added tabbed nav to the template gallery and new information per template
Project: http://git-wip-us.apache.org/repos/asf/incubator-predictionio/repo Commit: http://git-wip-us.apache.org/repos/asf/incubator-predictionio/commit/3d1b777d Tree: http://git-wip-us.apache.org/repos/asf/incubator-predictionio/tree/3d1b777d Diff: http://git-wip-us.apache.org/repos/asf/incubator-predictionio/diff/3d1b777d Branch: refs/heads/develop Commit: 3d1b777d0ec2e4e6d6c77d43a7d528ac44287cb5 Parents: 5335b31 Author: pferrel <[email protected]> Authored: Mon Dec 26 14:12:33 2016 -0800 Committer: pferrel <[email protected]> Committed: Mon Dec 26 14:12:33 2016 -0800 ---------------------------------------------------------------------- docs/manual/lib/gallery_generator.rb | 84 ++- docs/manual/source/gallery/templates.yaml | 604 +++++++++++-------- .../source/stylesheets/partials/_tabs.css.scss | 11 + 3 files changed, 426 insertions(+), 273 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/incubator-predictionio/blob/3d1b777d/docs/manual/lib/gallery_generator.rb ---------------------------------------------------------------------- diff --git a/docs/manual/lib/gallery_generator.rb b/docs/manual/lib/gallery_generator.rb index 351a381..84d2e54 100644 --- a/docs/manual/lib/gallery_generator.rb +++ b/docs/manual/lib/gallery_generator.rb @@ -22,49 +22,52 @@ module Gallery private - INTRO = -'--- + INTRO = '--- title: Engine Template Gallery --- + +Pick a tab for the type of template you are looking for. Some still need to be ported (a simple process) to Apache PIO and these are marked. Also see each Template description for special support instructions. + ' - UNSUPERVISED = '## Unsupervised Learning ' + BEGIN_TABS = '<div class="tabs">' - CLASSIFICATION = '## Classification' + RECOMMENDER_SYSTEMS = '<div data-tab="Recommenders">' - REGRESSION = '## Regression' + CLASSIFICATION = '<div data-tab="Classification">' - RECOMMENDER_SYSTEMS = '## Recommender Systems' + REGRESSION = '<div data-tab="Regression">' - NLP = '## Natural Language Processing' + CLUSTERING = '<div data-tab="Clustering">' - OTHER = '## Other' + NLP = '<div data-tab="NLP">' - TEMPLATE_INTRO = ' -***[%{name}](%{repo})*** ' + SIMILARITY = '<div data-tab="Similarity">' - STAR_BUTTON = -' -<iframe src="https://ghbtns.com/github-btn.html?user=%{user}&repo=%{repo}&type=star&count=true"; -frameborder="0" align="middle" scrolling="0" width="170px" height="20px"></iframe> + OTHER = '<div data-tab="Other">' -' + TEMPLATE_INTRO = '<h3><a href="%{repo}">%{name}</a></h3>' + + STAR_BUTTON ='<iframe src="https://ghbtns.com/github-btn.html?user=%{user}&repo=%{repo}&type=star&count=true"; frameborder="0" align="middle" scrolling="0" width="170px" height="20px"></iframe>' TEMPLATE_DETAILS = ' +<p> %{description} - -Type | Language | License | Status | PIO min version -:----: | :-----:| :-----: | :----: | :-------------: -%{type} | %{language} | %{license} | %{status} | %{pio_min_version} +</p> +<p>Support: %{support}</p> <br/> -' - - SECTION_SEPARATOR = -' +<table> +<tr><th>Type</th><th>Language</th><th>License</th><th>Status</th><th>PIO min version</th><th>Apache PIO Convesion Required</th</tr> +<tr><td>%{type}</td><td>%{language}</td><td>%{license}</td><td>%{status}</td><td>%{pio_min_version}</td><td>%{apache_pio_convesion_required}</td></tr> +</table> <br/> ' + SECTION_SEPARATOR ='</div>' + + END_TABS ='</div>' + class Template public attr_accessor :has_github, :github_repo, :github_user @@ -113,7 +116,9 @@ Type | Language | License | Status | PIO min version language: template.language, license: template.license, status: template.status, + support: template.support_link, pio_min_version: template.pio_min_version, + apache_pio_convesion_required: template.apache_pio_convesion_required }) end @@ -124,15 +129,23 @@ Type | Language | License | Status | PIO min version end def self.write_markdown(mdfile, templates) + recommenders = templates.select{ |engine| engine.tags.include? 'recommender' } classification = templates.select{ |engine| engine.tags.include? 'classification' } regression = templates.select{ |engine| engine.tags.include? 'regression' } - unsupervised = templates.select{ |engine| engine.tags.include? 'unsupervised' } - recommenders = templates.select{ |engine| engine.tags.include? 'recommender' } + similarity = templates.select{ |engine| engine.tags.include? 'similarity' } nlps = templates.select{ |engine| engine.tags.include? 'nlp' } + clustering = templates.select{ |engine| engine.tags.include? 'clustering' } others = templates.select{ |engine| engine.tags.include? 'other' } mdfile.write(INTRO) + mdfile.write(BEGIN_TABS) + + mdfile.write(RECOMMENDER_SYSTEMS) + write_templates(mdfile, recommenders) + + mdfile.write(SECTION_SEPARATOR) + mdfile.write(CLASSIFICATION) write_templates(mdfile, classification) @@ -143,22 +156,29 @@ Type | Language | License | Status | PIO min version mdfile.write(SECTION_SEPARATOR) - mdfile.write(UNSUPERVISED) - write_templates(mdfile, unsupervised) + mdfile.write(NLP) + write_templates(mdfile, nlps) mdfile.write(SECTION_SEPARATOR) - mdfile.write(RECOMMENDER_SYSTEMS) - write_templates(mdfile, recommenders) + mdfile.write(CLUSTERING) + write_templates(mdfile, clustering) mdfile.write(SECTION_SEPARATOR) - mdfile.write(NLP) - write_templates(mdfile, nlps) + mdfile.write(SIMILARITY) + write_templates(mdfile, similarity) + + mdfile.write(SECTION_SEPARATOR) mdfile.write(OTHER) write_templates(mdfile, others) - end + + mdfile.write(SECTION_SEPARATOR) + + mdfile.write(END_TABS) + + end public http://git-wip-us.apache.org/repos/asf/incubator-predictionio/blob/3d1b777d/docs/manual/source/gallery/templates.yaml ---------------------------------------------------------------------- diff --git a/docs/manual/source/gallery/templates.yaml b/docs/manual/source/gallery/templates.yaml index aa650bd..4dc7e61 100644 --- a/docs/manual/source/gallery/templates.yaml +++ b/docs/manual/source/gallery/templates.yaml @@ -1,22 +1,131 @@ +# Similarity + +- template: + name: Content Based SVD Item Similarity Engine + repo: "https://github.com/alexice/template-scala-parallel-svd-item-similarity"; + description: |- + Template to calculate similarity between items based on their attributes—sometimes called content-based similarity. Attributes can be either numeric or categorical in the last case it will be encoded using one-hot encoder. Algorithm uses SVD in order to reduce data dimensionality. Cosine similarity is now implemented but can be easily extended to other similarity measures. + tags: [similarity] + type: Parallel + language: Scala + license: "Apache Licence 2.0" + status: alpha + pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://groups.google.com/forum/#!forum/actionml-user";>The Universal Recommender user group</a>' + +- template: + name: Cstablo-template-text-similarity-classification + repo: "https://github.com/goliasz/pio-template-text-similarity"; + description: |- + Text similarity engine based on Word2Vec algorithm. Builds vectors of full documents in training phase. Finds similar documents in query phase. + tags: [similarity, nlp] + type: Parallel + language: Scala + license: "Apache Licence 2.0" + status: alpha + pio_min_version: 0.9.5 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/goliasz/pio-template-text-similarity/issues";>Github issues</a>' + +# Clustering + +- template: + name: MLlibKMeansClustering + repo: "https://github.com/sahiliitm/predictionio-MLlibKMeansClusteringTemplate"; + description: |- + This is a template which demonstrates the use of K-Means clustering algorithm which can be deployed on a spark-cluster using prediction.io. + tags: [clustering] + type: Parallel + language: Scala + license: "Apache Licence 2.0" + status: alpha + pio_min_version: '-' + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/sahiliitm/predictionio-MLlibKMeansClusteringTemplate/issues";>Github issues</a>' + +- template: + name: Topc Model (LDA) + repo: "https://github.com/EmergentOrder/template-scala-topic-model-LDA"; + description: |- + A PredictionIO engine template using Latent Dirichlet Allocation to learn a topic model from raw text + tags: [clustering] + type: Parallel + language: Scala + license: "Apache Licence 2.0" + status: alpha + pio_min_version: 0.9.4 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/EmergentOrder/template-scala-topic-model-LDA/issues";>Github issues</a>' + +- template: + name: KMeans-Clustering-Template + repo: "https://github.com/singsanj/KMeans-parallel-template"; + description: |- + forked from PredictionIO/template-scala-parallel-vanilla. It implements the KMeans Algorithm. Can be extended to mainstream implementation with minor changes. + tags: [clustering] + type: Parallel + language: Scala + license: "Apache Licence 2.0" + status: alpha + pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/singsanj/KMeans-parallel-template/issues";>Github issues</a>' + +- template: + name: Topic Labelling with Wikipedia + repo: "https://github.com/peoplehum/template-Labelling-LDA-Topics-with-wikipedia"; + description: |- + This template will label topics (e.g. topic generated through LDA topic modeling) with relevant category by referring to Wikipedia as a knowledge base. + tags: [clustering, nlp] + type: Parallel + language: Scala + license: "Apache Licence 2.0" + status: stable + pio_min_version: 0.10.0-incubating + apache_pio_convesion_required: "already compatible" + support_link: '<a href="https://github.com/peoplehum/template-Labelling-LDA-Topics-with-wikipedia/issues";>Github issues</a>' + +# Recommenders + - template: name: The Universal Recommender repo: "https://github.com/actionml/universal-recommender"; description: |- Use for: + <ul class=tab-list> + <li class=tab-list-element>Personalized recommendations—user-based</li> + <li class=tab-list-element>Similar items—item-based</li> + <li class=tab-list-element>Viewed this bought that—item-based cross-action</li> + <li class=tab-list-element>Popular Items and User-defined ranking</li> + <li class=tab-list-element>Item-set recommendations for complimentarty purchases or shopping carts—item-set-based</li> + <li class=tab-list-element>Hybrid collaborative filtering and content based recommendations—limited content-based</li> + <li class-tab-list-element>Business rules</li> + </ul> + + <p>The name "Universal" refers to the use of this template in virtually any case that calls for recommendations - ecommerce, news, videos, virtually anywhere user behavioral data is known. This recommender uses the new <a href="http://mahout.apache.org/users/algorithms/intro-cooccurrence-spark.html";>Cross-Occurrence (CCO) algorithm</a> to auto-correlate different user actions (clickstream data), profile data, contextual information (location, device), and some content types to make better recommendations. It also implements flexible filters and boosts for implementing business rules.</p> + tags: [recommender] + type: Parallel + language: Scala + license: "Apache Licence 2.0" + status: stable + pio_min_version: 0.10.0-incubating + apache_pio_convesion_required: "already compatible" + support_link: '<a href="https://groups.google.com/forum/#!forum/actionml-user";>The Universal Recommender user group</a>' - * Personalized recommendations—user-based - * Similar items—item-based - * Popular Items, User-defined ranking - * Complimentarty Purchases / Shopping Cart—item-set-based - * Hybrid collaborative filtering and content based recommendations for applying business rules - - The name refers to the use of this template in virtually any case that calls for recommendations - ecom, news, videos, virtually anywhere usage data is known. This recommender can auto-correlate different user actions (clickstream data), profile data, contextual information (location, device), and some content types to make better recommendations that follow