Merge pull request #70 from HPI-Information-Systems/develop

phpfs · web-flow · commit 46ffda49e589 · 2021-03-04T11:10:30.000+01:00
Release v1.1.1
diff --git a/app/package.json b/app/package.json
@@ -2,7 +2,7 @@
   "name": "snowman-app",
   "author": "Snowman Team",
   "description": "Compare data matching algorithms with each other",
-  "version": "1.1.0",
+  "version": "1.1.1",
   "license": "MIT",
   "homepage": "./",
   "dependencies": {
diff --git a/app/src/api/apis/ExperimentsApi.ts b/app/src/api/apis/ExperimentsApi.ts
@@ -341,5 +341,7 @@ export enum SetExperimentFileFormatEnum {
     Magellan = 'magellan',
     ClusterEr = 'clusterER',
     Pilot = 'pilot',
-    Sigmod2021 = 'sigmod2021'
+    Sigmod2021 = 'sigmod2021',
+    Bhana = 'BHANA',
+    Bpies = 'BPIES'
 }
diff --git a/app/src/components/PageStruct/PageStruct.View.tsx b/app/src/components/PageStruct/PageStruct.View.tsx
@@ -29,7 +29,7 @@ const PageStructView = ({
           </IonButtons>
           <IonTitle>{title}</IonTitle>
           <div slot="end" className="spinner-container">
-            {showIndicator ? <IonSpinner color="light" /> : null}
+            {showIndicator ? <IonSpinner className="spinner-white" /> : null}
           </div>
         </IonToolbar>
       </IonHeader>
diff --git a/app/src/components/PageStruct/PageStructStyles.css b/app/src/components/PageStruct/PageStructStyles.css
@@ -1,3 +1,7 @@
 .spinner-container {
   margin-right: 15px;
 }
+
+.spinner-white {
+  color: #fff !important;
+}
diff --git a/app/src/pages/DatasetsPage/DatasetsPage.tsx b/app/src/pages/DatasetsPage/DatasetsPage.tsx
@@ -34,8 +34,8 @@ const mapStateToProps = (state: Store): DatasetsPageStateProps => ({
         description: aDataset.description,
         subtitle: (aDataset?.tags ?? []).join(', ').toUpperCase(),
         tags: [
-          `Total: ${aDataset.numberOfRecords}`,
-          `Uploaded: ${aDataset.numberOfUploadedRecords}`,
+          `Total: ${aDataset.numberOfRecords ?? 'unknown'}`,
+          `Uploaded: ${aDataset.numberOfUploadedRecords ?? 'none'}`,
         ],
       })
     ),
diff --git a/app/src/store/actions/DatasetsStoreActions.ts b/app/src/store/actions/DatasetsStoreActions.ts
@@ -13,6 +13,7 @@ import {
   easyPrimitiveActionReturn,
 } from 'utils/easyActionsFactory';
 import RequestHandler from 'utils/requestHandler';
+import { SUCCESS_DELETE_DATASET } from 'utils/statusMessages';
 
 export const clickOnDataset = (
   aDatasetId: number
@@ -77,6 +78,7 @@ export const deleteDataset = (
   dispatch(resetSelectedDataset());
   return RequestHandler(
     (): Promise<void> => new DatasetsApi().deleteDataset({ datasetId: id }),
-    dispatch
+    dispatch,
+    SUCCESS_DELETE_DATASET
   ).then((): Promise<void> => dispatch(getDatasets()));
 };
diff --git a/app/src/store/actions/ExperimentDialogStoreActions.ts b/app/src/store/actions/ExperimentDialogStoreActions.ts
@@ -177,19 +177,23 @@ const addNewExperiment = (): SnowmanThunkAction<Promise<void>> => async (
 ): Promise<void> => {
   dispatch(createNewExperiment())
     .then((id: number): Promise<void> => dispatch(uploadExperimentFile(id)))
-    .then((): Promise<void> => dispatch(getExperiments()))
     .then((): void => dispatch(resetDialog()))
-    .finally((): void => dispatch(closeDialog()));
+    .finally((): void => {
+      dispatch(getExperiments());
+      dispatch(closeDialog());
+    });
 };
 
 const updateExistingExperiment = (): SnowmanThunkAction<
   Promise<void>
 > => async (dispatch: SnowmanDispatch): Promise<void> => {
   dispatch(editExistingExperiment())
     .then((): Promise<void> => dispatch(uploadExperimentFile()))
-    .then((): Promise<void> => dispatch(getExperiments()))
     .then((): void => dispatch(resetDialog()))
-    .finally((): void => dispatch(closeDialog()));
+    .finally((): void => {
+      dispatch(getExperiments());
+      dispatch(closeDialog());
+    });
 };
 
