From 9fd425173c3b33d9f309215502efb49cf03b5b82 Mon Sep 17 00:00:00 2001
From: haotian <2421912570@qq.com>
Date: Tue, 25 Feb 2025 16:05:06 +0800
Subject: [PATCH] =?UTF-8?q?=E5=89=8D=E7=AB=AF--=E8=8E=B7=E5=8F=96=E5=92=8C?=
 =?UTF-8?q?=E5=B1=95=E7=A4=BA=E6=95=B0=E6=8D=AE=E5=AE=8C=E6=88=90?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 api/__pycache__/data_api.cpython-39.pyc       | Bin 3375 -> 3397 bytes
 api/data_api.py                               |   1 +
 doc/接口文档code.md                           |   2 +-
 frontend/index.html                           |  13 +
 frontend/src/api/data.ts                      |  40 ++-
 frontend/src/components/data/DataPreview.vue  | 189 ++++++-------
 .../src/components/data/DataProcessDialog.vue | 197 ++++++++++++++
 frontend/src/components/data/DatasetList.vue  | 192 ++++++-------
 frontend/src/router/index.ts                  |  37 ++-
 frontend/src/types/data.ts                    |  16 +-
 frontend/src/views/data/DataView.vue          |  51 ++++
 frontend/src/views/data/DatasetView.vue       |  47 +++-
 frontend/src/views/data/FeatureView.vue       | 202 ++++++++++++++
 frontend/src/views/data/PreprocessView.vue    | 253 ++++++++++++++++++
 function_old/data_process/__init__.py         |   0
 .../__pycache__/__init__.cpython-39.pyc       | Bin 0 -> 151 bytes
 .../__pycache__/data_cleaner.cpython-39.pyc   | Bin 0 -> 2919 bytes
 .../__pycache__/data_processor.cpython-39.pyc | Bin 0 -> 2492 bytes
 .../data_processor_date.cpython-39.pyc        | Bin 0 -> 8675 bytes
 .../__pycache__/data_splitter.cpython-39.pyc  | Bin 0 -> 1713 bytes
 .../feature_engineer.cpython-39.pyc           | Bin 0 -> 3098 bytes
 .../__pycache__/method_reader.cpython-39.pyc  | Bin 0 -> 2955 bytes
 .../method_reader_date_feature.cpython-39.pyc | Bin 0 -> 3498 bytes
 .../method_reader_date_process.cpython-39.pyc | Bin 0 -> 3757 bytes
 function_old/data_process/data_cleaner.py     |  66 +++++
 function_old/data_process/data_processor.py   |  63 +++++
 function_old/data_process/data_splitter.py    |  49 ++++
 function_old/data_process/feature_engineer.py |  77 ++++++
 .../data_process/test_data_processor.py       |  34 +++
 function_old/data_process/ttt.py              |   2 +
 function_old/test_data_processor.py           |  93 +++++++
 function_old/test_method_reader.py            |  49 ++++
 function_old/test_model_manager.py            |  99 +++++++
 function_old/test_model_trainer.py            |  85 ++++++
 function_old/test_system_monitor.py           |  86 ++++++
 function_old/处理乳腺癌数据集.py              |   6 +
 36 files changed, 1739 insertions(+), 210 deletions(-)
 create mode 100644 frontend/index.html
 create mode 100644 frontend/src/components/data/DataProcessDialog.vue
 create mode 100644 frontend/src/views/data/DataView.vue
 create mode 100644 frontend/src/views/data/FeatureView.vue
 create mode 100644 frontend/src/views/data/PreprocessView.vue
 create mode 100644 function_old/data_process/__init__.py
 create mode 100644 function_old/data_process/__pycache__/__init__.cpython-39.pyc
 create mode 100644 function_old/data_process/__pycache__/data_cleaner.cpython-39.pyc
 create mode 100644 function_old/data_process/__pycache__/data_processor.cpython-39.pyc
 create mode 100644 function_old/data_process/__pycache__/data_processor_date.cpython-39.pyc
 create mode 100644 function_old/data_process/__pycache__/data_splitter.cpython-39.pyc
 create mode 100644 function_old/data_process/__pycache__/feature_engineer.cpython-39.pyc
 create mode 100644 function_old/data_process/__pycache__/method_reader.cpython-39.pyc
 create mode 100644 function_old/data_process/__pycache__/method_reader_date_feature.cpython-39.pyc
 create mode 100644 function_old/data_process/__pycache__/method_reader_date_process.cpython-39.pyc
 create mode 100644 function_old/data_process/data_cleaner.py
 create mode 100644 function_old/data_process/data_processor.py
 create mode 100644 function_old/data_process/data_splitter.py
 create mode 100644 function_old/data_process/feature_engineer.py
 create mode 100644 function_old/data_process/test_data_processor.py
 create mode 100644 function_old/data_process/ttt.py
 create mode 100644 function_old/test_data_processor.py
 create mode 100644 function_old/test_method_reader.py
 create mode 100644 function_old/test_model_manager.py
 create mode 100644 function_old/test_model_trainer.py
 create mode 100644 function_old/test_system_monitor.py
 create mode 100644 function_old/处理乳腺癌数据集.py

diff --git a/api/__pycache__/data_api.cpython-39.pyc b/api/__pycache__/data_api.cpython-39.pyc
index 4776ebd58fb6599071a3b571a6cd5fa75d25fa33..006115bba7a41031390c255c52ceefb58c090e37 100644
GIT binary patch
delta 220
zcmZ24bySKsk(ZZ?0SFf6?oHpck@p5?N*s_^C0D|*fN>#1Ekg-Y3S$jJGZQ023R4Y3
z3iBMMaE4$87KRe$$_Pe=T1G~ODy0&Z6qXd$64n~VX2#hJbD2`udYPIS!x<tOQrK%5
z>lpL6AhZF40Z=5EL6c*$J(q&~Esm7LlEmWFlHw@#;?m^g)Z$`IrXoe4^+l#YVsa&y
zo&;NwI*=K~ot|0}4^>@c1d`mv<;X1tWH2x@F>)|+ZD!#XWMquoEXE_o$jr~d2mr*q
BF@^vD

delta 198
zcmX>qwO)!hk(ZZ?0SHQT_NMo3<h{We6$0c{iIgxbU|h&h%aFoY!;r!>hbf#Pn1O|%
zgsIYxk)f86k)cYdggJ#dg{6e0hOwD(Hp5(|6xLp*CdP1vNQM-)TE;rYJT3@rz+eCr
z31-k_pX|w{AQi=4T$-GmT3oEjRHO*B>J~>zVo73gYDw|r4lX@m)*^MFU=(+HYDqj)
iV)8jIM@|u-C<8MSBgbYbZb3%Ih|M}YVvNju9E<=`n=RD<

diff --git a/api/data_api.py b/api/data_api.py
index f70e1b3..6385779 100644
--- a/api/data_api.py
+++ b/api/data_api.py
@@ -75,6 +75,7 @@ async def get_datasets():
     """获取可用数据集列表"""
     try:
         datasets = data_manager.get_dataset()
+        print("datasets", datasets)
         return {
             "status": "success",
             "datasets": datasets
diff --git a/doc/接口文档code.md b/doc/接口文档code.md
index 8daf658..16d1595 100644
--- a/doc/接口文档code.md
+++ b/doc/接口文档code.md
@@ -764,7 +764,7 @@ Error Response:
 
 ### 3.3 获取系统中训练状态 ---- 未完成, 等开发系统后台时再实现.
 ```http
-GET /api/train/status/{task_id}
+GET /model/train/status/{task_id}
 
 Response:
 {
diff --git a/frontend/index.html b/frontend/index.html
new file mode 100644
index 0000000..1f10fdf
--- /dev/null
+++ b/frontend/index.html
@@ -0,0 +1,13 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+  <head>
+    <meta charset="UTF-8" />
+    <link rel="icon" type="image/svg+xml" href="/favicon.ico" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>机器学习平台</title>
+  </head>
+  <body>
+    <div id="app"></div>
+    <script type="module" src="/src/main.ts"></script>
+  </body>
+</html> 
\ No newline at end of file
diff --git a/frontend/src/api/data.ts b/frontend/src/api/data.ts
index 795aa8a..39de53d 100644
--- a/frontend/src/api/data.ts
+++ b/frontend/src/api/data.ts
@@ -5,11 +5,15 @@ import type {
   FeatureMethod,
   ProcessRequest,
   CSVRequest,
-  DatasetInfo
+  DatasetInfo,
+  MethodDetail
 } from '@/types/data'
 
 // 获取预处理方法列表
-export const getPreprocessMethods = (): Promise<AxiosResponse<PreprocessMethod[]>> => {
+export const getPreprocessMethods = (): Promise<{
+  status: string;
+  methods: PreprocessMethod[];
+}> => {
   return request({
     url: '/data/preprocessing/methods',
     method: 'get'
@@ -17,7 +21,10 @@ export const getPreprocessMethods = (): Promise<AxiosResponse<PreprocessMethod[]
 }
 
 // 获取预处理方法详情
-export const getPreprocessMethodDetails = (methodName: string): Promise<AxiosResponse> => {
+export const getPreprocessMethodDetails = (methodName: string): Promise<{
+  status: string;
+  method: MethodDetail;
+}> => {
   return request({
     url: `/data/preprocessing/method/${methodName}`,
     method: 'get'
@@ -25,7 +32,10 @@ export const getPreprocessMethodDetails = (methodName: string): Promise<AxiosRes
 }
 
 // 获取特征工程方法列表
-export const getFeatureMethods = (): Promise<AxiosResponse<FeatureMethod[]>> => {
+export const getFeatureMethods = (): Promise<{
+  status: string;
+  methods: FeatureMethod[];
+}> => {
   return request({
     url: '/data/feature/methods',
     method: 'get'
@@ -33,7 +43,10 @@ export const getFeatureMethods = (): Promise<AxiosResponse<FeatureMethod[]>> =>
 }
 
 // 获取特征工程方法详情
-export const getFeatureMethodDetails = (methodName: string): Promise<AxiosResponse> => {
+export const getFeatureMethodDetails = (methodName: string): Promise<{
+  status: string;
+  method: MethodDetail;
+}> => {
   return request({
     url: `/data/feature/method/${methodName}`,
     method: 'get'
@@ -41,7 +54,10 @@ export const getFeatureMethodDetails = (methodName: string): Promise<AxiosRespon
 }
 
 // 处理数据集
-export const processDataset = (data: ProcessRequest): Promise<AxiosResponse> => {
+export const processDataset = (data: ProcessRequest): Promise<{
+  status: string;
+  data: any;
+}> => {
   return request({
     url: '/data/process',
     method: 'post',
@@ -49,8 +65,11 @@ export const processDataset = (data: ProcessRequest): Promise<AxiosResponse> =>
   })
 }
 
-// 获取可用数据集列表
-export const getDatasets = (): Promise<AxiosResponse<DatasetInfo[]>> => {
+// 获取数据集列表
+export const getDatasets = (): Promise<{
+  status: string;
+  datasets: DatasetInfo[];
+}> => {
   return request({
     url: '/data/datasets',
     method: 'get'
@@ -58,7 +77,10 @@ export const getDatasets = (): Promise<AxiosResponse<DatasetInfo[]>> => {
 }
 
 // 读取CSV文件
-export const readCSV = (data: CSVRequest): Promise<AxiosResponse> => {
+export const readCSV = (data: CSVRequest): Promise<{
+  status: string;
+  data: any;
+}> => {
   return request({
     url: '/data/csv',
     method: 'post',
diff --git a/frontend/src/components/data/DataPreview.vue b/frontend/src/components/data/DataPreview.vue
index 5721ea1..919c650 100644
--- a/frontend/src/components/data/DataPreview.vue
+++ b/frontend/src/components/data/DataPreview.vue
@@ -4,74 +4,80 @@
     title="数据预览"
     width="80%"
   >
-    <el-tabs v-model="activeTab">
-      <!-- 训练集预览 -->
-      <el-tab-pane label="训练集" name="train">
-        <div v-loading="loading.train">
-          <el-descriptions title="数据集信息" :column="3" border>
-            <el-descriptions-item label="行数">
-              {{ dataInfo.train?.info?.rows || '-' }}
-            </el-descriptions-item>
-            <el-descriptions-item label="列数">
-              {{ dataInfo.train?.info?.columns || '-' }}
-            </el-descriptions-item>
-            <el-descriptions-item label="内存占用">
-              {{ dataInfo.train?.info?.memory_usage || '-' }}
-            </el-descriptions-item>
-          </el-descriptions>
-          
-          <div class="mt-4">
-            <h4>数据预览</h4>
-            <el-table
-              :data="dataInfo.train?.head || []"
-              style="width: 100%"
-              max-height="400"
-              border
-            >
-              <el-table-column
-                v-for="col in getColumns(dataInfo.train?.head)"
-                :key="col"
-                :prop="col"
-                :label="col"
-              />
-            </el-table>
-          </div>
-          
-          <div class="mt-4">
-            <h4>数据统计</h4>
-            <el-table
-              :data="getDescribeData(dataInfo.train?.describe)"
-              style="width: 100%"
-              border
-            >
-              <el-table-column prop="metric" label="统计量" width="180" />
-              <el-table-column
-                v-for="col in getDescribeColumns(dataInfo.train?.describe)"
-                :key="col"
-                :prop="col"
-                :label="col"
-              />
-            </el-table>
-          </div>
-        </div>
-      </el-tab-pane>
-      
-      <!-- 验证集预览 -->
-      <el-tab-pane label="验证集" name="val">
-        <!-- 与训练集类似的内容 -->
-      </el-tab-pane>
-      
-      <!-- 测试集预览 -->
-      <el-tab-pane label="测试集" name="test">
-        <!-- 与训练集类似的内容 -->
-      </el-tab-pane>
-    </el-tabs>
+    <div v-loading="loading">
+      <!-- 数据集基本信息 -->
+      <el-descriptions title="数据集信息" :column="3" border>
+        <el-descriptions-item label="行数">
+          {{ dataInfo?.info?.rows || '-' }}
+        </el-descriptions-item>
+        <el-descriptions-item label="列数">
+          {{ dataInfo?.info?.columns || '-' }}
+        </el-descriptions-item>
+        <el-descriptions-item label="内存占用">
+          {{ dataInfo?.info?.memory_usage || '-' }}
+        </el-descriptions-item>
+      </el-descriptions>
+
+      <!-- 数据预览表格 -->
+      <div class="preview-section">
+        <h4>数据预览</h4>
+        <el-table
+          :data="dataInfo?.head || []"
+          style="width: 100%"
+          max-height="400"
+          border
+        >
+          <el-table-column
+            v-for="col in getColumns(dataInfo?.head)"
+            :key="col"
+            :prop="col"
+            :label="col"
+          />
+        </el-table>
+      </div>
+
+      <!-- 数据统计信息 -->
+      <div class="statistics-section">
+        <h4>数据统计</h4>
+        <el-table
+          :data="getDescribeData(dataInfo?.describe)"
+          style="width: 100%"
+          border
+        >
+          <el-table-column prop="metric" label="统计量" width="180" />
+          <el-table-column
+            v-for="col in getDescribeColumns(dataInfo?.describe)"
+            :key="col"
+            :prop="col"
+            :label="col"
+          />
+        </el-table>
+      </div>
+
+      <!-- 缺失值信息 -->
+      <div class="missing-section">
+        <h4>缺失值统计</h4>
+        <el-table
+          :data="getMissingData(dataInfo?.info?.missing_values)"
+          style="width: 100%"
+          border
+        >
+          <el-table-column prop="column" label="列名" />
+          <el-table-column prop="count" label="缺失值数量" />
+          <el-table-column prop="percentage" label="缺失比例">
+            <template #default="{ row }">
+              {{ row.percentage }}%
+            </template>
+          </el-table-column>
