lhcb-ntuple-wizard-test 1.0.6 → 1.0.8

package/dist/components/semform.js

@@ -0,0 +1,182 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _Form = _interopRequireDefault(require("react-bootstrap/Form"));
+var _Button = _interopRequireDefault(require("react-bootstrap/Button"));
+var _semantic = require("./semantic");
+var _react = require("react");
+var _MetadataContext = _interopRequireDefault(require("../contexts/MetadataContext"));
+var _propTypes = _interopRequireDefault(require("prop-types"));
+var _DeleteButton = _interopRequireDefault(require("./DeleteButton"));
+var _jsxRuntime = require("react/jsx-runtime");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/*****************************************************************************\
+* (c) Copyright 2024 CERN for the benefit of the LHCb Collaboration           *
+*                                                                             *
+* This software is distributed under the terms of the GNU General Public      *
+* Licence version 3 (GPL Version 3), copied verbatim in the file "COPYING".   *
+*                                                                             *
+* In applying this licence, CERN does not waive the privileges and immunities *
+* granted to it by virtue of its status as an Intergovernmental Organization  *
+* or submit itself to any jurisdiction.                                       *
+\*****************************************************************************/
+
+function getmetafromcontext() {
+  const context = (0, _react.useContext)(_MetadataContext.default);
+  return context;
+}
+
+/**
+ * Make the output of the search more readable
+ * @param {Array} data
+ * @returns
+ */
+function FormatOutput(_ref) {
+  let {
+    data
+  } = _ref;
+  let topchoice_ttool = [data.ttool[0]];
+  let data_ttool = data.ttool.slice(1);
+  let topchoice_loki = [data.loki[0]];
+  let data_loki = data.loki.slice(1);
+  return /*#__PURE__*/(0, _jsxRuntime.jsxs)(_jsxRuntime.Fragment, {
+    children: [/*#__PURE__*/(0, _jsxRuntime.jsxs)("div", {
+      children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("h2", {
+        children: "Best match (TupleTools):"
+      }), /*#__PURE__*/(0, _jsxRuntime.jsx)("ul", {
+        children: topchoice_ttool.map((item, index) => /*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+          children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+            children: "Matched TupleTool:"
+          }), " ", item[2] === "LoKi_functors" ? "LoKi__Hybrid__TupleTool" : item[2], /*#__PURE__*/(0, _jsxRuntime.jsxs)("ul", {
+            children: [/*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+              children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+                children: "Variable name:"
+              }), " ", item[1]]
+            }), /*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+              children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+                children: "Definition:"
+              }), " ", item[0]]
+            })]
+          })]
+        }, index))
+      }), /*#__PURE__*/(0, _jsxRuntime.jsx)("h3", {
+        children: "Other matches (TupleTools):"
+      }), /*#__PURE__*/(0, _jsxRuntime.jsx)("ul", {
+        children: data_ttool.map((item, index) => /*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+          children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+            children: "Matched TupleTool:"
+          }), " ", item[2] === "LoKi_functors" ? "LoKi__Hybrid__TupleTool" : item[2], /*#__PURE__*/(0, _jsxRuntime.jsxs)("ul", {
+            children: [/*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+              children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+                children: "Variable name:"
+              }), " ", item[1]]
+            }), /*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+              children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+                children: "Definition:"
+              }), " ", item[0]]
+            })]
+          })]
+        }, index))
