th1522856954的博客

LSTM算法的详细推导，一共10页纸。 LSTM(Long Short-Term Memory)是长短期记忆网络，是一种时间递归神经网络，适合于处理和预测时间序列中间隔和延迟相对较长的重要事件。

Preface What Is Data Science? Who Is This Book For? Why Python? Python 2 Versus Python 3 Outline of This Book Using Code Examples Installation Considerations Conventions Used in This Book O’Reilly Safari How to Contact Us 1. IPython: Beyond Normal Python Shell or Notebook? Launching the IPython Shell Launching the Jupyter Notebook Help and Documentation in IPython Accessing Documentation with ? Accessing Source Code with ?? Exploring Modules with Tab Completion Tab completion of object contents Tab completion when importing Beyond tab completion: Wildcard matching Keyboard Shortcuts in the IPython Shell Navigation Shortcuts Text Entry Shortcuts Command History Shortcuts Miscellaneous Shortcuts IPython Magic Commands Pasting Code Blocks: %paste and %cpaste Running External Code: %run Timing Code Execution: %timeit Help on Magic Functions: ?, %magic, and %lsmagic Input and Output History IPython’s In and Out Objects Underscore Shortcuts and Previous Outputs Suppressing Output Related Magic Commands IPython and Shell Commands Quick Introduction to the Shell Shell Commands in IPython Passing Values to and from the Shell Shell-Related Magic Commands Errors and Debugging Controlling Exceptions: %xmode Debugging: When Reading Tracebacks Is Not Enough Partial list of debugging commands Profiling and Timing Code Timing Code Snippets: %timeit and %time Profiling Full Scripts: %prun Line-by-Line Profiling with %lprun Profiling Memory Use: %memit and %mprun More IPython Resources Web Resources Books 2. Introduction to NumPy Understanding Data Types in Python A Python Integer Is More Than Just an Integer A Python List Is More Than Just a List Fixed-Type Arrays in Python Creating Arrays from Python Lists Creating Arrays from Scratch NumPy Standard Data Types The Basics of NumPy Arrays NumPy Array Attributes Array Indexing: Accessing Single Elements Array Slicing: Accessing Subarrays One-dimensional subarrays Multidimensional subarrays Accessing array rows and columns Subarrays as no-copy views Creating copies of arrays Reshaping of Arrays Array Concatenation and Splitting Concatenation of arrays Splitting of arrays Computation on NumPy Arrays: Universal Functions The Slowness of Loops Introducing UFuncs Exploring NumPy’s UFuncs Array arithmetic Absolute value Trigonometric functions Exponents and logarithms Specialized ufuncs Advanced Ufunc Features Specifying output Aggregates Outer products Ufuncs: Learning More Aggregations: Min, Max, and Everything in Between Summing the Values in an Array Minimum and Maximum Multidimensional aggregates Other aggregation functions Example: What Is the Average Height of US Presidents? Computation on Arrays: Broadcasting Introducing Broadcasting Rules of Broadcasting Broadcasting example 1 Broadcasting example 2 Broadcasting example 3 Broadcasting in Practice Centering an array Plotting a two-dimensional function Comparisons, Masks, and Boolean Logic Example: Counting Rainy Days Digging into the data Comparison Operators as ufuncs Working with Boolean Arrays Counting entries Boolean operators Boolean Arrays as Masks Fancy Indexing Exploring Fancy Indexing Combined Indexing Example: Selecting Random Points Modifying Values with Fancy Indexing Example: Binning Data Sorting Arrays Fast Sorting in NumPy: np.sort and np.argsort Sorting along rows or columns Partial Sorts: Partitioning Example: k-Nearest Neighbors Structured Data: NumPy’s Structured Arrays Creating Structured Arrays More Advanced Compound Types RecordArrays: Structured Arrays with a Twist On to Pandas 3. Data Manipulation with Pandas Installing and Using Pandas Introducing Pandas Objects The Pandas Series Object Series as generalized NumPy array Series as specialized dictionary Constructing Series objects The Pandas DataFrame Object DataFrame as a generalized NumPy array DataFrame as specialized dictionary Constructing DataFrame objects From a single Series object From a list of dicts From a dictionary of Series objects From a two-dimensional NumPy array From a NumPy structured array The Pandas Index Object Index as immutable array Index as ordered set Data Indexing and Selection Data Selection in Series Series as dictionary Series as one-dimensional array Indexers: loc, iloc, and ix Data Selection in DataFrame DataFrame as a dictionary DataFrame as two-dimensional array Additional indexing conventions Operating on Data in Pandas Ufuncs: Index Preservation UFuncs: Index Alignment Index alignment in Series Index alignment in DataFrame Ufuncs: Operations Between DataFrame and Series Handling Missing Data Trade-Offs in Missing Data Conventions Missing Data in Pandas None: Pythonic missing data NaN: Missing numerical data NaN and None in Pandas Operating on Null Values Detecting null values Dropping null values Filling null values Hierarchical Indexing A Multiply Indexed