Machine Learning

Package lambda provides the API client, operations, and parameter types for AWS Lambda. Lambda is a compute service that lets you run code without provisioning or managing servers. Lambda runs your code on a high-availability compute infrastructure and performs all of the administration of the compute resources, including server and operating system maintenance, capacity provisioning and automatic scaling, code monitoring and logging. With Lambda, you can run code for virtually any type of application or backend service. For more information about the Lambda service, see What is Lambdain the Lambda Developer Guide. The Lambda API Reference provides information about each of the API methods, including details about the parameters in each API request and response. You can use Software Development Kits (SDKs), Integrated Development Environment (IDE) Toolkits, and command line tools to access the API. For installation instructions, see Tools for Amazon Web Services. For a list of Region-specific endpoints that Lambda supports, see Lambda endpoints and quotas in the Amazon Web Services General Reference.. When making the API calls, you will need to authenticate your request by providing a signature. Lambda supports signature version 4. For more information, see Signature Version 4 signing processin the Amazon Web Services General Reference.. Because Amazon Web Services SDKs use the CA certificates from your computer, changes to the certificates on the Amazon Web Services servers can cause connection failures when you attempt to use an SDK. You can prevent these failures by keeping your computer's CA certificates and operating system up-to-date. If you encounter this issue in a corporate environment and do not manage your own computer, you might need to ask an administrator to assist with the update process. The following list shows minimum operating system and Java versions: Microsoft Windows versions that have updates from January 2005 or later installed contain at least one of the required CAs in their trust list. Mac OS X 10.4 with Java for Mac OS X 10.4 Release 5 (February 2007), Mac OS X 10.5 (October 2007), and later versions contain at least one of the required CAs in their trust list. Red Hat Enterprise Linux 5 (March 2007), 6, and 7 and CentOS 5, 6, and 7 all contain at least one of the required CAs in their default trusted CA list. Java 1.4.2_12 (May 2006), 5 Update 2 (March 2005), and all later versions, including Java 6 (December 2006), 7, and 8, contain at least one of the required CAs in their default trusted CA list. When accessing the Lambda management console or Lambda API endpoints, whether through browsers or programmatically, you will need to ensure your client machines support any of the following CAs: Amazon Root CA 1 Starfield Services Root Certificate Authority - G2 Starfield Class 2 Certification Authority Root certificates from the first two authorities are available from Amazon trust services, but keeping your computer up-to-date is the more straightforward solution. To learn more about ACM-provided certificates, see Amazon Web Services Certificate Manager FAQs.

Package golearn is a machine learning library for Go.

Package emr provides the API client, operations, and parameter types for Amazon EMR. Amazon EMR is a web service that makes it easier to process large amounts of data efficiently. Amazon EMR uses Hadoop processing combined with several Amazon Web Services services to do tasks such as web indexing, data mining, log file analysis, machine learning, scientific simulation, and data warehouse management.

Package gorgonia is a library that helps facilitate machine learning in Go. Write and evaluate mathematical equations involving multidimensional arrays easily. Do differentiation with them just as easily. Autodiff showcases automatic differentiation Basic example of representing mathematical equations as graphs. In this example, we want to represent the following equation Gorgonia provides an API that is fairly idiomatic - most of the functions in in the API return (T, error). This is useful for many cases, such as an interactive shell for deep learning. However, it must also be acknowledged that this makes composing functions together a bit cumbersome. To that end, Gorgonia provides two alternative methods. First, the `Lift` based functions; Second the `Must` function Linear Regression Example The formula for a straight line is We want to find an `m` and a `c` that fits the equation well. We'll do it in both float32 and float64 to showcase the extensibility of Gorgonia This example showcases the reasons for the more confusing functions. This example showcases dealing with errors. This is part 2 of the raison d'être of the more complicated functions - dealing with errors SymbolicDiff showcases symbolic differentiation

