2 numerical attributes works

coral/sql.py

@@ -1011,45 +1011,46 @@ def recommendSplit():
 
 @app.route("/createAutomatically", methods=["GET", "POST"])
 # TODO add login_required
-def createAutomatically():
+def create_automatically():
   # error msg is wrong, it is based on the cohortData route
-  # cohortData?cohortId=2&attribute=gender
+  # cohortData?cohortId=2&attribute=genderdata
   error_msg = """Paramerter missing or wrong!
   For the {route} query the following parameter is needed:
   - cohortId: id of the cohort
-  There is also one optional parameter:
+  There are also  optional parameters:
+  - attribute1: one column of the entity table, used when called for 2 attributes
+  - attribute2: one column of the entity table, used when called for 2 attributes
   - attribute: one column of the entity table""".format(
     route="cohortData"
   )
 
   _log.debug("request.values %s", request.values)
 
-  # TODO: base on createUseNumFilter and create cohorts based on hdbscan grouping
+  # based on createUseNumFilter and create cohorts with hdbscan clustering
   try:
-    ##########
-    # query = QueryElements()
-    # cohort = query.get_cohort_from_db(request.values, error_msg)  # get parent cohort
-    # new_cohort = query.create_cohort_automatically(request.values, cohort,
-    #                                               error_msg)  # get filtered cohort from args and cohort
-    # return query.add_cohort_to_db(new_cohort)  # save new cohort into DB
-    # return jsonify("not implemented yet")
-    ############
-
     query = QueryElements()
     cohort = query.get_cohort_from_db(request.values, error_msg)  # get parent cohort
     sql_text = query.get_cohort_data_sql(request.values, cohort)  # get sql statement to retrieve data
     query_results = query.execute_sql_query(sql_text, cohort.entity_database)
     # _log.debug("query_results %s ", query_results.get_json())
 
-    tissues = [item for item in query_results.get_json() if item[request.values['attribute']] is not None]
-    _log.debug("tissues[0] %s", tissues[0])
-    tissues_df = pd.DataFrame(tissues)
-    tissues_attribute_df = tissues_df.iloc[:, 0].values.reshape(-1, 1) # get only the first column of tissues_df (e.g. attribute age)
-    _log.debug("tissues_attribute_df[0] %s", tissues_attribute_df[0])
-    _log.debug("tissues_attribute_df shape %s", tissues_attribute_df.shape)
+    # if there are 2 attributes, use both, if there is just 1 attribute, use one
+    if 'attribute1' in request.values:
+        attribute1 = request.values['attribute1']
+        attribute2 = request.values['attribute2']
+        tissues = [item for item in query_results.get_json() if item[attribute1] is not None and item[attribute2] is not None]
+        tissues_df = pd.DataFrame(tissues)
+        # get only the values of the attributes
+        tissues_attribute_df = tissues_df[[attribute1, attribute2]].values
+    else:
+        attribute = request.values['attribute']
+        tissues = [item for item in query_results.get_json() if item[attribute] is not None]
+        tissues_df = pd.DataFrame(tissues)
+        tissues_attribute_df = tissues_df[attribute].values.reshape(-1, 1)
+
 
     # hdbscan
-    clusterer = hdbscan.HDBSCAN(min_cluster_size=round(tissues_attribute_df.shape[0]/20), gen_min_span_tree=True) # one tenth of the number of tissues, to get a reasonable amount of clusters
+    clusterer = hdbscan.HDBSCAN(min_cluster_size=round(tissues_attribute_df.shape[0]/50), gen_min_span_tree=True) # one tenth of the number of tissues, to get a reasonable amount of clusters
     clusterer.fit(tissues_attribute_df)
     # get the labels of the clusters
     labels = clusterer.labels_

coral/sql_query_mapper.py

@@ -661,10 +661,14 @@ def create_cohort_automatically_from_tissue_names(self, args, cohort, error_msg)
         if name is None:
             raise RuntimeError(error_msg)
 
-
         attribute = args.get("attribute")
         if attribute is None:
-            raise RuntimeError(error_msg)
+            attribute1 = args.get("attribute1")
+            attribute2 = args.get("attribute2")
+            if attribute1 is None or attribute2 is None:
+                raise RuntimeError(error_msg)
+
+
 
         sql_text = "SELECT p.* FROM ({entities}) p".format(entities=cohort.statement)
         _log.debug("sql_text_create_cohort_automatically_from_tissue_names: %s", sql_text)

src/Taskview/visualizations/AVegaVisualization.ts

@@ -23,7 +23,7 @@ import {
 
 import {
   recommendSplit,
-  createAutomatically
+  createAutomatically, createDBCohortAutomatically
 } from './../../base/rest';
 
 export const MISSING_VALUES_LABEL = 'Missing Values';
@@ -256,6 +256,7 @@ export abstract class AVegaVisualization implements IVegaVisualization {
   abstract show(container: HTMLDivElement, attributes: IAttribute[], cohorts: ICohort[]);
   abstract filter(): void;
   abstract split(): void;
+  abstract createAutomatically(): void;
   abstract showImpl(chart: HTMLDivElement, data: Array<IdValuePair>); // probably the method impl from SingleAttributeVisualization can be moved here
 
   destroy() {
@@ -731,7 +732,7 @@ export abstract class SingleAttributeVisualization extends AVegaVisualization {
         cohortId: cohort.dbId,
         attribute: this.attribute.dataKey
       };
-      newCohortIds = await createAutomatically(params, false)
+      newCohortIds = await createDBCohortAutomatically(params)
       console.log("createAutomatically data", newCohortIds);
     }
 