+        </el-table>
+      </div>
+    </div>
   </el-dialog>
 </template>
 
 <script setup lang="ts">
 import { ref, watch } from 'vue'
-import type { DatasetInfo } from '@/types/data'
+import type { DatasetInfo, DataPreview } from '@/types/data'
 import { readCSV } from '@/api/data'
 
 const props = defineProps<{
@@ -84,24 +90,14 @@ const emit = defineEmits<{
 }>()
 
 const dialogVisible = ref(false)
-const activeTab = ref('train')
-const loading = ref({
-  train: false,
-  val: false,
-  test: false
-})
-
-const dataInfo = ref({
-  train: null,
-  val: null,
-  test: null
-})
+const loading = ref(false)
+const dataInfo = ref<DataPreview | null>(null)
 
 // 监听对话框显示状态
 watch(() => props.visible, (val) => {
   dialogVisible.value = val
   if (val && props.dataset) {
-    loadData('train')
+    loadData()
   }
 })
 
@@ -110,34 +106,24 @@ watch(dialogVisible, (val) => {
   emit('update:visible', val)
 })
 
-// 监听标签页切换
-watch(activeTab, (val) => {
-  if (!dataInfo.value[val]) {
-    loadData(val)
-  }
-})
-
 // 加载数据
-const loadData = async (type: 'train' | 'val' | 'test') => {
+const loadData = async () => {
   if (!props.dataset) return
   
-  const filePath = props.dataset.output_files[type]
-  if (!filePath) return
-  
-  loading.value[type] = true
+  loading.value = true
   try {
     const { data } = await readCSV({
-      data_path: filePath,
+      data_path: props.dataset.input_file,
       head: 10,
       tail: 5,
       info: true,
       describe: true
     })
-    dataInfo.value[type] = data.data
+    dataInfo.value = data
   } catch (error) {
     console.error(error)
   } finally {
-    loading.value[type] = false
+    loading.value = false
   }
 }
 
@@ -166,10 +152,27 @@ const getDescribeData = (describe: any = {}) => {
     )
   }))
 }
+
+// 转换缺失值数据为表格格式
+const getMissingData = (missingValues: Record<string, number> = {}) => {
+  if (!dataInfo.value?.info?.rows) return []
+  
+  return Object.entries(missingValues).map(([column, count]) => ({
+    column,
+    count,
+    percentage: ((count / dataInfo.value!.info.rows) * 100).toFixed(2)
+  }))
+}
 </script>
 
 <style scoped>
-.mt-4 {
-  margin-top: 1rem;
+.preview-section,
+.statistics-section,
+.missing-section {
+  margin-top: 20px;
+}
+
+h4 {
+  margin-bottom: 10px;
 }
 </style> 
\ No newline at end of file
diff --git a/frontend/src/components/data/DataProcessDialog.vue b/frontend/src/components/data/DataProcessDialog.vue
new file mode 100644
index 0000000..be0b916
--- /dev/null
+++ b/frontend/src/components/data/DataProcessDialog.vue
@@ -0,0 +1,197 @@
+<template>
+  <el-dialog
+    v-model="dialogVisible"
+    title="数据处理配置"
+    width="60%"
+  >
+    <el-form
+      ref="formRef"
+      :model="form"
+      label-width="120px"
+    >
+      <!-- 预处理方法配置 -->
+      <el-form-item label="预处理方法">
+        <el-select
+          v-model="form.preprocessing"
+          multiple
+          filterable
+          placeholder="选择预处理方法"
+        >
+          <el-option-group
+            v-for="group in preprocessMethods"
+            :key="group.name"
+            :label="group.description"
+          >
+            <el-option
+              v-for="method in group.method"
+              :key="method"
+              :label="method"
+              :value="method"
+            />
+          </el-option-group>
+        </el-select>
+      </el-form-item>
+
+      <!-- 特征工程方法配置 -->
+      <el-form-item label="特征工程">
+        <el-select
+          v-model="form.feature_methods"
+          multiple
+          filterable
+          placeholder="选择特征工程方法"
+        >
+          <el-option-group
+            v-for="group in featureMethods"
+            :key="group.name"
+            :label="group.description"
+          >
+            <el-option
+              v-for="method in group.method"
+              :key="method"
+              :label="method"
+              :value="method"
+            />
+          </el-option-group>
+        </el-select>
+      </el-form-item>
+
+      <!-- 数据集划分配置 -->
+      <el-form-item label="数据集划分">
+        <el-row :gutter="20">
+          <el-col :span="8">
+            <el-form-item label="训练集">
+              <el-input-number
+                v-model="form.split_params.train"
+                :min="0"
+                :max="1"
+                :step="0.1"
+              />
+            </el-form-item>
+          </el-col>
+          <el-col :span="8">
+            <el-form-item label="验证集">
+              <el-input-number
+                v-model="form.split_params.val"
+                :min="0"
+                :max="1"
+                :step="0.1"
+              />
+            </el-form-item>
+          </el-col>
+          <el-col :span="8">
+            <el-form-item label="测试集">
+              <el-input-number
+                v-model="form.split_params.test"
+                :min="0"
+                :max="1"
+                :step="0.1"
+                :disabled="true"
+                :modelValue="1 - form.split_params.train - form.split_params.val"
+              />
+            </el-form-item>
+          </el-col>
+        </el-row>
+      </el-form-item>
+    </el-form>
+
+    <template #footer>
+      <span class="dialog-footer">
+        <el-button @click="dialogVisible = false">取消</el-button>
+        <el-button type="primary" @click="handleSubmit" :loading="loading">
+          确认
+        </el-button>
+      </span>
+    </template>
+  </el-dialog>
+</template>
+
+<script setup lang="ts">
+import { ref, watch } from 'vue'
+import { ElMessage } from 'element-plus'
+import type { DatasetInfo, PreprocessMethod, FeatureMethod } from '@/types/data'
+import { getPreprocessMethods, getFeatureMethods, processDataset } from '@/api/data'
+
+const props = defineProps<{
+  visible: boolean
+  dataset: DatasetInfo | null
+}>()
+
+const emit = defineEmits<{
+  (e: 'update:visible', value: boolean): void
+  (e: 'success'): void
+}>()
+
+const dialogVisible = ref(false)
+const loading = ref(false)
+const preprocessMethods = ref<PreprocessMethod[]>([])
+const featureMethods = ref<FeatureMethod[]>([])
+
+const form = ref({
+  preprocessing: [],
+  feature_methods: [],
+  split_params: {
+    train: 0.7,
+    val: 0.2,
+    test: 0.1
+  }
+})
+
+// 监听对话框显示状态
+watch(() => props.visible, (val) => {
+  dialogVisible.value = val
+  if (val) {
+    loadMethods()
+  }
+})
+
+// 监听对话框关闭
+watch(dialogVisible, (val) => {
+  emit('update:visible', val)
+})
+
+// 加载处理方法
+const loadMethods = async () => {
+  try {
+    const [preprocess, feature] = await Promise.all([
+      getPreprocessMethods(),
+      getFeatureMethods()
+    ])
+    preprocessMethods.value = preprocess.data
+    featureMethods.value = feature.data
+  } catch (error) {
+    console.error('Failed to load methods:', error)
+    ElMessage.error('加载处理方法失败')
+  }
+}
+
+// 提交处理
+const handleSubmit = async () => {
+  if (!props.dataset) return
+  
+  loading.value = true
+  try {
+    await processDataset({
+      input_path: props.dataset.input_file,
+      output_dir: 'dataset/dataset_processed',
+      preprocessing: form.value.preprocessing.map(method => ({
+        method,
+        params: {}
+      })),
+      feature_methods: form.value.feature_methods.map(method => ({
+        method,
+        params: {}
+      })),
+      split_params: form.value.split_params
+    })
+    
+    ElMessage.success('处理成功')
+    dialogVisible.value = false
+    emit('success')
+  } catch (error) {
+    console.error('Failed to process dataset:', error)
+    ElMessage.error('处理失败')
+  } finally {
+    loading.value = false
+  }
+}
+</script> 
\ No newline at end of file
diff --git a/frontend/src/components/data/DatasetList.vue b/frontend/src/components/data/DatasetList.vue
index a06c34a..6edea69 100644
--- a/frontend/src/components/data/DatasetList.vue
+++ b/frontend/src/components/data/DatasetList.vue
@@ -1,22 +1,36 @@
 <template>
   <div class="dataset-list">
-    <el-table :data="datasets" style="width: 100%">
-      <el-table-column prop="input_file" label="数据集" width="200">
+    <!-- 上传数据集 -->
+    <div class="upload-section">
+      <el-upload
+        class="upload-demo"
+        action="/data/upload"
+        :on-success="handleUploadSuccess"
+        :on-error="handleUploadError"
+        :before-upload="beforeUpload"
+      >
+        <el-button type="primary">上传数据集</el-button>
+      </el-upload>
+    </div>
+
+    <!-- 数据集列表 -->
+    <el-table :data="datasets" style="width: 100%" v-loading="loading">
+      <el-table-column prop="input_file" label="数据集名称" width="180">
         <template #default="{ row }">
           {{ getFileName(row.input_file) }}
         </template>
       </el-table-column>
       
-      <el-table-column prop="timestamp" label="处理时间" width="180">
+      <el-table-column prop="timestamp" label="创建时间" width="180">
         <template #default="{ row }">
           {{ formatTime(row.timestamp) }}
         </template>
       </el-table-column>
       
-      <el-table-column label="数据处理">
+      <el-table-column label="预处理方法">
         <template #default="{ row }">
           <el-tag 
-            v-for="method in row.process_methods" 
+            v-for="method in row.process_methods"
             :key="method.method_name"
             class="mx-1"
           >
@@ -28,7 +42,7 @@
       <el-table-column label="特征工程">
         <template #default="{ row }">
           <el-tag 
-            v-for="method in row.feature_methods" 
+            v-for="method in row.feature_methods"
             :key="method.method_name"
             type="success"
             class="mx-1"
@@ -38,98 +52,56 @@
         </template>
       </el-table-column>
       
-      <el-table-column label="数据划分">
+      <el-table-column label="操作" width="250">
         <template #default="{ row }">
-          <el-tooltip effect="dark" placement="top">
-            <template #content>
-              <div>训练集: {{ (1 - row.split_params.test_size - row.split_params.val_size) * 100 }}%</div>
-              <div>验证集: {{ row.split_params.val_size * 100 }}%</div>
-              <div>测试集: {{ row.split_params.test_size * 100 }}%</div>
-            </template>
-            <el-progress :percentage="100" :format="() => '查看详情'" />
-          </el-tooltip>
-        </template>
-      </el-table-column>
-      
-      <el-table-column label="操作" width="200">
-        <template #default="{ row }">
-          <el-button 
-            type="primary" 
-            link
-            @click="handlePreview(row)"
-          >
+          <el-button link type="primary" @click="handlePreview(row)">
             预览
           </el-button>
-          <el-button 
-            type="success" 
-            link
-            @click="handleDownload(row)"
-          >
+          <el-button link type="success" @click="handleProcess(row)">
+            处理
+          </el-button>
+          <el-button link type="info" @click="handleDownload(row)">
             下载
           </el-button>
-          <el-button 
-            type="info" 
-            link
-            @click="handleDetails(row)"
-          >
-            详情
+          <el-button link type="danger" @click="handleDelete(row)">
+            删除
           </el-button>
         </template>
       </el-table-column>
     </el-table>
-    
-    <!-- 预览对话框 -->
+
+    <!-- 数据预览对话框 -->
     <DataPreview
       v-model:visible="previewVisible"
       :dataset="selectedDataset"
     />
-    
-    <!-- 详情对话框 -->
-    <el-dialog
-      v-model="detailsVisible"
-      title="数据处理详情"
-      width="60%"
-    >
-      <el-timeline>
-        <el-timeline-item
-          v-for="step in selectedDataset?.steps"
-          :key="step.step"
-          :type="getStepType(step.step)"
-        >
-          <h4>{{ getStepTitle(step) }}</h4>
-          <p>数据形状: {{ step.shape[0] }} × {{ step.shape[1] }}</p>
-          <template v-if="step.method">
-            <p>处理方法: {{ step.method }}</p>
-            <p>参数配置:</p>
-            <el-descriptions :column="1" border>
-              <el-descriptions-item 
-                v-for="(value, key) in step.params"
-                :key="key"
-                :label="key"
-              >
-                {{ value }}
-              </el-descriptions-item>
-            </el-descriptions>
-          </template>
-        </el-timeline-item>
-      </el-timeline>
-    </el-dialog>
+
+    <!-- 数据处理对话框 -->
+    <DataProcessDialog
+      v-model:visible="processVisible"
+      :dataset="selectedDataset"
+      @success="handleProcessSuccess"
+    />
   </div>
 </template>
 
 <script setup lang="ts">
 import { ref } from 'vue'
-import type { DatasetInfo } from '@/types/data'
-import DataPreview from './DataPreview.vue'
 import { ElMessage } from 'element-plus'
 import dayjs from 'dayjs'
+import type { DatasetInfo } from '@/types/data'
+import DataPreview from './DataPreview.vue'
+import DataProcessDialog from './DataProcessDialog.vue'
 
 const props = defineProps<{
   datasets: DatasetInfo[]
 }>()
 
+const emit = defineEmits(['refresh'])
+
+const loading = ref(false)
 const previewVisible = ref(false)
-const detailsVisible = ref(false)
+const processVisible = ref(false)
 const selectedDataset = ref<DatasetInfo | null>(null)
 
 // 获取文件名
@@ -142,42 +114,65 @@ const formatTime = (timestamp: string) => {
   return dayjs(timestamp).format('YYYY-MM-DD HH:mm:ss')
 }
 
-// 获取步骤类型
-const getStepType = (step: string) => {
-  const typeMap: Record<string, string> = {
-    'load_data': 'primary',
-    'cleaning': 'success',
-    'feature_engineering': 'warning'
+// 上传前检查
+const beforeUpload = (file: File) => {
+  const isCSV = file.type === 'text/csv'
+  if (!isCSV) {
+    ElMessage.error('只能上传CSV文件!')