business rules. +- template: + name: Recommendation + repo: "https://github.com/apache/incubator-predictionio-template-recommender"; + description: |- + An engine template is an almost-complete implementation of an engine. PredictionIO's Recommendation Engine Template has integrated Apache Spark MLlib's Collaborative Filtering algorithm by default. You can customize it easily to fit your specific needs. tags: [recommender] type: Parallel language: Scala license: "Apache Licence 2.0" status: stable pio_min_version: 0.10.0-incubating + apache_pio_convesion_required: "already compatible" + support_link: '<a href="http://predictionio.incubator.apache.org/support/";>Apache PredictionIO mailing lists</a>' - template: name: E-Commerce Recommendation @@ -24,16 +133,34 @@ description: |- This engine template provides personalized recommendation for e-commerce applications with the following features by default: - * Exclude out-of-stock items - * Provide recommendation to new users who sign up after the model is trained - * Recommend unseen items only (configurable) - * Recommend popular items if no information about the user is available (added in template version v0.4.0) + <ul class=tab-list> + <li class=tab-list-element>Exclude out-of-stock items</li> + <li class=tab-list-element>Provide recommendation to new users who sign up after the model is trained</li> + <li class=tab-list-element>Recommend unseen items only (configurable)</li> + <li class=tab-list-element>Recommend popular items if no information about the user is available (added in template version v0.4.0)</li> + </ul> tags: [recommender] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha - pio_min_version: 0.9.2 + pio_min_version: 0.10.0-incubating + apache_pio_convesion_required: "already compatible" + support_link: '<a href="http://predictionio.incubator.apache.org/support/";>Apache PredictionIO mailing lists</a>' + +- template: + name: Similar Product + repo: "https://github.com/apache/incubator-predictionio-template-similar-product"; + description: |- + This engine template recommends products that are "similar" to the input product(s). Similarity is not defined by user or item attributes but by users' previous actions. By default, it uses 'view' action such that product A and B are considered similar if most users who view A also view B. The template can be customized to support other action types such as buy, rate, like..etc + tags: [recommender] + type: Parallel + language: Scala + license: "Apache Licence 2.0" + status: stable + pio_min_version: 0.10.0-incubating + apache_pio_convesion_required: "already compatible" + support_link: '<a href="http://predictionio.incubator.apache.org/support/";>Apache PredictionIO mailing lists</a>' - template: name: E-Commerce Recommendation (Java) @@ -41,167 +168,187 @@ description: |- This engine template provides personalized recommendation for e-commerce applications with the following features by default: - * Exclude out-of-stock items - * Provide recommendation to new users who sign up after the model is trained - * Recommend unseen items only (configurable) - * Recommend popular items if no information about the user is available + <ul class=tab-list> + <li class=tab-list-element>Exclude out-of-stock items</li> + <li class=tab-list-element>Provide recommendation to new users who sign up after the model is trained</li> + <li class=tab-list-element>Recommend unseen items only (configurable)</li> + <li class=tab-list-element>Recommend popular items if no information about the user is available</li> + </ul> tags: [recommender] type: Parallel language: Java license: "Apache Licence 2.0" status: alpha pio_min_version: 0.9.3 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="http://predictionio.incubator.apache.org/support/";>Apache PredictionIO mailing lists</a>' - template: name: Product Ranking repo: "https://github.com/PredictionIO/template-scala-parallel-productranking"; description: |- This engine template sorts a list of products for a user based on his/her preference. This is ideal for personalizing the display order of product page, catalog, or menu items if you have large number of options. It creates engagement and early conversion by placing products that a user prefers on the top. - tags: [unsupervised] - type: Parallel - language: Scala - license: "Apache Licence 2.0" - status: stable - pio_min_version: 0.9.2 - -- template: - name: Similar Product - repo: "https://github.com/apache/incubator-predictionio-template-similar-product"; - description: |- - This engine template recommends products that are "similar" to the input product(s). Similarity is not defined by user or item attributes but by users' previous actions. By default, it uses 'view' action such that product A and B are considered similar if most users who view A also view B. The template can be customized to support other action types such as buy, rate, like..etc tags: [recommender] type: Parallel language: Scala license: "Apache Licence 2.0" status: stable pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" - template: name: Complementary Purchase repo: "https://github.com/PredictionIO/template-scala-parallel-complementarypurchase"; description: |- This engine template recommends the complementary items which most user frequently buy at the same time with one or more items in the query. - tags: [unsupervised] + tags: [recommender] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" - template: - name: Lead Scoring - repo: "https://github.com/PredictionIO/template-scala-parallel-leadscoring"; + name: Music Recommendations + repo: "https://github.com/vaibhavist/template-scala-parallel-recommendation"; description: |- - This engine template predicts the probability of an user will convert (conversion event by user) in the current session. - tags: [classification] + This is very similar to music recommendations template. It is integrated with all the