@@ -756,6 +757,7 @@ export abstract class SingleAttributeVisualization extends AVegaVisualization {
 
     let cohortDescs: INewCohortDesc[];
     cohortDescs = [];
+    // for every selected cohort
     for (const cohort of this.cohorts) {
       // for every newCohort create a filter (for now... the filter is actually not needed, will be changed in the future)
       for (const newCohort of newCohortIds){

src/Taskview/visualizations/MultiAttributeVisualization.ts

@@ -137,6 +137,7 @@ export abstract class MultiAttributeVisualization extends AVegaVisualization {
     </div>
     <div class="d-grid gap-2">
       <button type="button" class="btn btn-coral-prime btn-block applyBtn">Apply</button>
+      <button type="button" class="btn createAutomaticallyBtn btn-coral-prime" title="Calculate meaningful splits.">Create cohorts automatically</button>
     </div>
     `,
     );
@@ -147,6 +148,15 @@ export abstract class MultiAttributeVisualization extends AVegaVisualization {
         this.addIntervalControls(attr, axis);
       }
     }
+
+    select(this.controls)
+      .select('button.createAutomaticallyBtn')
+      .on('click', () => {
+        console.log("createAutomaticallyBtn clicked");
+        this.createAutomatically();
+      });
+
+
     select(this.controls)
       .select('button.applyBtn')
       .on('click', () => {

src/Taskview/visualizations/Scatterplot.ts

@@ -8,12 +8,21 @@ import { TopLevel, LayerSpec } from 'vega-lite/build/src/spec';
 import { Field } from 'vega-lite/build/src/channeldef';
 import { ICohort } from '../../app/interfaces';
 import { AttributeType, IAttribute, IdValuePair, ServerColumnAttribute } from '../../data';
-import { NumRangeOperators } from '../../base';
-import { IFilterDesc, inRange } from '../../util';
-import { FilterEvent } from '../../base/events';
+import {
+  ICohortDBDataParams,
+  ICohortMultiAttrDBDataParams,
+  NumRangeOperators
+} from '../../base';
+import {IFilterDesc, INewCohortDesc, inRange} from '../../util';
+import {AutoSplitEvent, FilterEvent} from '../../base/events';
 import { DATA_LABEL } from './constants';
 import { AxisType, MultiAttributeVisualization } from './MultiAttributeVisualization';
 
+import {
+  createDBCohortAutomatically,
+  createAutomatically
+} from '../../base/rest';
+
 export class Scatterplot extends MultiAttributeVisualization {
   static readonly NAME: string = 'Scatterplot';
 
@@ -869,6 +878,37 @@ export class Scatterplot extends MultiAttributeVisualization {
     this.container.dispatchEvent(new FilterEvent(filterDescs));
   }
 
+  async createAutomatically() {
+    console.log("createAutomatically scatterplot");
+
+    let newCohortIds = [];
+    for (const cht of this.cohorts) {
+      const params: ICohortMultiAttrDBDataParams = {
+        cohortId: cht.dbId,
+        attribute1: "age",
+        attribute2: "bmi"
+      };
+      newCohortIds = await createDBCohortAutomatically(params)
+      console.log("createAutomatically scatterplot data", newCohortIds);
+    }
+
+    let cohortDescs: INewCohortDesc[];
+    cohortDescs = [];
+    // for every selected cohort
+    for (const cohort of this.cohorts) {
+      // for every newCohort create a filter (for now... the filter is actually not needed, will be changed in the future)
+      for (const newCohort of newCohortIds){
+        cohortDescs.push({
+          cohort: cohort,
+          newCohortId: newCohort,
+          attr:[this.attributes[0], this.attributes[1]]
+        });
+      }
+    }
+
+    this.container.dispatchEvent(new AutoSplitEvent(cohortDescs));
+  }
+
   split() {
     const filterDescs: IFilterDesc[] = [];
     for (const cht of this.cohorts) {
@@ -1259,3 +1299,5 @@ export class TsneScatterplot extends Scatterplot {
     this.container.dispatchEvent(new FilterEvent(filterDescs));
   }
 }
+
+

src/base/interfaces.ts

@@ -46,6 +46,7 @@ export interface ICohortDBWithNumFilterParams extends ICohortNumFilterParams {
 
 export interface ICohortDBWithAutoSplitParams extends ICohortAutoSplitParams {
   name: string;
+
 }
 
 export const valueListDelimiter = '⸱';
@@ -87,6 +88,12 @@ export interface ICohortDBDataParams extends IParams {
   attribute?: string;
 }
 