+      })]
+    }), /*#__PURE__*/(0, _jsxRuntime.jsxs)("div", {
+      children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("h2", {
+        children: "Best match (LoKi functors):"
+      }), /*#__PURE__*/(0, _jsxRuntime.jsx)("ul", {
+        children: topchoice_loki.map((item, index) => /*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+          children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+            children: "Matched TupleTool:"
+          }), " ", item[2] === "LoKi_functors" ? "LoKi__Hybrid__TupleTool" : item[2], /*#__PURE__*/(0, _jsxRuntime.jsxs)("ul", {
+            children: [/*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+              children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+                children: "Variable name:"
+              }), " ", item[1]]
+            }), /*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+              children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+                children: "Definition:"
+              }), " ", item[0]]
+            })]
+          })]
+        }, index))
+      }), /*#__PURE__*/(0, _jsxRuntime.jsx)("h3", {
+        children: "Other matches (LoKi functors):"
+      }), /*#__PURE__*/(0, _jsxRuntime.jsx)("ul", {
+        children: data_loki.map((item, index) => /*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+          children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+            children: "Matched TupleTool:"
+          }), " ", item[2] === "LoKi_functors" ? "LoKi__Hybrid__TupleTool" : item[2], /*#__PURE__*/(0, _jsxRuntime.jsxs)("ul", {
+            children: [/*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+              children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+                children: "Variable name:"
+              }), " ", item[1]]
+            }), /*#__PURE__*/(0, _jsxRuntime.jsxs)("li", {
+              children: [/*#__PURE__*/(0, _jsxRuntime.jsx)("strong", {
+                children: "Definition:"
+              }), " ", item[0]]
+            })]
+          })]
+        }, index))
+      })]
+    })]
+  });
+}
+FormatOutput.propTypes = {
+  data: _propTypes.default.objectOf(_propTypes.default.array).isRequired
+};
+const SearchTTool = () => {
+  const [inputData, setInputData] = (0, _react.useState)({
+    query: ""
+  });
+  const [responseData, setResponseData] = (0, _react.useState)(null);
+  let metadata = getmetafromcontext();
+  // Load the model and embed the corpus when the component mounts
+  (0, _react.useMemo)(async () => {
+    await (0, _semantic.loadModel)("TaylorAI/gte-tiny");
+    await (0, _semantic.embedCorpus)(metadata);
+  }, []);
+  const handleChange = event => {
+    setInputData({
+      ...inputData,
+      query: event.target.value
+    });
+  };
+  const handleSubmit = async event => {
+    event.preventDefault();
+    // clean input field
+    setInputData({
+      query: ""
+    });
+    let response = await (0, _semantic.getSimilarity)(inputData.query);
+    setResponseData(response);
+  };
+  const handleDelete = () => {
+    setResponseData(null);
+  };
+  return /*#__PURE__*/(0, _jsxRuntime.jsxs)(_Form.default, {
+    onSubmit: handleSubmit,
+    children: [/*#__PURE__*/(0, _jsxRuntime.jsxs)(_Form.default.Group, {
+      controlId: "formQuery",
+      children: [/*#__PURE__*/(0, _jsxRuntime.jsx)(_Form.default.Label, {
+        children: "Search for TupleTools"
+      }), /*#__PURE__*/(0, _jsxRuntime.jsx)(_Form.default.Control, {
+        type: "text",
+        value: inputData.query,
+        onChange: handleChange
+      })]
+    }), /*#__PURE__*/(0, _jsxRuntime.jsx)(_Button.default, {
+      variant: "primary",
+      type: "submit",
+      children: "Submit"
+    }), /*#__PURE__*/(0, _jsxRuntime.jsx)(_DeleteButton.default, {
+      disabled: !responseData,
+      action: handleDelete
+    }), responseData && /*#__PURE__*/(0, _jsxRuntime.jsx)("div", {
+      children: /*#__PURE__*/(0, _jsxRuntime.jsx)(FormatOutput, {
+        data: responseData
+      })
+    })]
+  });
+};
+var _default = exports.default = SearchTTool;