events a music application can have such as song played, liked, downloaded, purchased, etc. + tags: [recommender] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/vaibhavist/template-scala-parallel-recommendation/issues";>Github issues</a>' - template: - name: Recommendation - repo: "https://github.com/apache/incubator-predictionio-template-recommender"; + name: Viewed This Bought That + repo: "https://github.com/vngrs/template-scala-parallel-viewedthenbought"; description: |- - An engine template is an almost-complete implementation of an engine. PredictionIO's Recommendation Engine Template has integrated Apache Spark MLlib's Collaborative Filtering algorithm by default. You can customize it easily to fit your specific needs. - tags: [unsupervised] + This Engine uses co-occurence algorithm to match viewed items to bought items. Using this engine you may predict which item the user will buy, given the item(s) browsed. + tags: [recommender] type: Parallel language: Scala license: "Apache Licence 2.0" status: stable pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/vngrs/template-scala-parallel-viewedthenbought/issues";>Github issues</a>' - template: - name: Classification - repo: "https://github.com/apache/incubator-predictionio-template-attribute-based-classifier"; + name: Frequent Pattern Mining + repo: "https://github.com/goliasz/pio-template-fpm"; description: |- - An engine template is an almost-complete implementation of an engine. PredictionIO's Classification Engine Template has integrated Apache Spark MLlib's Naive Bayes algorithm by default. - tags: [classification] + Template uses FP Growth algorithm allowing to mine for frequent patterns. Template returns subsequent items together with confidence score. Sometimes used as a shopping cart recommender but has other uses. + tags: [recommender] type: Parallel language: Scala license: "Apache Licence 2.0" - status: stable - pio_min_version: 0.9.2 + status: alpha + pio_min_version: 0.9.5 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/goliasz/pio-template-fpm/issues";>Github issues</a>' - template: - name: Content Based SVD Item Similarity Engine - repo: "https://github.com/alexice/template-scala-parallel-svd-item-similarity"; + name: Similar Product with Rating + repo: "https://github.com/ramaboo/template-scala-parallel-similarproduct-with-rating"; description: |- - Template to calculate similarity between items based on their attributes. Attributes can be either numeric or categorical in the last case it will be encoded using one-hot encoder. Algorithm uses SVD in order to reduce data dimensionality. Cosine similarity is now implemented but can be easily extended to other similarity measures. - tags: [unsupervised] + Similar product template with rating support! Used for the MovieLens Demo. + tags: [recommender, similarity] type: Parallel language: Scala license: "Apache Licence 2.0" - status: alpha - pio_min_version: 0.9.2 + status: beta + pio_min_version: 0.9.0 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/ramaboo/template-scala-parallel-similarproduct-with-rating/issues";>Github issues</a>' - template: - name: Survival Regression - repo: "https://github.com/goliasz/pio-template-sr"; + name: Frequent Pattern Mining + repo: "https://github.com/goliasz/pio-template-fpm"; description: |- - Survival regression template is based on brand new Spark 1.6 AFT (accelerated failure time) survival analysis algorithm. There are interesting applications of survival analysis like: - - * Business Planning : Profiling customers who has a higher survival rate and make strategy accordingly. - * Lifetime Value Prediction : Engage with customers according to their lifetime value - * Active customers : Predict when the customer will be active for the next time and take interventions accordingly. * Campaign evaluation : Monitor effect of campaign on the survival rate of customers. - - Source: http://www.analyticsvidhya.com/blog/2014/04/survival-analysis-model-you/ - tags: [regression] + Template uses FP Growth algorithm allowing to mine for frequent patterns. Template returns subsequent items together with confidence score. + tags: [recommender, other] type: Parallel language: Scala license: "Apache Licence 2.0" - status: beta + status: alpha pio_min_version: 0.9.5 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/goliasz/pio-template-fpm/issues";>Github issues</a>' + +# classification - template: - name: Churn Prediction - H2O Sparkling Water - repo: "https://github.com/andrewwuan/PredictionIO-Churn-Prediction-H2O-Sparkling-Water"; + name: Classification + repo: "https://github.com/apache/incubator-predictionio-template-attribute-based-classifier"; description: |- - This is an engine template with Sparkling Water integration. The goal is to use Deep Learning algorithm to predict the churn rate for a phone carrier's customers. + An engine template is an almost-complete implementation of an engine. PredictionIO's Classification Engine Template has integrated Apache Spark MLlib's Naive Bayes algorithm by default. tags: [classification] type: Parallel language: Scala license: "Apache Licence 2.0" - status: alpha + status: stable pio_min_version: 0.9.2 + apache_pio_convesion_required: "already compatible" + support_link: '<a href="http://predictionio.incubator.apache.org/support/";>Apache PredictionIO mailing lists</a>' - template: - name: Classification Deeplearning4j - repo: "https://github.com/detrevid/predictionio-template-classification-dl4j"; + name: Lead Scoring + repo: "https://github.com/PredictionIO/template-scala-parallel-leadscoring"; description: |- - A classification engine template that uses Deeplearning4j library. + This engine template predicts the probability of an user will convert (conversion event by user) in the current session. tags: [classification] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" - template: - name: Sparkling Water-Deep Learning Energy Forecasting - repo: "https://github.com/BensonQiu/predictionio-template-recommendation-sparklingwater"; + name: Text Classification + repo: "https://github.com/apache/incubator-predictionio-template-text-classifier"; description: |- - This Engine Template demonstrates an energy forecasting engine. It integrates Deep Learning from the Sparkling Water library to perform energy analysis. We can query the circuit and time, and return predicted energy usage. - tags: [regression] + Use this engine for general text classification purposes. Uses OpenNLP library for text vectorization, includes t.f.