Package guardduty provides the API client, operations, and parameter types for Amazon GuardDuty. Amazon GuardDuty is a continuous security monitoring service that analyzes and processes the following foundational data sources - VPC flow logs, Amazon Web Services CloudTrail management event logs, CloudTrail S3 data event logs, EKS audit logs, DNS logs, Amazon EBS volume data, runtime activity belonging to container workloads, such as Amazon EKS, Amazon ECS (including Amazon Web Services Fargate), and Amazon EC2 instances. It uses threat intelligence feeds, such as lists of malicious IPs and domains, and machine learning to identify unexpected, potentially unauthorized, and malicious activity within your Amazon Web Services environment. This can include issues like escalations of privileges, uses of exposed credentials, or communication with malicious IPs, domains, or presence of malware on your Amazon EC2 instances and container workloads. For example, GuardDuty can detect compromised EC2 instances and container workloads serving malware, or mining bitcoin. GuardDuty also monitors Amazon Web Services account access behavior for signs of compromise, such as unauthorized infrastructure deployments like EC2 instances deployed in a Region that has never been used, or unusual API calls like a password policy change to reduce password strength. GuardDuty informs you about the status of your Amazon Web Services environment by producing security findings that you can view in the GuardDuty console or through Amazon EventBridge. For more information, see the Amazon GuardDuty User Guide.

Package transfer provides the API client, operations, and parameter types for AWS Transfer Family. Transfer Family is a fully managed service that enables the transfer of files over the File Transfer Protocol (FTP), File Transfer Protocol over SSL (FTPS), or Secure Shell (SSH) File Transfer Protocol (SFTP) directly into and out of Amazon Simple Storage Service (Amazon S3) or Amazon EFS. Additionally, you can use Applicability Statement 2 (AS2) to transfer files into and out of Amazon S3. Amazon Web Services helps you seamlessly migrate your file transfer workflows to Transfer Family by integrating with existing authentication systems, and providing DNS routing with Amazon Route 53 so nothing changes for your customers and partners, or their applications. With your data in Amazon S3, you can use it with Amazon Web Services services for processing, analytics, machine learning, and archiving. Getting started with Transfer Family is easy since there is no infrastructure to buy and set up.

Package face implements face recognition for Go using dlib, a popular machine learning toolkit. This example shows the basic usage of the package: create an recognizer, recognize faces, classify them using few known ones.