+    return false
   }
-  return typeMap[step] || 'info'
+  return true
 }
 
-// 获取步骤标题
-const getStepTitle = (step: DatasetInfo['steps'][0]) => {
-  const titleMap: Record<string, string> = {
-    'load_data': '数据加载',
-    'cleaning': '数据清洗',
-    'feature_engineering': '特征工程'
-  }
-  return titleMap[step.step] || step.step
+// 上传成功
+const handleUploadSuccess = () => {
+  ElMessage.success('上传成功')
+  emit('refresh')
 }
 
-// 处理预览
+// 上传失败
+const handleUploadError = () => {
+  ElMessage.error('上传失败')
+}
+
+// 预览数据集
 const handlePreview = (dataset: DatasetInfo) => {
   selectedDataset.value = dataset
   previewVisible.value = true
 }
 
-// 处理下载
-const handleDownload = (dataset: DatasetInfo) => {
-  // 实现文件下载逻辑
-  ElMessage.success('开始下载数据集')
+// 处理数据集
+const handleProcess = (dataset: DatasetInfo) => {
+  selectedDataset.value = dataset
+  processVisible.value = true
 }
 
-// 处理详情查看
-const handleDetails = (dataset: DatasetInfo) => {
-  selectedDataset.value = dataset
-  detailsVisible.value = true
+// 处理成功
+const handleProcessSuccess = () => {
+  processVisible.value = false
+  emit('refresh')
+  ElMessage.success('数据处理成功')
+}
+
+// 下载数据集
+const handleDownload = async (dataset: DatasetInfo) => {
+  try {
+    // 实现下载逻辑
+    ElMessage.success('开始下载')
+  } catch (error) {
+    ElMessage.error('下载失败')
+  }
+}
+
+// 删除数据集
+const handleDelete = async (dataset: DatasetInfo) => {
+  try {
+    // 实现删除逻辑
+    ElMessage.success('删除成功')
+    emit('refresh')
+  } catch (error) {
+    ElMessage.error('删除失败')
+  }
 }
 </script>
 
@@ -186,7 +181,12 @@ const handleDetails = (dataset: DatasetInfo) => {
   padding: 20px;
 }
 
+.upload-section {
+  margin-bottom: 20px;
+}
+
 .el-tag {
   margin-right: 5px;
+  margin-bottom: 5px;
 }
 </style> 
\ No newline at end of file
diff --git a/frontend/src/router/index.ts b/frontend/src/router/index.ts
index 0494112..8ba15ba 100644
--- a/frontend/src/router/index.ts
+++ b/frontend/src/router/index.ts
@@ -9,11 +9,38 @@ const router = createRouter({
     },
     {
       path: '/data',
-      name: 'Data',
-      component: () => import('@/views/data/DatasetView.vue'),
-      meta: {
-        title: '数据管理'
-      }
+      component: () => import('@/views/data/DataView.vue'),
+      children: [
+        {
+          path: '',
+          name: 'Data',
+          redirect: '/data/datasets'
+        },
+        {
+          path: 'datasets',
+          name: 'Datasets',
+          component: () => import('@/views/data/DatasetView.vue'),
+          meta: {
+            title: '数据集管理'
+          }
+        },
+        {
+          path: 'preprocess',
+          name: 'Preprocess',
+          component: () => import('@/views/data/PreprocessView.vue'),
+          meta: {
+            title: '预处理方法'
+          }
+        },
+        {
+          path: 'feature',
+          name: 'Feature',
+          component: () => import('@/views/data/FeatureView.vue'),
+          meta: {
+            title: '特征工程方法'
+          }
+        }
+      ]
     },
     {
       path: '/model',
diff --git a/frontend/src/types/data.ts b/frontend/src/types/data.ts
index c8e442f..c8f9d8d 100644
--- a/frontend/src/types/data.ts
+++ b/frontend/src/types/data.ts
@@ -16,7 +16,7 @@ export interface FeatureMethod {
 export interface MethodParameter {
   name: string
   type: string
-  default: any
+  default: string | number | boolean | null
   description: string
 }
 
@@ -86,4 +86,18 @@ export interface DatasetInfo {
     validation: string
     test: string
   }
+}
+
+// 数据预览信息
+export interface DataPreview {
+  info: {
+    rows: number
+    columns: number
+    column_types: Record<string, string>
+    memory_usage: string
+    missing_values: Record<string, number>
+  }
+  head: any[]
+  tail: any[]
+  describe: Record<string, any>
 } 
\ No newline at end of file
diff --git a/frontend/src/views/data/DataView.vue b/frontend/src/views/data/DataView.vue
new file mode 100644
index 0000000..fec9f0b
--- /dev/null
+++ b/frontend/src/views/data/DataView.vue
@@ -0,0 +1,51 @@
+<template>
+  <div class="data-view">
+    <!-- 左侧导航 -->
+    <div class="sidebar">
+      <el-menu
+        :default-active="$route.path"
+        router
+      >
+        <el-menu-item index="/data/datasets">
+          <el-icon><Folder /></el-icon>
+          <span>数据集管理</span>
+        </el-menu-item>
+        <el-menu-item index="/data/preprocess">
+          <el-icon><Tools /></el-icon>
+          <span>预处理方法</span>
+        </el-menu-item>
+        <el-menu-item index="/data/feature">
+          <el-icon><Operation /></el-icon>
+          <span>特征工程方法</span>
+        </el-menu-item>
+      </el-menu>
+    </div>
+
+    <!-- 右侧内容 -->
+    <div class="content">
+      <router-view />
+    </div>
+  </div>
+</template>
+
+<script setup lang="ts">
+import { Folder, Tools, Operation } from '@element-plus/icons-vue'
+</script>
+
+<style scoped>
+.data-view {
+  display: flex;
+  height: 100%;
+}
+
+.sidebar {
+  width: 200px;
+  border-right: 1px solid #e6e6e6;
+}
+
+.content {
+  flex: 1;
+  padding: 20px;
+  overflow: auto;
+}
+</style> 
\ No newline at end of file
diff --git a/frontend/src/views/data/DatasetView.vue b/frontend/src/views/data/DatasetView.vue
index fd5e985..bb63b66 100644
--- a/frontend/src/views/data/DatasetView.vue
+++ b/frontend/src/views/data/DatasetView.vue
@@ -1,25 +1,56 @@
 <template>
   <div class="dataset-view">
-    <h2>数据集管理</h2>
-    <DatasetList :datasets="datasets" />
+    <el-card>
+      <template #header>
+        <div class="card-header">
+          <span>数据集管理</span>
+          <el-button type="primary" @click="refreshData">刷新</el-button>
+        </div>
+      </template>
+      
+      <DatasetList 
+        :datasets="datasets"
+        @refresh="refreshData"
+      />
+    </el-card>
   </div>
 </template>
 
 <script setup lang="ts">
 import { ref, onMounted } from 'vue'
+import { ElMessage } from 'element-plus'
 import { getDatasets } from '@/api/data'
 import DatasetList from '@/components/data/DatasetList.vue'
 import type { DatasetInfo } from '@/types/data'
 
 const datasets = ref<DatasetInfo[]>([])
+const loading = ref(false)
 
-onMounted(async () => {
+// 加载数据集列表
+const loadDatasets = async () => {
+  loading.value = true
   try {
-    const { data } = await getDatasets()
-    datasets.value = data.datasets
+    const response = await getDatasets()
+    if (response.status === 'success' && response.datasets) {
+      datasets.value = response.datasets
+    } else {
+      ElMessage.error('加载数据集失败')
+    }
   } catch (error) {
     console.error('Failed to load datasets:', error)
+    ElMessage.error('加载数据集失败')
+  } finally {
+    loading.value = false
   }
+}
+
+// 刷新数据
+const refreshData = () => {
+  loadDatasets()
+}
+
+onMounted(() => {
+  loadDatasets()
 })
 </script>
 
@@ -27,4 +58,10 @@ onMounted(async () => {
 .dataset-view {
   min-height: 100%;
 }
+
+.card-header {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+}
 </style> 
\ No newline at end of file
diff --git a/frontend/src/views/data/FeatureView.vue b/frontend/src/views/data/FeatureView.vue
new file mode 100644
index 0000000..c8ef8d2
--- /dev/null
+++ b/frontend/src/views/data/FeatureView.vue
@@ -0,0 +1,202 @@
+<template>
+  <div class="feature-view">
+    <el-card v-loading="loading" class="method-card-container">
+      <template #header>
+        <div class="card-header">
+          <span>特征工程方法列表</span>
+          <el-button type="primary" @click="refreshMethods">刷新</el-button>
+        </div>
+      </template>
+
+      <el-scrollbar height="400px">
+        <el-space wrap>
+          <el-card
+            v-for="method in methods"
+            :key="method"
+            class="method-card"
+            @click="showMethodDetails(method)"
+          >
+            {{ method }}
+          </el-card>
+        </el-space>
+      </el-scrollbar>
+    </el-card>
+
+    <!-- 方法详情对话框 -->
+    <el-dialog
+      v-model="detailsVisible"
+      :title="methodDetails?.name"
+      width="60%"
+    >
+      <div v-loading="detailsLoading">
+        <el-descriptions :column="1" border>
+          <el-descriptions-item label="方法名称">
+            {{ methodDetails?.name }}
+          </el-descriptions-item>
+          <el-descriptions-item label="描述">
+            {{ methodDetails?.description }}
+          </el-descriptions-item>
+          <el-descriptions-item label="原理" v-if="methodDetails?.principle">
+            {{ methodDetails?.principle }}
+          </el-descriptions-item>
+        </el-descriptions>
+
+        <div class="mt-4">
+          <h4>优点</h4>
+          <el-tag
+            v-for="(adv, index) in methodDetails?.advantages"
+            :key="index"
+            class="mx-1"
+            type="success"
+          >
+            {{ adv }}
+          </el-tag>
+        </div>
+
+        <div class="mt-4">
+          <h4>缺点</h4>
+          <el-tag
+            v-for="(dis, index) in methodDetails?.disadvantages"
+            :key="index"
+            class="mx-1"
+            type="danger"
+          >
+            {{ dis }}
+          </el-tag>
+        </div>
+
+        <div class="mt-4">
+          <h4>适用场景</h4>
+          <el-tag
+            v-for="(scene, index) in methodDetails?.applicable_scenarios"
+            :key="index"
+            class="mx-1"
+            type="warning"
+          >
+            {{ scene }}
+          </el-tag>
+        </div>
+
+        <div class="mt-4">
+          <h4>参数说明</h4>
+          <el-table :data="methodDetails?.parameters || []" border>
+            <el-table-column prop="name" label="参数名" width="180" />
+            <el-table-column prop="type" label="类型" width="180" />
+            <el-table-column prop="default" label="默认值" width="180">
+              <template #default="{ row }">
+                {{ row.default === null ? 'null' : row.default }}
+              </template>
+            </el-table-column>
+            <el-table-column prop="description" label="说明" />
+          </el-table>
+        </div>
+      </div>
+    </el-dialog>
+  </div>
+</template>
+
+<script setup lang="ts">
+import { ref, onMounted } from 'vue'
+import { ElMessage } from 'element-plus'
+import { getFeatureMethods, getFeatureMethodDetails } from '@/api/data'
+import type { FeatureMethod, MethodDetail } from '@/types/data'
+
+const loading = ref(false)
+const methods = ref<string[]>([])
+const detailsVisible = ref(false)
+const detailsLoading = ref(false)
+const methodDetails = ref<MethodDetail | null>(null)
+
+// 加载方法列表
+const loadMethods = async () => {
+  loading.value = true
+  try {
+    const response = await getFeatureMethods()
+    if (response.status === 'success' && Array.isArray(response.methods)) {
+      // 获取第一个分组的方法列表
+      const featureGroup = response.methods.find(g => g.name === 'feature_engineering_methods')
+      methods.value = featureGroup?.method || []
+    } else {
+      ElMessage.error('加载特征工程方法失败')
+    }
+  } catch (error) {
+    console.error('Failed to load feature methods:', error)
+    ElMessage.error('加载特征工程方法失败')
+  } finally {
+    loading.value = false
+  }
+}
+
+// 显示方法详情
+const showMethodDetails = async (methodName: string) => {
+  detailsVisible.value = true
+  detailsLoading.value = true
+  try {
+    const response = await getFeatureMethodDetails(methodName)
+    if (response.status === 'success' && response.method) {
+      methodDetails.value = response.method
+    } else {
+      ElMessage.error('加载方法详情失败')
+    }
+  } catch (error) {
+    console.error('Failed to load method details:', error)
+    ElMessage.error('加载方法详情失败')
+  } finally {
+    detailsLoading.value = false
+  }
+}
+
+// 刷新方法列表
+const refreshMethods = () => {
+  loadMethods()
+}
+
+onMounted(() => {
+  loadMethods()
+})
+</script>
+
+<style scoped>
+.feature-view {
+  height: 100%;
+  overflow: hidden;
+}
+
+.method-card-container {
+  height: 100%;
+}
+
+.card-header {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+}
+
+.method-card {
+  width: 200px;
+  cursor: pointer;
+  transition: all 0.3s;
+  margin: 10px;
+}
+
+.method-card:hover {
+  transform: translateY(-5px);
+  box-shadow: 0 2px 12px 0 rgba(0,0,0,.1);
+}
+
+.el-space {
+  padding: 10px;
+}
+
+.mt-4 {
+  margin-top: 1rem;
+}
+
+.mx-1 {
+  margin: 0 0.25rem;
+}
+
+h4 {
+  margin-bottom: 0.5rem;
+}
+</style> 
\ No newline at end of file
diff --git a/frontend/src/views/data/PreprocessView.vue b/frontend/src/views/data/PreprocessView.vue
new file mode 100644
index 0000000..5c2e518
--- /dev/null
+++ b/frontend/src/views/data/PreprocessView.vue
@@ -0,0 +1,253 @@
+<template>
+  <div class="preprocess-view">
+    <el-card v-loading="loading" class="method-card-container">
+      <template #header>
+        <div class="card-header">
+          <span>预处理方法列表</span>
+          <el-button type="primary" @click="refreshMethods">刷新</el-button>
+        </div>
+      </template>
+
+      <el-tabs v-model="activeTab">
+        <!-- 数据缩放 -->
+        <el-tab-pane label="数据缩放" name="data_scaler">
+          <el-scrollbar height="400px">
+            <el-space wrap>