-i.d.f.-based feature transformation and reduction, and uses Spark MLLib's Multinomial Naive Bayes implementation for classification. + tags: [classification, nlp] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/apache/incubator-predictionio-template-text-classifier/issues";>Github issues</a>' +- template: + name: Churn Prediction - H2O Sparkling Water + repo: "https://github.com/andrewwuan/PredictionIO-Churn-Prediction-H2O-Sparkling-Water"; + description: |- + This is an engine template with Sparkling Water integration. The goal is to use Deep Learning algorithm to predict the churn rate for a phone carrier's customers. + tags: [classification] + type: Parallel + language: Scala + license: "Apache Licence 2.0" + status: alpha + pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/andrewwuan/PredictionIO-Churn-Prediction-H2O-Sparkling-Water/issues";>Github issues</a>' - template: - name: OpenNLP Sentiment Analysis Template - repo: "https://github.com/vshwnth2/OpenNLP-SentimentAnalysis-Template"; + name: Classification Deeplearning4j + repo: "https://github.com/detrevid/predictionio-template-classification-dl4j"; description: |- - Given a sentence, this engine will return a score between 0 and 4. This is the sentiment of the sentence. The lower the number the more negative the sentence is. It uses the OpenNLP library. - tags: [nlp] + A classification engine template that uses Deeplearning4j library. + tags: [classification] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha - pio_min_version: "-" + pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/detrevid/predictionio-template-classification-dl4j/issues";>Github issues</a>' - template: name: Probabilistic Classifier (Logistic Regression w/ LBFGS) @@ -214,18 +361,22 @@ license: "MIT License" status: alpha pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/EmergentOrder/template-scala-probabilistic-classifier-batch-lbfgs/issues";>Github issues</a>' - template: name: Document Classification with OpenNLP repo: "https://github.com/chrischris292/template-classification-opennlp"; description: |- Document Classification template with OpenNLP GISModel. - tags: [nlp] + tags: [classification] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha pio_min_version: 0.9.0 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/chrischris292/template-classification-opennlp/issues";>Github issues</a>' - template: name: Circuit End Use Classification @@ -238,150 +389,144 @@ license: "Apache Licence 2.0" status: alpha pio_min_version: 0.9.1 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/harry5z/template-circuit-classification-sparkling-water/issues";>Github issues</a>' - template: - name: Viewed This Bought That - repo: "https://github.com/vngrs/template-scala-parallel-viewedthenbought"; - description: |- - This Engine uses co-occurence algorithm to match viewed items to bought items. Using this engine you may predict which item the user will buy, given the item(s) browsed. - tags: [unsupervised] - type: Parallel - language: Scala - license: "Apache Licence 2.0" - status: stable - pio_min_version: 0.9.2 - -- template: - name: Music Recommendations - repo: "https://github.com/vaibhavist/template-scala-parallel-recommendation"; + name: GBRT_Classification + repo: "https://github.com/ailurus1991/GBRT_Template_PredictionIO"; description: |- - This is very similar to music recommendations template. It is integrated with all the events a music application can have such as song played, liked, downloaded, purchased, etc. - tags: [unsupervised] + The Gradient-Boosted Regression Trees(GBRT) for classification. + tags: [classification] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/ailurus1991/GBRT_Template_PredictionIO/issues";>Github issues</a>' - template: - name: template-decision-tree-feature-importance - repo: "https://github.com/anthill/template-decision-tree-feature-importance"; + name: MLlib-Decision-Trees-Template + repo: "https://github.com/mohanaprasad1994/PredictionIO-MLlib-Decision-Trees-Template"; description: |- - This template shows how to use spark' decision tree. It enables : - both categorical and continuous features - feature importance calculation - tree output in json - reading training data from a csv file - tags: [unsupervised] + An engine template is an almost-complete implementation of an engine. This is a classification engine template which has integrated Apache Spark MLlib's Decision tree algorithm by default. + tags: [classification] type: Parallel language: Scala license: "Apache Licence 2.0" - status: stable + status: alpha pio_min_version: 0.9.0 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/mohanaprasad1994/PredictionIO-MLlib-Decision-Trees-Template/issues";>Github issues</a>' - template: - name: Electric Load Forecasting - repo: "https://github.com/detrevid/predictionio-load-forecasting"; + name: Classification with MultiLayerNetwork + repo: "https://github.com/jimmyywu/predictionio-template-classification-dl4j-multilayer-network"; description: |- - This is a PredictionIO engine for electric load forecasting. The engine is using linear regression with stochastic gradient descent from Spark MLlib. - tags: [regression] + This engine template integrates the MultiLayerNetwork implementation from the Deeplearning4j library into PredictionIO. In