小男孩‘自慰网亚洲一区二区,亚洲一级在线播放毛片,亚洲中文字幕av每天更新,黄aⅴ永久免费无码,91成人午夜在线精品,色网站免费在线观看,亚洲欧洲wwwww在线观看

分享

大數(shù)據(jù)分析與機器學(xué)習(xí)領(lǐng)域Python兵器譜

 htxu91 2015-03-31
曾經(jīng)因為NLTK的緣故開始學(xué)習(xí)Python,之后漸漸成為我工作中的第一輔助腳本語言,雖然開發(fā)語言是C/C++,但平時的很多文本數(shù)據(jù)處理任務(wù)都交給了Python。離開騰訊創(chuàng)業(yè)后,第一個作品課程圖譜也是選擇了Python系的Flask框架,漸漸的將自己的絕大部分工作交給了Python。這些年來,接觸和使用了很多Python工具包,特別是在文本處理,科學(xué)計算,機器學(xué)習(xí)和數(shù)據(jù)挖掘領(lǐng)域,有很多很多優(yōu)秀的Python工具包可供使用,所以作為Pythoner,也是相當幸福的。其實如果仔細留意微博,你會發(fā)現(xiàn)很多這方面的分享,自己也Google了一下,發(fā)現(xiàn)也有同學(xué)總結(jié)了“Python機器學(xué)習(xí)庫”,不過總感覺缺少點什么。最近流行一個詞,全棧工程師(full stack engineer),作為一個苦逼的創(chuàng)業(yè)者,天然的要把自己打造成一個full stack engineer,而這個過程中,這些Python工具包給自己提供了足夠的火力,所以想起了這個系列。當然,這也僅僅是拋磚引玉,希望大家能提供更多的線索,來匯總整理一套Python網(wǎng)頁爬蟲,文本處理,科學(xué)計算,機器學(xué)習(xí)和數(shù)據(jù)挖掘的兵器譜。

一、Python網(wǎng)頁爬蟲工具集
一個真實的項目,一定是從獲取數(shù)據(jù)開始的。無論文本處理,機器學(xué)習(xí)和數(shù)據(jù)挖掘,都需要數(shù)據(jù),除了通過一些渠道購買或者下載的專業(yè)數(shù)據(jù)外,常常需要大家自己動手爬數(shù)據(jù),這個時候,爬蟲就顯得格外重要了,幸好,Python提供了一批很不錯的網(wǎng)頁爬蟲工具框架,既能爬取數(shù)據(jù),也能獲取和清洗數(shù)據(jù),我們也就從這里開始了:

1. Scrapy
Scrapy, a fast high-level screen scraping and web crawling framework for Python.
鼎鼎大名的Scrapy,相信不少同學(xué)都有耳聞,課程圖譜中的很多課程都是依靠Scrapy抓去的,這方面的介紹文章有很多,推薦大牛pluskid早年的一篇文章:《Scrapy 輕松定制網(wǎng)絡(luò)爬蟲》,歷久彌新。
官方主頁:http:///
Github代碼頁: https://github.com/scrapy/scrapy

2. Beautiful Soup
You didn’t write that awful page. You’re just trying to get some data out of it. Beautiful Soup is here to help. Since 2004, it’s been saving programmers hours or days of work on quick-turnaround screen scraping projects.
讀書的時候通過《集體智慧編程》這本書知道Beautiful Soup的,后來也偶爾會用用,非常棒的一套工具。客觀的說,Beautifu Soup不完全是一套爬蟲工具,需要配合urllib使用,而是一套HTML/XML數(shù)據(jù)分析,清洗和獲取工具。
官方主頁:http://www./software/BeautifulSoup/

3. Python-Goose
Html Content / Article Extractor, web scrapping lib in Python
Goose最早是用Java寫得,后來用Scala重寫,是一個Scala項目。Python-Goose用Python重寫,依賴了Beautiful Soup。前段時間用過,感覺很不錯,給定一個文章的URL, 獲取文章的標題和內(nèi)容很方便。
Github主頁:https://github.com/grangier/python-goose