+              <el-card
+                v-for="method in methodGroups.data_scaler || []"
+                :key="method"
+                class="method-card"
+                @click="showMethodDetails(method)"
+              >
+                {{ method }}
+              </el-card>
+            </el-space>
+          </el-scrollbar>
+        </el-tab-pane>
+
+        <!-- 缺失值处理 -->
+        <el-tab-pane label="缺失值处理" name="missing_value_handler">
+          <el-scrollbar height="400px">
+            <el-space wrap>
+              <el-card
+                v-for="method in methodGroups.missing_value_handler || []"
+                :key="method"
+                class="method-card"
+                @click="showMethodDetails(method)"
+              >
+                {{ method }}
+              </el-card>
+            </el-space>
+          </el-scrollbar>
+        </el-tab-pane>
+
+        <!-- 异常值检测 -->
+        <el-tab-pane label="异常值检测" name="outlier_detector">
+          <el-scrollbar height="400px">
+            <el-space wrap>
+              <el-card
+                v-for="method in methodGroups.outlier_detector || []"
+                :key="method"
+                class="method-card"
+                @click="showMethodDetails(method)"
+              >
+                {{ method }}
+              </el-card>
+            </el-space>
+          </el-scrollbar>
+        </el-tab-pane>
+      </el-tabs>
+    </el-card>
+
+    <!-- 方法详情对话框 -->
+    <el-dialog
+      v-model="detailsVisible"
+      :title="methodDetails?.name"
+      width="60%"
+    >
+      <div v-loading="detailsLoading">
+        <el-descriptions :column="1" border>
+          <el-descriptions-item label="方法名称">
+            {{ methodDetails?.name }}
+          </el-descriptions-item>
+          <el-descriptions-item label="描述">
+            {{ methodDetails?.description }}
+          </el-descriptions-item>
+          <el-descriptions-item label="原理">
+            {{ methodDetails?.principle }}
+          </el-descriptions-item>
+        </el-descriptions>
+
+        <div class="mt-4">
+          <h4>优点</h4>
+          <el-tag
+            v-for="(adv, index) in methodDetails?.advantages"
+            :key="index"
+            class="mx-1"
+            type="success"
+          >
+            {{ adv }}
+          </el-tag>
+        </div>
+
+        <div class="mt-4">
+          <h4>缺点</h4>
+          <el-tag
+            v-for="(dis, index) in methodDetails?.disadvantages"
+            :key="index"
+            class="mx-1"
+            type="danger"
+          >
+            {{ dis }}
+          </el-tag>
+        </div>
+
+        <div class="mt-4">
+          <h4>适用场景</h4>
+          <el-tag
+            v-for="(scene, index) in methodDetails?.applicable_scenarios"
+            :key="index"
+            class="mx-1"
+            type="warning"
+          >
+            {{ scene }}
+          </el-tag>
+        </div>
+
+        <div class="mt-4">
+          <h4>参数说明</h4>
+          <el-table :data="methodDetails?.parameters || []" border>
+            <el-table-column prop="name" label="参数名" />
+            <el-table-column prop="type" label="类型" />
+            <el-table-column prop="default" label="默认值" />
+            <el-table-column prop="description" label="说明" />
+          </el-table>
+        </div>
+      </div>
+    </el-dialog>
+  </div>
+</template>
+
+<script setup lang="ts">
+import { ref, onMounted } from 'vue'
+import { ElMessage } from 'element-plus'
+import { getPreprocessMethods, getPreprocessMethodDetails } from '@/api/data'
+import type { PreprocessMethod, MethodDetail } from '@/types/data'
+
+// 修改 PreprocessMethod 接口以匹配后端返回的数据结构
+interface PreprocessMethodGroup {
+  name: string
+  description: string
+  method: string[]
+}
+
+const activeTab = ref('missing_value_handler')
+const loading = ref(false)
+const methodGroups = ref<Record<string, string[]>>({
+  data_scaler: [],
+  missing_value_handler: [],
+  outlier_detector: []
+})
+const detailsVisible = ref(false)
+const detailsLoading = ref(false)
+const methodDetails = ref<MethodDetail | null>(null)
+
+// 加载方法列表
+const loadMethods = async () => {
+  loading.value = true
+  try {
+    const response = await getPreprocessMethods()
+    if (response.status === 'success' && Array.isArray(response.methods)) {
+      // 将返回的数据按类型分组
+      methodGroups.value = response.methods.reduce((groups: Record<string, string[]>, group: PreprocessMethodGroup) => {
+        groups[group.name] = group.method
+        return groups
+      }, {
+        data_scaler: [],
+        missing_value_handler: [],
+        outlier_detector: []
+      })
+    } else {
+      ElMessage.error('加载预处理方法失败')
+    }
+  } catch (error) {
+    console.error('Failed to load preprocess methods:', error)
+    ElMessage.error('加载预处理方法失败')
+  } finally {
+    loading.value = false
+  }
+}
+
+// 显示方法详情
+const showMethodDetails = async (methodName: string) => {
+  detailsVisible.value = true
+  detailsLoading.value = true
+  try {
+    const response = await getPreprocessMethodDetails(methodName)
+    if (response.status === 'success' && response.method) {
+      methodDetails.value = response.method
+    } else {
+      ElMessage.error('加载方法详情失败')
+    }
+  } catch (error) {
+    console.error('Failed to load method details:', error)
+    ElMessage.error('加载方法详情失败')
+  } finally {
+    detailsLoading.value = false
+  }
+}
+
+// 刷新方法列表
+const refreshMethods = () => {
+  loadMethods()
+}
+
+onMounted(() => {
+  loadMethods()
+})
+</script>
+
+<style scoped>
+.preprocess-view {
+  height: 100%;
+  overflow: hidden;
+}
+
+.method-card-container {
+  height: 100%;
+}
+
+.card-header {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+}
+
+.method-card {
+  width: 200px;
+  cursor: pointer;
+  transition: all 0.3s;
+  margin: 10px;
+}
+
+.method-card:hover {
+  transform: translateY(-5px);
+  box-shadow: 0 2px 12px 0 rgba(0,0,0,.1);
+}
+
+.el-space {
+  padding: 10px;
+}
+
+.mt-4 {
+  margin-top: 1rem;
+}
+
+.mx-1 {
+  margin: 0 0.25rem;
+}
+
+h4 {
+  margin-bottom: 0.5rem;
+}
+</style> 
\ No newline at end of file
diff --git a/function_old/data_process/__init__.py b/function_old/data_process/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/function_old/data_process/__pycache__/__init__.cpython-39.pyc b/function_old/data_process/__pycache__/__init__.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..8fb5816cb4c0b4a7e9253c38089fb65695737abe
GIT binary patch
literal 151
zcmYe~<>g`kg6liiri19mAOaaM0yz#qT+9L_QW%06G#UL?G8BP?5yUSW{fzwFRQ<%1
z+{`@PqWt_4{fxx?lFY<BeP5q|oWzo}{Gwd_l*E$6_=2MR<kaF~{rLFIyv&mLc)fzk
UTO2mI`6;D2sdgY!KLarX0KJbSzyJUM

literal 0
HcmV?d00001

diff --git a/function_old/data_process/__pycache__/data_cleaner.cpython-39.pyc b/function_old/data_process/__pycache__/data_cleaner.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..553627f6f99b4dfe503e490381c449d6567a242a
GIT binary patch
literal 2919
zcmZuzTZ<gW6|U;(+uYZymE)CUdu(zWC($aG2P2GQu<T%P788+}^h?v~s+sLoU&d9{
zig)N0MpB|c*pQbH97`}F`(i^v3<)TSenFo6T(4nQ>|Zc}<eci6-SNsj^r`Bus?+Dx
z_tkeM>ULWMuIZyck3WOnfAC@Xvf<%1xFrL_2%{;<Xh11p7Hgzd&@inXIMCXun|Xnk
z`GIf7owS*?f|lvKX*=r#9n<&HZq^HWl>CS=pEd6g*5vedBj~fnRWfWHQTWu5>h6_D
zMem3r=28~o2wsxSp{4CBNvyQ}b|Mu{x|(E@l)sftO2q}d=)Wb4G*U^CzgY-w<~UMC
zO2+75`EutEvVsmL0c9kx7=@Hpxy>5)=v^|R%x2D=E~IycyW1Z3d6WC=1pCapXPfYy
zpvBhA=*d{?UW2t+=Z+J!+1dHZj#<@*RV(Z%80p?6HVJx=^3%GFxxSwADCeT=Lp+DS
z|Lfu2Uk)Gs^6+nec>L+VHX$=NF7i<_j;*C6u#b5(;Fd3gQRFt6(TY9*h!kYQtUU@X
zz+_r`-U3{El)3lpii8bDAO>$!+ZlWxKIBU!BE`o$+RZpiqFi^gLaJ~i_<JSKmG&VL
z*wb7MZPA90iY^#fUN9~&_@S*GSx&gnei$ZsqQX#Ml=^IzNSWm0@J5uDJj}S-Dwsr2
zB~M2JsrWI~%`lA9NXjt$n0)@)##WK>jfiDQ{vA;iYGW%Z6a=;L<G0@dphtzsHW=()
zIH{>pKg9K3UYzWRRq)z@TcRPfWBJtl{ySY;+VzXakzz)WfyG9cKSrp%xJb(^m)aFv
zl_HPvSS&8g3?qLXZutqA=~mTXv?Ss}MYoBf+t%3Nu-({gR8~c{?Hg45KsgMaJ|g$6
z+w>O2x0SU{cJ0cZxfQJ%>*N98ST$ZDFy_sC2IC(Q=G<=}wiSIBP_v0@?(9>t>rgWN
zs+refu4-4#ZHk_8<}LCr`8gciUFW8gx9av1xdd+zbwjp;{X36;_p8T`{&}$f>A?q&
zHUR@K$>X$Se7g429H5*OLUA^zx8w3)`qI@h#&bC;({yLB73D0&;Tqk6L01k+gnIC~
zH(xe={tY1tQP0MaFHXNa7<P0Qc)(*7GPN_|Qd{{%yLp*i<3gN=ofT)m=+@7WJ;s^t
zj(}Z2*IXhIw3`;=G4Re#@=>9iZ@eG#32K3Mz(XN)1E@W8#TxorM{^Dhx(+-L64Ve)
zx%djcHRc)U>9ci$;TPB|&%%(zabj7(s8y>)dvLE>Yt*%R^l3VMVVPfF>SNe2VQ5#D
z*Cbcs0(gt@FfT3#I>+Qfp_*PsQUQ_ZHm%@*@6lZ(k2QlM4zvT>;5fF=5TJ{FiZ1rf
z4WNrXr;9ann4{dveu6IUu6@%6x|r6`#XX_RuV+Ue?jPOVJJ{a?x(uoKHU{SZglEMK
zpn<>yru_jcCutIck_<%g3pqVs!!K|a!hbw0FAp|{9!SPkG~v3>L@^0Z2F2IFoA^4K
zZ=m@mnjx5>vxFl?pnHW##z`Kfp>ZW%!l|dQe9C;EFMR+V$`vq(qf0yVMX(0HXP5DN
zVx4xUGKLy+gz1739`i{z)fSYVts-SLpv!9E!{lQ?KZA$qZxP1pmUvl#aw`B50JIg^
zc52ml09uZ!P&KaG+b$@%4UjweMOfv)s*&=T%RJ`qS-WoK&ivD>S@XKJ>i|WXvleSD
zw1Ksansn|vwVG5;pR9vY7)|Ny{2NH(%}LUnby-*SD(?xB^me_Q9+1Seh9p?c`gH;O
z(+7ut|INXpTL%vx0!hSoAyx4#nt6G*qxTaTtR#za9l`;IdOiN*hj{(thewDWl!h)8
z8x?{2o1(5eaMoFog;>-1(f{C@Hm`66q5;gCt_+G&r3n`c^%2kG7N4uB$ILwB-eMLq
zuP<JJIl2*DlLFDHLmgo6#d;v$5gzv1C^i!TH8EBvv;<Kpv(w!4m$+#(=KJ6v@TZ}n
zjMV-jf}jOEFwgx<3EQuu4i^j1(UR<3psOH09eU1s4oaJ$?fGTeo?1Pm@E^()ZTL%p
zU4zT_z~``!)jE$d9)`LVhEUDR6#Jbpe6Nhs`G^;WtcanYBdJYo)z*aRCVulx0jtf~
z6sTL`TWBtU(atC>A|+nMes^BpW1gnq=j42%pb8XJ(FB9H#FOGv+gfWrcjiLdydSRU
z9$TvSg%J2JNV^jtMkEE6VeLTCfYNV(b)l93=5@drm+r~y@b^IE7w3|X6+Bp3yyUs$
q*|n6{m^(5~z>^^chO`v#NrCWRsdwvD<hJaA>6rf*D*z1qtp5W*X9siu

literal 0
HcmV?d00001

diff --git a/function_old/data_process/__pycache__/data_processor.cpython-39.pyc b/function_old/data_process/__pycache__/data_processor.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..8a8485f39361e1a1018d9b71fa2c51a1e02ed84e
GIT binary patch
literal 2492
zcmZuz-HRMW5by5!*xAoq?kkEK*Qnse<Sv4WgdmY<L`W{dBMHvSFxl?Co6CIJ(;IWk
zMld;i5EKz4f(h<{3W5phgAYm!_~hTvuX>683qGh-J-6}hNW)ZjSJm{?$FHg<Y&L5I
z#*aVTTzbzV<agX`9Tsek!c%+#gcD9<;!`s---4ONcH;O>;`(k<@hgevdldDoxSG`b
zT2lAxNyBd#o*g%nmftdKC*GAz_!DML<K6ylbLON!39}ndB~$*?rfk}uHnJIi=5@j=
z+*>2uyUP4oP8Uh1`WM(m7CN@JUyZs-+b5zzY3EEDWvTW~<qGC7?pV6DsKS(ok}r0{
zSV-MC8Koz~OXJ;}+4+8<%3X)*=3<oOv3MiN`$|Y)Oeh&fX`n=*f+CM21w4<3N~kCi
zU9@5Auwio)p5g=$VIt-;P9b6~VRP#`<u-TLAa2~{l{MnKq9VMND)+84Ugfnl+ppnX
zRCpaY4c-J!oip%vmu|iqs_?YTx}qpD*`I_j-2L>syC2@#_;T&u$M0`^@zcHUe_jCd
z+-{ckqNOeajq$)Wrt}y*#XcZIn!6Dhl7J{WV#->lu(pR}<g61+0DO`zbX?g4U0sQ@
zrKKoc($yuQPQV)C=mkL<CL##5i&EgUf<mZ%9&9Rin6?WM_skLB5IGGe{r$@Pa+Zks
zkS9@kP-dB$Uk)=Bh3Wjs6Q|=)^)i{vLwLg=H;!(u$6n9ntN7t4jZ_d!pf4^ELTj`^
z2eaD(G&ff3QdHR-xW*)zIG{y}tWbC$Nt}Jiz;g>cxBCqc{dwz`d$(`hz4q0{ooj>V
zpMEARx|sA%(LUII`WbY7a~X?^BHpr3AVc92NFfA{5o#A53)Mo$k}Wt|*UyJV)IDYr
zrR_Hsj-TpKIRz3ErjpFy7SoK20*aInW>cH8e+G~4aCK+ktGy@|K_04Q?Mg_BOt+!I
zfupeeO%#5E#o+xR9YK+=Llhn+Bf3s5vmxWw1tt$Gwqgxwk0M%D?2*Imh^(_O=|}Xk
zmA(jC4rnbXHgbpXKJfMd&jsFj;8iwxE#>jbkbO>Wu&eY6U~Q#3s&Q{fk+V)I8CvH6
zb2d@+)n6&OY*R9L%4jusRW*n9)%%)P$T{*B;kC>5yLMVD=R@QWa3FJalevu#Mt|PE
zT~>#tbASB{LtEYAqF)07agkwC=nBkl_XYHhW!`&Xu;)x#^z%HEO7J$uudP;dakxF$
zyV&ny(e?UqyxNYlkb?qZwB3_g(jH8|CS@j#0BXcY4!0LNE$x_w0T9UEf%0HE*Paw1
z55R`9t}G}g-7vhdEu{t+q-$rxxG&7vayR5i+fmxfboI4MU18drb_9M{TZNJxr$o;q
zs90tnt=9|=qGAWAbQPTl(1k}qzd%A5qm$I5d*Nx|!&+>Tx~xTK>0r-xxZQud!{j`?
zD)FmbY%k-n4Pf5_cd#;KI{;=4Ed#IvL%M=sgU*NrnC=HY!sjSJ(i$3Yq_e=Q0Pig5
z+Mw(4D(V72oRQ0GC9n`i=SX@4KvY@%dJBl0k;m(*`T!6$HbG=&1EL0isA)j-$DJD+
zH$N*uBp(AG<X$9?133;|)`?OsF3C3Xo&ch4j3)@J3u1Nf$TrLr;l(jzRMs9$m4E^6
zR=m_C_GS4bp5>|xQKD-wkCA~qz=gqr+>ffyA~}HMAdoQx?q@{Kq3942>~#M(6<tMx
zO#V??JOpH%|B21~x7h3hbASI$ydD}7d$6trL6Y%4beuppg5d3bXu2WnDnY=rZV*Vk
zf8;C@Y-q+_`4qleMQ9y|dKB_Gl)QxGe{;>sG(zmico`MgxIAjJ3CF8UPD|u>_GmZ9
zTfQg{b<%zUHw8;`h~#PxQ7#QYh)Qh#5&`PZ6c=I<%5*N5A}_BPRK+VrR*+!N^;=^t
z_%pztf+{lijG5rLh~eUk1zZkUD$%;K#aEWYVmXe^%Q~>My;8uB3Cjv&@Pj<m-jOnj
YFXJUuV6Z$$#zS-(3KC1QEKHC62P?si+yDRo

literal 0
HcmV?d00001

diff --git a/function_old/data_process/__pycache__/data_processor_date.cpython-39.pyc b/function_old/data_process/__pycache__/data_processor_date.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..0d8123d5ebe5f09ae7e7e764963f4bcedd8769d3
GIT binary patch
literal 8675
zcmcIpTaX;pdG6cv^jvrLzPb;R7PLZI2}}Z!6=FaVQjit}$q+iWht{0l)vWq5I^DBq
zCq39k0+zC5<O{~Omej7xRKTe~Qcjhz9g`Pc{FayGp<lyFC@)S`Di0yX<oi$0%+Bf(
zQ$=N_`tSc-|8x28Z50Yx3BS*O@Y9)pxlfY*jS9U#6@@S03AW0T#3Uv=k|~R~Vybv6
zj^?J!l&hP%n>N#~VH$GMFJorVt~yyaXXe^<c{7hX%_+D=v*`AjeQwDtx&3CpJ75mD
zgXW++WDdE*=CC_rj<}=ds5@qkx$DezVtmS3?`|+RxEsxlqO3cc+|A}@cZ<12l+#Yx
zy~Dgi;D)o+-DYkRc*fc8j+^7|o#vhHUFKcx4s(a7&pH$CPIITgbI#rFE_0W_^UiK}
z(wr1{!P(>PHTMd<=-lJpYu+nx+4-FLxkn||$4VC@Rywbk_c8f|G|_*ZPH$>Li?su_
zY8Y!rYe5*NPB!X}9UG6=!<z3|&V(Fm$F1=6L_RK_2rZ9UoSmpzj?Lrzv6^?xI@c*Z
z;h$;*VY`%_^0{j{wI=#y9<F&77ij*db;@=QdR3pHq4XG9f&;an%I#3J4<2fGRU&+n
zTV61YIjGxl|5=;&)(rkx!}7wKWA|1L9QU1h&v$E<bI7*B2DgK_@VI9m_QN*82_-JH
zn+{vSX-r+Doj++;Ltm^99dajZ2j#~ews9Eh6Ne7s0Mz4;JcQSn?OCTByHX2nZiTfu
zU~avE0*<h70=Q!zNh;#fkxrjZP4=;=sSaK`RttifH*>^ewW<Z$n7r>u;5(Sr_YV13
zd5EeU7XOH21;L3YkD)kl)W^9$-UywV%@0|$X4IArI!+CDRXym<*^XbgsV?MJ&8vi%
zrV`YhT3Dr<?)@1kd;w3e2w)32F%>35PKIoasf#kxSn2|#h3PDPK{9najlW@Q>!dc+
z(9c-ZS%zgVXlBOF&gN{5Aj>VPEYAw4&EHU4WPPYDuwhYOw2OA1z-TO<X?2~%`WH1e
zzy?9P#1wGpNL)Bzh1PNISM4D1d7}?2zWVClUA^@7%8xHxyZqv{zyIYF_N-TZZ@M;9
zRnXk|5njae2%dleL~>oPNs&~MLU~CE)nysD7D-E~Wl5GoJxqs2m<h9CF3g98uo(7*
zrLaF7VDe%CJqN>~a5x+ZN5ipjUAR8n5N-@Ng`2}IOj*pMz06dsSZj=d)XKu^D}Vis
zm5bl&UF*sZ-kd1#b!g`632Y#+k-#Pbn+a?oP$rNjKsUuR1W5bw9Kb}L=LsJmP#{2?