Series The bad way The better way: Pandas MultiIndex MultiIndex as extra dimension Methods of MultiIndex Creation Explicit MultiIndex constructors MultiIndex level names MultiIndex for columns Indexing and Slicing a MultiIndex Multiply indexed Series Multiply indexed DataFrames Rearranging Multi-Indices Sorted and unsorted indices Stacking and unstacking indices Index setting and resetting Data Aggregations on Multi-Indices Combining Datasets: Concat and Append Recall: Concatenation of NumPy Arrays Simple Concatenation with pd.concat Duplicate indices Catching the repeats as an error Ignoring the index Adding MultiIndex keys Concatenation with joins The append() method Combining Datasets: Merge and Join Relational Algebra Categories of Joins One-to-one joins Many-to-one joins Many-to-many joins Specification of the Merge Key The on keyword The left_on and right_on keywords The left_index and right_index keywords Specifying Set Arithmetic for Joins Overlapping Column Names: The suffixes Keyword Example: US States Data Aggregation and Grouping Planets Data Simple Aggregation in Pandas GroupBy: Split, Apply, Combine Split, apply, combine The GroupBy object Column indexing Iteration over groups Dispatch methods Aggregate, filter, transform, apply Aggregation Filtering Transformation The apply() method Specifying the split key A list, array, series, or index providing the grouping keys A dictionary or series mapping index to group Any Python function A list of valid keys Grouping example Pivot Tables Motivating Pivot Tables Pivot Tables by Hand Pivot Table Syntax Multilevel pivot tables Additional pivot table options Example: Birthrate Data Further data exploration Vectorized String Operations Introducing Pandas String Operations Tables of Pandas String Methods Methods similar to Python string methods Methods using regular expressions Miscellaneous methods Vectorized item access and slicing Indicator variables Example: Recipe Database A simple recipe recommender Going further with recipes Working with Time Series Dates and Times in Python Native Python dates and times: datetime and dateutil Typed arrays of times: NumPy’s datetime64 Dates and times in Pandas: Best of both worlds Pandas Time Series: Indexing by Time Pandas Time Series Data Structures Regular sequences: pd.date_range() Frequencies and Offsets Resampling, Shifting, and Windowing Resampling and converting frequencies Time-shifts Rolling windows Where to Learn More Example: Visualizing Seattle Bicycle Counts Visualizing the data Digging into the data High-Performance Pandas: eval() and query() Motivating query() and eval(): Compound Expressions pandas.eval() for Efficient Operations Operations supported by pd.eval() Arithmetic operators Comparison operators Bitwise operators Object attributes and indices Other operations DataFrame.eval() for Column-Wise Operations Assignment in DataFrame.eval() Local variables in DataFrame.eval() DataFrame.query() Method Performance: When to Use These Functions Further Resources 4. Visualization with Matplotlib General Matplotlib Tips Importing matplotlib Setting Styles show() or No show()? How to Display Your Plots Plotting from a script Plotting from an IPython shell Plotting from an IPython notebook Saving Figures to File Two Interfaces for the Price of One MATLAB-style interface Object-oriented interface Simple Line Plots Adjusting the Plot: Line Colors and Styles Adjusting the Plot: Axes Limits Labeling Plots Simple Scatter Plots Scatter Plots with plt.plot Scatter Plots with plt.scatter plot Versus scatter: A Note on Efficiency Visualizing Errors Basic Errorbars Continuous Errors Density and Contour Plots Visualizing a Three-Dimensional Function Histograms, Binnings, and Density Two-Dimensional Histograms and Binnings plt.hist2d: Two-dimensional histogram plt.hexbin: Hexagonal binnings Kernel density estimation Customizing Plot Legends Choosing Elements for the Legend Legend for Size of Points Multiple Legends Customizing Colorbars Customizing Colorbars Choosing the colormap Color limits and extensions Discrete colorbars Example: Handwritten Digits Multiple Subplots plt.axes: Subplots by Hand plt.subplot: Simple Grids of Subplots plt.subplots: The Whole Grid in One Go plt.GridSpec: More Complicated Arrangements Text and Annotation Example: Effect of Holidays on US Births Transforms and Text Position Arrows and Annotation Customizing Ticks Major and Minor Ticks Hiding Ticks or Labels Reducing or Increasing the Number of Ticks Fancy Tick Formats Summary of Formatters and Locators Customizing Matplotlib: Configurations and Stylesheets Plot Customization by Hand Changing the Defaults: rcParams Stylesheets Default style FiveThirtyEight style ggplot Bayesian Methods for Hackers style Dark background Grayscale Seaborn style Three-Dimensional Plotting in Matplotlib Three-Dimensional Points and Lines Three-Dimensional Contour Plots Wireframes and Surface Plots Surface Triangulations