二、Python文本處理工具集
從網(wǎng)頁上獲取文本數(shù)據(jù)之后,依據(jù)任務(wù)的不同,就需要進行基本的文本處理了,譬如對于英文來說,需要基本的tokenize,對于中文,則需要常見的中文分詞,進一步的話,無論英文中文,還可以詞性標注,句法分析,關(guān)鍵詞提取,文本分類,情感分析等等。這個方面,特別是面向英文領(lǐng)域,有很多優(yōu)秀的工具包,我們一一道來。

1. NLTK — Natural Language Toolkit
NLTK is a leading platform for building Python programs to work with human language data. It provides easy-to-use interfaces to over 50 corpora and lexical resources such as WordNet, along with a suite of text processing libraries for classification, tokenization, stemming, tagging, parsing, and semantic reasoning, and an active discussion forum.
搞自然語言處理的同學(xué)應(yīng)該沒有人不知道NLTK吧,這里也就不多說了。不過推薦兩本書籍給剛剛接觸NLTK或者需要詳細了解NLTK的同學(xué): 一個是官方的《Natural Language Processing with Python》,以介紹NLTK里的功能用法為主,同時附帶一些Python知識,同時國內(nèi)陳濤同學(xué)友情翻譯了一個中文版,這里可以看到:推薦《用Python進行自然語言處理》中文翻譯-NLTK配套書;另外一本是《Python Text Processing with NLTK 2.0 Cookbook》,這本書要深入一些,會涉及到NLTK的代碼結(jié)構(gòu),同時會介紹如何定制自己的語料和模型等,相當不錯。
官方主頁:http://www./
Github代碼頁:https://github.com/nltk/nltk

2. Pattern
Pattern is a web mining module for the Python programming language.
It has tools for data mining (Google, Twitter and Wikipedia API, a web crawler, a HTML DOM parser), natural language processing (part-of-speech taggers, n-gram search, sentiment analysis, WordNet), machine learning (vector space model, clustering, SVM), network analysis and canvas visualization.
Pattern由比利時安特衛(wèi)普大學(xué)CLiPS實驗室出品,客觀的說,Pattern不僅僅是一套文本處理工具,它更是一套web數(shù)據(jù)挖掘工具,囊括了數(shù)據(jù)抓取模塊(包括Google, Twitter, 維基百科的API,以及爬蟲和HTML分析器),文本處理模塊(詞性標注,情感分析等),機器學(xué)習(xí)模塊(VSM, 聚類,SVM)以及可視化模塊等,可以說,Pattern的這一整套邏輯也是這篇文章的組織邏輯,不過這里我們暫且把Pattern放到文本處理部分。我個人主要使用的是它的英文處理模塊Pattern.en, 有很多很不錯的文本處理功能,包括基礎(chǔ)的tokenize, 詞性標注,句子切分,語法檢查,拼寫糾錯,情感分析,句法分析等,相當不錯。
官方主頁:http://www.clips./pattern

3. TextBlob: Simplified Text Processing
TextBlob is a Python (2 and 3) library for processing textual data. It provides a simple API for diving into common natural language processing (NLP) tasks such as part-of-speech tagging, noun phrase extraction, sentiment analysis, classification, translation, and more.
TextBlob是一個很有意思的Python文本處理工具包,它其實是基于上面兩個Python工具包NLKT和Pattern做了封裝(TextBlob stands on the giant shoulders of NLTK and pattern, and plays nicely with both),同時提供了很多文本處理功能的接口,包括詞性標注,名詞短語提取,情感分析,文本分類,拼寫檢查等,甚至包括翻譯和語言檢測,不過這個是基于Google的API的,有調(diào)用次數(shù)限制。TextBlob相對比較年輕,有興趣的同學(xué)可以關(guān)注。
官方主頁:http://textblob./en/dev/
Github代碼頁:https://github.com/sloria/textblob