z<a98+M4+F*Ab}wQqXdQti~vkc+`+fu9j6_CW(HhnW@ha0C~(MwQK@*AYga0<POT&%
zmB0=g^-8<*XI^|fT<3N@xlItSxORBjXTfLLQM_R~k@t%2VMDgfdnSfRYk}=di#@+3
z@w>70j~?A~+IQ_e7ISOfZtnZxp3{~e)+}$&v7^T!g`{})FtA;vz0x%WpI6XkPuAz@
zylP%8tW@ZXgZ%)Kl9ltaky2#wS8jOA%6}LmsH5L%j|Bfsb7T#xPj)7+!k~43Wae}{
zf~lVY62jD-ms@fq&&o_;>LnShtSqS!ggDe@HDYd-x}q`pb#;TZEVq<MS<=xX&Gcn?
z8NDNE)>z6!N*B+D%508GEDeS>8pLiNzWv^{U%h?xwKrD&>9wXd34S;Uu`}#*uo@Nr
z48*nPyyyZxDvUop?vAs{_~G$m<0qQ;jqk7mD0kPM2+F(5<2#7c+NfhgdG(ZC$htLy
z)+sPM?KV!iXIPE%?ZD04A*lYtutj8r47v-NHC8?USu+oIg$8x45E?knbWwgMjm%n%
zwFjC8dLAXZv36wY(Bl&--${f>EGi&n=BGiWaylU+_$C3n(2L&%a0pL85+*5zoL4k?
z<P%NRWCJiSH#gpJmutjmLXWdG55}WXhi#3sej}s;$i{tbmg`7H+}Gjmwy4B;q0=#v
zTW%2Ru$>L=Rq2#EKaz7&7lKD3sKLuhb7v$kfm4>jBkLq!P<{;RyrqY71l2z(Mf#`&
zK1xUFS%szW*DopH4LMY2)g^6ND9K2Tv?w(LzF5>-2KYt?7a5U!MS5LuPe^<O8m&xZ
zung#ASvJZDqmXcydO-T}y{#-%Za&IH*=41tXFkfZ!a51C2uP#)7B%9+vlk<+JFalk
zxYBLMy^j?Z(Lc4+$NJg8vLdiS!r0Iy^-F3i*UGmF-5r+LFxFm-(rhHsuSje(DgutZ
zp4uR_`cS*>rrHu}*WXmzALVBIqdvBQZ4_siN2$~;6;SH$l){0i@4O6H60rZg%r-5m
zIK9pLCCt60XYR6C$3Qq34X``dR<`Yu`pVW8jMD6IWJH5(JLVj}q{-4#61!8AH0iu5
zOWwdexcxxe3j;_0r}4D!?XD=@xi_|hO@QXkMfEA^1V)A<mzDWBS!xZ*Qgbi68|xc7
zFK)RtEJlw;I4S6dUC}Vxy{J3|mGm^IwuYV?I?;abmG%OI{+Mk17Zg~w-2NqIJ28vb
zue{i;?;;QJnP6YHM59(kWncNj_rA08!W+r(4}bQ~%6k{qbX}FCr0Yw+xOV03m0!KO
zrc>3iEw9H&>?<epU48e3tN-xY)$jfM>Q7%?S$OTk<u`xxj~B1L^U4SB{v@fq`u%r4
zc=u~4uKew5D=)l@)|HDdtX%$^L^Or%T>19JL^9V<yg`Qdm9M@0^Og6$zVfp-uD$t<
z{||z_I-;{Zoc7AXw^tTkTzTbrY`DAn#8HF;j<wHOP9*@kX7$~|6GGSAa64^3?3drU
z`d5p|xpez~B=5QY34XCW$;pVFggH**cx*2W_#`S;6(MQcI75m&2rakHA3!VrBLe#X
z;#3gY^`HqS*kZW3GFhAQH22*ye;Dm%#z6zwWlLCmbjFa=R^2v@&TYrJo@<Kr<d!Bh
zPFgb7lQvFDogbhX2RnDx<5ggR!l}jqUHjn===bYCiH**gO(^^@4gXUDduR?l@x)`f
z0+U${=1h(Hnkg~MA=uAU&13et2^Cf3vzuA8*RTu30kKBC;(VK<>3jmS)UgiSuKJu+
zD$Ug7Y=F-4v&~c^oZkI_Fv=8Q;gqhE2aNO3iHe80Y%f4uRDm6?)ux)e$V8P_ow0J&
zrywS@*<|?%J7_pzP!6m)o0UVq9H)aum3;8#owprUZg-h(IL`cp8tb^quo1-RwmpxF
zYnR_#e~@#Z_b!2M5T<fpIZoNshBN&l9p{s@lQG;W#WTVs;Cre59s>6Q#F<*)ljCNE
z!q&%H&71aPrOr%)+u#ixf2>>ey6rJ>!SP51C1<|l<8=-0aJ#;9{|RT1Crq>jk70$e
z3b#2nf{;%W)8eXqK|)1MtRWD?1&W)|Si`NynS<x5wuq_upVL-Ggtx)}kd}WxfgAWe
zBfJlCiOgJ^1ISh2PtjHtHq9R;B%AOT9a_SM0!x^bQ2r2lneARQ-W1F#u%wqjb8T*-
zLM%_mG9*!)e#H%DZg7289hCM}odk*CIRI%`Q^(YjT+|e}z-{;TBRxAHXJrFr?RSO&
zM@ititjpSOvp1DB^vlZGkMrr0IwIq*6lMH1>aTyCO^?VW`Cer}6|;YA=%5DI3#H#R
zHyyx+k9Xq4$quKrR|)s7h9!z)<DUmsB}cmRqbRHEF#RhE&2N%Z1oueA8xB)TgX<&B
zN^>&b8OltJR5G3C<>wJW&Pov?*J%lnrS@a_n{q1^sZ5)b_*dX=DC7>Y)ETv<M{=ZN
zCfQpLhXZcZQi|H(wxeYh&iEx2PP}l%Svr}YOl%~#O>%brpJ9;GFvvSauN)jNtb%32
ze3TZ(SvX72!~DY(XIts#(jMF|dJ9vWg(=Q8DCAuE#doiL_szBi{?UcDK^9hzA4I!Q
zg3Zle^v=Me_8^@-0b4ndhJ9ry&RYeoe~j^OLCIHrr{Q`5KT3zW=^+SO4SM8OQ<a<B
z6D=U5k#zeldwrzrD^DSM-hm0@?30$$u*EPlHw~f05ad!q{v~S75GNdhcWlQ6YJ`v^
z$t2FvES4lx1pf;v&JZA(<W+zPBN5D1X6c?toN4ov4*_?r;0*U@6h)Lhk-=9`{576{
z0uBkRX~+g*!lE*y8erxuMF_GcYai?SfUKitqukuSmUVBfm)0;W<pGFciHQRz@$k#5
zEDQf$sY&pzHN<-G^(i)7R$d09f^`%y@q-~)bPW?LYnk|ElvxT){O^&xAi<N@mL<X1
z`Wb~^T#(?8kF@j!1x%bGwgw~Py<a-Zz5Pk;vi!0f>I-t1o;A)Z{QWR9n_ZA!l3tRh
z6^5wcf<d#KCjrQ@%q8_@d4WVnp3N_SeJ>%R#fSogCN-n59Lrx)TJmMt+lqA+=A_Fq
zKPBjh)xm2|FDSD`Ry?DiW$R1Iw2XvjmqyF*imZgPl+bJ;%`=;g((s$x)PEmk?<b(!
zFX+C%mM-F@K9+-EXOcOQz5<=F6lKoKz5DyU6b`SQw>{h7>Z(8OT5-qyO9O1^7D{9g
ze*HAmNVcs;`j>{-uuvl-;c%3_NsWxQvd?9qM#NjFkx{6Tu_VPM)X2?_?5YkC^48qm
zQ6z1HTJCYER@I5plLDfA!!45@l++5yX3ijp`SK)KL|UM<2N*O|7QjsF@qjf4kmNwP
z!Vua*PpjWj&u%`eVd2Vk@<RDz0B}!I&<n_Mk+&DCj_tjr#>(X0ScUG2<r+K>QWtUB
z7U^oXD&ui>zk{p?c}ou>oRa<%-K6IIw-n;FPQ>JXhmyF#gFren@Us{_At$<NUf`x?
zA+3Ts%I?Lw@7bsQ@b(9?6TQTNY!wG0%_1Mva|lxR5C+5{$jSZ{-o!XF?Nv@83t!=p
zAkCk}Yjvyq>nIkmNB%sJHA^7hQp0lsPcQ-?mQbWb6iy!2@moql&P)>p&rVM8Erqwx
znUlwGqwXYPeH~)3*rU{^o4NdS)EO)$+2$^FqjLp<8g5mP|LSeX<NM5K+G~E*+O#*!
zFWiO{KIbH)n%g?|@%9o@ZtlFnO8y^xc>t1A@G&hSEsWj-VIe@QRsH%rpCdF|!)FNi
z=w8*16|Wwr>GKY^=7kyM4H`oB+te8M>mtRD&lRzr2!xOu!9%w<rn%c1Q!~w`@r43`
z9x;NM>)L3WnT5`ck^38%S+CNr2v#jFxI^sgYqUtgvm!57LGeR80X0g<$&tfZ?Al*)
zJ`FgPl%pkAbAaq{it=@+gDuX>LrM{&$i1W%DpP${^e%Pkw4x|u4$)^oAxmB&OTO(>
zC;@&1ON09)T#VI#Q8=X}P@Nyy_pVd=CJN2z5X?<ho+-#)!MY2J3>S4wLWW95s}||q
z*0jjb;X?=Vz-r<mvJ^0bv^>*+rG&mm78q_O*}~LxC;y|(|44>KgO%70Ya%bDSUS|n
zqIEJxZ8y_sWuD8xK8Uxl4+hk1Mtr47at&=a^U90YNliigXvc9Ls+ak0g#tvIlh$jF
z($OKXDvK}+8RC-^5$`KE)4R%W_kb9?$|n&L16!BKg6J7`(g7lDoSI1UJ1|`jPyQtp
zZ}9T6J&f7C0<)NeQxu~!ik=*dH2bMYDUpiBX7Pm+Vm(VUo*{565AYc@+z;6fD8V76
zyP1B3FWs={<E*ZO+w@N~dOp!od2rdtEwaYFA?JiVh4UlsNm!_#j{}dhm5S@L29nj4
zIA5upZCE0ej#9c(VScqz;iRkiZUT1^AV-&z>&WW_$Z1Zbot#%rG8Ct#kx&Ua@gskR
zz^a=oFd=PQ(Lf3CU<UxaTBWqdD3R<?xQ6$C=NltiMxKC;{H@ZKs)7IEG-~1xC;<a?
