-
mechine-learning
本书第一部分主要介绍机器学习基础，以及如何利用算法进行分类，并逐步介绍了多种经典的监督学习算法，如k近邻算法、朴素贝叶斯算法、Logistic回归算法、支持向量机、AdaBoost集成方法、基于树的回归算法和分类回归树（CART）算法等。第三部分则重点介绍无监督学习及其一些主要算法：k均值聚类算法、Apriori算法、FP-Growth算法。第四部分介绍了机器学习算法的一些附属工具。
全书通过精心编排的实例，切入日常工作任务，摒弃学术化语言，利用高效的可复用Python代码来阐释如何处理统计数据，进行数据分析及可视化。通过各种实例，...( U672C u4E66 u7B2C u4E00 u90E8 u5206 u5206 u4E3B u8991 u4ECB u7ECD u673A u5668 u5B66 u4E60 u57FA u7840 uFF0C u4EE5 u53CA u5982 u4F55 u5229 u7528 u7B97 u6CD5 U8FDB u883C u5206 u7C7B uFF0C u5E76 u9010 u6B65 u4ECB u7ECD u4E86 u591A U90BB u6CD2 u3001 u6734 u7D2 u8D1D u53F6 u65AF u7B97 u6CD5 u3001Logistic u56DE u5F52 u7B97 u6CD5 u3001 u652F u6301 u5411 u91CF u673A u3001AdaBoost u96C6 u6210 U65B9 u6CD5 u3001 u57FA u4E8E u6811 u7R4 u5F52 u7B97 u6CD2 u5286 u5206 u7C7B u56DE u5F52 u6811 uFF08CART uFF09 u7B97 u6CD5 u7B49 u3002 u7B2C u4E09 U90E8 u5209 u5109 u91A u0312 u4E9B u8E1B u8981 u7B97 u6CD5 uFF1Ak u5747 u503C u805A u7B7B U7B97 u6CD3 u30011 by default for uppercase and uupstr U4E9B u9644 u5C5E u5DE5 u5177 u3002 u5168 u4E66 u901A u8FC7 u7CBE U5FC3 u7396 u7392 u7B09 u5B09 u5B09 u5B09 u5B03 U7528 u9184 u5R4 u5904 u7403 u7R03 u7 U5206 u6790 u53CA u53EF u89)
- 2017-05-24 16:06:49下载
- 积分：1
-
interpy-zh-v1.3.pdf
说明： 《Python进阶》是《Intermediate Python》的中?译本(This talk is about web scraping in Python, why web scraping is useful and what Python libraries are available to help you. I will also look into proprietary alternatives and will discuss how they work and why they are not useful. I will show you different libraries used in web scraping and some example code so that you can choose your own personal favourite. I will also tell why writing your own scrapper in scrapy allows you to have more control over the scraping process.)
- 2020-04-26 14:52:55下载
- 积分：1
-
Python-opencv车牌识别
算法思想来自于网上资源，先使用图像边缘和车牌颜色定位车牌，再识别字符。车牌定位在predict方法中，为说明清楚，完成代码和测试后，加了很多注释，请参看源码。车牌字符识别也在predict方法中，请参看源码中的注释，需要说明的是，车牌字符识别使用的算法是opencv的SVM， opencv的SVM使用代码来自于opencv附带的sample，StatModel类和SVM类都是sample中的代码。SVM训练使用的训练样本来自于github上的EasyPR的c++版本。由于训练样本有限，你测试时会发现，车牌字符识别，可能存在误差，尤其是第一个中文字符出现的误差概率较大。(Bits in the predict method, for clarity, add a lot of comments after completing the code and testing, see the source code. License plate character recognition is also included in the predict method. Please refer to the comments in the source code. It needs to be noted that the algorithm used for license plate character recognition is SVM of opencv. The training sample used for SVM training comes from the c++ version of EasyPR on github. Due to limited training samples, you may find errors in license plate character recognition when testing, especially the error probability of the first Chinese character is large.)
- 2018-08-30 16:46:33下载
- 积分：1
-
lecture 3-11.py
美国本科python课堂实用初级入门教学实例(Python introduction teaching example)
- 2019-03-05 12:47:58下载
- 积分：1
-
deleteFailedElementPlugin
用于abaqus软件的单元删除，是应用在abaqus软件后处理时，删除已经失效的单元(Unit for abaqus software delete application abaqus software processing, the unit has failed to delete)
- 2013-01-25 09:00:47下载
- 积分：1
-
Selective Search的Python实现
Selective Search来自于2012年IJCV的文章。其思想是先使用图像分割的方法得到一些初始分割区域(类似于是在图像上生成很多的超像素)，然后利用层次分组的策略(类似于层次聚类)将这些初始区域进行合并，得到的这些区域作为目标定位的候选区域.相对于对候选区域的蛮力搜索， Selective Search大幅度降低了搜索空间, 提高了算法速度。 该版本利用Python实现，安装依赖库后可以直接运行，提取任意图片的Proposals。
- 2022-08-20 19:36:52下载
- 积分：1
-
strain-stress-curve
读取abaqus结果文件odb中的内容，并存储到文件中。有助于快速查看结果。提高效率(Abaqus results file odb is read and stored in the file. Help you quickly see the results. Improve efficiency)
- 2021-03-10 08:39:27下载
- 积分：1
-
FaceDetection
利用Python人工智能实现的人脸检测功能(Face Detection Using Python Artificial Intelligence)
- 2019-07-01 15:30:48下载
- 积分：1
-
kaldi_cvte_model_test-master
说明： CVTE的模型测试实现。适应下载清华数据(The testing program of the modle of CVTE)
- 2020-06-16 08:20:01下载
- 积分：1
-
谱聚类
谱聚类的目的便是要找到一种合理的分割图的方法，使得分割后形成若干个子图，连接不同子图的边的权重（相似度）尽可能低，同子图内的边的权重（相似度）尽可能高(The purpose of spectral clustering is to find a reasonable method of segmentation graphs, so that several subgraphs are formed after segmentation, and the weights (similarities) of the edges connecting different subgraphs are as low as possible, and the weights of the edges in the same subgraph are as low as possible. (similarity) as high as possible)
- 2020-06-23 21:20:01下载
- 积分：1