4. MBSP for Python
MBSP is a text analysis system based on the TiMBL and MBT memory based learning applications developed at CLiPS and ILK. It provides tools for Tokenization and Sentence Splitting, Part of Speech Tagging, Chunking, Lemmatization, Relation Finding and Prepositional Phrase Attachment.
MBSP與Pattern同源,同出自比利時安特衛(wèi)普大學(xué)CLiPS實驗室,提供了Word Tokenization, 句子切分,詞性標注,Chunking, Lemmatization,句法分析等基本的文本處理功能,感興趣的同學(xué)可以關(guān)注。
官方主頁:http://www.clips./pages/MBSP

5. Gensim: Topic modeling for humans
Gensim是一個相當專業(yè)的主題模型Python工具包,無論是代碼還是文檔,我們曾經(jīng)用《如何計算兩個文檔的相似度》介紹過Gensim的安裝和使用過程,這里就不多說了。
官方主頁:http:///gensim/index.html
github代碼頁:https://github.com/piskvorky/gensim

6. langid.py: Stand-alone language identification system
語言檢測是一個很有意思的話題,不過相對比較成熟,這方面的解決方案很多,也有很多不錯的開源工具包,不過對于Python來說,我使用過langid這個工具包,也非常愿意推薦它。langid目前支持97種語言的檢測,提供了很多易用的功能,包括可以啟動一個建議的server,通過json調(diào)用其API,可定制訓(xùn)練自己的語言檢測模型等,可以說是“麻雀雖小,五臟俱全”。
Github主頁:https://github.com/saffsd/langid.py

7. Jieba: 結(jié)巴中文分詞
“結(jié)巴”中文分詞:做最好的Python中文分詞組件 “Jieba” (Chinese for “to stutter”) Chinese text segmentation: built to be the best Python Chinese word segmentation module.
好了,終于可以說一個國內(nèi)的Python文本處理工具包了:結(jié)巴分詞,其功能包括支持三種分詞模式(精確模式、全模式、搜索引擎模式),支持繁體分詞,支持自定義詞典等,是目前一個非常不錯的Python中文分詞解決方案。
Github主頁:https://github.com/fxsjy/jieba

8. xTAS
xtas, the eXtensible Text Analysis Suite, a distributed text analysis package based on Celery and Elasticsearch.
感謝微博朋友 @大山坡的春 提供的線索:我們組同事之前發(fā)布了xTAS,也是基于python的text mining工具包,歡迎使用,鏈接:http:///RPbEZOW??雌饋砗懿诲e的樣子,回頭試用一下。
Github代碼頁:https://github.com/NLeSC/xtas

三、Python科學(xué)計算工具包
說起科學(xué)計算,大家首先想起的是Matlab,集數(shù)值計算,可視化工具及交互于一身,不過可惜是一個商業(yè)產(chǎn)品。開源方面除了GNU Octave在嘗試做一個類似Matlab的工具包外,Python的這幾個工具包集合到一起也可以替代Matlab的相應(yīng)功能:NumPy+SciPy+Matplotlib+iPython。同時,這幾個工具包,特別是NumPy和SciPy,也是很多Python文本處理 & 機器學(xué)習(xí) & 數(shù)據(jù)挖掘工具包的基礎(chǔ),非常重要。最后再推薦一個系列《用Python做科學(xué)計算》,將會涉及到NumPy, SciPy, Matplotlib,可以做參考。

