The process of capturing people's lives, business or social activities and converting them into data

clean data

Organize data

EDA method

Resistance

residual

re-express

descriptive analysis

Predictive analytics

normative analysis

Missing data handling

Redundant data processing

Noisy data processing

According to the binning strategy of the original data set

Replacement method based on member data in each box

Smoothing

Feature construction

gather

standardization

discretization

Content integration

structural integration

Unidirectionality

No residue

easy to accomplish

Dimension reduction

value reduction

Grammar annotation

Semantic annotation

Data Dictionary

User-defined integrity constraints

self-descriptive information about data

domain value of attribute

Data self-contained associated information

Variable definition rules

Function definition rules

first law of numbers

small probability principle

linguistic rules

data continuity theory

data authentication technology

Focus on the past and answer what has happened

The first step in data analysis

Descriptive statistical analysis methods

Focus on the past and answer why it happened

Correlation analysis and causal analysis

Focus on the future and answer what will happen

Use classification analysis and trend analysis

is the basis for normative analysis

Pay attention to the problems of simulation and optimization, and how to optimize the problems that will occur

Using operations research, simulation and emulation techniques

Can directly generate industrial value

scientific visualization

information visualization

visual analytics

information visualization

data mining

Statistical Analysis

analytical reasoning

human-computer interaction

Emphasis on the process of converting data into knowledge

Emphasis on the interplay between visual analytics and automated modeling

Emphasize the importance of data mapping and data mining

Emphasis on the need for data processing

Emphasis on the importance of human-computer interaction

Methodological basis

basic method

domain methods

visual perception

visual cognition

Categorized data

ordinal data

interval data

Ratio data

Accuracy

legibility

Refers to a false or inaccurate visual perception produced by the target user that is inconsistent with the intent of the data visualizer or the reality of the data itself

Six famous practices in data visualization and their source codes

easy to remember

Easy to recognize

Easy to experience

Business needs

data

Analytical Insights

story model

Storytelling

audience behavior

Data-driven storytelling

visual storytelling

Analytical Storytelling

Interactive storytelling

Tell stories with data

digital storytelling

attract

explain

Inspire

Data story perception

Understanding data stories

Data Stories in Action

Project sponsor

project manager

client

data scientist

data engineer

operator

Definition of project goals

Data acquisition and management

patterns, insights from models

Patterns, model validation and optimization

Visualization and documentation of results

Patterns, application and maintenance of models

Analyzing data without checking it

Analyze data without understanding it

Putting the model into use without testing it

Data science analysis work only has goals and no research hypotheses

The data model is not updated simultaneously with the data and uses an outdated model.

Draw conclusions casually without discussing the results of data analysis

Lack of involvement of business experts

Adopt or train overly complex model algorithms

The existence of data bias

Not enough attention is paid to the presentation effect of data analysis project results

Insufficient emphasis on user experience of data science products

Overestimating or underestimating the target user’s ability to understand