 export const addOrUpdateExperiment = (): SnowmanThunkAction<
diff --git a/app/src/store/actions/ExperimentsStoreActions.ts b/app/src/store/actions/ExperimentsStoreActions.ts
@@ -10,6 +10,7 @@ import {
   easyPrimitiveActionReturn,
 } from 'utils/easyActionsFactory';
 import RequestHandler from 'utils/requestHandler';
+import { SUCCESS_DELETE_EXPERIMENT } from 'utils/statusMessages';
 
 export const clickOnExperimentTag = (aTag: string): easyPrimitiveActionReturn =>
   easyPrimitiveAction({
@@ -59,6 +60,7 @@ export const deleteExperiment = (
   return RequestHandler(
     (): Promise<void> =>
       new ExperimentsApi().deleteExperiment({ experimentId: id }),
-    dispatch
+    dispatch,
+    SUCCESS_DELETE_EXPERIMENT
   ).then((): Promise<void> => dispatch(getExperiments()));
 };
diff --git a/app/src/utils/statusMessages.ts b/app/src/utils/statusMessages.ts
@@ -22,3 +22,5 @@ export const SUCCESS_TO_UPDATE_DATASET =
   'Successfully updated the designated dataset!';
 export const SUCCESS_TO_UPDATE_EXPERIMENT =
   'Successfully updated the designated experiment!';
+export const SUCCESS_DELETE_DATASET = 'Successfully deleted the dataset!';
+export const SUCCESS_DELETE_EXPERIMENT = 'Successfully deleted the experiment!';
diff --git a/docs/api_specification.yaml b/docs/api_specification.yaml
@@ -453,6 +453,8 @@ paths:
               - clusterER
               - pilot
               - sigmod2021
+              - BHANA
+              - BPIES
           required: true
       requestBody:
         content:
diff --git a/docs/basic_usage/experiments.md b/docs/basic_usage/experiments.md
@@ -33,6 +33,9 @@ Within the side menu on the left, you can then see the order in which the experi
 
 To ease the import process, Snowman understands several file formats out of the box. Those include:
 
+**Attention:** The tool only accepts source files in **csv** format at the moment - so in case your source file is a Microsoft Excel file,
+you'll first have to export it to csv!
+
 ### Pilot
 