1. NumPy
NumPy is the fundamental package for scientific computing with Python. It contains among other things:
1)a powerful N-dimensional array object
2)sophisticated (broadcasting) functions
3)tools for integrating C/C++ and Fortran code
4) useful linear algebra, Fourier transform, and random number capabilities
Besides its obvious scientific uses, NumPy can also be used as an efficient multi-dimensional container of generic data. Arbitrary data-types can be defined. This allows NumPy to seamlessly and speedily integrate with a wide variety of databases.
NumPy幾乎是一個無法回避的科學(xué)計算工具包,最常用的也許是它的N維數(shù)組對象,其他還包括一些成熟的函數(shù)庫,用于整合C/C++和Fortran代碼的工具包,線性代數(shù)、傅里葉變換和隨機數(shù)生成函數(shù)等。NumPy提供了兩種基本的對象:ndarray(N-dimensional array object)和 ufunc(universal function object)。ndarray是存儲單一數(shù)據(jù)類型的多維數(shù)組,而ufunc則是能夠?qū)?shù)組進行處理的函數(shù)。
官方主頁:http://www./

2. SciPy:Scientific Computing Tools for Python
SciPy refers to several related but distinct entities:
1)The SciPy Stack, a collection of open source software for scientific computing in Python, and particularly a specified set of core packages.
2)The community of people who use and develop this stack.
3)Several conferences dedicated to scientific computing in Python – SciPy, EuroSciPy and SciPy.in.
4)The SciPy library, one component of the SciPy stack, providing many numerical routines.
“SciPy是一個開源的Python算法庫和數(shù)學(xué)工具包,SciPy包含的模塊有最優(yōu)化、線性代數(shù)、積分、插值、特殊函數(shù)、快速傅里葉變換、信號處理和圖像處理、常微分方程求解和其他科學(xué)與工程中常用的計算。其功能與軟件MATLAB、Scilab和GNU Octave類似。 Numpy和Scipy常常結(jié)合著使用,Python大多數(shù)機器學(xué)習(xí)庫都依賴于這兩個模塊?!薄?引用自“Python機器學(xué)習(xí)庫”
官方主頁:http://www./

3. Matplotlib
matplotlib is a python 2D plotting library which produces publication quality figures in a variety of hardcopy formats and interactive environments across platforms. matplotlib can be used in python scripts, the python and ipython shell (ala MATLAB?* or Mathematica??), web application servers, and six graphical user interface toolkits.
matplotlib 是python最著名的繪圖庫,它提供了一整套和matlab相似的命令A(yù)PI,十分適合交互式地進行制圖。而且也可以方便地將它作為繪圖控件,嵌入GUI應(yīng)用程序中。Matplotlib可以配合ipython shell使用,提供不亞于Matlab的繪圖體驗,總之用過了都說好。
官方主頁:http:///

4. iPython
IPython provides a rich architecture for interactive computing with:
1)Powerful interactive shells (terminal and Qt-based).
2)A browser-based notebook with support for code, text, mathematical expressions, inline plots and other rich media.
3)Support for interactive data visualization and use of GUI toolkits.
4)Flexible, embeddable interpreters to load into your own projects.
5)Easy to use, high performance tools for parallel computing.
“iPython 是一個Python 的交互式Shell,比默認的Python Shell 好用得多,功能也更強大。 她支持語法高亮、自動完成、代碼調(diào)試、對象自省,支持 Bash Shell 命令,內(nèi)置了許多很有用的功能和函式等,非常容易使用。 ” 啟動iPython的時候用這個命令“ipython –pylab”,默認開啟了matploblib的繪圖交互,用起來很方便。
官方主頁:http:///

四、Python 機器學(xué)習(xí) & 數(shù)據(jù)挖掘 工具包
機器學(xué)習(xí)和數(shù)據(jù)挖掘這兩個概念不太好區(qū)分,這里就放到一起了。這方面的開源Python工具包有很多,這里先從熟悉的講起,再補充其他來源的資料,也歡迎大家補充。