+export interface ICohortMultiAttrDBDataParams extends IParams {
+  cohortId: number;
+  attribute1?: string;
+  attribute2?: string;
+}
+
 export interface ICohortDBSizeParams extends IParams {
   cohortId: number;
 }

src/base/rest.ts

@@ -12,7 +12,7 @@ import {
   ICohortDBPanelAnnotationParams,
   ICohortDBParams,
   ICohortDBSizeParams,
-  ICohortDBUpdateName,
+  ICohortDBUpdateName, ICohortDBWithAutoSplitParams,
   ICohortDBWithDepletionScoreFilterParams,
   ICohortDBWithEqualsFilterParams,
   ICohortDBWithGeneEqualsFilterParams,
@@ -23,7 +23,7 @@ import {
   ICohortDepletionScoreFilterParams,
   ICohortEqualsFilterParams,
   ICohortGeneEqualsFilterParams,
-  ICohortGeneNumFilterParams,
+  ICohortGeneNumFilterParams, ICohortMultiAttrDBDataParams,
   ICohortNumFilterParams,
   ICohortPanelAnnotationFilterParams,
   ICohortRow,
@@ -149,15 +149,15 @@ export function createDBCohortWithNumFilter(params: ICohortDBWithNumFilterParams
   return getCohortDataImpl(CohortRoutes.createUseNumFilter, newParams, assignIds);
 }
 
-export function createDBCohortAutomatically(params: ICohortDBWithNumFilterParams, assignIds = false): Promise<IRow[]> {
-  const newParams: IParams = {
-    cohortId: params.cohortId,
-    name: params.name,
-    attribute: params.attribute,
-    ranges: convertNumRanges(params.ranges),
-  };
-  return getCohortDataImpl(CohortRoutes.createAutomatically, newParams, assignIds);
-}
+// export function createDBCohortAutomatically(params: ICohortDBWithNumFilterParams, assignIds = false): Promise<IRow[]> {
+//   const newParams: IParams = {
+//     cohortId: params.cohortId,
+//     name: params.name,
+//     attribute: params.attribute,
+//     ranges: convertNumRanges(params.ranges),
+//   };
+//   return getCohortDataImpl(CohortRoutes.createAutomatically, newParams, assignIds);
+// }
 
 export function recommendSplit(params: ICohortDBDataParams, assignIds = false): Promise<IRow[]> {
   const url = `/cohortdb/db/${'recommendSplit'}`;
@@ -169,13 +169,26 @@ export function recommendSplit(params: ICohortDBDataParams, assignIds = false):
   return AppContext.getInstance().getAPIJSON(url, params);
 }
 
-export function createAutomatically(params: ICohortDBDataParams, assignIds = false): Promise<IRow[]> {
-  const newParams: IParams = {
-    cohortId: params.cohortId,
-    name: "TODO: create name",
-    attribute: params.attribute,
-    ranges: "TODO: remove ranges since they are not needed",
-  };
+// TODO: remove this? not used?
+export function createDBCohortAutomatically(params: ICohortDBDataParams | ICohortMultiAttrDBDataParams, assignIds = false): Promise<IRow[]> {
+  let newParams: IParams = {};
+  // check if params is ICohortDBDataParams
+  if ("attribute" in params) {
+    newParams = {
+      cohortId: params.cohortId,
+      name: "TODO: create name", // this will be used to create a name for the cohort in the database afaik TODO: check this and implement
+      attribute: params.attribute,
+    };
+  } else {
+    if ("attribute1" in params) {
+      newParams = {
+        cohortId: params.cohortId,
+        name: "TODO: create name",
+        attribute1: params.attribute1,
+        attribute2: params.attribute2,
+      };
+    }
+  }
   return getCohortDataImpl(CohortRoutes.createAutomatically, newParams, assignIds);
 }
 

src/data/Attribute.ts

@@ -499,15 +499,15 @@ export async function multiAttributeGetAutoCohort(baseCohort: ICohort, attr: IAt
 
   // when only one filter is used the labels don't have to be set again
   // minimizes the number of time a cohort in the DB has to be updated
-  // if (filters.length > 1) {
-  //   newCohort.setLabels(labelOne.join(', '), labelTwo.join(', '));
-  //   newCohort.values = values;
-  // }
+  if (attr.length > 1) {
+    newCohort.setLabels(labelOne.join(', '), labelTwo.join(', '));
+    newCohort.values = values;
+  }
 
   return newCohort;
 }
 
-export async function multiAttributeFilter(baseCohort: ICohort, filters: IAttributeFilter[], autofilter?: boolean): Promise<ICohort> {
+export async function multiAttributeFilter(baseCohort: ICohort, filters: IAttributeFilter[]): Promise<ICohort> {
   let newCohort = baseCohort;
 
   const labelOne = [];