package/dist/components/worker.js

@@ -0,0 +1,196 @@
+"use strict";
+
+var _transformers = require("@xenova/transformers");
+/*****************************************************************************\
+* (c) Copyright 2024 CERN for the benefit of the LHCb Collaboration           *
+*                                                                             *
+* This software is distributed under the terms of the GNU General Public      *
+* Licence version 3 (GPL Version 3), copied verbatim in the file "COPYING".   *
+*                                                                             *
+* In applying this licence, CERN does not waive the privileges and immunities *
+* granted to it by virtue of its status as an Intergovernmental Organization  *
+* or submit itself to any jurisdiction.                                       *
+\*****************************************************************************/
+
+// This is so that we will download the models from huggingface.co
+_transformers.env.allowLocalModels = false;
+_transformers.env.useBrowserCache = false;
+// store the embeddings in a dict
+let query_embedding;
+/**
+ * @type {Object.<string, Array>}
+ */
+let embedding_dict = {};
+/**
+ * @type {pipeline}
+ */
+let embedder;
+
+// these will hold the information to tie variable explanations to TupleTools
+let dataKeys;
+let paths;
+/**
+ * @type {Array}
+ * */
+let vars;
+/**
+ * This function calculates the embedding and stores it in a dict.
+ * If the text is already embedded, it will return the embedding from the dict.
+ * @param {string} text
+ * @param {bool} embedNew
+ * @returns embeddingVector
+ */
+async function embed(text) {
+  let embedNew = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : true;
+  if (text in embedding_dict) {
+    return embedding_dict[text];
+  }
+  const e0 = await embedder(text, {
+    pooling: "mean",
+    normalize: true
+  });
+  if (embedNew) {
+    embedding_dict[text] = e0.data;
+  }
+  return e0.data;
+}
+/**
+ * This function calculates the cosine similarity between two embeddings.
+ * @param {Array} corpus_embedding
+ * @param {Array} query_embedding
+ * @returns cosine similarity
+ * */
+function calcCosSim(corpus_embedding, query_embedding) {
+  let dotProduct = 0;
+  let queryMag = 0;
+  let embMag = 0;
+  let loop_length = query_embedding.length;
+  // because the embeddings might have different dimensions
+  if (query_embedding.length > corpus_embedding.length) {
+    loop_length = corpus_embedding.length;
+  }
+  for (let i = 0; i < loop_length; i++) {
+    dotProduct += query_embedding[i] * corpus_embedding[i];
+    queryMag += query_embedding[i] * query_embedding[i];
+    embMag += corpus_embedding[i] * corpus_embedding[i];
+  }
+  const sim = dotProduct / (Math.sqrt(queryMag) * Math.sqrt(embMag));
+  return sim;
+}
+/**This is a helper function to read the nested json file containing the documentation.
+ * @returns [vars, paths, dataKeys]
+ */
+
+function readJsonFile(data) {
+  // go through nested object
+  vars = [];
+  paths = [];
+  const iterateObject = function (obj) {
+    let path = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : "";
+    Object.keys(obj).forEach(key => {
+      const currentPath = path ? `${path}.${key}` : key;
+      if (obj[key] instanceof Object) {
+        iterateObject(obj[key], currentPath);
+      } else {
+        vars.push(obj[key]);
+        paths.push(currentPath);
+      }
+    });
+  };
+
+  // go through data and put it into an array
+  const dataArray = Object.values(data);
+  dataKeys = Object.keys(data);
+  iterateObject(dataArray);
+  return [vars, paths, dataKeys];
+}
+
+// worker on message definition
+self.onmessage = async event => {
+  const message = event.data;
+  switch (message.type) {
+    case "init":
+      // load the model and reset the embedding dict
+      embedding_dict = {};
+      embedder = await (0, _transformers.pipeline)("feature-extraction", message.model, {
+        progress_callback: progress => {
+          self.postMessage({
+            type: "progress",
+            progress: progress
+          });
+        }
+      });
+      break;
+    case "corpus":
+      {
+        // embed the corpus or load the embeddings
+        readJsonFile(message.kgdoc); // this is so we can later match variables to tupletools
+
+        Object.keys(message.emb).forEach(key => {
+          let embarr = [];
+          for (const fl of message.emb[key].split(",")) {
+            embarr.push(fl.replace("[", "").replace("]", "").replace("np.float32", "").replace("(", "").replace(")", "").replace(" ", ""));
+          }
+          embedding_dict[key] = embarr;
+        });
+        self.postMessage({
+          type: "corpus"
+        });
+        break;
+      }
+    case "similarity":
+      {
+        //calculate query embedding and then calculate similarity
+        query_embedding = await embed(message.query, false);
+        let sim_dict = {};
+        Object.keys(embedding_dict).forEach(key => {
+          sim_dict[key] = calcCosSim(embedding_dict[key], query_embedding);
+        });
+        // sort by highest similarity (closest to 1)
+        const sortedSimDict = Object.fromEntries(Object.entries(sim_dict).sort((_ref, _ref2) => {
+          let [, a] = _ref;
+          let [, b] = _ref2;
+          return b - a;
+        }));
+        const top5 = Object.fromEntries(Object.entries(sortedSimDict).slice(0, 20));
+        let loki_result = [];
+        let ttool_result = [];
+        let result = {
+          loki: loki_result,
+          ttool: ttool_result
+        };
+        Object.keys(top5).forEach(key => {
+          if (key === "basic,charged: : ") {
+            return;
+          } // This is a workaround until we implement a fix in Analysis (and corresponding DaVinci release)
+          let description = key.substring(key.indexOf(":") + 2);
+          let variable = key.substring(0, key.indexOf(":") - 1);
+          let varpath = paths[vars.indexOf(description)];
+          let tupletool = dataKeys[varpath.split(".")[0]];
+          if (tupletool === "LoKi_functors") {
+            if (top5[key] > 0.86) {
+              if (loki_result.length < 5) {
+                loki_result.push([description, variable, tupletool]);
+              }
+            }
+          } else {
+            if (top5[key] > 0.75) {
+              if (ttool_result.length < 5) {
+                ttool_result.push([description, variable, tupletool]);
+              }
+            }
+          }
+        });
+        if (loki_result.length === 0) {
+          loki_result.push(["No matches found", "No matches found", "No matches found"]);
+        }
+        if (ttool_result.length === 0) {
+          ttool_result.push(["No matches found", "No matches found", "No matches found"]);
+        }
+        self.postMessage({
+          type: "result",
+          result: result
+        });
+      }
+  }
+};