Package lingua accurately detects the natural language of written text, be it long or short. Its task is simple: It tells you which language some text is written in. This is very useful as a preprocessing step for linguistic data in natural language processing applications such as text classification and spell checking. Other use cases, for instance, might include routing e-mails to the right geographically located customer service department, based on the e-mails' languages. Language detection is often done as part of large machine learning frameworks or natural language processing applications. In cases where you don't need the full-fledged functionality of those systems or don't want to learn the ropes of those, a small flexible library comes in handy. So far, the only other comprehensive open source library in the Go ecosystem for this task is Whatlanggo (https://github.com/abadojack/whatlanggo). Unfortunately, it has two major drawbacks: 1. Detection only works with quite lengthy text fragments. For very short text snippets such as Twitter messages, it does not provide adequate results. 2. The more languages take part in the decision process, the less accurate are the detection results. Lingua aims at eliminating these problems. It nearly does not need any configuration and yields pretty accurate results on both long and short text, even on single words and phrases. It draws on both rule-based and statistical methods but does not use any dictionaries of words. It does not need a connection to any external API or service either. Once the library has been downloaded, it can be used completely offline. Compared to other language detection libraries, Lingua's focus is on quality over quantity, that is, getting detection right for a small set of languages first before adding new ones. Currently, 75 languages are supported. They are listed as variants of type Language. Lingua is able to report accuracy statistics for some bundled test data available for each supported language. The test data for each language is split into three parts: 1. a list of single words with a minimum length of 5 characters 2. a list of word pairs with a minimum length of 10 characters 3. a list of complete grammatical sentences of various lengths Both the language models and the test data have been created from separate documents of the Wortschatz corpora (https://wortschatz.uni-leipzig.de) offered by Leipzig University, Germany. Data crawled from various news websites have been used for training, each corpus comprising one million sentences. For testing, corpora made of arbitrarily chosen websites have been used, each comprising ten thousand sentences. From each test corpus, a random unsorted subset of 1000 single words, 1000 word pairs and 1000 sentences has been extracted, respectively. Given the generated test data, I have compared the detection results of Lingua, and Whatlanggo running over the data of Lingua's supported 75 languages. Additionally, I have added Google's CLD3 (https://github.com/google/cld3/) to the comparison with the help of the gocld3 bindings (https://github.com/jmhodges/gocld3). Languages that are not supported by CLD3 or Whatlanggo are simply ignored during the detection process. Lingua clearly outperforms its contenders. Every language detector uses a probabilistic n-gram (https://en.wikipedia.org/wiki/N-gram) model trained on the character distribution in some training corpus. Most libraries only use n-grams of size 3 (trigrams) which is satisfactory for detecting the language of longer text fragments consisting of multiple sentences. For short phrases or single words, however, trigrams are not enough. The shorter the input text is, the less n-grams are available. The probabilities estimated from such few n-grams are not reliable. This is why Lingua makes use of n-grams of sizes 1 up to 5 which results in much more accurate prediction of the correct language. A second important difference is that Lingua does not only use such a statistical model, but also a rule-based engine. This engine first determines the alphabet of the input text and searches for characters which are unique in one or more languages. If exactly one language can be reliably chosen this way, the statistical model is not necessary anymore. In any case, the rule-based engine filters out languages that do not satisfy the conditions of the input text. Only then, in a second step, the probabilistic n-gram model is taken into consideration. This makes sense because loading less language models means less memory consumption and better runtime performance. In general, it is always a good idea to restrict the set of languages to be considered in the classification process using the respective api methods. If you know beforehand that certain languages are never to occur in an input text, do not let those take part in the classifcation process. The filtering mechanism of the rule-based engine is quite good, however, filtering based on your own knowledge of the input text is always preferable. There might be classification tasks where you know beforehand that your language data is definitely not written in Latin, for instance. The detection accuracy can become better in such cases if you exclude certain languages from the decision process or just explicitly include relevant languages. Knowing about the most likely language is nice but how reliable is the computed likelihood? And how less likely are the other examined languages in comparison to the most likely one? In the example below, a slice of ConfidenceValue is returned containing those languages which the calling instance of LanguageDetector has been built from. The entries are sorted by their confidence value in descending order. Each value is a probability between 0.0 and 1.0. The probabilities of all languages will sum to 1.0. If the language is unambiguously identified by the rule engine, the value 1.0 will always be returned for this language. The other languages will receive a value of 0.0. By default, Lingua uses lazy-loading to load only those language models on demand which are considered relevant by the rule-based filter engine. For web services, for instance, it is rather beneficial to preload all language models into memory to avoid unexpected latency while waiting for the service response. If you want to enable the eager-loading mode, you can do it as seen below. Multiple instances of LanguageDetector share the same language models in memory which are accessed asynchronously by the instances. By default, Lingua returns the most likely language for a given input text. However, there are certain words that are spelled the same in more than one language. The word `prologue`, for instance, is both a valid English and French word. Lingua would output either English or French which might be wrong in the given context. For cases like that, it is possible to specify a minimum relative distance that the logarithmized and summed up probabilities for each possible language have to satisfy. It can be stated as seen below. Be aware that the distance between the language probabilities is dependent on the length of the input text. The longer the input text, the larger the distance between the languages. So if you want to classify very short text phrases, do not set the minimum relative distance too high. Otherwise Unknown will be returned most of the time as in the example below. This is the return value for cases where language detection is not reliably possible.

