"Python machine learning Practice Guidelines" (Chinese edition with a bookmark), the original book code, data sets)

"Python machine learning Practice Guidelines" (Chinese edition with a bookmark), the original book code, data sets)

Links: https://pan.baidu.com/s/1qEqvjkOWWJVYM9oZRAf1GA extraction code: 4bc6

​

brief introduction· · · · · ·

Machine learning is becoming popular in recent years, a field, while the Python language after a period of development has gradually become the mainstream programming languages. This book combines two popular Python language and machine learning to play the Python language advantages in terms of data analysis, machine learning algorithms to the extreme by using two cores.

The book has 10 chapters. Chapter 1 explains the ecosystem Python Machine Learning, and the remaining nine chapters introduce a number associated with machine learning algorithms, including various types of classification algorithms, data visualization techniques, recommendation engines, including machine learning in an apartment, airfare, IPO market , application news source, content marketing, stock market, images, chat robots and recommendation engines.

The book for Python programmers, data analysts, for readers interested in algorithms, machine learning practitioners and researchers to read.

About the Author· · · · · ·

Alexander T. Combs is an experienced data scientists, strategists and developers. He has the financial data extraction, natural language processing and generation, as well as quantitative and statistical modeling background. He is currently a full-time senior lecturer at New York immersive data science projects.

table of Contents· · · · · ·

Chapter 1 Python ecosystem machine learning 1
1.1 Data Science / Machine Learning workflow 2
1.1.1 Gets 2
1.1.2 inspection and exploration 2
1.1.3 clean and prepare 3
1.1.4 Modeling 3
1.1.5 Evaluation 3
1.1.6 deployment 3
1.2Python libraries and functions 3
1.2.1 Gets 4
1.2.2 check 4
1.2.3 preparation 20
1.2.4 modeling and evaluation 26
1.2.5 deploy 34
1.3 set of machine learning environment 34
34 1.4 Summary
of Building applications Chapter 2, found cheap apartments 35
2.1 apartment listings data 36 acquired
using import.io fetch data listings 36
2.2 38 check and prepare the data
2.2.1 data analysis 46
2.2.2 visualization data 50
2.3 pairs of data model 51
2.3.1 prediction 54
2.3.2 extended model 57
2.4 57 Summary
Chapter 3. Building applications found cheap tickets 58
3.1 59 acquires data for flights
3.2 advanced web crawler technology to retrieve data fare 60
3.3 parsed 62 DOM to extract pricing data
clustering techniques to identify unusual fare 66
3.4 75 IFTTT transmitting real-time alerts
3.5 together 78
3.6 82 Summary
Chapter 4 Logistic regression was used to predict the IPO market 83
84 4.1IPO market
4.1.1 What is IPO84
4.1.2 the recent IPO market performance 84
4.1.3 Basic IPO strategies 93
4.2 feature works 94
4.3 103 binary classification
importance 4.4 features 108
4.5 Summary 111
Chapter 5 Creating a custom news source 112
5.1 Pocket application, create a supervised training set of 112
5.1.1 installation Pocket Chrome extension 113
5.1.2 use PocketAPI to retrieve the story 114
5.2 embed. lyAPI download story content 119
5.3 120 natural language processing base
5.4 SVM 123
5.5IFTTT the article source, Google forms and e-mail integration 125
by setting IFTTT news source Google forms 125 and
set your daily personalized newsletters 5.6 133
5.7 Summary 137
Chapter 6 predict whether your content will be widely circulated 138
6.1 on viral, research tells us that what 139
6.2 to get the number and content sharing 140
6.3 Discovery Communications of features 149
6.3.1 explore image data 149
6.3.2 exploring title 152
6.3.3 content to explore the story of 156
predictive models to build content ratings 6.4 157
6.5 Summary 162
Chapter 7 Using machine learning to predict the stock market 163
7.1 Market Analysis of type 164
7.2 on the stock market, what the research tells us that 165
7.3 How to develop a trading strategy 166
7.3.1 extend our analysis cycle 172
7.3.2 Using Support Vector Regression build our model 175
7.3.3 modeling and dynamic time warping 182
7.4 Summary 186
Chapter 8 build up an image similarity engine 187
8.1 188 learning machine images
8.2 image processing 189
8.3 Find similar images 191
8.4 195 understand the depth of learning
engine 8.5 image similarity to build 198
8.6 Summary 206
Chapter 9 to build the bot 207
9.1 207 Turing test
history 208 9.2 bot
9.3 bot design 212
9.4 217 to build a bot
9.5 Summary 227
Chapter 10 to build a recommendation engine 228
10.1 229 collaborative filtering
10.1.1 user based filter 230
10.1.2 233 based filtering project
10.2 236 content based filtering
10.3 hybrid system 237
10.4 Construction of the recommendation engine 238
10.5 Summary 251

Reproduced in: https: //juejin.im/post/5cfbb341e51d4555fd20a305