this template, we use PredictionIO to classify the widely-known IRIS flower dataset by constructing a deep-belief net. + tags: [classification] type: Parallel language: Scala license: "Apache Licence 2.0" - status: stable - pio_min_version: 0.9.2 + status: alpha + pio_min_version: 0.9.0 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/jimmyywu/predictionio-template-classification-dl4j-multilayer-network/issues";>Github issues</a>' - template: - name: Sentiment analysis - repo: "https://github.com/pawel-n/template-scala-cml-sentiment"; + name: Deeplearning4j RNTN + repo: "https://github.com/ts335793/template-scala-parallel-dl4j-rntn"; description: |- - This template implements various algorithms for sentiment analysis, most based on recursive neural networks (RNN) and recursive neural tensor networks (RNTN)[1]. It uses an experimental library called Composable Machine Learning (CML) and the Stanford Parser. The example data set is the Stanford Sentiment Treebank. - tags: [nlp] + Recursive Neural Tensor Network algorithm is supervised learning algorithm used to predict sentiment of sentences. This template is based on deeplearning4j RNTN example: https://github.com/SkymindIO/deeplearning4j-nlp-examples/tree/master/src/main/java/org/deeplearning4j/rottentomatoes/rntn. It's goal is to show how to integrate deeplearning4j library with PredictionIO. + tags: [classification, nlp] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/ts335793/template-scala-parallel-dl4j-rntn/issues";>Github issues</a>' - template: - name: GBRT_Classification - repo: "https://github.com/ailurus1991/GBRT_Template_PredictionIO"; + name: classifier-kafka-streaming-template + repo: "https://github.com/singsanj/classifier-kafka-streaming-template"; description: |- - The Gradient-Boosted Regression Trees(GBRT) for classification. + The template will provide a simple integration of DASE with kafka using spark streaming capabilites in order to play around with real time notification, messages .. tags: [classification] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha - pio_min_version: 0.9.2 + pio_min_version: "-" + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/singsanj/classifier-kafka-streaming-template/issues";>Github issues</a>' - template: - name: MLlibKMeansClustering - repo: "https://github.com/sahiliitm/predictionio-MLlibKMeansClusteringTemplate"; + name: Sentiment Analysis - Bag of Words Model + repo: "https://github.com/peoplehum/BagOfWords_SentimentAnalysis_Template"; description: |- - This is a template which demonstrates the use of K-Means clustering algorithm which can be deployed on a spark-cluster using prediction.io. - tags: [unsupervised] + This sentiment analysis template uses a bag of words model. Given text, the engine will return sentiment as 1.0 (positive) or 0.0 (negative) along with scores indicating how +ve or -ve it is. + tags: [classification, nlp] type: Parallel language: Scala license: "Apache Licence 2.0" - status: alpha - pio_min_version: '-' + status: stable + pio_min_version: 0.10.0-incubating + apache_pio_convesion_required: "already compatible" + support_link: '<a href="https://github.com/peoplehum/BagOfWords_SentimentAnalysis_Template/issues";>Github issues</a>' + +# Regression - template: - name: Word2Vec - repo: "https://github.com/pawel-n/template-scala-parallel-word2vec"; + name: Survival Regression + repo: "https://github.com/goliasz/pio-template-sr"; description: |- - This template integrates the Word2Vec implementation from deeplearning4j with PredictionIO. The Word2Vec algorithm takes a corpus of text and computes a vector representation for each word. These representations can be subsequently used in many natural language processing applications. - tags: [nlp] + Survival regression template is based on brand new Spark 1.6 AFT (accelerated failure time) survival analysis algorithm. There are interesting applications of survival analysis like: + + <ul class=tab-list> + <li class=tab-list-element>Business Planning : Profiling customers who has a higher survival rate and make strategy accordingly.</li> + <li class=tab-list-element>Lifetime Value Prediction : Engage with customers according to their lifetime value</li> + <li class=tab-list-element>Active customers : Predict when the customer will be active for the next time and take interventions accordingly. * Campaign evaluation : Monitor effect of campaign on the survival rate of customers.</li> + </ul> + + Source: http://www.analyticsvidhya.com/blog/2014/04/survival-analysis-model-you/ + tags: [regression] type: Parallel language: Scala license: "Apache Licence 2.0" - status: alpha - pio_min_version: 0.9.0 + status: beta + pio_min_version: 0.9.5 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="http://www.analyticsvidhya.com/blog/2014/04/survival-analysis-model-you/";>Blog post</a>' - template: - name: MLlib-Decision-Trees-Template - repo: "https://github.com/mohanaprasad1994/PredictionIO-MLlib-Decision-Trees-Template"; + name: Sparkling Water-Deep Learning Energy Forecasting + repo: "https://github.com/BensonQiu/predictionio-template-recommendation-sparklingwater"; description: |- - An engine template is an almost-complete implementation of an engine. This is a classification engine template which has integrated Apache Spark MLlib's Decision tree algorithm by default. - tags: [classification] + This Engine Template demonstrates an energy forecasting engine. It integrates Deep Learning from the Sparkling Water library to perform energy analysis. We can query the circuit and time, and return predicted energy usage. + tags: [regression] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha - pio_min_version: 0.9.0 + pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/BensonQiu/predictionio-template-recommendation-sparklingwater/issues";>Github issues</a>' - template: - name: Spark Deeplearning4j Word2Vec - repo: "https://github.com/ts335793/template-scala-spark-dl4j-word2vec"; + name: Electric Load Forecasting + repo: "https://github.com/detrevid/predictionio-load-forecasting"; description: |- - This template shows how to integrate Deeplearnign4j spark api with PredictionIO on example of app which uses Word2Vec algorithm to predict nearest words. - tags: [nlp] + This is a PredictionIO engine for electric load forecasting. The engine is using linear regression with stochastic gradient descent from Spark MLlib. + tags: [regression] type: Parallel language: Scala license: "Apache Licence 2.0" status: stable pio_min_version: 0.9.2 - -- template: - name: Sentiment Analysis Template - repo: "https://github.com/whhone/template-sentiment-analysis"; - description: |- - Given a sentence, return a score between 0 and 4, indicating the sentence's sentiment. 