Package nlp provides implementations of selected machine learning algorithms for natural language processing of text corpora. The primary focus is the statistical semantics of plain-text documents supporting semantic analysis and retrieval of semantically similar documents. The package makes use of the Gonum (http://http//www.gonum.org/) library for linear algebra and scientific computing with some inspiration taken from Python's scikit-learn (http://scikit-learn.org/stable/) and Gensim(https://radimrehurek.com/gensim/) The primary intended use case is to support document input as text strings encoded as a matrix of numerical feature vectors called a `term document matrix`. Each column in the matrix corresponds to a document in the corpus and each row corresponds to a unique term occurring in the corpus. The individual elements within the matrix contain the frequency with which each term occurs within each document (referred to as `term frequency`). Whilst textual data from document corpora are the primary intended use case, the algorithms can be used with other types of data from other sources once encoded (vectorised) into a suitable matrix e.g. image data, sound data, users/products, etc. These matrices can be processed and manipulated through the application of additional transformations for weighting features, identifying relationships or optimising the data for analysis, information retrieval and/or predictions. Typically the algorithms in this package implement one of three primary interfaces: One of the implementations of Vectoriser is Pipeline which can be used to wire together pipelines composed of a Vectoriser and one or more Transformers arranged in serial so that the output from each stage forms the input of the next. This can be used to construct a classic LSI (Latent Semantic Indexing) pipeline (vectoriser -> TF.IDF weighting -> Truncated SVD): Whilst they take different inputs, both Vectorisers and Transformers have 3 primary methods:

Package sparse provides implementations of selected sparse matrix formats. Matrices and linear algebra are used extensively in scientific computing and machine learning applications. Large datasets are analysed comprising vectors of numerical features that represent some object. The nature of feature encoding schemes, especially those like "one hot", tends to lead to vectors with mostly zero values for many of the features. In text mining applications, where features are typically terms from a vocabulary, it is not uncommon for 99% of the elements within these vectors to contain zero values. Sparse matrix formats take advantage of this fact to optimise memory usage and processing performance by only storing and processing non-zero values. Sparse matrix formats can broadly be divided into 3 main categories: 1. Creational - Sparse matrix formats suited to construction and building of matrices. Matrix formats in this category include DOK (Dictionary Of Keys) and COO (COOrdinate aka triplet). 2. Operational - Sparse matrix formats suited to arithmetic operations e.g. multiplication. Matrix formats in this category include CSR (Compressed Sparse Row aka CRS - Compressed Row Storage) and CSC (Compressed Sparse Column aka CCS - Compressed Column Storage) 3. Specialised - Specialised matrix formats suiting specific sparsity patterns. Matrix formats in this category include DIA (DIAgonal) for efficiently storing and manipulating symmetric diagonal matrices. A common practice is to construct sparse matrices using a creational format e.g. DOK or COO and then convert them to an operational format e.g. CSR for arithmetic operations. All sparse matrix implementations in this package implement the Matrix interface defined within the gonum/mat package and so may be used interchangeably with matrix types defined within the package e.g. mat.Dense, mat.VecDense, etc.

Package iotanalytics provides the API client, operations, and parameter types for AWS IoT Analytics. IoT Analytics allows you to collect large amounts of device data, process messages, and store them. You can then query the data and run sophisticated analytics on it. IoT Analytics enables advanced data exploration through integration with Jupyter Notebooks and data visualization through integration with Amazon QuickSight. Traditional analytics and business intelligence tools are designed to process structured data. IoT data often comes from devices that record noisy processes (such as temperature, motion, or sound). As a result the data from these devices can have significant gaps, corrupted messages, and false readings that must be cleaned up before analysis can occur. Also, IoT data is often only meaningful in the context of other data from external sources. IoT Analytics automates the steps required to analyze data from IoT devices. IoT Analytics filters, transforms, and enriches IoT data before storing it in a time-series data store for analysis. You can set up the service to collect only the data you need from your devices, apply mathematical transforms to process the data, and enrich the data with device-specific metadata such as device type and location before storing it. Then, you can analyze your data by running queries using the built-in SQL query engine, or perform more complex analytics and machine learning inference. IoT Analytics includes pre-built models for common IoT use cases so you can answer questions like which devices are about to fail or which customers are at risk of abandoning their wearable devices.