z6C^Hs%0rMm&tF1QtcUY;+-b6Cu}ZOu6xu}opE5|{X{UB7Ndr&@z#I<FAg9MYgnd21
z%56WPCBDXOznu-xl<PZFcC?Xw4(uVmPOpAkGuPeN3m=>C{TTV1Rl~KqI)<!`Tla&S
z=s@Pp9O_J9pR41`m5V%$<?u0TDt4OiZJE9^-{QleS?csbYR7i*d0IqeX0B5m%(>#b
zqS@c6@$A~n=~F%r#HU7cpi^J<=kS%DYymG5_0diPn9GI)boV91%SIP*lec1w*w~+N
g<bx0cDcBA`dUs4{V?%xbL3|0^pGOVB<Zmed3%JfL=>Px#

literal 0
HcmV?d00001

diff --git a/function_old/data_process/__pycache__/data_splitter.cpython-39.pyc b/function_old/data_process/__pycache__/data_splitter.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..f97444e2e1a92627bf04ebcfea8118b02b8a54c7
GIT binary patch
literal 1713
zcmZ`)OK%)S5bmD$jCYL*w!xe>5-3`v*gjh*fN(%UU`2{W#0Y6LneJVWGmoXa7va?y
z5o{%qNG_Ig04Gv71}O;~IE6pJg%hW~Mv3j8Kok&FGmf)Cp+{X?UGq(Mb=6n3al0K5
z7(2h+>8B1M4{$L)ELgk?Q!ayGgwc%TG^CU;gPEBTn(%97R&IxO?u1Tlw=*~QLXVOU
z33HgcO_<B+mKplYJWIOX0fnu)RJWI76`v7h!lf+50T{_j*U;8-nka3r4hI<r)RYo&
zT11LV70E%Cssw@KqrLzb<SGbGLdr;JFbb|saEqBY=w;HQ%wqO-JG5DgJL@j@xDQXj
zC+ZbiVD`*8!n_*}^I5QMhpo%RB4Ha`ZtE8MdKQmYTnvxFL65Hg{OH=<gWXFHuk1X$
za%u0E`zzqBlaxg-?I*^VgQ%N_Q%-@R$QHRpEBYgbk-+{G?`_NBfD7$KQCg%biZB$C
zXFcJ;C%38gqbSK@DWm8%dHmkOTAA~OnB{44Qk11ySc^-Q#>K)XAD_u$)hk85z`*Bd
z&;+<y)B%JW%nvpMhRug5YhUSTX8eltPrcat;d>mvzjN>wV7rbsSWi1D7JaU?-()2n
zaqWE>XOTp$CE|jWc_dY=xON0rLs2Bat)npk8lL_>O!+5>(T*Y&t<1^>Y0Qyz%IF0{
zbedIRAlI&0pBtObrVB`?vH<CfAwOzXV@Pk)ugJP_%VbvNtwZwX$S$z4@{e@4a*uTH
zri;m_yvnbD2In9t7E$)bACzncl#Je}_X1)lw+goCF1cwS{#$a6d<K=U8GIcSLG!yv
z7Qq5Z4TdM+Y7IN~@7~$FzXfD@@Xf`8pRVrTyNJZux%%kW@AmIq2VFbm`E{PCm98nK
z;WIG{LVFU(uhQPe=v2@d8<?q1oy$&A=1?b!FFgl1*;&P^NsE3*a<$YE$iLBvj*Jm4
z|AYNB&Qjn?S{4m@bo_sSt5Af8keL@kMzg1dC`IF&!sC&HOP#JKkO10dYGVMT$jW{n
zxNfCIuLR<+#bESLf0gh7dZBHOyJ!=x-<=Rh7l9=wUO`cZX9hKlQRp}Q0qCbKq@%WL
zgErAZxtK&`EnWgmPana@T1pGv$VCvuHw=R|&udQtZ%lVR!~4fFy}vEXdlI-UW0KC&
z(edYs=0$sBahn3mz7a2j)}6#MFXEg>kq)9LFWE3dy%j}Y4CCzZjT=R*Orl6&6Rzu3
z8v~|&Jo5tqUyBaB&~`5?W2McsP{Ky!n`mtxwu^*k8Eo+^40u_Au@Ei@OpAOSghwr7
z+9ed8$A)1Y2Em}m{;F}^Ku=;WpZ1ed2<#i$89=qiQebz0zOXTXq&NPeE8(m1LdIiJ
p%)=EqGzgvn$sxrx9qNt8JbRWU@9icer|_>rVgqbZk518+@h{Sk#@7G<

literal 0
HcmV?d00001

diff --git a/function_old/data_process/__pycache__/feature_engineer.cpython-39.pyc b/function_old/data_process/__pycache__/feature_engineer.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..98c7c740996c44b147a977bffcd9150250fd5b5a
GIT binary patch
literal 3098
zcmZ{m&5s;M6~L?dyL&!%z1}3d!E%PgBpDFiC?FwOQ9xuJ4#ZZ(3KII#>P*$l&bX(0
zsICFesK<h=r4U8FA#(6qnnfVtNF0z5Q3#5}zrYFAflFdr`!66N<-O{j+1WL8tE;PC
zy{>xw-mhL&+-L*@uHYYk>d87GpJQY7vY_!jc=CNH7-2LaLmE;_n8D1%2u=OALL1&z
z;tbu;9eSas`|ZRZ24OI)g|%TltZSK*G=|NvIa~|ZhU?)vB|jj{W!`PVJWdbH@EkMu
zNZUWAFkPFf#%?U*H$~Rrd7g=55R&U{Ls`51j#Sng{am(9)!dVD%3{IxI&s2<s$c7;
z*W#Ot){nAx#<?t8pk3SJ3Gc`sexK(sL}$PMvhur8CyDdC-|gTGtCw3f@|#fMB&3Xl
z2BYxb8{A^%A$^Z@DYKY;y8%8p&z*tGJ??XFn_!)}hZgggf7=cNwpsOhyr%o=hc;`l
zCiK;-9{ghM&}8fE+-)mtyhkh&Ho+fHsI}L5EXRUhO?&;6b1_~6dmg?2$%D^+_2A<_
zJo@7YkN*7Wb#R!|$<l7W*D+Rp0_zw@6Q2AM6p|c}IW6cB#8DatM4Iqe2N2yuvmlYp
z2+V0*2WNSC<yz$o`{^*g89G9{v+XE5ACJJ>UKI7yzKkN_z|aC6COjyVo9l4o7_Xcs
zUC{vPeX9JZ^mY{8C;!>q+0TZ2CuT7GH$|4oo&7kI{W#sZ_Qsn@EW4Q)?l6EL8kH36
zbW2A>yz<25(L|hsk!$ee8fIEIEDHC3r(0*dc6n)Q6SUiwGFTV>jLZFuDYug)<6)XB
zM{sa;+CiT!F8ntf{55#;kD!?D7bc@)A}$nkKqMU)J<5zbbYRZR!YIhV`Z*QfmNtXd
zU2@Mjpzl(Y7REN2S%o!s3R;-k<Ot$Wn6D7%bLSp|{=0<P_e_jULEnN%SVa1h-%~QP
zDVbi<dI57}t*{R$j*Ob`lDEiDA$~LamYoLW`z7)cNFb8#7*=)#%cH;FfB2ivkQBF{
zc9JpU(+fXNA(Ep^NX}XqvwqrZl|H%Bnm)HT?%?X{j+11fyFsgpLEakYs62Hm{pr?K
zAu_QXWubSa)vl`sKmZFbVsbL#xiZp`a?<he9WKPvV4v84LIppGlQGw$s74pCk|IuX
zq(C`I*6RUqRzK}#%D;NE!$-28rOJj8GNH^|inb%p<5*i*Y-52#hfay2qFg+QLR~xs
zHPzHT(ZW#tILD8PVNj257y)g<vtevf$7s?g>Ga}Rq)rbY5Rzjo+P1brIWiVKF10m^
z-Vk4bzK#vW;zDqjX#EQs)88Ue1p-CyKu7@)gvJ5jj2niyEU7dKNIrLrnVVh$sRhzq
zkeW+rQ$k8A%q4j4+%D|GIWlHmVGo?box4Y5o6Nl<GV=i`e_kTxBT~#=;8*x)#Z#bJ
zfmomX6F>|q5dC?Bd9qmqkAdjVf?ENAsNWhyA3zLNKs^5C`wu_3-=<~kwZo|R2K>E1
ze@vfWg|doHs{{x_euAf8W^-V2>MyaJK3!p`fkQ$U@x9Wz-d<A{6WK`kI2lf?XA~{0
zeH9ChObucdRqFy`m?f~+h-b0;IVhBw@Kj(f6<@>Rc_`Yo752W4QVk&flcH}cI)QAe
z4a!6qyd9Nw&cbtx+LA)?0)Bml)U{G=sf1JJ7ok8@o76Kr0Mr9qn?@ag-J<Iyu+KaO
zY`F{<E@_)3r)!X9x$F;lROZ1FRNONb7v{qys9!*1`a7xj5yVsHF$40LhIL>JOsoM+
z^xmq}s-(s#sYV=h%~Mj$kT`;MS~_=`&72<Oy{g~U{bb<Hedd+f_Eh!^CjSO#%?es?
zUSqzj7v^Ko1~c=P3DD}dhBg3bYhz4I4}N|3!KZ(F_~BoVKm1F%?J7H(@K}USG|W=D
zA6gNMC!rVpg7X_tJH{n`jN3+7i~6}1^OQ}Wc}>6u2D~oZy=1f171^*geYRw`gKCKG
zV|vJNLm4BcYBGaK%c#Lt2FDq+NZHyTWr7vTt;~U}390%7;Ir&nE9`y?jQ*bpZfT?V
za?T}-ufiA0w7CIkvb<Zy#v*OLc$UKdH&mO#0Z-uejBmX>+t7ej3kQuf20SAbMBsBa
zPOx5&qMwc9r0Q{_h-Do(iy*7|SRlRwHRbQZ5#n_LpX;S6FgW5x>@oYP6fa}*yVz`0
zhm#IZ5*X%W4Q`?eZW#hMQ#|14!-hvKW7E5M{=$})w>MN1BC<TKWJ2KSOF1Jvq2{GA
zHtc$EXu-7$nPoD9D3|u4RqBcSMgmbxFOLMT&OE4qB%K_t!tI4twT!ED0=e;QUPE(N
c{^Mlp^Ij>P_$r>Yb5yHC{_yBJ-K3kwmwI<E*Z=?k

literal 0
HcmV?d00001

diff --git a/function_old/data_process/__pycache__/method_reader.cpython-39.pyc b/function_old/data_process/__pycache__/method_reader.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..20a9060406d8603cd90302757b3773a267bd7fd6
GIT binary patch
literal 2955
zcmaJ@-H#kc5%2E#+}-=K6B{lNXA?ri0=_eOLJ^8UaSRXkDZ&y~Mk2#xdv<Ta?98U8
z*UGNuqToA{D2WLViBW<r?FI{C9&88#5^RIS6aNA&o*=t-{ue-4RQ1eWc8y_1Q_~;S
zRXx?eU)2PQi&X;GJAeJ4{lqdM|G>`dWkBca@MI@IaKdR!Jbbg5c9_RHhG)=X-1JO6
zZ+RBHjo9uuo<qqu2{*a5L%6lgJeSkcq+#CzTV$iblzBXAN@bpmGTETYd@7KeO`My(
z_IGd`MnmFJPCUk`XK==i9pagx#m$S9Tio6;J-h5V+=ZSKy3ns&WW362(68_X@V}@Q
zPK9za<=+ki9*W)}Fg&^N(d0L8-}>SC-J4hUu3aC$d13s{`%OBt5p3gLo`5I24}>H`
zD%ptU#5Zy>G)Dwlmi|K4`!pzwU%fQ`#p~lYE)>T1&2BVo<-}>b9VKnA(hlWGXoo_%
zzMll0(D#*%voLaxAEyELJ9@W%Gfi4iTP@CYF>YBHx2_Pe06zcujrGm66Rrom6D3DQ
zn#%RfAeB*&te-mhR2;}wDmv>tkb&P7X*0~S_0pWs!C33|aUW3<N#93kWF`p07U<y6
zY|z%GI^f?Hq3nrdE?O2W!sR+zzl6qMQv!On=@!lDkd8=JmyENV{*+u|+w>fjMozhb
zSUGRJdEXY3=FrL^x?9E>!flh7WE+r{tbB!J8^;LM_tPMA@|-<%xHF>A2Hn%3Dc$~M
zO14Z&1`q4`3U_5SH@CGn)I3Mdkf*`!mieNYREzg9atuZQAC=<tUK{S+yg7@D$%R)w
zzW%$x5r|$0(F@A}!YP(9T<Zs&cu+6mR4<OJ-iqR|o}{wgN_z>f2ePiH7+5{oI{H-z
zo*O33l!J|p!GouJO+1lSFOK_lJo%8<i_<BM4eozZh*an~STaBPSiMmbcv{L1UjRmB
z>c9!`y^+cj=vl8+X4(xCW#UG?N*1(2jWFTjGBZkAsj58rLNn~jC{2_VqBmt^QZy`4
z10Ance3jn?sw&#@>=KkT)bK0BB4~;V2*@ZTI}Cy_MqRj<*b4mufXQY{^e~-<s^H<;
zUBEtvDI4tUW9skF8NAgdTT~(j=n!&3L`H0Aj0m8N<xD&ZNHZ}@<P0)|f#<%jYt85y
zxgnm>x;A%mz~CLa?u@RPo8mRCTj7AHsV=VpdKWIT5`R|zZ-74w@OP}l=c06T>l6I(
zrJ~Q5agB{wT-mZ-v`&|Ajl~tf;(^|0;6wL*^n1uix8B<sU*6gM@yi7$$FKfmZ}h&p
zN0T{g25~6LOp$rDnZe#curPW1SCjKscW+#oy!FSzNW)MjrW?==v!;lOBex5@sUw{z
z%K&2j*&yzP{$`Ny7`w%E<{i4rJfu=Q@ZB4K7+?PN_@x_#AGMnHWE{cfcqqdr0&CyO
z%KTJX7#QC;H~#QLFfjSqOOxNeuAHpk1r!WBlY#7I$|?6T_<TVKNTL!6F~`c19@%4c
zf$8`P6A!^lw>KIUWyU}ffq+s5tXJmu!+xghpbHG);!~)Kw9xuu6<Q5jb3l9!+TPL~
z5nrALWE!F6>9>^w0uS;IlBiX1JfBLYv8jW0_BaTnj%ggGCfp3~f4k2A>w(5?*8+OM
zI{WtEkyA6JZtZ`%gV@%Jjp`aC@F1HE-Iv!~LjMa44hEbaC*S=ZPz_4pb5IO(hD13_
zgpK{2t&*Isk}W9IpkWMkdLJ>}vf7}jTlRj-!4`Kf>VnN6wIi9Hx1mf_u}tvVB?Ak^
z8IpVpQoPasbD83iVo)sjg0yE-JYOvOd}*Iz%b4zgV*0HqwhR<o={*RaQ&4R3#w+8i
z?-u;peRpT?+Rt~dzx?r^Mw1_0YZ&6QpeG(cQAdHxRHZATq#1SNP!UxP_}L(lK|9RU
zB9F3}?!ADkIBEvZ#-X1z!z2(<nn6~*A1!?e#ZeS%DAqwVO0*t<_P{9)u|BANQb`6!
z=AmDlUL8mlMDY~!;$c|6(Qq`(#Us#B)$bsq_1e3Fyh!xoi>T{1q13fg(f6j{z!Gs+
zBp*a*l?W>La1u;pxB-ALbLm0I{&3N1asSJ_y;Qpw>p%h22a0bjYr%h8+h|mUgPW@Q
zekbKUh@-C-eE<1g5SPDAj_>od>HA^{^aP?;S0T~B7BW~oiUR+WW`wR*2ye8WVLouF
z$$&x!mcA@-yipPOi>Peb??RF(4CAk$VreF@Dk%r+VH`cH>#trk<3RgEFUtK|vGd3A
NXR>s)q6^~!`wv$0M$-TQ

literal 0
HcmV?d00001

diff --git a/function_old/data_process/__pycache__/method_reader_date_feature.cpython-39.pyc b/function_old/data_process/__pycache__/method_reader_date_feature.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..20dfd1fba2892c0e702c69048fb1fbf7d5e60f48
GIT binary patch
literal 3498
zcmds3?T;J98K2pmeX)J#I4?wmE5S4&#I3kHD3uV3s!E0Q%f*Ta0<luHT0CRlw(DKr
z>>A;f9nrfhAYK~2a8)6Z>=w0LKai@ZEmes6e~kK}67l8oClskspP5}dc6#&=s4YMH
z%+Aa+<C)*@_dMR>ViCb7y7i~lKMo`Gm2Av@bZGn#e(`xQ6j2-?M?SRxw>3v=>yD1I
z_rxKp-*60g>Ves|91Ei#BTA^Tji|AuIX1<YP|dspu~5CH3G$rZNCa8)<D`ZKx#%V9
z4cRyQneN~Pc*~H3DRMN59i3`a-$o8$1|?T9HK@5w95ZiO)P|Oow+gffEt?gfUAn5#
z1-c0BA}zyi4vB>eELo4}3(TX8cOQUd_ICcZ_xXo+e)0b8o1g7pzcIeDGye6b4Lq|g
z>C2t{2!8QtFbNvsL>u8ga`iqMk`V&W0MAsOrT)3reGrC@-@Z2f{k!A$cCuxr3)E}2
zu!5-7^23%>Xt87se8z?Cx}n!*t}9I03vZ6PLF7@lt@iCUqOj?=#NvGOcs8cvahRJh
zJ{eZI|BXEPm<7#U#LKX|uj?!8QJbxJwC#sa@F+@F*1ah4y>R8i+Qq<2nh|fWP%rV^
z4v!ivj#u)9xjH}>x|rK!Uee`kxzm%|_d`E%U5T{V1cS5%T*T=E7iP|Vc`^#NV{!(Q
z!?^=DV44h|4*U<`r0WU5aSIP{9}n>e#nnWkS|5Lmu4!9%6DN8fQ(c1Zef`Qq11%v#
zqYoD}&|gN>B#59bfNofM62<jZgw^*IuzmDXb7)a(gu#cgmtbUK_ddaBKrl*AtNsGD
zlVYE2snz7jP4qH)1>z3KWfB&%=PFu-Hvq9hcJ1#B_ix^uh1TBATeoifC4F%A#PY*j
z?s@GXt!5`w&2G5b^aEB6qomr5x*@H4NmXF}wb4zQPdu}Wh0Vf7L;*bY^wCS*hP;|)
zHwb!F2^L1H*)`?C(ubetJmRVkrp$LfTiq>j0*5S2_BxO=7KhKn+Vv<oFIQGG1&KN=
z6hv;+Da2lrDZp`CP9uKUj6~u2*Bh*p_)#bfCRY=BobX+PFTxn7l>IBW1FRRg>6kf=
zF;h6q%pn-b3t%eni;sgrnucxombD5#3qUfpGCqzcN0pIy`2c?WU!rMzWpnStKW0Le
zqiJalO;fUGfI4+?A_w1$DSiYFnIDzr7?^r``XDe(15fZ&oyXJt{m)jpygmMiG*V|~
z?zaTZN8xwy{bF^$r{={%>ECpXT-)ZZSi*NI81FzMJ=a15oJfM>A!HCAjkKXYLLebp
zU*k`Kj1ZYq`WoaDU6Ps_AR*>eEf)c!w+$iyqLHpnL?W^K`aKZ<QBZAKkaJ8a2*rVZ
zS-+G&l^_&B5K7%8*wFqj{|cGq&TqEIpKRa$;LS`K#&7>>fApzX$_3PAA*2JwIB+!A
z``D>O-6Zfq(kTdgBZ+ud(q#PQ=J<;*#&3MN_uDu2{`_uD7euBFQKBqva6jXrnTdd~
z;!GeQ37c^OS{(~3>x$FIvYUhilt^XhaFz@GJ)MZ*Iv<8LcQyVvJd|Ir6$A-DEx0^(
zp~HMZe#UySFue{)1?At8L!~~b@%$usHKN3Tp9SAJH2GioPPhcceP9tMATDH{nLSO;
z<w+PFe;bUH2ttly0$)vj|7}}f@7e}H3Hr>t>6tk=ePc*Co>I0Mm4Z2xNT{L7CGw9<
zXA-_DEv-UTkp7bbo~ZU5`pMY=q#!^FR0e%rqU|-ri?ZF<PoO?Nfd(2z8&7W(0dcsC
z_!=ZInDH@GOxFNan;0TN`kINP&qR6=BI(mekeW6wZ@kziD$>q0l9@-cU?*gVsZ9$b
zKs$KFsaI;j-qgE=skf*+IioB+dg!V}D^n(r4{+~0zy%}cf-yAd;l%12Gh8^5wdv6*
z7x2KiYycP3Q*l97gU7n^mNPEwz4zAmvyU<&-2P~L|N8H4-+1%Z-$#2tzh19lF7GzA
zvYV@>OEam^59bqD4LfK42ZJEz<W*6eo}3Re?a6hGpMgcWtndU9g%0qr;dcTiiXMH<
z3lp!!VzEg5c&2#_;2!u5@6~|0af5{(_oG-8r;+2D#ZOJ5a*100lr-Oy=4olZ52lt=
z>oM@tlk=3!AXx?adwwwCBCp9=wqhUuF8HGOk{5KDn#vd8#eoDgGXkzazcazQ%HDPZ
z3b|Iqdro<}b*SW^{5y!2M<j=Gs^t4xgOKq#Fu+HRK*~M>Qf_KCuIO_u0^Lv#PQU*m
zckRW>gsG2Y_njy9|6ZkDD{%|f5JlH*N3;uv?urH1-ROEjUN&2<OQVMCa#=)hNnce`
za7kRgERB>R{){yDQj_vj{UK{lxkM}v(Z)ox&GO-LrM$#tPp!Zof`>4ZUI!F1i?7Q!
