Data analysis is popular on the Internet, and the full version of "Introduction to data science" is free to download

Why study data analysis

big data 、 Are there any skills that can be applied in various industries in the era of artificial intelligence ？

Yes , Data analysis is , Extracting valuable information from data is big data 、 One of the necessary skills in the artificial age ！

Marketers can improve their marketing strategies through data analysis , Product managers can gain insight into user habits through data analysis , Financial practitioners can avoid investment risks through data analysis , Company executives can guide decision-making through data analysis .

No matter what industry you're in , Master the ability of data analysis , You will be more competitive .

High pay

Bytes to beat 11w After the news of the monthly salary data analyst was exposed , The salary problem of data analysis talents has once again hit the hot search ！

As you can see from the diagram , Although the average salary of relevant posts is as high as 13.5k, But down to 4.5k Up to 50k, The span is very large . What is it , This has led to such polarization in the salary of data analysis posts ？

The root cause is , The field of data analysis does not exist 「 The ceiling 」 said , Advanced ability directly determines the salary level of data analysis talents .

That's why , High salary data analysis posts in large factories not only require proficiency in various data tools , Complete project experience is also required 、 Can quickly analyze the causes of data changes 、 Able to handle complex business decisions .

How to learn

Data analysis is an interdisciplinary subject , To put it simply , Learn how to use Excel You can do some data analysis , More complicated , Want to use SQL Knowledge ,“ senior ” Some , We need to use data analysis methods , The most common is statistical models , For example, analysis of variance 、 Contingency analysis 、 Linear regression 、 Logical regression 、 Principal component analysis 、 Time series, etc . If you want to further study, you still need to master the decision tree 、 Clustering analysis 、 Association rules 、 neural network 、 Random forest and other data mining model algorithms . In addition to learning theoretical knowledge, you also need to master some common data analysis tools , such as SPSS、SAS、R、Python etc. , Pay special attention to the learning of programming language , Mastering a programming language can make the analysis work more efficient .

These are the basic skills you need to master on the road of learning data analysis , As for how to learn ？ Of course, the most effective method is the combination of theory and practice , We should really apply what we have learned .

Here I would like to recommend an authoritative 《 Introduction to data science 》 Books , By reading this book , You can ： Learn a lesson Python Crash course ;
Learn linear algebra 、 Basic methods of statistics and probability theory , Understand how they apply to data science ; Master how to collect 、 Explore 、 clear 、 Transform and manipulate data ;
In depth understanding of the basics of machine learning ; Application k- a near neighbor 、 Naive Bayes 、 Linear regression and logistic regression 、 Decision tree 、 Various data models such as neural networks and clustering ;
Explore the recommendation system 、 natural language processing 、 Network analysis 、MapReduce And the database .

Friends, if you need a full set of 《 Introduction to data science 》, Scan the QR code below for free （ In case of code scanning problem , Comment area message collection ）~

Chapter one python Introduction

1.1　 The power of data
1.2　 What is data science
1.3　 Incentive hypothesis ：DataSciencester
…

Chapter two python Fast track

2.1　 Basic content
2.2　 Advanced content
2.3　 Extended learning
…

The third chapter Visualization data

3.1 matplotlib
3.2　 Bar chart
3.3　 Line graph
…

The first 4 Chapter 　 linear algebra

4.1　 vector 　　
4.2　 matrix 　　
4.3　 Extended learning 　　

The first 5 Chapter 　 statistical

5.1　 Describe a single dataset 　　
5.1.1　 Central tendency 　　
5.1.2　 Dispersion 　　
5.2　 relevant 　　
5.3　 Simpson paradox 　　
5.4　 Correlation coefficient other considerations 　　
5.5　 Correlation and causality 　　
5.6　 Extended learning 　　

The first 6 Chapter 　 probability

6.1　 Not independent and independent 　　
6.2　 Conditional probability 　　
6.3　 Bayes theorem 　　
6.4　 A random variable 　　
6.5　 Continuous distribution 　　
6.6　 Normal distribution 　
6.7　 Central limit theorem 　　
6.8　 Extended learning 　　

The first 7 Chapter 　 Assumptions and inferences 　　75

7.1　 Statistical hypothesis testing 　　
7.2　 Case study ： Flip a coin 　　
7.3　 confidence interval 　　
7.4　P-hacking　　
7.5　 Case study ： function A/B test 　　
7.6　 Bayesian inference 　　
7.7　 Extended learning 　　

The first 8 Chapter 　 gradient descent

8.1　 The idea of gradient descent 　　
8.2　 Estimate the gradient 　　
8.3　 Use gradients 　　
8.4　 Select the correct step size 　　
8.5　 comprehensive 　　
8.6　 Random gradient descent method 　　
8.7　 Extended learning 　　

The first 9 Chapter 　 get data

9.1　stdin and stdout　　
9.2　 Read the file 　　
9.2.1　 Text file foundation 　
9.2.2　 Restricted files 　　
9.3　 Network capture 　　
9.3.1　HTML And analytic methods 　　
9.3.2　 Case study ： About data O’Reilly The book 　　
9.4　 Use API　　
9.4.1　JSON（ and XML）　　
9.4.2　 Use an unverified API　　
9.4.3　 seek API　　
9.5　 Case study ： Use Twitter API　　
9.6　 Extended learning 　　

