feature: add data-evaluation

* feature: add evaluation task management function * feature: add evaluation task detail page * fix: delete duplicate definition for table t_model_config * refactor: rename package synthesis to ratio * refactor: add eval file table and refactor related code * fix: calling large models in parallel during evaluation
2025-12-04 09:23:54 +08:00
parent 265e284fb8
commit 1d19cd3a62
52 changed files with 2882 additions and 1244 deletions
--- a/frontend/src/pages/RatioTask/Create/CreateRatioTask.tsx
+++ b/frontend/src/pages/RatioTask/Create/CreateRatioTask.tsx
@@ -1,4 +1,4 @@
-import { useMemo, useState } from "react";
+import { useState } from "react";
 import { Button, Form, message } from "antd";
 import { ArrowLeft, ChevronRight } from "lucide-react";
 import { createRatioTaskUsingPost } from "@/pages/RatioTask/ratio.api.ts";
--- a/frontend/src/pages/RatioTask/Create/components/RatioConfig.tsx
+++ b/frontend/src/pages/RatioTask/Create/components/RatioConfig.tsx
@@ -2,14 +2,12 @@ import React, { useMemo, useState, useEffect, FC } from "react";
 import {
  Badge,
  Card,
-  Progress,
  Button,
  Select,
  Table,
  InputNumber,
-  Space,
 } from "antd";
-import { BarChart3, Filter } from "lucide-react";
+import { BarChart3 } from "lucide-react";
 import type { Dataset } from "@/pages/DataManagement/dataset.model.ts";

 const TIME_RANGE_OPTIONS = [
@@ -20,6 +18,11 @@ const TIME_RANGE_OPTIONS = [
  { label: '最近30天', value: 30 },
 ];

+interface LabelFilter {
+  label: string;
+  value: string;
+}
+
 interface RatioConfigItem {
  id: string;
  name: string;
@@ -27,7 +30,7 @@ interface RatioConfigItem {
  quantity: number;
  percentage: number;
  source: string; // dataset id
-  labelFilter?: string;
+  labelFilter?: LabelFilter;
  dateRange?: number;
 }

@@ -36,7 +39,8 @@ interface RatioConfigProps {
  selectedDatasets: string[];
  datasets: Dataset[];
  totalTargetCount: number;
-  distributions: Record<string, Record<string, number>>;
+  // distributions now: { datasetId: { labelName: { labelValue: count } } }
+  distributions: Record<string, Record<string, Record<string, number>>>;
  onChange?: (configs: RatioConfigItem[]) => void;
 }

@@ -63,6 +67,10 @@ const RatioConfig: FC<RatioConfigProps> = ({
    return Object.keys(dist);
  };

+  const getLabelValues = (datasetId: string, label: string): string[] => {
+    return Object.keys(distributions[String(datasetId)]?.[label] || {});
+  };
+
  const addConfig = (datasetId: string) => {
    const dataset = datasets.find((d) => String(d.id) === datasetId);
    const newConfig: RatioConfigItem = {
@@ -208,46 +216,85 @@ const RatioConfig: FC<RatioConfigProps> = ({
              );

              const labels = getDatasetLabels(datasetId);
-              const usedLabels = datasetConfigs
-                .map((c) => c.labelFilter)
-                .filter(Boolean) as string[];
+
+              // helper: used values per label for this dataset (exclude a given row when needed)
+              const getUsedValuesForLabel = (label: string, excludeId?: string) => {
+                return new Set(
+                  datasetConfigs
+                    .filter((c) => c.id !== excludeId && c.labelFilter?.label === label)
+                    .map((c) => c.labelFilter?.value)
+                    .filter(Boolean) as string[]
+                );
+              };