pS`>3B5W<o*PT;?)YAQA9pml_OF8c#N03AWGR8cr9RqQNi{{b*^%U}Qi

literal 0
HcmV?d00001

diff --git a/function_old/data_process/__pycache__/method_reader_date_process.cpython-39.pyc b/function_old/data_process/__pycache__/method_reader_date_process.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..1e22f73599daca90a3dc564680be60c379661a1e
GIT binary patch
literal 3757
zcmds4ZI2t(6~1@gZSQ)$35gmgi_-)e(<ZyL^esZDQX&14SP?-WMxvv^ckG>ZJmbAH
zj<Ds8Xm)uKkcJPiRUwhQZPc>;khDcD&?N2uxZ*?AV(;cB6sb|qxidEQcHsxqBcHi1
z=bn3g?s=Yb?9R^S34C7u<WG$s93bRh*qQvO(D@;J<5M6QVKg8%zLkJB6<cYlwo21+
z&DP|+ZtL(?1EXo$CM7>6Ok?^wVfvb4Ta2C~72^)rBGrl_v?u&pBDB+foK&dL&brBR
z4d*65;}bjuqaLv-Beue*tulqF>%`VPooQDn)0wfZ*+$kgnFT#F>*ZJ;dX|@ie&LG3
zX4owB^Q;J`nG-W-ykt3IPkAo$cpJPxh8rIbKX~WP%a^uqU*EZLb8vZM@T>Q0bmCap
z#*_UBzVT5I3F*^B*`z(<s6EoxHVL$JXc@9)%3rRuzXGa**RBqJ_r~DOjdYvw2Gxos
z%phts{IFr?8eVc5+8!5{<AiS0a~xsdER5`Tg2-h~Q=Z$YMPc1<h}r4x!BnT^a#)*q
ze56*|J%XN(y`a8Dco9zbS#@zaYI=(<Yx?1F9!1IGvKuA78!nzXeKv5Ddc>QH%uQUU
z#iN=R$BWs<TsqK!DQ`4&qSe9U`=OsW4n|sRfFQ~Y&C~9IGZTJ4G17wL7~D(RJe+d4
z4$IJhbolR~(Opg;9M|Y7?a@BnByl-Wn9`%~k*mrYy+{+aN12MjcS*f`@2Zk$eZ2=4
zw5mQ!n4uAktU>68rAJ6yT_RLI&w=cbpBjCWnVS^apnDE96RUHLl2wh8?om0PV^)&y
zX=`#f)VxTZCC`D~RqcWn=F|5QS%MJ=v0QrXulILu-<}Mu;l`_<-uz2<A@i7*`4g@`
zbLokW+YGwp)KBH~p38MV@XBG7l<QGDWMwxg3(7y!+e!WS_qV99ys#EAuu<(EKG&|{
z1=ZU@&?#fcc&waWR%Wbw|C5|YT+YFg>B*DjtpeA;)xz*z1c=6B{uJz8jgnKivs@{(
zsO5!1!-Lwn*sXgq?6`%?G(W6IBKPErHLsQUQ7Ci|cN1!y@GYIsf{tBCf0fe$><e1A
zjVzj}C!;YHbD+s{AWHC!4}u_yLM?cTN{JqWa59u4JxE8cN}+sW50w00#?;{Q#o;@D
zNa-qzsl$83)EM|_SRFY#qJ}SyEWQt1&G)0Y2Sl}dbgz&a8y-bfc{-|g&z~%FyhHu~
z3gn!LTP{HNFnssEWh!s^$TV?CE*$TX@!Zr!Bk7FE<Dby!zTF_JG(oV_K4cT0Y$|<q
zlK`D4J%xV@C`H5k(o-O}s0i?}u0Elw_Ei28scSH^2V}EL*P77PdK!OS>OwZ^X(L@$
z0GgV)qGUv)cRm54(Sc}|G9sEyte*Zk(Xe9LXLGp5K+-9#>KF8L*;|rM2}ozYeINYL
zonL$i+3U`)*9X_ux8HgtWuL)ozueh;U+kA89@pFevO`J>v0a!LY~$@iWDPG}-@dgq
zeEV;yk%}rbOh}@@ytu~w6x&8>K`b==I0i0p&bvX|bC%tZ1=t;JaA1#lNV^E}?OT5x
zT>InTrCaGf;!xC10v`^?Ac578LB>`}(^FAuU~uc=;G>Vg!0<OO4gdUxFyoW}q0}(q
z#7)|<Ftc-XA53Eu(rkjv*WwfOoAF=_fqFljYfIr3c*%CPk`r10Y{)U7gbM40_A{>&
z3&U*z6*B%+R7L)i`g{Re6+@C8e;C?!ahJ#EMh+QyXm0e|vH^~G*o6~u2sVZ+J8|fd
zZyo{d_;C=(k(zptYVaud{KqoCtOpu*EgcXB>x{eIht5o<=P%q2d|OBlDytMe4;$AM
z+&=pt_z=}Hb1y;R)cpqom@(xE^8B$?$kGt#P(1Zi1j~8C^VsjHhe(eeBC84|E03<^
z0f@9s_-V-Tu;M)^DzB=T<-rmFb;6Q5Vd-hG1Q5+ELH1s`u<|rO4=rtsE$Nvh15Tp#
zDTC5+6G#ABkma*hz5!>GV})^RMz(OpEVfwjikX5^Rt(x(wDa%;l=Z&BN{KlI<@vPF
z_Kl%TGbqcqgfbS)``Z`+DU^qAzB;)6Zi?gWch`4r{C4~1E1&*-bNKTc)r!i$28#S4
z6ki9?HPbsRcki3182oTL&vzH5C&yHp(K$bc_OQqmMC4lB4{Lra@I>Ba=iM-I8(u7C
znIBJd?*S|Xe$9O$@SM2jg)aA_Smei+<BG|TjI8o+W9v~A-$C(R6yF0;$#C}|w7Uz_
zcuhmD49wvA!3e1Q8@S4n(B#LVE%MJG3(2K?1_r(iod_Iz6w9)7v1(AuHX`1!i{qn1
zF$)#&UXa{}7|EcJo$Glp89xRBu&8KIuk3>iW+)adsZ%`-rlBMrKmXS5TC=4Q5+6u!
zF{^6+cb96Vz)jdg<Q=COu{Jo}5i^dn(sqOFpM&W*EUGyU#|nxgJY_w_5tw`l1@aU>
ziQ@B&EL*bp!txuph|!4_)fCGp&KFC?Z*rWe<oLbt5=PQ#0hy-uRUA>Gm?HrQ6AQe+
fe?b<Ma?xJ<2<x%*2RsfuL1Ls>@Rh9eW|aQ|)DI+Z

literal 0
HcmV?d00001

diff --git a/function_old/data_process/data_cleaner.py b/function_old/data_process/data_cleaner.py
new file mode 100644
index 0000000..58532e1
--- /dev/null
+++ b/function_old/data_process/data_cleaner.py
@@ -0,0 +1,66 @@
+from .data_processor import DataProcessor
+import pandas as pd
+import numpy as np
+from typing import Dict, List
+from sklearn.impute import SimpleImputer
+from sklearn.ensemble import IsolationForest
+from scipy import stats
+
+class DataCleaner(DataProcessor):
+    """数据清洗类"""
+    
+    def __init__(self, config: Dict = None):
+        super().__init__(config)
+        self.missing_value_methods = {
+            'mean': SimpleImputer(strategy='mean'),
+            'median': SimpleImputer(strategy='median'),
+            'mode': SimpleImputer(strategy='most_frequent'),
+            'constant': SimpleImputer(strategy='constant')
+        }
+        
+    def handle_missing_values(self, df: pd.DataFrame, method: str = 'mean', columns: List[str] = None) -> pd.DataFrame:
+        """处理缺失值"""
+        try:
+            if columns is None:
+                columns = df.select_dtypes(include=[np.number]).columns
+                
+            if method not in self.missing_value_methods:
+                raise ValueError(f"Unsupported method: {method}")
+                
+            imputer = self.missing_value_methods[method]
+            df[columns] = imputer.fit_transform(df[columns])
+            
+            self.logger.info(f"Successfully handled missing values using {method} method")
+            return df
+            
+        except Exception as e:
+            self.logger.error(f"Error handling missing values: {str(e)}")
+            raise
+            
+    def remove_duplicates(self, df: pd.DataFrame, subset: List[str] = None) -> pd.DataFrame:
+        """删除重复值"""
+        try:
+            original_shape = df.shape
+            df = df.drop_duplicates(subset=subset)
+            self.logger.info(f"Removed {original_shape[0] - df.shape[0]} duplicate rows")
+            return df
+        except Exception as e:
+            self.logger.error(f"Error removing duplicates: {str(e)}")
+            raise
+            
+    def detect_outliers(self, df: pd.DataFrame, method: str = 'zscore', threshold: float = 3) -> pd.DataFrame:
+        """检测异常值"""
+        try:
+            if method == 'zscore':
+                z_scores = np.abs(stats.zscore(df.select_dtypes(include=[np.number])))
+                outliers = (z_scores > threshold).any(axis=1)
+            elif method == 'isolation_forest':
+                iso_forest = IsolationForest(contamination=0.1, random_state=42)
+                outliers = iso_forest.fit_predict(df.select_dtypes(include=[np.number])) == -1
+                
+            self.logger.info(f"Detected {sum(outliers)} outliers using {method} method")
+            return df[~outliers]
+            
+        except Exception as e:
+            self.logger.error(f"Error detecting outliers: {str(e)}")
+            raise 
\ No newline at end of file
diff --git a/function_old/data_process/data_processor.py b/function_old/data_process/data_processor.py
new file mode 100644
index 0000000..f5ed18c
--- /dev/null
+++ b/function_old/data_process/data_processor.py
@@ -0,0 +1,63 @@
+import pandas as pd
+import numpy as np
+from typing import Dict, List, Union, Optional
+from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler
+from sklearn.impute import SimpleImputer
+from sklearn.model_selection import train_test_split
+import logging
+import hashlib
+from datetime import datetime
+import json
+import os
+
+class DataProcessor:
+    """数据处理基类"""
+    
+    def __init__(self, config: Dict = None):
+        self.config = config or {}
+        self.logger = logging.getLogger(__name__)
+        self._setup_logging()
+        
+    def _setup_logging(self):
+        """设置日志"""
+        logging.basicConfig(
+            level=logging.INFO,
+            format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+        )
+    
+    def load_data(self, file_path: str) -> pd.DataFrame:
+        """加载数据"""
+        try:
+            file_type = file_path.split('.')[-1].lower()
+            if file_type == 'csv':
+                df = pd.read_csv(file_path, **self.config.get('csv_params', {}))
+            elif file_type == 'parquet':
+                df = pd.read_parquet(file_path)
+            elif file_type == 'hdf5':
+                df = pd.read_hdf(file_path)
+            else:
+                raise ValueError(f"Unsupported file type: {file_type}")
+                
+            self.logger.info(f"Successfully loaded data from {file_path}")
+            return df
+            
+        except Exception as e:
+            self.logger.error(f"Error loading data: {str(e)}")
+            raise
+            
+    def save_data(self, df: pd.DataFrame, file_path: str):
+        """保存数据"""
+        try:
+            file_type = file_path.split('.')[-1].lower()
+            if file_type == 'csv':
+                df.to_csv(file_path, index=False)
+            elif file_type == 'parquet':
+                df.to_parquet(file_path)
+            elif file_type == 'hdf5':
+                df.to_hdf(file_path, key='data')
+                
+            self.logger.info(f"Successfully saved data to {file_path}")
+            
+        except Exception as e:
+            self.logger.error(f"Error saving data: {str(e)}")
+            raise 
\ No newline at end of file
diff --git a/function_old/data_process/data_splitter.py b/function_old/data_process/data_splitter.py
new file mode 100644
index 0000000..0018422
--- /dev/null
+++ b/function_old/data_process/data_splitter.py
@@ -0,0 +1,49 @@
+from .data_processor import DataProcessor
+import pandas as pd
+from typing import Dict, Tuple
+from sklearn.model_selection import train_test_split
+
+class DataSplitter(DataProcessor):
+    """数据集划分类"""
+    
+    def __init__(self, config: Dict = None):
+        super().__init__(config)
+        
+    def train_val_test_split(
+        self,
+        df: pd.DataFrame,
+        target: str,
+        test_size: float = 0.2,
+        val_size: float = 0.2,
+        random_state: int = 42
+    ) -> Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
+        """划分训练集、验证集和测试集"""
+        try:
+            # 首先划分训练集和测试集
+            train_val, test = train_test_split(
+                df,
+                test_size=test_size,
+                random_state=random_state,
+                stratify=df[target] if df[target].dtype == 'object' else None
+            )
+            
+            # 再划分训练集和验证集
+            train, val = train_test_split(
+                train_val,
+                test_size=val_size,
+                random_state=random_state,
+                stratify=train_val[target] if train_val[target].dtype == 'object' else None
+            )
+            
+            self.logger.info(f"""
+            Data split complete:
+            - Training set: {train.shape[0]} samples
+            - Validation set: {val.shape[0]} samples
+            - Test set: {test.shape[0]} samples
+            """)
+            
+            return train, val, test
+            
+        except Exception as e:
+            self.logger.error(f"Error splitting data: {str(e)}")
+            raise 
\ No newline at end of file
diff --git a/function_old/data_process/feature_engineer.py b/function_old/data_process/feature_engineer.py
new file mode 100644
index 0000000..57105e8
--- /dev/null
+++ b/function_old/data_process/feature_engineer.py
@@ -0,0 +1,77 @@
+from .data_processor import DataProcessor
+import pandas as pd
+import numpy as np
+from typing import Dict, List
+from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler
+from sklearn.feature_selection import SelectKBest, chi2, f_classif
+
+class FeatureEngineer(DataProcessor):
+    """特征工程类"""
+    
+    def __init__(self, config: Dict = None):
+        super().__init__(config)
+        self.scalers = {
+            'standard': StandardScaler(),
+            'minmax': MinMaxScaler(),
+            'robust': RobustScaler()
+        }
+        
+    def scale_features(self, df: pd.DataFrame, method: str = 'standard', columns: List[str] = None) -> pd.DataFrame:
+        """特征缩放"""
+        try:
+            if columns is None:
+                columns = df.select_dtypes(include=[np.number]).columns
+                
+            if method not in self.scalers:
+                raise ValueError(f"Unsupported scaling method: {method}")
+                
+            scaler = self.scalers[method]
+            df[columns] = scaler.fit_transform(df[columns])
+            
+            self.logger.info(f"Successfully scaled features using {method} method")
+            return df
+            
+        except Exception as e:
+            self.logger.error(f"Error scaling features: {str(e)}")
+            raise
+            
+    def select_features(self, df: pd.DataFrame, target: str, method: str = 'chi2', k: int = 10) -> pd.DataFrame:
+        """特征选择"""
+        try:
+            X = df.drop(columns=[target])
+            y = df[target]
+            
+            if method == 'chi2':
+                # 要求输入x不能为负的
+                selector = SelectKBest(chi2, k=k)
+            elif method == 'f_classif':
+                selector = SelectKBest(f_classif, k=k)
+            else:
+                raise ValueError(f"Unsupported feature selection method: {method}")
+                
+            X_selected = selector.fit_transform(X, y)
+            selected_features = X.columns[selector.get_support()].tolist()
+            
+            self.logger.info(f"Selected {len(selected_features)} features")
+            return df[selected_features + [target]]
+            
+        except Exception as e:
+            self.logger.error(f"Error selecting features: {str(e)}")
+            raise
+            
+    def create_datetime_features(self, df: pd.DataFrame, datetime_column: str) -> pd.DataFrame:
+        """创建时间特征"""
+        try:
+            df[datetime_column] = pd.to_datetime(df[datetime_column])
+            df[f'{datetime_column}_year'] = df[datetime_column].dt.year
+            df[f'{datetime_column}_month'] = df[datetime_column].dt.month
+            df[f'{datetime_column}_day'] = df[datetime_column].dt.day
+            df[f'{datetime_column}_weekday'] = df[datetime_column].dt.weekday
+            df[f'{datetime_column}_is_weekend'] = df[datetime_column].dt.weekday.isin([5, 6])
+            
+            self.logger.info(f"Created datetime features from {datetime_column}")
+            return df
+            
+        except Exception as e:
+            self.logger.error(f"Error creating datetime features: {str(e)}")
+            raise 
\ No newline at end of file
diff --git a/function_old/data_process/test_data_processor.py b/function_old/data_process/test_data_processor.py
new file mode 100644
index 0000000..317c35b
--- /dev/null
+++ b/function_old/data_process/test_data_processor.py
@@ -0,0 +1,34 @@
+import unittest
+import pandas as pd
+import numpy as np
+from data_processor import DataProcessor
+from data_cleaner import DataCleaner