 This file format was introduced with the initial prototype and is the easiest available format.
@@ -88,10 +91,14 @@ The open-source matching solution Magellan is widely used in research. We suppor
 ...
 ```
 
-### Sigmod2021
+### SIGMOD2021
+
+For more information, see [here](/sigmod2021).
 
-See [here](https://dbgroup.ing.unimore.it/sigmod21contest/task.shtml).
+### Proprietary Formats
 
-### ClusterER
+We support a range of proprietary experiment formats. A list of those can be found here:
 
-This is an internal file format.
+- BHANA
+- BPIES
+- ClusterER
diff --git a/docs/basic_usage/introduction.md b/docs/basic_usage/introduction.md
@@ -4,12 +4,16 @@ Welcome to the Snowman Data Matching Benchmark - this guide aims to help you get
 
 ## Setup
 
-1. Download the latest artifact for you platform from the Github Releases page.
+1. Download the latest artifact for you platform from the [Github Releases](https://github.com/HPI-Information-Systems/snowman/releases) page.
 
 2. Extract the zip somewhere safe (e.g. your Documents folder) and run `snowman.exe`, `snowman.app` or `snowman` according to the platform you are on.
 
 3. The benchmark will now start and ask you whether you want to spin up a local instance or connect to a remote.
 
+The benchmark software is completely self-contained within the extracted directory (or .app file on macOS). Upgrading
+is as easy as to download and use the newer version. Necessary migration steps will be applied to the stored data upon
+the first start. See the following section on where data is persisted.
+
 ### Local usage
 
 If you select local usage, a folder will be created within your home directory which houses our data store. This exact location of this folder is platform specific.
diff --git a/docs/sigmod2021.md b/docs/sigmod2021.md
@@ -0,0 +1,37 @@
+# ACM SIGMOD 2021
+
+Welcome participants of the [ACM SIGMOD 2021 programming contest](https://dbgroup.ing.unimore.it/sigmod21contest/)! This page contains some special information for you to get
+started more easily with our tool.
+
+Feel free to open an [issue](https://github.com/HPI-Information-Systems/snowman/issues/new/choose) in case you find a bug or see space for improvement :)
+
+## Introduction
+
+This tool will help you to compare and evaluate your data matching solutions. You can upload experiment results from
+your data matching solution and then compare it with a goldstandard, compare two experiment runs with each other or
+calculate binary metrics like precision or recall.
+
+We are working closely with the contest team to allow for a seamless experience.
+
+## Setup
+
+To use snowman, you'll have to download the latest [release (Github Releases)](https://github.com/HPI-Information-Systems/snowman/releases) of
+snowman for your specific os. After that you are able to start snowman!  
+As a first step, we'd suggest for you to start with our section [Basic Usage](/basic_usage/introduction)
+for a guide of how to benchmark and evaluate matching solutions with snowman.
+
+Some contest datasets are already bundled with the release. Select one of them, upload your own experiment result and
+start benchmarking!
+
+In case you'll want to upgrade later on, simply download the newest release and you're ready to go!
+
+## Datasets
+
+We've included an automatic importer for the gold standard format and validated that the below datasets can be imported
+out of the box. More datasets will be added as soon as they are released by the contest team.
+
+1. **Computers**: prepackaged dataset X1 and gold standard Y1
+
+## Appendix
+
+We wish all participants best of luck!
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -14,10 +14,14 @@ nav:
     - Setup: dev_setup/introduction.md
     - Contributing: contributing/knowledge.md
     - REST API: ./swagger
+  - SIGMOD2021: sigmod2021.md
 
 extra_css:
   - assets/extra.css
 
+repo_url: https://github.com/HPI-Information-Systems/snowman
+repo_name: snowman (GitHub)
+
 theme:
   name: material
   logo: assets/V2-128.png
diff --git a/package.json b/package.json
@@ -2,7 +2,7 @@
   "name": "snowman",
   "author": "Snowman Team",
   "description": "Compare data matching algorithms with each other",
-  "version": "1.1.0",
+  "version": "1.1.1",
   "license": "MIT",
   "repository": "https://github.com/HPI-Information-Systems/snowman",
   "scripts": {
diff --git a/wrapper/assets/api_specification.yaml b/wrapper/assets/api_specification.yaml
@@ -586,6 +586,8 @@ paths:
               - clusterER
               - pilot
               - sigmod2021
+              - BHANA
+              - BPIES
             type: string
           style: form
       requestBody:
diff --git a/wrapper/package.json b/wrapper/package.json
@@ -2,7 +2,7 @@
   "name": "snowman-wrapper",
   "author": "Snowman Team",
   "description": "Compare data matching algorithms with each other",
-  "version": "1.1.0",
+  "version": "1.1.1",
   "license": "MIT",
   "main": "dist/main.js",
   "scripts": {
diff --git a/wrapper/src/api/providers/experiment/experimentProvider/file/formats/bHana.ts b/wrapper/src/api/providers/experiment/experimentProvider/file/formats/bHana.ts
@@ -0,0 +1,58 @@
+import { Readable } from 'stream';