              const columns = [
                {
-                  title: "配比项",
-                  dataIndex: "id",
-                  key: "id",
-                  render: (_: any, record: RatioConfigItem) => (
-                    <Space>
-                      <Filter size={14} className="text-gray-400" />
-                      <span className="text-sm">{record.name}</span>
-                    </Space>
-                  ),
-                },
-                {
-                  title: "标签筛选",
+                  title: "标签",
                  dataIndex: "labelFilter",
                  key: "labelFilter",
                  render: (_: any, record: RatioConfigItem) => {
                    const availableLabels = labels
-                      .map((l) => ({ label: l, value: l }))
-                      .filter(
-                        (opt) =>
-                          opt.value === record.labelFilter ||
-                          !usedLabels.includes(opt.value)
-                      );
+                      .map((l) => ({
+                        label: l,
+                        value: l,
+                        disabled: getLabelValues(datasetId, l).every((v) => getUsedValuesForLabel(l, record.id).has(v)),
+                      }))
                    return (
                      <Select
                        style={{ width: "160px" }}
                        placeholder="选择标签"
-                        value={record.labelFilter}
+                        value={record.labelFilter?.label}
                        options={availableLabels}
                        allowClear
-                        onChange={(value) =>
+                        onChange={(value) => {
+                          if (!value) {
+                            updateConfig(record.id, { labelFilter: undefined });
+                          } else {
+                            // reset value when label changes
+                            updateConfig(record.id, {
+                              labelFilter: { label: value, value: "" },
+                            });
+                          }
+                        }}
+                      />
+                    );
+                  },
+                },
+                {
+                  title: "标签值",
+                  dataIndex: "labelValue",
+                  key: "labelValue",
+                  render: (_: any, record: RatioConfigItem) => {
+                    const selectedLabel = record.labelFilter?.label;
+                    const options = selectedLabel
+                      ? getLabelValues(datasetId, selectedLabel).map((v) => ({
+                        label: v,
+                        value: v,
+                        disabled: datasetConfigs.some(
+                          (c) =>
+                            c.id !== record.id &&
+                            c.labelFilter?.label === selectedLabel &&
+                            c.labelFilter?.value === v
+                        ),
+                      }))
+                      : [];
+                    return (
+                      <Select
+                        style={{ width: "180px" }}
+                        placeholder="选择标签值"
+                        value={record.labelFilter?.value || undefined}
+                        options={options}
+                        allowClear
+                        disabled={!selectedLabel}
+                        onChange={(value) => {
+                          if (!selectedLabel) return;
                          updateConfig(record.id, {
-                            labelFilter: value || undefined,
-                          })
-                        }
+                            labelFilter: {
+                              label: selectedLabel,
+                              value: value || "",
+                            },
+                          });
+                        }}
                      />
                    );
                  },
@@ -286,23 +333,6 @@ const RatioConfig: FC<RatioConfigProps> = ({
                    />
                  ),
                },
-                {
-                  title: "占比",
-                  dataIndex: "percentage",
-                  key: "percentage",
-                  render: (_: any, record: RatioConfigItem) => (
-                    <div style={{ minWidth: 140 }}>
-                      <div className="text-xs mb-1">
-                        {record.percentage ?? 0}%
-                      </div>
-                      <Progress
-                        percent={record.percentage ?? 0}
-                        size="small"
-                        showInfo={false}
-                      />
-                    </div>
-                  ),
-                },
                {
                  title: "操作",
                  dataIndex: "actions",
--- a/frontend/src/pages/RatioTask/Create/components/SelectDataset.tsx
+++ b/frontend/src/pages/RatioTask/Create/components/SelectDataset.tsx
@@ -1,3 +1,4 @@
+// typescript
 import React, { useEffect, useState } from "react";
 import { Badge, Button, Card, Checkbox, Input, Pagination } from "antd";
 import { Search as SearchIcon } from "lucide-react";
@@ -5,32 +6,48 @@ import type { Dataset } from "@/pages/DataManagement/dataset.model.ts";
 import {
  queryDatasetsUsingGet,
  queryDatasetByIdUsingGet,
-  queryDatasetStatisticsByIdUsingGet,
 } from "@/pages/DataManagement/dataset.api.ts";

 interface SelectDatasetProps {
  selectedDatasets: string[];
  onSelectedDatasetsChange: (next: string[]) => void;
+  // distributions now: { datasetId: { labelName: { labelValue: count } } }
  onDistributionsChange?: (
-    next: Record<string, Record<string, number>>
+    next: Record<string, Record<string, Record<string, number>>>
  ) => void;
  onDatasetsChange?: (list: Dataset[]) => void;
 }