0 being very negative, 4 being very positive, 2 being neutral. The engine uses the stanford CoreNLP library and the Scala binding `gangeli/CoreNLP-Scala` for parsing. - tags: [nlp] - type: Parallel - language: Scala - license: None - status: stable - pio_min_version: 0.9.0 - -- template: - name: Classification with MultiLayerNetwork - repo: "https://github.com/jimmyywu/predictionio-template-classification-dl4j-multilayer-network"; - description: |- - This engine template integrates the MultiLayerNetwork implementation from the Deeplearning4j library into PredictionIO. In this template, we use PredictionIO to classify the widely-known IRIS flower dataset by constructing a deep-belief net. - tags: [classification] - type: Parallel - language: Scala - license: "Apache Licence 2.0" - status: alpha - pio_min_version: 0.9.0 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/detrevid/predictionio-load-forecasting/issues";>Github issues</a>' - template: name: MLLib-LinearRegression @@ -394,114 +539,124 @@ license: "Apache Licence 2.0" status: alpha pio_min_version: 0.9.1 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/RAditi/PredictionIO-MLLib-LinReg-Template/issues";>Github issues</a>' -- template: - name: Text Classification - repo: "https://github.com/apache/incubator-predictionio-template-text-classifier"; - description: |- - Use this engine for general text classification purposes. Uses OpenNLP library for text vectorization, includes t.f.-i.d.f.-based feature transformation and reduction, and uses Spark MLLib's Multinomial Naive Bayes implementation for classification. - tags: [nlp] - type: Parallel - language: Scala - license: "Apache Licence 2.0" - status: alpha - pio_min_version: 0.9.2 +# NLP - template: - name: Deeplearning4j RNTN - repo: "https://github.com/ts335793/template-scala-parallel-dl4j-rntn"; + name: OpenNLP Sentiment Analysis Template + repo: "https://github.com/vshwnth2/OpenNLP-SentimentAnalysis-Template"; description: |- - Recursive Neural Tensor Network algorithm is supervised learning algorithm used to predict sentiment of sentences. This template is based on deeplearning4j RNTN example: https://github.com/SkymindIO/deeplearning4j-nlp-examples/tree/master/src/main/java/org/deeplearning4j/rottentomatoes/rntn. It's goal is to show how to integrate deeplearning4j library with PredictionIO. + Given a sentence, this engine will return a score between 0 and 4. This is the sentiment of the sentence. The lower the number the more negative the sentence is. It uses the OpenNLP library. tags: [nlp] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha - pio_min_version: 0.9.2 + pio_min_version: "-" + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/vshwnth2/OpenNLP-SentimentAnalysis-Template/issues";>Github issues</a>' - template: - name: Recursive Neural Networks (Sentiment Analysis) - repo: "https://github.com/ts335793/template-scala-rnn"; + name: Sentiment analysis + repo: "https://github.com/pawel-n/template-scala-cml-sentiment"; description: |- - Predicting sentiment of phrases with use of Recursive Neural Network algorithm and OpenNLP parser. + This template implements various algorithms for sentiment analysis, most based on recursive neural networks (RNN) and recursive neural tensor networks (RNTN)[1]. It uses an experimental library called Composable Machine Learning (CML) and the Stanford Parser. The example data set is the Stanford Sentiment Treebank. tags: [nlp] type: Parallel language: Scala license: "Apache Licence 2.0" - status: stable + status: alpha pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/pawel-n/template-scala-cml-sentiment/issues";>Github issues</a>' - template: - name: CoreNLP Text Classification - repo: "https://github.com/Ling-Ling/CoreNLP-Text-Classification"; + name: Word2Vec + repo: "https://github.com/pawel-n/template-scala-parallel-word2vec"; description: |- - This engine uses CoreNLP to do text analysis in order to classify the category a strings of text falls under. + This template integrates the Word2Vec implementation from deeplearning4j with PredictionIO. The Word2Vec algorithm takes a corpus of text and computes a vector representation for each word. These representations can be subsequently used in many natural language processing applications. tags: [nlp] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha - pio_min_version: "-" + pio_min_version: 0.9.0 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/pawel-n/template-scala-parallel-word2vec/issues";>Github issues</a>' - template: - name: Topc Model (LDA) - repo: "https://github.com/EmergentOrder/template-scala-topic-model-LDA"; + name: Spark Deeplearning4j Word2Vec + repo: "https://github.com/ts335793/template-scala-spark-dl4j-word2vec"; description: |- - A PredictionIO engine template using Latent Dirichlet Allocation to learn a topic model from raw text + This template shows how to integrate Deeplearnign4j spark api with PredictionIO on example of app which uses Word2Vec algorithm to predict nearest words. tags: [nlp] type: Parallel language: Scala license: "Apache Licence 2.0" - status: alpha - pio_min_version: 0.9.4 + status: stable + pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/ts335793/template-scala-spark-dl4j-word2vec/issues";>Github issues</a>' - template: - name: Cstablo-template-text-similarityelassification - repo: "https://github.com/goliasz/pio-template-text-similarity"; + name: Sentiment Analysis Template + repo: "https://github.com/whhone/template-sentiment-analysis"; description: |- - Text similarity engine based on Word2Vec algorithm. Builds vectors of full documents in training phase. Finds similar documents in query phase. + Given a sentence, return a score between 0 and 4, indicating the sentence's sentiment. 