package/dist/config.json

@@ -1,5 +1,5 @@
 {
-  "metadata_baseurl": "https://lbwizard-metadata.web.cern.ch/2.1.0/",
+  "metadata_baseurl": "https://lbwizard-metadata.web.cern.ch/3.0.1/",
   "metadata_files": {
     "particleProperties": "particle_properties",
     "lokiVariables": "loki",
@@ -8,7 +8,9 @@
     "strippingHints": "stripping_hints",
     "userHints": "user_hints",
     "tupleTools": "tupletools",
-    "dataset": "dataset"
+    "dataset": "dataset",
+    "kgdoc": "kgdoc",
+    "embedding": "embedding"
   },
   "batch_size": 10,
   "particleTagGroupStyles": {

package/dist/contexts/MetadataContext.js

@@ -15,7 +15,7 @@ var _react = require("react");
 var _utils = require("../lib/utils");
 var _config2 = _interopRequireDefault(require("../config"));
 var _jsxRuntime = require("react/jsx-runtime");
-function _interopRequireDefault(obj) { return obj && obj.__esModule ? obj : { default: obj }; }
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /*****************************************************************************\
 * (c) Copyright 2021 CERN for the benefit of the LHCb Collaboration           *
 *                                                                             *
@@ -67,7 +67,7 @@ function createMetadataProvider(_config, _ref) {
   }, []);
   if (error) {
     return /*#__PURE__*/(0, _jsxRuntime.jsxs)("h1", {
-      children: ["Oops: ", "".concat(error)]
+      children: ["Oops: ", `${error}`]
     });
   } else {
     return /*#__PURE__*/(0, _jsxRuntime.jsx)(MetadataContext.Provider, {

package/dist/index.js

@@ -3,7 +3,7 @@
 var _reactDom = _interopRequireDefault(require("react-dom"));
 var _App = _interopRequireDefault(require("./components/App"));
 var _jsxRuntime = require("react/jsx-runtime");
-function _interopRequireDefault(obj) { return obj && obj.__esModule ? obj : { default: obj }; }
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /*****************************************************************************\
 * (c) Copyright 2021 CERN for the benefit of the LHCb Collaboration           *
 *                                                                             *
@@ -15,4 +15,4 @@ function _interopRequireDefault(obj) { return obj && obj.__esModule ? obj : { de
 * or submit itself to any jurisdiction.                                       *
 \*****************************************************************************/
 
