Scribd
Upload
55 views

Applications of Data Science

The document discusses three main applications of data science: traditional machine learning, the internet of things, and deep learning. It then describes four roles in data science: data engineer, data analyst, data scientist, and machine learning scientist. It outlines the main tools used by each role, including SQL, Python, R, cloud computing platforms, spreadsheets, and business intelligence tools.

Uploaded by

song studio
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
55 views

Applications of Data Science

The document discusses three main applications of data science: traditional machine learning, the internet of things, and deep learning. It then describes four roles in data science: data engineer, data analyst, data scientist, and machine learning scientist. It outlines the main tools used by each role, including SQL, Python, R, cloud computing platforms, spreadsheets, and business intelligence tools.

Uploaded by

song studio
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Applications of Data Science

1. Traditional machine learning


2. Internet of things
3. Deep learning
 Traditional machine learning
Fraud detection machine, we needed a data, from which an algorithm is designed and the algo is
implemented into machine to check weather it’s a fraud or valid, record the data into database

 Internet of things:
Any device which is not a computer, but transmit data is an application of IOT, like smart watch,
house security system.

 Deep Learning:
1. Many neurons work together
2. Requires much more training data
3. Used in complex problems
 Image classification
 Language learning/understanding

Data Science Roles and tools:


 Data engineer
 Information architects
 Control the flow of data
 Build data pipelines and storage solutions
 Maintain data access

FOUR STAGES

 Data collection and storage

DATA ENGINEERING TOOLS

 SQL(to store and organize data)


 also uses java ,scala or python(to process data)
 Shell(command line to automate and run tasks)
 Cloud computing(AwS, azure , google cloud platform)
 Data analyst
Perform simpler analyses that describe data

Data analysts describe the present via data

Create reports and dashboards to summarize data

Have to clean data for analysis of data

Main focus within the workflow is

 Data preparation
 Exploration & visualization

DATA ANALYST TOOLS

 SQL(retrieve and aggregate data)


 Use existing database to aggregate data
 SPREADSHEETS(Simple Analysis)
 BUSINESS INTELLIGENCE TOOLS Tableau, power BI, looker(Dashboards and visualizations)
 May have:Python or R(Clean and analyze data)
 Data scientist
 Have strong background in statistical methods
 Run experiments and analyses for insights
 Also use traditional machine learning for prediction and forecasting

Main focus within the workflow is

 Data preparation
 Exploration & visualization
 Experimentation & prediction

DATA ANALYST TOOLS

 SQL(retrieve and aggregate data)


 PYTHON OR R( Data science libraries eg pandas and tidyverse
 Machine learning scientist
Are similar to data scientist, but with machine learning specialization

 Predictions and extrapolations


 Scientist use training data to classify larger data
 Deep learning
1. Image processing
2. Natural language processing

Main focus within the workflow is

 Data preparation
 Exploration & visualization
 Strong focus(Experimentation & prediction)

MACHINE LEARNING TOOLS

 Python or R(Machine learning libraries eg tensorflow(to run powerful deep learning algo) or
spark)

You might also like