机器学习与模式识别中文版 +pdf+书籍中的算法实现。论坛中只有书籍的pdf。我这个资源包含文中的一些算法的实现。可以说是理论和实践相结合了。希望大家都能成为机器学习大牛。一起努力！

《OpenCV图像处理编程实例》以OpenCV开源库为基础实现图像处理领域的很多通用算法，并结合当今图像处理领域前沿技术，对多个典型工程实例进行讲解及实现。全书内容覆盖面广，由基础到进阶，各个技术点均提供详细的代码实现，以帮助读者快速上手和深入学习。 《OpenCV图像处理编程实例》内容共三个部分，其中1～2章为基础篇，3～6章为进阶篇，7～9章为高级篇。第一部分基础篇主要介绍OpenCV开发基础的相关知识，让读者熟悉图像处理开发环境以及简单的图像处理操作；第二部分进阶篇主要介绍图像处理技术，包括灰度变换技术、平滑技术、边缘检测及形态学技术；第三部分高级篇主要介绍图像应用技术，包括图像分割技术、特征分析和复杂视频处理技术。进阶篇与高级篇的每章末节均提供了与本章内容相关的应用实例，意在让读者更好理解知识点，进而有效地进行图像处理开发。

Python机器学习实践指南 数据和代码。《Python机器学习实践指南 》学习机器学习的一本很好的教程，偏重实践。

压缩包文件，内含25个pdf文件。Scikit-learn是一个功能强大的python包。在数据量不是过大的情况下，可以解决大部分问题。学习使用scikit-learn的过程中，最好在实践的过程中掌握各个机器学习的技能。希望大家都能成为机器学习大神。

基于Keras的神经网络的股票价格预测，实测有效。也是根据人家分享的总结的

北航 Machine-Learning-with-Python教学资料。压缩文档中包含机器学习的各种算法实践。

在一年的机器学习时间里积累的学习文档。压缩包文件中包含：Matplotlib知识点总结,常用算法文档，时间序列的Arima和ANN结合的预测算法，LSTM算法解析，以及常用的多变量时间序列的实战，房价预测。深度学习核心技术文档等。

斯坦福大学机器学习课程个人笔记完整版。页面清晰，内容详实。是机器学习入门的好教材。

模式识别和机器学习 中文版 内含数据目录。中文教程 值得学习。 包含一些常用算法的解释：如神经网络，图模型等

长短期记忆网络详解 ，内含详细的解释。英文资源。对理解LSTM网络的结构有很大的帮助！

Scikit-Learn是基于python的机器学习模块，基于BSD开源许可证。 它包含有完善的文档和丰富的机器学习算法。 这个项目最早由DavidCournapeau 在2007 年发起的，目前也是由社区自愿者进行维护。

Pandas教程 。Python Data Analysis Library 或 pandas 是基于NumPy 的一种工具，该工具是为了解决数据分析任务而创建的。Pandas 纳入了大量库和一些标准的数据模型，提供了高效地操作大型数据集所需的工具。pandas提供了大量能使我们快速便捷地处理数据的函数和方法。你很快就会发现，它是使Python成为强大而高效的数据分析环境的重要因素之一。

《深入浅出深度学习：原理剖析与Python实践》介绍了深度学习相关的原理与应用，全书共分为三大部分，第一部分主要回顾了深度学习的发展历史，以及Theano的使用；第二部分详细讲解了与深度学习相关的基础知识，包括线性代数、概率论、概率图模型、机器学习和至优化算法；在第三部分中，针对若干核心的深度学习模型，如自编码器、受限玻尔兹曼机、递归神经网络和卷积神经网络等进行详细的原理分析与讲解，并针对不同的模型给出相应的具体应用。

NumPy攻略 Python科学计算与数据分析