-_reactDom.default.render( /*#__PURE__*/(0, _jsxRuntime.jsx)(_App.default, {}), document.getElementById("root"));
+_reactDom.default.render(/*#__PURE__*/(0, _jsxRuntime.jsx)(_App.default, {}), document.getElementById("root"));

package/dist/lib/DTTConfig.js

@@ -5,7 +5,7 @@ Object.defineProperty(exports, "__esModule", {
 });
 exports.default = void 0;
 var _lodash = _interopRequireDefault(require("lodash"));
-function _interopRequireDefault(obj) { return obj && obj.__esModule ? obj : { default: obj }; }
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /*****************************************************************************\
 * (c) Copyright 2021 CERN for the benefit of the LHCb Collaboration           *
 *                                                                             *
@@ -64,7 +64,7 @@ class DTTConfig {
   // Set the class+name combination
   setName(name) {
     const safeName = name.replace(/\W/g, "");
-    this.config.name = "DecayTreeTuple/".concat(safeName);
+    this.config.name = `DecayTreeTuple/${safeName}`;
   }
 
   // Return the name of the DecayTreeTuple algorithm
@@ -89,16 +89,16 @@ class DTTConfig {
     this.pruneGroups();
     if (branch.length === 0) {
       return this.config;
-    } else if ("".concat(branch) in this.config.branches) {
+    } else if (`${branch}` in this.config.branches) {
       return this.config.branches[branch];
     } else {
-      if (!("".concat(branch) in this.config.groups)) {
-        this.config.groups["".concat(branch)] = {
+      if (!(`${branch}` in this.config.groups)) {
+        this.config.groups[`${branch}`] = {
           particles: branch.map(element => this.config.branches[element].particle),
           tools: []
         };
       }
-      return this.config.groups["".concat(branch)];
+      return this.config.groups[`${branch}`];
     }
   }
 
@@ -106,7 +106,7 @@ class DTTConfig {
   findTool(target, toolString) {
     const index = target.tools.findIndex(tool => toolString in tool);
     if (index < 0) {
-      throw new Error("".concat(toolString, " not found in ").concat(target));
+      throw new Error(`${toolString} not found in ${target}`);
     }
     return index;
   }
@@ -117,7 +117,7 @@ class DTTConfig {
     let target = this.getTarget(branch);
     // The toolString identifies the tool in the target's tool list
     // If the tool is given a name (recommended), append it following a slash
-    const toolString = toolName.length ? "".concat(toolClass, "/").concat(toolName) : toolClass;
+    const toolString = toolName.length ? `${toolClass}/${toolName}` : toolClass;
     // Add the tool to the list if not already there
     try {
       this.findTool(target, toolString);
@@ -128,7 +128,7 @@ class DTTConfig {
       target.tools.push(toolConfig);
       return true;
     }
-    throw new Error("".concat(toolString, " already exists in ").concat(target));
+    throw new Error(`${toolString} already exists in ${target}`);
   }
 
   // Return a dict containing the default configuration of a TupleTool

package/dist/lib/utils.js

@@ -21,7 +21,7 @@ var _pako = _interopRequireDefault(require("pako"));
 var _config = _interopRequireDefault(require("../config"));
 var _jszip = _interopRequireDefault(require("jszip"));
 var _jsxRuntime = require("react/jsx-runtime");
-function _interopRequireDefault(obj) { return obj && obj.__esModule ? obj : { default: obj }; }
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /*****************************************************************************\
 * (c) Copyright 2021 CERN for the benefit of the LHCb Collaboration           *
 *                                                                             *

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "lhcb-ntuple-wizard-test",
-  "version": "1.0.6",
+  "version": "1.0.8",
   "description": "An application to access large-scale open data from LHCb",
   "url": "https://gitlab.cern.ch/lhcb-dpa/wp6-analysis-preservation-and-open-data/lhcb-ntuple-wizard-frontend/issues",
   "private": false,