Scribd
Upload
18 views4 pages

Introduction to Data Science Concepts

revision dat science just

Uploaded by

abaasmuuse
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
18 views4 pages

Introduction to Data Science Concepts

revision dat science just

Uploaded by

abaasmuuse
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Chapter one

1. Data is the new oil. It’s valuable, but if unrefined, it cannot really be
used. changed gas, plastic, chemicals,
2. Types of Data
 Unstructured Text Data (Web)
 Semi-structured Dat (XML)
 Streaming Data (images and videos)
3. What is data science ?
 field of study that combines domain expertise
 Data scientists require background in these fundamental
related disciplines

4. Career Opportunities After Completion?


 Data Architect and Administrators
 Data Engineer
 Data Analyst
 Data Scientist
 Machine Learning Engineer
 Statisticians and Mathematicians
 Business IT Analyst
 Marketing Analyst
5. Why study data science ?
 Data is oneof theimportant assets of every organization or
business to make informed decisions - ‘new oil’.
 Big data - people and devices generate data at a growing and
unprecedented speed, e.g. social media.

6. Data science workflow ?


 Capture date : collect date from various resource, also known as
data acquisition, data extraction, data ingestion,

1 | Page writer:
Abaas Muuse
 Managing & date cleaning: remove errors and duplicates, also
known as data cleansing, data preparation
 Exploratory analysis:(EDA): if look data understand use
histogram like prices also knows as exploration analysis ,
descriptive analysis
 Final analysis
 Reporting
7. Major components Artificial intelligence (AI)
 Knowledge Representation
 Natural language processing (NLP)
 Reasoning
 Machine learning
8. What is machine learning?
 study computer algorithms that improve automatically through
experience
9. Difference between AI, machine learning , deep learning ?
Artificial Intelligence (AI): machines think and act like humans.
Machine Learning: enable computer perform tasks without explicit
programming.
Deep learning: subset machine learning basic artificial neural
networks
10. Big data definitions in terms of volume, velocity, and variety,
big data characteristics are often referred to as the “3 Vs of big data”
first defined by Gartner in 2001.
 Volume : This describes the enormous amount of data that is
available for collection and produced from a variety of sources
and devices on a continuous basis.
 Velocity: refers to the speed at which data is generated
 Variety : data is heterogeneous many different sources and can
be structured, unstructured, or semi-structured
11. Data analytics is the process of transforming raw data into
meaningful insights for better decision making, mostly using statistical
processing and machine learning.

12. What is Data Science Used For?


 used for an array of applications, predicting customer behavior
to optimizing business processes.
13. There are four major types of data analytics.

2 | Page writer:
Abaas Muuse
 Descriptive analytics: Analyzes past data to understand
current state and trend identification. retail stores might use
it to analyze last quarter's sales or identify best-selling
products.
 Diagnostic analytics. Explores data to understand why
certain events occurred, identifying patterns and anomalies.
 Predictive analytics. Uses statistical models to forecast
future outcomes based on past data, used widely in finance,
healthcare, and marketing.
 Prescriptive analytics: actions based on results from other
types of analytics to mitigate future problems or leverage
promising trends. example, a navigation app advising based
on current traffic conditions
14. Data science applications.
 Data exploration and visualization
 Financial analysis and fraud detection
 Healthcare Analysis
 Driverless cars (Google)
 Election polling and predictions
 Customer behavior analysis
 Question answering (Siri, IBM Watson, …)
15. Why Python ?
 easy to learn
 Free open-source tool
 Employment opportunities
 No 1 in data science and machine learning
 Rich library and large community
 Particularly designed for scientific computing
16. Anaconda distribution combines thousands of open-source
data science libraries and packages in a single framework, e.g.
 data analysis (e.g., Pandas)
 data visualization (e.g., Matplotlib)
 statistical analysis (e.g. Stats models)
 machine learning (e.g. Scikit-learn)
17. It runs on all major OS platforms, windows, , e.g. Windows, Mac
OS, and Linux, and includes the following:
 Standard Python
 Jupyter notebook (interactive coding via a browser)
 Spyder, a code editor
3 | Page writer:
Abaas Muuse
End- chapter one data science