0 being very negative, 4 being very positive, 2 being neutral. The engine uses the stanford CoreNLP library and the Scala binding `gangeli/CoreNLP-Scala` for parsing. tags: [nlp] type: Parallel language: Scala - license: "Apache Licence 2.0" - status: alpha - pio_min_version: 0.9.5 + license: None + status: stable + pio_min_version: 0.9.0 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/whhone/template-sentiment-analysis/issues";>Github issues</a>' - template: - name: KMeans-Clustering-Template - repo: "https://github.com/singsanj/KMeans-parallel-template"; + name: Recursive Neural Networks (Sentiment Analysis) + repo: "https://github.com/ts335793/template-scala-rnn"; description: |- - forked from PredictionIO/template-scala-parallel-vanilla. It implements the KMeans Algorithm. Can be extended to mainstream implementation with minor changes. - tags: [unsupervised] + Predicting sentiment of phrases with use of Recursive Neural Network algorithm and OpenNLP parser. + tags: [nlp] type: Parallel language: Scala license: "Apache Licence 2.0" - status: alpha + status: stable pio_min_version: 0.9.2 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/ts335793/template-scala-rnn/issues";>Github issues</a>' - template: - name: classifier-kafka-streaming-template - repo: "https://github.com/singsanj/classifier-kafka-streaming-template"; + name: CoreNLP Text Classification + repo: "https://github.com/Ling-Ling/CoreNLP-Text-Classification"; description: |- - The template will provide a simple integration of DASE with kafka using spark streaming capabilites in order to play around with real time notification, messages .. - tags: [classification] + This engine uses CoreNLP to do text analysis in order to classify the category a strings of text falls under. + tags: [nlp] type: Parallel language: Scala license: "Apache Licence 2.0" status: alpha pio_min_version: "-" + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/Ling-Ling/CoreNLP-Text-Classification/issues";>Github issues</a>' + +# other - template: - name: Frequent Pattern Mining - repo: "https://github.com/goliasz/pio-template-fpm"; + name: template-decision-tree-feature-importance + repo: "https://github.com/anthill/template-decision-tree-feature-importance"; description: |- - Template uses FP Growth algorithm allowing to mine for frequent patterns. Template returns subsequent items together with confidence score. - tags: [unsupervised] + This template shows how to use spark' decision tree. It enables : - both categorical and continuous features - feature importance calculation - tree output in json - reading training data from a csv file + tags: [other] type: Parallel language: Scala license: "Apache Licence 2.0" - status: alpha - pio_min_version: 0.9.5 + status: stable + pio_min_version: 0.9.0 + apache_pio_convesion_required: "requires conversion" + support_link: '<a href="https://github.com/anthill/template-decision-tree-feature-importance/issues";>Github issues</a>' - template: name: Skeleton @@ -514,39 +669,6 @@ license: "Apache Licence 2.0" status: stable pio_min_version: 0.9.2 + apache_pio_convesion_required: "already compatible" + support_link: '<a href="http://predictionio.incubator.apache.org/support/";>Apache PredictionIO mailing lists</a>' -- template: - name: Similar Product with Rating - repo: "https://github.com/ramaboo/template-scala-parallel-similarproduct-with-rating"; - description: |- - Similar product template with rating support! Used for the MovieLens Demo. - tags: [unsupervised] - type: Parallel - language: Scala - license: "Apache Licence 2.0" - status: beta - pio_min_version: 0.9.0 - -- template: - name: Sentiment Analysis - Bag of Words Model - repo: "https://github.com/peoplehum/BagOfWords_SentimentAnalysis_Template"; - description: |- - This sentiment analysis template uses a bag of words model. Given text, the engine will return sentiment as 1.0 (positive) or 0.0 (negative) along with scores indicating how +ve or -ve it is. - tags: [nlp] - type: Parallel - language: Scala - license: "Apache Licence 2.0" - status: stable - pio_min_version: 0.10.0-incubating - -- template: - name: Topic Labelling with Wikipedia - repo: "https://github.com/peoplehum/template-Labelling-LDA-Topics-with-wikipedia"; - description: |- - This template will label topics (e.g. topic generated through LDA topic modeling) with relevant category by referring to Wikipedia as a knowledge base. - tags: [nlp] - type: Parallel - language: Scala - license: "Apache Licence 2.0" - status: stable - pio_min_version: 0.10.0-incubating http://git-wip-us.apache.org/repos/asf/incubator-predictionio/blob/3d1b777d/docs/manual/source/stylesheets/partials/_tabs.css.scss ---------------------------------------------------------------------- diff --git a/docs/manual/source/stylesheets/partials/_tabs.css.scss b/docs/manual/source/stylesheets/partials/_tabs.css.scss index 63da5df..eff9b73 100644 --- a/docs/manual/source/stylesheets/partials/_tabs.css.scss +++ b/docs/manual/source/stylesheets/partials/_tabs.css.scss @@ -38,4 +38,15 @@ } } } + ul.tab-list { + list-style-type: disc; + list-style-position: inside; + margin-top: 0px; + margin-bottom: 15px; + } + li.tab-list-element { + display: list-item; + float: none; + width: 100% + } } \ No newline at end of file