1. scikit-learn: Machine Learning in Python
scikit-learn (formerly scikits.learn) is an open source machine learning library for the Python programming language. It features various classification, regression and clustering algorithms including support vector machines, logistic regression, naive Bayes, random forests, gradient boosting, k-means and DBSCAN, and is designed to interoperate with the Python numerical and scientific libraries NumPy and SciPy.
首先推薦大名鼎鼎的scikit-learn,scikit-learn是一個基于NumPy, SciPy, Matplotlib的開源機器學(xué)習(xí)工具包,主要涵蓋分類,回歸和聚類算法,例如SVM, 邏輯回歸,樸素貝葉斯,隨機森林,k-means等算法,代碼和文檔都非常不錯,在許多Python項目中都有應(yīng)用。例如在我們熟悉的NLTK中,分類器方面就有專門針對scikit-learn的接口,可以調(diào)用scikit-learn的分類算法以及訓(xùn)練數(shù)據(jù)來訓(xùn)練分類器模型。這里推薦一個視頻,也是我早期遇到scikit-learn的時候推薦過的:推薦一個Python機器學(xué)習(xí)工具包Scikit-learn以及相關(guān)視頻–Tutorial: scikit-learn – Machine Learning in Python
官方主頁:http:///

2. Pandas: Python Data Analysis Library
Pandas is a software library written for the Python programming language for data manipulation and analysis. In particular, it offers data structures and operations for manipulating numerical tables and time series.
第一次接觸Pandas是由于Udacity上的一門數(shù)據(jù)分析課程“Introduction to Data Science” 的Project需要用Pandas庫,所以學(xué)習(xí)了一下Pandas。Pandas也是基于NumPy和Matplotlib開發(fā)的,主要用于數(shù)據(jù)分析和數(shù)據(jù)可視化,它的數(shù)據(jù)結(jié)構(gòu)DataFrame和R語言里的data.frame很像,特別是對于時間序列數(shù)據(jù)有自己的一套分析機制,非常不錯。這里推薦一本書《Python for Data Analysis》,作者是Pandas的主力開發(fā),依次介紹了iPython, NumPy, Pandas里的相關(guān)功能,數(shù)據(jù)可視化,數(shù)據(jù)清洗和加工,時間數(shù)據(jù)處理等,案例包括金融股票數(shù)據(jù)挖掘等,相當不錯。
官方主頁:http://pandas./
=======================================================
分割線,以上工具包基本上都是自己用過的,以下來源于其他同學(xué)的線索,特別是《Python機器學(xué)習(xí)庫》,《23個python的機器學(xué)習(xí)包》,做了一點增刪修改,歡迎大家補充
========================================================
mlpy is a Python module for Machine Learning built on top of NumPy/SciPy and the GNU Scientific Libraries.
mlpy provides a wide range of state-of-the-art machine learning methods for supervised and unsupervised problems and it is aimed at finding a reasonable compromise among modularity, maintainability, reproducibility, usability and efficiency. mlpy is multiplatform, it works with Python 2 and 3 and it is Open Source, distributed under the GNU General Public License version 3.
官方主頁:http://mlpy./

4. MDP:The Modular toolkit for Data Processing
Modular toolkit for Data Processing (MDP) is a Python data processing framework.
From the user’s perspective, MDP is a collection of supervised and unsupervised learning algorithms and other data processing units that can be combined into data processing sequences and more complex feed-forward network architectures.
From the scientific developer’s perspective, MDP is a modular framework, which can easily be expanded. The implementation of new algorithms is easy and intuitive. The new implemented units are then automatically integrated with the rest of the library.
The base of available algorithms is steadily increasing and includes signal processing methods (Principal Component Analysis, Independent Component Analysis, Slow Feature Analysis), manifold learning methods ([Hessian] Locally Linear Embedding), several classifiers, probabilistic methods (Factor Analysis, RBM), data pre-processing methods, and many others.
“MDP用于數(shù)據(jù)處理的模塊化工具包,一個Python數(shù)據(jù)處理框架。 從用戶的觀點,MDP是能夠被整合到數(shù)據(jù)處理序列和更復(fù)雜的前饋網(wǎng)絡(luò)結(jié)構(gòu)的一批監(jiān)督學(xué)習(xí)和非監(jiān)督學(xué)習(xí)算法和其他數(shù)據(jù)處理單元。計算依照速度和內(nèi)存需求而高效的執(zhí)行。從科學(xué)開發(fā)者的觀點,MDP是一個模塊框架,它能夠被容易地擴展。新算法的實現(xiàn)是容易且直觀的。新實現(xiàn)的單元然后被自動地與程序庫的其余部件進行整合。MDP在神經(jīng)科學(xué)的理論研究背景下被編寫,但是它已經(jīng)被設(shè)計為在使用可訓(xùn)練數(shù)據(jù)處理算法的任何情況中都是有用的。其站在用戶一邊的簡單性,各種不同的隨時可用的算法,及應(yīng)用單元的可重用性,使得它也是一個有用的教學(xué)工具。”
官方主頁:http://mdp-toolkit./