+
+import { CSVInserter } from '../csvInserter';
+
+type BHANARow = {
+  'External ID'?: string;
+  Customer?: string;
+  'Fuzzy Match Percent'?: string;
+};
+
+const BHANA_MIN_MATCH_PERCENT = 90;
+
+export class BHANAExperimentInserter extends CSVInserter {
+  protected readonly separator: string = ';';
+  protected readonly quote: string = '"';
+  protected readonly escape: string = '\\';
+  protected readonly requiredColumns: string[] = [
+    'External ID',
+    'Customer',
+    'Fuzzy Match Percent',
+  ];
+
+  protected lastClusterHeader?: BHANARow;
+  protected lastClusterRows: BHANARow[] = [];
+
+  protected processLastCluster(): void {
+    if (this.lastClusterHeader && this.lastClusterRows.length >= 1) {
+      const rows = this.lastClusterRows.filter((row) => row['Customer']);
+      for (const row of rows) {
+        const fuzzyMatchPercent = parseFloat(
+          (row['Fuzzy Match Percent'] ?? '0').replace(',', '.')
+        );
+        this.addDuplicate(
+          // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
+          `external${parseInt(this.lastClusterHeader['External ID']!)}`,
+          // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
+          `customer${parseInt(row['Customer']!)}`,
+          fuzzyMatchPercent >= BHANA_MIN_MATCH_PERCENT,
+          { fuzzyMatchPercent }
+        );
+      }
+      this.lastClusterRows.length = 0;
+    }
+  }
+
+  protected addRow(row: BHANARow): void {
+    if (row['External ID']) {
+      this.processLastCluster();
+      this.lastClusterHeader = row;
+    } else {
+      this.lastClusterRows.push(row);
+    }
+  }
+  async insert_internal(file: Readable): Promise<void> {
+    await super.insert_internal(file);
+    this.processLastCluster();
+  }
+}
diff --git a/wrapper/src/api/providers/experiment/experimentProvider/file/formats/bPies.ts b/wrapper/src/api/providers/experiment/experimentProvider/file/formats/bPies.ts
@@ -0,0 +1,58 @@
+import { Readable } from 'stream';
+
+import { CSVInserter } from '../csvInserter';
+
+type BPIESRow = {
+  Partner?: string;
+  Customer?: string;
+  Relevance?: string;
+};
+
+const BPIES_MIN_MATCH_PERCENT = 90;
+
+export class BPIESExperimentInserter extends CSVInserter {
+  protected readonly separator: string = ';';
+  protected readonly quote: string = '"';
+  protected readonly escape: string = '\\';
+  protected readonly requiredColumns: string[] = [
+    'Partner',
+    'Customer',
+    'Relevance',
+  ];
+
+  protected lastClusterHeader?: BPIESRow;
+  protected lastClusterRows: BPIESRow[] = [];
+
+  protected processLastCluster(): void {
+    if (this.lastClusterHeader && this.lastClusterRows.length >= 1) {
+      const rows = this.lastClusterRows.filter((row) => row['Customer']);
+      for (const row of rows) {
+        const relevance = parseFloat(
+          (row['Relevance'] ?? '0').replace(',', '.')
+        );
+        this.addDuplicate(
+          // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
+          `external${parseInt(this.lastClusterHeader!['Partner']!)}`,
+          // eslint-disable-next-line @typescript-eslint/no-non-null-assertion
+          `customer${parseInt(row['Customer']!)}`,
+          relevance >= BPIES_MIN_MATCH_PERCENT,
+          { relevance }
+        );
+      }
+      this.lastClusterRows.length = 0;
+    }
+  }
+
+  protected addRow(row: BPIESRow): void {
+    if (!row['Customer']) {
+      this.processLastCluster();
+      this.lastClusterHeader = row;
+    } else {
+      this.lastClusterRows.push(row);
+    }
+  }
+  async insert_internal(file: Readable): Promise<void> {
+    await super.insert_internal(file);
+    this.processLastCluster();
+  }
+}
diff --git a/wrapper/src/api/providers/experiment/experimentProvider/file/index.ts b/wrapper/src/api/providers/experiment/experimentProvider/file/index.ts
@@ -1,4 +1,6 @@
 import type { ExperimentInserter } from './experimentInserter';
+import { BHANAExperimentInserter } from './formats/bHana';
+import { BPIESExperimentInserter } from './formats/bPies';
 import { ClusterERExperimentInserter } from './formats/clusterER';
 import { MagellanExperimentInserter } from './formats/magellan';
 import { PilotExperimentInserter } from './formats/pilot';
@@ -18,6 +20,8 @@ export const experimentFormats = [
   ['clusterER', ClusterERExperimentInserter],
   ['pilot', PilotExperimentInserter],
   ['sigmod2021', Sigmod2021ExperimentInserter],
+  ['BHANA', BHANAExperimentInserter],
+  ['BPIES', BPIESExperimentInserter],
 ] as const;
 const experimentInserters = new Map<string, InstantiableExperimentInserter>(
   experimentFormats

Original file line number	Diff line number	Diff line change
`@@ -341,5 +341,7 @@ export enum SetExperimentFileFormatEnum {`
`341`	`341`	`Magellan = 'magellan',`
`342`	`342`	`ClusterEr = 'clusterER',`
`343`	`343`	`Pilot = 'pilot',`
`344`		`- Sigmod2021 = 'sigmod2021'`
	`344`	`+ Sigmod2021 = 'sigmod2021',`
	`345`	`+ Bhana = 'BHANA',`
	`346`	`+ Bpies = 'BPIES'`
`345`	`347`	`}`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,7 @@`
`1`	`1`	`.spinner-container {`
`2`	`2`	`margin-right: 15px;`
`3`	`3`	`}`
	`4`	`+`
	`5`	`+.spinner-white {`
	`6`	`+ color: #fff !important;`
	`7`	`+}`