4 | Page writer:
Abaas Muuse

Common questions

Powered by AI

Data science is applied to predict customer behavior and optimize business processes through various applications like data exploration, visualization, and predictive analytics. For instance, customer behavior analysis can track purchasing patterns for targeted marketing, while predictive models in retail can optimize inventory based on forecasted sales trends. Data-driven insights derived from these analyses enable businesses to anticipate customer needs and streamline operations .

Descriptive analytics examines past data to identify trends and understand current company positions, whereas diagnostic analytics explores the reasons behind such occurrences by identifying anomalies and patterns. Predictive analytics leverages statistical models to forecast future outcomes, useful in sectors like finance and healthcare. In contrast, prescriptive analytics recommends actions based on the results of the other analyses, aiming to enhance decision-making processes .

The main types of data discussed in data science are unstructured text data, semi-structured data, and streaming data. Unstructured text data includes data from the web that lacks a predefined format. Semi-structured data, like XML, has a loose structure that includes tags and markers to separate data elements, allowing more flexibility than structured data. Streaming data consists of data like images and videos that are constantly generated and require real-time processing .

Within data science, machine learning (ML) and artificial intelligence (AI) are critical for developing systems that improve from experience and perform tasks by mimicking human thought processes. AI is a broad field involving machines designed to reason and make decisions like humans, whereas ML is a subset of AI focused on enabling computers to learn from data without explicit programming. Deep learning, another subset, extends ML through complex neural network structures .

Big data is considered a strategic asset for organizations because it provides comprehensive insights into business operations and customer behavior. By analyzing data volume, velocity, and variety, organizations can make informed decisions on product development, marketing strategies, and operational efficiencies. The continuous flow of data aids in real-time monitoring and adaptation to market changes, ensuring sustained competitive advantage .

Data science education opens up career opportunities in roles such as Data Architect and Administrator, Data Engineer, Data Analyst, Data Scientist, Machine Learning Engineer, Statistician, Mathematician, Business IT Analyst, and Marketing Analyst. Necessary skills for these roles encompass domain expertise, analytical skills, statistical knowledge, proficiency in programming languages, and understanding of machine learning and data management techniques .

The '3 Vs of big data'—volume, velocity, and variety—enhance the understanding of data management by framing the challenges and opportunities presented by big data. Volume refers to the vast amount of data generated, requiring efficient storage solutions. Velocity emphasizes the rapid accumulation and the need for swift real-time processing. Variety highlights the heterogeneity of data formats that must be integrated into coherent data management strategies. Together, these aspects help tailor data handling practices to meet specific analytical needs efficiently .

The data science workflow involves capturing data through acquisition, managing and cleaning data by removing errors, performing exploratory analysis with tools like histograms for understanding, and conducting final analyses followed by reporting insights. This structured process transforms raw data into actionable insights, enabling informed decision-making by ensuring data integrity, revealing patterns, and supporting predictive models .

The major components of artificial intelligence include knowledge representation, natural language processing (NLP), reasoning, and machine learning. Knowledge representation organizes information to facilitate reasoning, while NLP enables machines to comprehend and generate human language. Reasoning allows machines to make logical decisions, and machine learning entails developing algorithms to learn from data. Together, these components allow AI to simulate human intelligence in processing, analyzing, and decision-making tasks .

Python is considered the preferred programming language in data science due to its ease of learning, being an open-source tool, and offering rich libraries specifically designed for scientific computing. It also ranks high in employment opportunities and supports a large community, enhancing problem-solving collaboration. Frameworks like Anaconda enhance its usability by combining multiple data science libraries in a single platform .

You might also like