5. PyBrain
PyBrain is a modular Machine Learning Library for Python. Its goal is to offer flexible, easy-to-use yet still powerful algorithms for Machine Learning Tasks and a variety of predefined environments to test and compare your algorithms.
PyBrain is short for Python-Based Reinforcement Learning, Artificial Intelligence and Neural Network Library. In fact, we came up with the name first and later reverse-engineered this quite descriptive “Backronym”.
“PyBrain(Python-Based Reinforcement Learning, Artificial Intelligence and Neural Network)是Python的一個機器學(xué)習(xí)模塊,它的目標是為機器學(xué)習(xí)任務(wù)提供靈活、易應(yīng)、強大的機器學(xué)習(xí)算法。(這名字很霸氣)
PyBrain正如其名,包括神經(jīng)網(wǎng)絡(luò)、強化學(xué)習(xí)(及二者結(jié)合)、無監(jiān)督學(xué)習(xí)、進化算法。因為目前的許多問題需要處理連續(xù)態(tài)和行為空間,必須使用函數(shù)逼近(如神經(jīng)網(wǎng)絡(luò))以應(yīng)對高維數(shù)據(jù)。PyBrain以神經(jīng)網(wǎng)絡(luò)為核心,所有的訓(xùn)練方法都以神經(jīng)網(wǎng)絡(luò)為一個實例?!?/div>
官方主頁:http://www./

6. PyML – machine learning in Python
PyML is an interactive object oriented framework for machine learning written in Python. PyML focuses on SVMs and other kernel methods. It is supported on Linux and Mac OS X.
“PyML是一個Python機器學(xué)習(xí)工具包,為各分類和回歸方法提供靈活的架構(gòu)。它主要提供特征選擇、模型選擇、組合分類器、分類評估等功能。”
項目主頁:http://pyml./

7. Milk:Machine learning toolkit in Python.
Its focus is on supervised classification with several classifiers available:
SVMs (based on libsvm), k-NN, random forests, decision trees. It also performs
feature selection. These classifiers can be combined in many ways to form
different classification systems.
“Milk是Python的一個機器學(xué)習(xí)工具箱,其重點是提供監(jiān)督分類法與幾種有效的分類分析:SVMs(基于libsvm),K-NN,隨機森林經(jīng)濟和決策樹。它還可以進行特征選擇。這些分類可以在許多方面相結(jié)合,形成不同的分類系統(tǒng)。對于無監(jiān)督學(xué)習(xí),它提供K-means和affinity propagation聚類算法?!?/div>
官方主頁:http:///software/milk
http:///software/milk

8. PyMVPA: MultiVariate Pattern Analysis (MVPA) in Python
PyMVPA is a Python package intended to ease statistical learning analyses of large datasets. It offers an extensible framework with a high-level interface to a broad range of algorithms for classification, regression, feature selection, data import and export. It is designed to integrate well with related software packages, such as scikit-learn, and MDP. While it is not limited to the neuroimaging domain, it is eminently suited for such datasets. PyMVPA is free software and requires nothing but free-software to run.
“PyMVPA(Multivariate Pattern Analysis in Python)是為大數(shù)據(jù)集提供統(tǒng)計學(xué)習(xí)分析的Python工具包,它提供了一個靈活可擴展的框架。它提供的功能有分類、回歸、特征選擇、數(shù)據(jù)導(dǎo)入導(dǎo)出、可視化等”
官方主頁:http://www./