The first 10 Chapter 　 Data work

10.1　 Explore your data 　　
10.1.1　 Explore one-dimensional data 　　
10.1.2　 Two dimensional data 　　
10.1.3　 Multidimensional data 　　
10.2　 Clean up and modify 　　
10.3　 Data processing 　　
10.4　 Data adjustment 　　
10.5　 Dimension reduction 　　
10.6　 Extended learning 　　

The first 11 Chapter 　 machine learning

11.1　 modeling 　　
11.2　 What is machine learning 　　
11.3　 Over fitting and under fitting 　　
11.4　 correctness 　　
11.5　 bias - Variance tradeoff 　　
11.6　 Feature extraction and selection 　　
11.7　 Extended learning 　　

The first 12 Chapter 　k Nearest neighbor method

12.1　 Model 　　
12.2　 Case study ： Favorite programming language 　
12.3　 Dimension disaster 　　
12.4　 Extended learning

The first 13 Chapter 　 Naive bayes algorithm

13.1　 A simple spam filter 　　
13.2　 A sophisticated spam filter 　　
13.3　 Implementation of algorithm 　　
13.4　 test model 　　
13.5　 Extended learning

The first 14 Chapter 　 Simple linear regression

14.1　 Model 　　
14.2　 Using gradient descent method 　　
14.3　 Maximum likelihood estimation 　
14.4　 Extended learning

The first 15 Chapter 　 Multiple regression analysis

15.1　 Model 　　
15.2　 Further assumptions of the least squares model 　　
15.3　 Fitting model 　
15.4　 Interpretive model 　　
15.5　 Goodness of fit 　　
15.6　 Digression ：Bootstrap　　
15.7　 Standard error of regression coefficient 　　
15.8　 Regularization 　　
15.9　 Extended learning

The first 16 Chapter 　 Logical regression

16.1　 problem 　
16.2　Logistic function 　
16.3　 Application model 　　
16.4　 Goodness of fit 　　
16.5　 Support vector machine 　　
16.6　 Extended learning 　　

The first 17 Chapter 　 Decision tree

17.1　 What is a decision tree 　　
17.2　 entropy 　　
17.3　 Entropy of partition 　　
17.4　 Create a decision tree 　　
17.5　 Comprehensive use 　　
17.6　 Random forests 　　
17.7　 Extended learning

The first 18 Chapter 　 neural network

18.1　 perceptron 　　
18.2　 Feedforward neural networks 　　
18.3　 Back propagation 　　
18.4　 example ： To overcome CAPTCHA　　
18.5　 Extended learning

The first 19 Chapter 　 Clustering analysis

19.1　 principle 　
19.2　 Model 　
19.3　 Example ： party 　　
19.4　 Select the number of clusters k　　
19.5　 Example ： Cluster colors 　　
19.6　 Bottom up hierarchical clustering 　　
19.7　 Extended learning 　

The first 20 Chapter 　 natural language processing

20.1　 The word cloud 　　
20.2　n-grams Model 　　　
20.3　 grammar 　　
20.4　 Digression ： Gibbs sampling 　　
20.5　 Topic modeling 　　
20.6　 Extended learning 　　

The first 21 Chapter 　 Network analysis

21.1　 Intermediary centrality 　　
21.2　 Centrality of eigenvector 　　
21.2.1　 Matrix multiplication 　　
21.2.2　 Centrality 　　
21.3　 Digraphs and graphs PageRank　　
21.4　 Extended learning

The first 22 Chapter 　 Recommendation system

22.1　 Hand screening 　　
22.2　 Recommend popular things 　　
22.3　 User based collaborative filtering method 　　
22.4　 Collaborative filtering algorithm based on items 　　
22.5　 Extended learning

The first 23 Chapter 　 Database and SQL　　257

23.1　CREATE TABLE And INSERT　　257
23.2　UPDATE　　259
23.3　DELETE　　260
23.4　SELECT　　260
23.5　GROUP BY　　262
23.6　ORDER BY　　264
23.7　JOIN　　264
23.8　 Subquery 　　267
23.9　 Indexes 　　267
23.10　 Query optimization 　　268
23.11　NoSQL　　268
23.12　 Extended learning 　　269

The first 24 Chapter 　MapReduce

24.1　 Case study ： Word count 　　
24.2　 Why MapReduce　　
24.3　 More general MapReduce　　
24.4　 Case study ： Analysis status update 　　
24.5　 Case study ： Matrix computing 　　
24.6　 Digression ： Combiner 　　
24.7　 Extended learning

The first 25 Chapter 　 Data science foresight

25.1　IPython　　
25.2　 mathematics 　　
25.3　 Don't start from scratch 　　
25.3.1　NumPy　　
25.3.2　pandas　　
25.3.3　scikit-learn　　
25.3.4　 visualization 　　
25.3.5　R　　
25.4　 Looking for data 　
25.5　 Engage in data science 　　
25.5.1　Hacker News　　
25.5.2　 fire engine 　　
25.5.3　T T-shirt 　　
25.5.4　 And you? ？　　

> For reasons of length , This is not going to unfold one by one , Friends, if you need a full set of 《 Introduction to data science 》, give the thumbs-up + Comment on data analysis , I'll always reply ！