Package machinelearning provides the API client, operations, and parameter types for Amazon Machine Learning. Definition of the public APIs exposed by Amazon Machine Learning

Package detective provides the API client, operations, and parameter types for Amazon Detective. Detective uses machine learning and purpose-built visualizations to help you to analyze and investigate security issues across your Amazon Web Services (Amazon Web Services) workloads. Detective automatically extracts time-based events such as login attempts, API calls, and network traffic from CloudTrail and Amazon Virtual Private Cloud (Amazon VPC) flow logs. It also extracts findings detected by Amazon GuardDuty. The Detective API primarily supports the creation and management of behavior graphs. A behavior graph contains the extracted data from a set of member accounts, and is created and managed by an administrator account. To add a member account to the behavior graph, the administrator account sends an invitation to the account. When the account accepts the invitation, it becomes a member account in the behavior graph. Detective is also integrated with Organizations. The organization management account designates the Detective administrator account for the organization. That account becomes the administrator account for the organization behavior graph. The Detective administrator account is also the delegated administrator account for Detective in Organizations. The Detective administrator account can enable any organization account as a member account in the organization behavior graph. The organization accounts do not receive invitations. The Detective administrator account can also invite other accounts to the organization behavior graph. Every behavior graph is specific to a Region. You can only use the API to manage behavior graphs that belong to the Region that is associated with the currently selected endpoint. The administrator account for a behavior graph can use the Detective API to do the following: Enable and disable Detective. Enabling Detective creates a new behavior graph. View the list of member accounts in a behavior graph. Add member accounts to a behavior graph. Remove member accounts from a behavior graph. Apply tags to a behavior graph. The organization management account can use the Detective API to select the delegated administrator for Detective. The Detective administrator account for an organization can use the Detective API to do the following: Perform all of the functions of an administrator account. Determine whether to automatically enable new organization accounts as member accounts in the organization behavior graph. An invited member account can use the Detective API to do the following: View the list of behavior graphs that they are invited to. Accept an invitation to contribute to a behavior graph. Decline an invitation to contribute to a behavior graph. Remove their account from a behavior graph. All API actions are logged as CloudTrail events. See Logging Detective API Calls with CloudTrail. We replaced the term "master account" with the term "administrator account". An administrator account is used to centrally manage multiple accounts. In the case of Detective, the administrator account manages the accounts in their behavior graph.

Package dataexchange provides the API client, operations, and parameter types for AWS Data Exchange. AWS Data Exchange is a service that makes it easy for AWS customers to exchange data in the cloud. You can use the AWS Data Exchange APIs to create, update, manage, and access file-based data set in the AWS Cloud. As a subscriber, you can view and access the data sets that you have an entitlement to through a subscription. You can use the APIs to download or copy your entitled data sets to Amazon Simple Storage Service (Amazon S3) for use across a variety of AWS analytics and machine learning services. As a provider, you can create and manage your data sets that you would like to publish to a product. Being able to package and provide your data sets into products requires a few steps to determine eligibility. For more information, visit the AWS Data Exchange User Guide. A data set is a collection of data that can be changed or updated over time. Data sets can be updated using revisions, which represent a new version or incremental change to a data set. A revision contains one or more assets. An asset in AWS Data Exchange is a piece of data that can be stored as an Amazon S3 object, Redshift datashare, API Gateway API, AWS Lake Formation data permission, or Amazon S3 data access. The asset can be a structured data file, an image file, or some other data file. Jobs are asynchronous import or export operations used to create or copy assets.