9. Pyrallel – Parallel Data Analytics in Python
Experimental project to investigate distributed computation patterns for machine learning and other semi-interactive data analytics tasks.
“Pyrallel(Parallel Data Analytics in Python)基于分布式計算模式的機器學(xué)習(xí)和半交互式的試驗項目,可在小型集群上運行”
Github代碼頁:http://github.com/pydata/pyrallel

10. Monte – gradient based learning in Python
Monte (python) is a Python framework for building gradient based learning machines, like neural networks, conditional random fields, logistic regression, etc. Monte contains modules (that hold parameters, a cost-function and a gradient-function) and trainers (that can adapt a module’s parameters by minimizing its cost-function on training data).
Modules are usually composed of other modules, which can in turn contain other modules, etc. Gradients of decomposable systems like these can be computed with back-propagation.
“Monte (machine learning in pure Python)是一個純Python機器學(xué)習(xí)庫。它可以迅速構(gòu)建神經(jīng)網(wǎng)絡(luò)、條件隨機場、邏輯回歸等模型,使用inline-C優(yōu)化,極易使用和擴展。”
官方主頁:http://montepython.

11. Theano
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Theano features:
1)tight integration with NumPy – Use numpy.ndarray in Theano-compiled functions.
2)transparent use of a GPU – Perform data-intensive calculations up to 140x faster than with CPU.(float32 only)
3)efficient symbolic differentiation – Theano does your derivatives for function with one or many inputs.
4)speed and stability optimizations – Get the right answer for log(1+x) even when x is really tiny.
5)dynamic C code generation – Evaluate expressions faster.
6) extensive unit-testing and self-verification – Detect and diagnose many types of mistake.
Theano has been powering large-scale computationally intensive scientific investigations since 2007. But it is also approachable enough to be used in the classroom (IFT6266 at the University of Montreal).
“Theano 是一個 Python 庫,用來定義、優(yōu)化和模擬數(shù)學(xué)表達式計算,用于高效的解決多維數(shù)組的計算問題。Theano的特點:緊密集成Numpy;高效的數(shù)據(jù)密集型GPU計算;高效的符號微分運算;高速和穩(wěn)定的優(yōu)化;動態(tài)生成c代碼;廣泛的單元測試和自我驗證。自2007年以來,Theano已被廣泛應(yīng)用于科學(xué)運算。theano使得構(gòu)建深度學(xué)習(xí)模型更加容易,可以快速實現(xiàn)多種模型。PS:Theano,一位希臘美女,Croton最有權(quán)勢的Milo的女兒,后來成為了畢達哥拉斯的老婆?!?/div>

12. Pylearn2
Pylearn2 is a machine learning library. Most of its functionality is built on top of Theano. This means you can write Pylearn2 plugins (new models, algorithms, etc) using mathematical expressions, and theano will optimize and stabilize those expressions for you, and compile them to a backend of your choice (CPU or GPU).
“Pylearn2建立在theano上,部分依賴scikit-learn上,目前Pylearn2正處于開發(fā)中,將可以處理向量、圖像、視頻等數(shù)據(jù),提供MLP、RBM、SDA等深度學(xué)習(xí)模型。”
官方主頁:http:///software/pylearn2/

    本站是提供個人知識管理的網(wǎng)絡(luò)存儲空間,所有內(nèi)容均由用戶發(fā)布,不代表本站觀點。請注意甄別內(nèi)容中的聯(lián)系方式、誘導(dǎo)購買等信息,謹防詐騙。如發(fā)現(xiàn)有害或侵權(quán)內(nèi)容,請點擊一鍵舉報。
    轉(zhuǎn)藏 分享 獻花(0

    0條評論

    發(fā)表

    請遵守用戶 評論公約

    類似文章 更多