data sources. It's a good choice for those
already working within the Google suite.
 Data Analytics Tools
• SQL (Structured Query Language): SQL is a language used to query
databases. It's fundamental for data analysts to retrieve, manipulate, and
manage data stored in relational databases. Understanding SQL is crucial for
working with large datasets and extracting specific information for analysis.
• Python: Python is a versatile programming language commonly used for
data analytics. Its extensive libraries (like Pandas for data manipulation,
NumPy for numerical operations, Matplotlib and Seaborn for visualization,
and Scikit-learn for machine learning) make it a powerful tool for complex
data analysis, statistical modeling, and building data-driven applications.
 Data Preparation
• Data preparation is a crucial step in data analytics that occurs before you
start analyzing the data. It involves several key processes to ensure the data is
clean, transformed, and organized for effective analysis
• In essence, data preparation is about making raw data ready for analysis by
improving its quality and usability, which directly impacts the accuracy and
reliability of the insights derived.
 Data Preparation
• Cleaning Data: This step focuses on identifying and correcting errors within your
dataset.
• This can include:
• Handling Missing Values: Addressing gaps in your data, either by removing rows
with missing information or by imputing values based on statistical methods or
other data points.
• Correcting Incorrect Data: Fixing typos, inconsistencies, or inaccurate entries.
• Removing Duplicates: Eliminating redundant records that could skew your analysis.
 Data Preparation
• Transforming Data: This involves converting data from one format to another to make it suitable for
analysis.
• Examples include:
• Converting Data Types: Changing a text field to a numerical field if it represents a quantifiable value.
• Normalizing or Scaling Data: Adjusting data to a common scale to prevent certain features from
dominating the analysis, especially important for machine learning algorithms.
• Aggregating Data: Summarizing data at a higher level of granularity (e.g., calculating total sales per
month from daily sales data).
• Creating New Features: Deriving new variables from existing ones that might provide more valuable
insights.
 Data Preparation
• Organizing Data: This step focuses on structuring the data in a way that makes it
easy to analyze. This might involve:
• Structuring Unstructured or Semi-structured Data: For data like text or images, this
could mean extracting relevant information and putting it into a more structured
format.
• Combining Data from Multiple Sources: Merging datasets from different origins
into a single, unified view.
• Reshaping Data: Pivoting or unpivoting data to change its layout to better suit the
analytical task.
 Data Analysis
• After the crucial step of data preparation, which involves cleaning,
transforming, and organizing the data , the next phase in data analytics is
Data Analysis. This stage is where you apply various techniques to extract
insights and meaning from the now-prepared data.
• Data analysis involves using different methods to uncover patterns, trends,
and valuable information hidden within the datasets. Some commonly used
data analysis techniques include:
 Categories of Data Analysis

• i. Descriptive Analysis
• ii. Diagnostic Analysis
• iii. Predictive Analysis
• iv. Prescriptive Analysis
 Categories of Data Analysis

• Descriptive Analysis focuses on summarizing historical data to understand

what has happened in the past.
• It involves techniques such as data aggregation, data visualization, and
Exploratory Data Analysis (EDA) to provide insights into patterns and
trends within the data.
 Categories of Data Analysis

• An example of descriptive analysis involves analyzing customer transaction

data to gain insights into purchasing behavior and trends.
• Scenario: A retail company wants to understand her customers' purchasing
patterns and preferences to optimize inventory management and marketing
strategies.
 Categories of Data Analysis

• Diagnostic Analysis: this aims to determine why certain events occurred by

identifying the root causes of observed outcomes.
• It involves analyzing relationships between variables, conducting hypothesis
testing, and performing statistical inference to understand the factors
influencing specific phenomena.
 Categories of Data Analysis

• An example of diagnostic analysis involves analyzing sales data to understand

why there was a decrease in revenue during a specific time period.
• Scenario: A retail company experienced a significant drop in sales revenue
during the holiday season compared to the previous year. The management
team wants to understand the root causes behind this decline to inform
future strategies and decision-making.
 Categories of Data Analysis

• Predictive Analysis involves using historical data to make predictions about

future events or trends.
• It uses statistical modeling, machine learning algorithms, and data mining
techniques to identify patterns and build predictive models that can forecast
future outcomes with a certain level of accuracy.
 Categories of Data Analysis

• An example of predictive analysis involves using historical sales data to

forecast future sales revenue for a retail company.

• Scenario: A retail company wants to predict her sales revenue for the
upcoming holiday season to optimize inventory management, staffing, and
marketing strategies.
 Categories of Data Analysis

• Prescriptive Analysis does not only predict future outcomes but also
recommend actions that can optimize decision-making and achieve desired
objectives.
• It combines predictive models with optimization algorithms, simulation
techniques, and decision theory to generate actionable insights and make
recommendations for action.
 Categories of Data Analysis

• An example of prescriptive analysis involves using customer data to

recommend personalized marketing strategies for a retail company.
• Scenario: A retail company wants to optimize its marketing campaigns to
increase customer engagement and drive sales. The company aims to leverage
prescriptive analytics to recommend personalized marketing strategies
tailored to individual customer preferences and behavior.
 Data Visualization
• Following data analysis, Data Visualization is the next crucial step in data
analytics. It involves representing data using charts, graphs, and other visual
tools. The primary importance of data visualization lies in its ability to help
you understand and effectively communicate the insights and meaning
extracted from the data.
• Commonly used data visualization tools include Tableau, Power BI, and
Excel. When creating visualizations, it is essential to choose the right type of
chart or graph that can best represent the data to ensure clarity and accurate
communication of findings.
 Conclusion
• Data analytics is an important field that involves analyzing and interpreting
data to extract insights and meaning. To get started in data analytics, you
need to understand the basics, including data preparation, data analysis, data
visualization, and ethics and privacy. With the right tools and techniques, you
can use data analytics to make better decisions and gain a competitive
advantage in your field.