Package CloudForest implements ensembles of decision trees for machine learning in pure Go (golang to search engines). It allows for a number of related algorithms for classification, regression, feature selection and structure analysis on heterogeneous numerical/categorical data with missing values. These include: Breiman and Cutler's Random Forest for Classification and Regression Adaptive Boosting (AdaBoost) Classification Gradiant Boosting Tree Regression Entropy and Cost driven classification L1 regression Feature selection with artificial contrasts Proximity and model structure analysis Roughly balanced bagging for unbalanced classification The API hasn't stabilized yet and may change rapidly. Tests and benchmarks have been performed only on embargoed data sets and can not yet be released. Library Documentation is in code and can be viewed with godoc or live at: http://godoc.org/github.com/ryanbressler/CloudForest Documentation of command line utilities and file formats can be found in README.md, which can be viewed fromated on github: http://github.com/ryanbressler/CloudForest Pull requests and bug reports are welcome. CloudForest was created by Ryan Bressler and is being developed in the Shumelivich Lab at the Institute for Systems Biology for use on genomic/biomedical data with partial support from The Cancer Genome Atlas and the Inova Translational Medicine Institute. CloudForest is intended to provide fast, comprehensible building blocks that can be used to implement ensembles of decision trees. CloudForest is written in Go to allow a data scientist to develop and scale new models and analysis quickly instead of having to modify complex legacy code. Data structures and file formats are chosen with use in multi threaded and cluster environments in mind. Go's support for function types is used to provide a interface to run code as data is percolated through a tree. This method is flexible enough that it can extend the tree being analyzed. Growing a decision tree using Breiman and Cutler's method can be done in an anonymous function/closure passed to a tree's root node's Recurse method: This allows a researcher to include whatever additional analysis they need (importance scores, proximity etc) in tree growth. The same Recurse method can also be used to analyze existing forests to tabulate scores or extract structure. Utilities like leafcount and errorrate use this method to tabulate data about the tree in collection objects. Decision tree's are grown with the goal of reducing "Impurity" which is usually defined as Gini Impurity for categorical targets or mean squared error for numerical targets. CloudForest grows trees against the Target interface which allows for alternative definitions of impurity. CloudForest includes several alternative targets: Additional targets can be stacked on top of these target to add boosting functionality: Repeatedly splitting the data and searching for the best split at each node of a decision tree are the most computationally intensive parts of decision tree learning and CloudForest includes optimized code to perform these tasks. Go's slices are used extensively in CloudForest to make it simple to interact with optimized code. Many previous implementations of Random Forest have avoided reallocation by reordering data in place and keeping track of start and end indexes. In go, slices pointing at the same underlying arrays make this sort of optimization transparent. For example a function like: can return left and right slices that point to the same underlying array as the original slice of cases but these slices should not have their values changed. Functions used while searching for the best split also accepts pointers to reusable slices and structs to maximize speed by keeping memory allocations to a minimum. BestSplitAllocs contains pointers to these items and its use can be seen in functions like: For categorical predictors, BestSplit will also attempt to intelligently choose between 4 different implementations depending on user input and the number of categories. These include exhaustive, random, and iterative searches for the best combination of categories implemented with bitwise operations against int and big.Int. See BestCatSplit, BestCatSplitIter, BestCatSplitBig and BestCatSplitIterBig. All numerical predictors are handled by BestNumSplit which relies on go's sorting package. Training a Random forest is an inherently parallel process and CloudForest is designed to allow parallel implementations that can tackle large problems while keeping memory usage low by writing and using data structures directly to/from disk. Trees can be grown in separate go routines. The growforest utility provides an example of this that uses go routines and channels to grow trees in parallel and write trees to disk as the are finished by the "worker" go routines. The few summary statistics like mean impurity decrease per feature (importance) can be calculated using thread safe data structures like RunningMean. Trees can also be grown on separate machines. The .sf stochastic forest format allows several small forests to be combined by concatenation and the ForestReader and ForestWriter structs allow these forests to be accessed tree by tree (or even node by node) from disk. For data sets that are too big to fit in memory on a single machine Tree.Grow and FeatureMatrix.BestSplitter can be reimplemented to load candidate features from disk, distributed database etc. By default cloud forest uses a fast heuristic for missing values. When proposing a split on a feature with missing data the missing cases are removed and the impurity value is corrected to use three way impurity which reduces the bias towards features with lots of missing data: Missing values in the target variable are left out of impurity calculations. This provided generally good results at a fraction of the computational costs of imputing data. Optionally, feature.ImputeMissing or featurematrixImputeMissing can be called before forest growth to impute missing values to the feature mean/mode which Brieman [2] suggests as a fast method for imputing values. This forest could also be analyzed for proximity (using leafcount or tree.GetLeaves) to do the more accurate proximity weighted imputation Brieman describes. Experimental support is provided for 3 way splitting which splits missing cases onto a third branch. [2] This has so far yielded mixed results in testing. At some point in the future support may be added for local imputing of missing values during tree growth as described in [3] [1] http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm#missing1 [2] https://code.google.com/p/rf-ace/ [3] http://projecteuclid.org/DPubS?verb=Display&version=1.0&service=UI&handle=euclid.aoas/1223908043&page=record In CloudForest data is stored using the FeatureMatrix struct which contains Features. The Feature struct implements storage and methods for both categorical and numerical data and calculations of impurity etc and the search for the best split. The Target interface abstracts the methods of Feature that are needed for a feature to be predictable. This allows for the implementation of alternative types of regression and classification. Trees are built from Nodes and Splitters and stored within a Forest. Tree has a Grow implements Brieman and Cutler's method (see extract above) for growing a tree. A GrowForest method is also provided that implements the rest of the method including sampling cases but it may be faster to grow the forest to disk as in the growforest utility. Prediction and Voting is done using Tree.Vote and CatBallotBox and NumBallotBox which implement the VoteTallyer interface.