 const SelectDataset: React.FC<SelectDatasetProps> = ({
-  selectedDatasets,
-  onSelectedDatasetsChange,
-  onDistributionsChange,
-  onDatasetsChange,
-}) => {
+                                                       selectedDatasets,
+                                                       onSelectedDatasetsChange,
+                                                       onDistributionsChange,
+                                                       onDatasetsChange,
+                                                     }) => {
  const [datasets, setDatasets] = useState<Dataset[]>([]);
  const [loading, setLoading] = useState(false);
  const [searchQuery, setSearchQuery] = useState("");
  const [pagination, setPagination] = useState({ page: 1, size: 10, total: 0 });
  const [distributions, setDistributions] = useState<
-    Record<string, Record<string, number>>
+    Record<string, Record<string, Record<string, number>>>
  >({});

+  // Helper: flatten nested distribution for preview and filter logic
+  const flattenDistribution = (
+    dist?: Record<string, Record<string, number>>
+  ): Array<{ label: string; value: string; count: number }> => {
+    if (!dist) return [];
+    const items: Array<{ label: string; value: string; count: number }> = [];
+    Object.entries(dist).forEach(([label, values]) => {
+      if (values && typeof values === "object") {
+        Object.entries(values).forEach(([val, cnt]) => {
+          items.push({ label, value: val, count: cnt });
+        });
+      }
+    });
+    return items;
+  };
+
  // Fetch dataset list
  useEffect(() => {
    const fetchDatasets = async () => {
@@ -52,10 +69,10 @@ const SelectDataset: React.FC<SelectDatasetProps> = ({
        setLoading(false);
      }
    };
-    fetchDatasets();
+    fetchDatasets().then(() => {});
  }, [pagination.page, pagination.size, searchQuery]);

-  // Fetch label distributions when in label mode
+  // Fetch label distributions when datasets change
  useEffect(() => {
    const fetchDistributions = async () => {
      if (!datasets?.length) return;
@@ -64,74 +81,25 @@ const SelectDataset: React.FC<SelectDatasetProps> = ({
        .filter((id) => !distributions[id]);
      if (!idsToFetch.length) return;
      try {
-        const results = await Promise.all(
-          idsToFetch.map(async (id) => {
-            try {
-              const statRes = await queryDatasetStatisticsByIdUsingGet(id);
-              return { id, stats: statRes?.data };
-            } catch {
-              return { id, stats: null };
-            }
-          })
-        );
-
-        const next: Record<string, Record<string, number>> = {
-          ...distributions,
-        };
-        for (const { id, stats } of results) {
-          let dist: Record<string, number> | undefined = undefined;
-          if (stats) {
-            const candidates: any[] = [
-              (stats as any).labelDistribution,
-              (stats as any).tagDistribution,
-              (stats as any).label_stats,
-              (stats as any).labels,
-              (stats as any).distribution,
-            ];
-            let picked = candidates.find(
-              (c) => c && (typeof c === "object" || Array.isArray(c))
-            );
-            if (Array.isArray(picked)) {
-              const obj: Record<string, number> = {};
-              picked.forEach((it: any) => {
-                const key = it?.label ?? it?.name ?? it?.tag ?? it?.key;
-                const val = it?.count ?? it?.value ?? it?.num ?? it?.total;
-                if (key != null && typeof val === "number")
-                  obj[String(key)] = val;
-              });
-              dist = obj;
-            } else if (picked && typeof picked === "object") {
-              dist = picked as Record<string, number>;
-            }
-          }
-          if (!dist) {
-            try {
-              const detRes = await queryDatasetByIdUsingGet(id);
-              const det = detRes?.data;
-              if (det) {
-                let picked =
-                  (det as any).distribution ||
-                  (det as any).labelDistribution ||
-                  (det as any).tagDistribution ||
-                  (det as any).label_stats ||
-                  (det as any).labels ||
-                  undefined;
-                if (Array.isArray(picked)) {
-                  const obj: Record<string, number> = {};
-                  picked.forEach((it: any) => {
-                    const key = it?.label ?? it?.name ?? it?.tag ?? it?.key;
-                    const val = it?.count ?? it?.value ?? it?.num ?? it?.total;
-                    if (key != null && typeof val === "number")
-                      obj[String(key)] = val;
-                  });
-                  dist = obj;
-                } else if (picked && typeof picked === "object") {
-                  dist = picked as Record<string, number>;
-                }
+        const next: Record<
+          string,
+          Record<string, Record<string, number>>
+        > = { ...distributions };
+        for (const id of idsToFetch) {
+          let dist: Record<string, Record<string, number>> | undefined =
+            undefined;
+          try {
+            const detRes = await queryDatasetByIdUsingGet(id);
+            const det = detRes?.data;
+            if (det) {
+              const picked = det?.distribution;
+              if (picked && typeof picked === "object") {
+                // Assume picked is now { labelName: { labelValue: count } }
+                dist = picked as Record<string, Record<string, number>>;
              }
-            } catch {
-              dist = undefined;
            }
+          } catch {
+            dist = undefined;
          }
          next[String(id)] = dist || {};
        }
@@ -141,7 +109,7 @@ const SelectDataset: React.FC<SelectDatasetProps> = ({
        // ignore
      }
    };
-    fetchDistributions();
+    fetchDistributions().then(() => {});
    // eslint-disable-next-line react-hooks/exhaustive-deps
  }, [datasets]);

@@ -195,6 +163,8 @@ const SelectDataset: React.FC<SelectDatasetProps> = ({
            datasets.map((dataset) => {
              const idStr = String(dataset.id);
              const checked = selectedDatasets.includes(idStr);
+              const distFor = distributions[idStr];
+              const flat = flattenDistribution(distFor);
              return (
                <Card
                  key={dataset.id}
@@ -224,17 +194,15 @@ const SelectDataset: React.FC<SelectDatasetProps> = ({
                        <span>{dataset.size}</span>
                      </div>
                      <div className="mt-2">
-                        {distributions[idStr] ? (
-                          Object.entries(distributions[idStr]).length > 0 ? (
+                        {distFor ? (
+                          flat.length > 0 ? (
                            <div className="flex flex-wrap gap-2 text-xs">
-                              {Object.entries(distributions[idStr])
-                                .slice(0, 8)
-                                .map(([tag, count]) => (
-                                  <Badge
-                                    key={tag}
-                                    color="gray"
-                                  >{`${tag}: ${count}`}</Badge>
-                                ))}
+                              {flat.slice(0, 8).map((it) => (
+                                <Badge
+                                  key={`${it.label}_${it.value}`}
+                                  color="gray"
+                                >{`${it.label}/${it.value}: ${it.count}`}</Badge>
+                              ))}
                            </div>
                          ) : (
                            <div className="text-xs text-gray-400">
--- a/frontend/src/pages/RatioTask/ratio.const.tsx
+++ b/frontend/src/pages/RatioTask/ratio.const.tsx
@@ -45,9 +45,7 @@ export function mapRatioTask(task: Partial<RatioTaskItem>): RatioTaskItem {
    status: ratioTaskStatusMap[task.status || RatioStatus.PENDING],
    createdAt: formatDate(task.created_at),
    updatedAt: formatDate(task.updated_at),
-    description:
-      task.description ||
-      (task.ratio_method === "DATASET" ? "按数据集配比" : "按标签配比"),
+    description: task.description,
    icon: <BarChart3 />,
    iconColor: task.ratio_method === "DATASET" ? "bg-blue-100" : "bg-green-100",
    statistics: [
@@ -73,16 +71,5 @@ export function mapRatioTask(task: Partial<RatioTaskItem>): RatioTaskItem {
        value: task.created_at || "-",
      },
    ],
-    type: task.ratio_method === "DATASET" ? "数据集配比" : "标签配比",
-    // progress: 100,
-    // sourceDatasets: ["sentiment_dataset", "news_classification"],
-    // targetRatio: { 正面: 33, 负面: 33, 中性: 34 },
-    // currentRatio: { 正面: 33, 负面: 33, 中性: 34 },
-    // totalRecords: 15000,
-    // processedRecords: 15000,
-    // estimatedTime: "已完成",
-    // quality: 95,
-    // strategy: "随机下采样",
-    // outputPath: "/data/balanced/sentiment_balanced_20250120",
  };
 }