Package goro provides a high level machine learning library based on Gorgonia.

Package golearn is a machine learning library for Go.

Package codeguruprofiler provides the API client, operations, and parameter types for Amazon CodeGuru Profiler. operations. Amazon CodeGuru Profiler collects runtime performance data from your live applications, and provides recommendations that can help you fine-tune your application performance. Using machine learning algorithms, CodeGuru Profiler can help you find your most expensive lines of code and suggest ways you can improve efficiency and remove CPU bottlenecks. Amazon CodeGuru Profiler provides different visualizations of profiling data to help you identify what code is running on the CPU, see how much time is consumed, and suggest ways to reduce CPU utilization. Amazon CodeGuru Profiler currently supports applications written in all Java virtual machine (JVM) languages and Python. While CodeGuru Profiler supports both visualizations and recommendations for applications written in Java, it can also generate visualizations and a subset of recommendations for applications written in other JVM languages and Python. For more information, see What is Amazon CodeGuru Profiler in the Amazon CodeGuru Profiler User Guide.

Package codegurureviewer provides the API client, operations, and parameter types for Amazon CodeGuru Reviewer. This section provides documentation for the Amazon CodeGuru Reviewer API operations. CodeGuru Reviewer is a service that uses program analysis and machine learning to detect potential defects that are difficult for developers to find and recommends fixes in your Java and Python code. By proactively detecting and providing recommendations for addressing code defects and implementing best practices, CodeGuru Reviewer improves the overall quality and maintainability of your code base during the code review stage. For more information about CodeGuru Reviewer, see the Amazon CodeGuru Reviewer User Guide. To improve the security of your CodeGuru Reviewer API calls, you can establish a private connection between your VPC and CodeGuru Reviewer by creating an interface VPC endpoint. For more information, see CodeGuru Reviewer and interface VPC endpoints (Amazon Web Services PrivateLink)in the Amazon CodeGuru Reviewer User Guide.

Package personalize provides the API client, operations, and parameter types for Amazon Personalize. Amazon Personalize is a machine learning service that makes it easy to add individualized recommendations to customers.

Package sagemakera2iruntime provides the API client, operations, and parameter types for Amazon Augmented AI Runtime. Amazon Augmented AI (Amazon A2I) adds the benefit of human judgment to any machine learning application. When an AI application can't evaluate data with a high degree of confidence, human reviewers can take over. This human review is called a human review workflow. To create and start a human review workflow, you need three resources: a worker task template, a flow definition, and a human loop. For information about these resources and prerequisites for using Amazon A2I, see Get Started with Amazon Augmented AIin the Amazon SageMaker Developer Guide. This API reference includes information about API actions and data types that you can use to interact with Amazon A2I programmatically. Use this guide to: Start a human loop with the StartHumanLoop operation when using Amazon A2I with a custom task type. To learn more about the difference between custom and built-in task types, see Use Task Types. To learn how to start a human loop using this API, see Create and Start a Human Loop for a Custom Task Typein the Amazon SageMaker Developer Guide. Manage your human loops. You can list all human loops that you have created, describe individual human loops, and stop and delete human loops. To learn more, see Monitor and Manage Your Human Loopin the Amazon SageMaker Developer Guide. Amazon A2I integrates APIs from various AWS services to create and start human review workflows for those services. To learn how Amazon A2I uses these APIs, see Use APIs in Amazon A2Iin the Amazon SageMaker Developer Guide.