+from feature_engineer import FeatureEngineer
+from data_splitter import DataSplitter
+
+class TestDataProcessor(unittest.TestCase):
+    def setUp(self):
+        # 创建测试数据
+        self.test_data = pd.DataFrame({
+            'feature1': [1, 2, np.nan, 4, 5],
+            'feature2': ['A', 'B', 'A', 'B', 'C'],
+            'target': [0, 1, 0, 1, 0]
+        })
+        
+    def test_data_cleaner(self):
+        cleaner = DataCleaner()
+        cleaned_data = cleaner.handle_missing_values(self.test_data.copy())
+        self.assertFalse(cleaned_data.isnull().any().any())
+        
+    def test_feature_engineer(self):
+        engineer = FeatureEngineer()
+        scaled_data = engineer.scale_features(self.test_data.copy())
+        self.assertTrue('feature1' in scaled_data.columns)
+        
+    def test_data_splitter(self):
+        splitter = DataSplitter()
+        train, val, test = splitter.train_val_test_split(self.test_data.copy(), 'target')
+        self.assertEqual(len(train) + len(val) + len(test), len(self.test_data))
+
+if __name__ == '__main__':
+    unittest.main() 
\ No newline at end of file
diff --git a/function_old/data_process/ttt.py b/function_old/data_process/ttt.py
new file mode 100644
index 0000000..3d0bf95
--- /dev/null
+++ b/function_old/data_process/ttt.py
@@ -0,0 +1,2 @@
+from data_processor import DataProcessor
+
diff --git a/function_old/test_data_processor.py b/function_old/test_data_processor.py
new file mode 100644
index 0000000..cdde864
--- /dev/null
+++ b/function_old/test_data_processor.py
@@ -0,0 +1,93 @@
+import unittest
+import pandas as pd
+import numpy as np
+from pathlib import Path
+from function.data_processor_date import DataProcessor
+
+class TestDataProcessor(unittest.TestCase):
+    def setUp(self):
+        self.processor = DataProcessor()
+        
+        # 创建测试数据
+        self.test_data = pd.DataFrame({
+            'feature1': [1, 2, np.nan, 4, 5],
+            'feature2': [10, 20, 30, 40, 50],
+            'target': [0, 1, 0, 1, 0]
+        })
+        
+        # 保存测试数据
+        self.input_path = 'dataset/dataset_raw/test_data.csv'
+        Path(self.input_path).parent.mkdir(parents=True, exist_ok=True)
+        self.test_data.to_csv(self.input_path, index=False)
+        
+        # 设置输出目录
+        self.output_dir = 'dataset/dataset_processed'
+        
+    def test_process_dataset(self):
+        # 定义处理方法
+        cleaning_methods = [
+            {
+                'method_name': 'SimpleImputer',
+                'params': {'strategy': 'mean'}
+            }
+        ]
+        
+        feature_methods = [
+            {
+                'method_name': 'StandardScaler',
+                'params': {}
+            }
+        ]
+        
+        split_params = {
+            'test_size': 0.2,
+            'val_size': 0.2
+        }
+        
+        # 处理数据集
+        result = self.processor.process_dataset(
+            self.input_path,
+            self.output_dir,
+            cleaning_methods,
+            feature_methods,
+            split_params
+        )
+        
+        # 验证结果
+        self.assertEqual(result['status'], 'success')
+        self.assertIn('process_record', result)
+        
+        # 验证输出文件
+        record = result['process_record']
+        self.assertTrue(Path(record['output_files']['train']).exists())
+        self.assertTrue(Path(record['output_files']['validation']).exists())
+        self.assertTrue(Path(record['output_files']['test']).exists())
+        
+    def test_invalid_method(self):
+        # 测试无效的方法名
+        cleaning_methods = [
+            {
+                'method_name': 'InvalidMethod',
+                'params': {}
+            }
+        ]
+        
+        result = self.processor.process_dataset(
+            self.input_path,
+            self.output_dir,
+            cleaning_methods,
+            [],
+            {'test_size': 0.2, 'val_size': 0.2}
+        )
+        
+        self.assertEqual(result['status'], 'error')
+        
+    def tearDown(self):
+        # 清理测试文件
+        try:
+            Path(self.input_path).unlink()
+        except:
+            pass
+            
+if __name__ == '__main__':
+    unittest.main() 
\ No newline at end of file
diff --git a/function_old/test_method_reader.py b/function_old/test_method_reader.py
new file mode 100644
index 0000000..9f7140e
--- /dev/null
+++ b/function_old/test_method_reader.py
@@ -0,0 +1,49 @@
+import unittest
+from function.method_reader_date_process import MethodReader
+
+class TestMethodReader(unittest.TestCase):
+    def setUp(self):
+        self.reader = MethodReader()
+        
+    def test_get_preprocessing_methods(self):
+        result = self.reader.get_preprocessing_methods()
+        self.assertEqual(result['status'], 'success')
+        self.assertIsInstance(result['methods'], list)
+        
+        # 检查返回的方法列表
+        methods = result['methods']
+        self.assertTrue(any(m['name'] == 'data_scaler' for m in methods))
+        self.assertTrue(any(m['name'] == 'missing_value_handler' for m in methods))
+        self.assertTrue(any(m['name'] == 'outlier_detector' for m in methods))
+        
+    def test_get_method_details(self):
+        # 测试获取StandardScaler的详细信息
+        result = self.reader.get_method_details('StandardScaler')
+        self.assertEqual(result['status'], 'success')
+        self.assertEqual(result['method']['name'], 'StandardScaler')
+        
+        # 检查返回的详细信息字段
+        method = result['method']
+        self.assertIn('description', method)
+        self.assertIn('principle', method)
+        self.assertIn('advantages', method)
+        self.assertIn('disadvantages', method)
+        self.assertIn('applicable_scenarios', method)
+        self.assertIn('parameters', method)
+        
+        # 检查参数信息
+        parameters = method['parameters']
+        self.assertIsInstance(parameters, list)
+        if parameters:
+            param = parameters[0]
+            self.assertIn('name', param)
+            self.assertIn('type', param)
+            self.assertIn('default', param)
+            self.assertIn('description', param)
+        
+        # 测试获取不存在的方法
+        result = self.reader.get_method_details('NonExistentMethod')
+        self.assertEqual(result['status'], 'error')
+        
+if __name__ == '__main__':
+    unittest.main() 
\ No newline at end of file
diff --git a/function_old/test_model_manager.py b/function_old/test_model_manager.py
new file mode 100644
index 0000000..47b6471
--- /dev/null
+++ b/function_old/test_model_manager.py
@@ -0,0 +1,99 @@
+import pytest
+import pandas as pd
+import numpy as np
+import mlflow
+from pathlib import Path
+from function.model_manager import ModelManager
+
+class TestModelManager:
+    @pytest.fixture
+    def model_manager(self):
+        return ModelManager()
+    
+    @pytest.fixture
+    def sample_data(self):
+        # 创建测试数据
+        np.random.seed(42)
+        n_samples = 100
+        X = np.random.randn(n_samples, 4)
+        y = (X[:, 0] + X[:, 1] > 0).astype(int)
+        
+        # 保存测试数据
+        data_dir = Path("dataset/dataset_processed/test_data")
+        data_dir.mkdir(parents=True, exist_ok=True)
+        
+        df = pd.DataFrame(X, columns=[f'feature_{i}' for i in range(4)])
+        df['label'] = y
+        
+        data_path = data_dir / "test_data.csv"
+        df.to_csv(data_path, index=False)
+        
+        return str(data_path)
+    
+    @pytest.fixture
+    def trained_model(self, sample_data):
+        # 训练一个简单的模型用于测试
+        from sklearn.ensemble import RandomForestClassifier
+        
+        # 加载数据
+        data = pd.read_csv(sample_data)
+        X = data.drop('label', axis=1).values
+        y = data['label'].values
+        
+        # 训练模型
+        model = RandomForestClassifier(n_estimators=10, random_state=42)
+        model.fit(X, y)
+        
+        # 使用MLflow记录模型
+        with mlflow.start_run() as run:
+            mlflow.sklearn.log_model(model, "model")
+            mlflow.log_param("algorithm", "RandomForestClassifier")
+        
+        return run.info.run_id
+    
+    def test_predict(self, model_manager, sample_data, trained_model):
+        # 设置输出路径
+        output_dir = Path("predictions/test")
+        output_dir.mkdir(parents=True, exist_ok=True)
+        output_path = str(output_dir / "test_predictions.csv")
+        
+        # 执行预测
+        result = model_manager.predict(
+            run_id=trained_model,
+            data_path=sample_data,
+            output_path=output_path,
+            metrics=['accuracy', 'f1']
+        )
+        
+        # 验证结果
+        assert result['status'] == 'success'
+        assert 'prediction' in result
+        assert Path(result['prediction']['output_file']).exists()
+        assert result['prediction']['samples_count'] == 100
+        assert 'accuracy' in result['prediction']['metrics']
+        assert 'f1' in result['prediction']['metrics']
+        
+        # 验证预测结果格式
+        predictions = pd.read_csv(output_path)
+        assert 'prediction' in predictions.columns
+        assert len(predictions) == 100
+    
+    def test_predict_invalid_run_id(self, model_manager, sample_data):
+        result = model_manager.predict(
+            run_id="invalid_run_id",
+            data_path=sample_data,
+            output_path="predictions/test/invalid.csv"
+        )
+        
+        assert result['status'] == 'error'
+        assert '未找到运行ID' in result['message']
+    
+    def test_predict_invalid_data_path(self, model_manager, trained_model):
+        result = model_manager.predict(
+            run_id=trained_model,
+            data_path="invalid/path/data.csv",
+            output_path="predictions/test/invalid.csv"
+        )
+        
+        assert result['status'] == 'error'
+        assert '数据加载失败' in result['message'] 
\ No newline at end of file
diff --git a/function_old/test_model_trainer.py b/function_old/test_model_trainer.py
new file mode 100644
index 0000000..efb19c2
--- /dev/null
+++ b/function_old/test_model_trainer.py
@@ -0,0 +1,85 @@
+import unittest
+import numpy as np
+from function.model_trainer import ModelTrainer
+
+class TestModelTrainer(unittest.TestCase):
+    def setUp(self):
+        self.trainer = ModelTrainer()
+        
+        # 创建测试数据
+        np.random.seed(42)
+        self.X_train = np.random.randn(100, 5)
+        self.y_train = np.random.randint(0, 2, 100)
+        self.X_val = np.random.randn(30, 5)
+        self.y_val = np.random.randint(0, 2, 30)
+        
+    def test_train_model(self):
+        # 准备训练数据
+        train_data = {
+            'features': self.X_train,
+            'labels': self.y_train
+        }
+        
+        val_data = {
+            'features': self.X_val,
+            'labels': self.y_val
+        }
+        
+        # 模型配置
+        model_config = {
+            'algorithm': 'LogisticRegression',
+            'task_type': 'classification',
+            'params': {
+                'random_state': 42
+            }
+        }
+        
+        # 训练模型
+        result = self.trainer.train_model(
+            train_data,
+            val_data,
+            model_config,
+            'test_experiment'
+        )
+        
+        # 验证结果
+        self.assertEqual(result['status'], 'success')
+        self.assertIn('run_id', result)
+        self.assertIn('metrics', result)
+        
+        # 验证指标
+        metrics = result['metrics']
+        self.assertIn('accuracy', metrics)
+        self.assertIn('precision', metrics)
+        self.assertIn('recall', metrics)
+        self.assertIn('f1', metrics)
+        
+    def test_invalid_algorithm(self):
+        # 测试无效的算法名
+        train_data = {
+            'features': self.X_train,
+            'labels': self.y_train
+        }
+        
+        val_data = {
+            'features': self.X_val,
+            'labels': self.y_val
+        }
+        
+        model_config = {
+            'algorithm': 'InvalidAlgorithm',
+            'task_type': 'classification',
+            'params': {}
+        }
+        
+        result = self.trainer.train_model(
+            train_data,
+            val_data,
+            model_config,
+            'test_experiment'
+        )
+        
+        self.assertEqual(result['status'], 'error')
+        
+if __name__ == '__main__':
+    unittest.main() 
\ No newline at end of file
diff --git a/function_old/test_system_monitor.py b/function_old/test_system_monitor.py
new file mode 100644
index 0000000..b591fcb
--- /dev/null
+++ b/function_old/test_system_monitor.py
@@ -0,0 +1,86 @@
+import pytest
+from function.system_monitor import SystemMonitor
+from typing import Dict
+
+class TestSystemMonitor:
+    @pytest.fixture
+    def system_monitor(self):
+        return SystemMonitor()
+    
+    def test_get_system_resources(self, system_monitor):
+        """测试获取系统资源信息"""
+        result = system_monitor.get_system_resources()
+        
+        # 验证返回格式
+        assert isinstance(result, dict)
+        assert 'status' in result
+        assert result['status'] == 'success'
+        assert 'resources' in result
+        assert 'timestamp' in result
+        
+        resources = result['resources']
+        
+        # 验证GPU信息
+        assert 'gpu' in resources
+        if resources['gpu']:  # 如果有GPU
+            gpu = resources['gpu'][0]
+            assert 'id' in gpu
+            assert 'name' in gpu
+            assert 'memory' in gpu
+            assert 'utilization' in gpu
+            assert 'temperature' in gpu
+            
+        # 验证CPU信息
+        assert 'cpu' in resources
+        cpu = resources['cpu']
+        assert 'count' in cpu
+        assert 'utilization' in cpu
+        assert 'memory' in cpu
+        assert 'swap' in cpu
+        
+        # 验证内存信息
+        memory = cpu['memory']
+        assert 'total' in memory
+        assert 'used' in memory
+        assert 'free' in memory
+        assert 'percent' in memory
+        assert memory['total'] > 0
+        assert 0 <= memory['percent'] <= 100
+        
+        # 验证磁盘信息
+        assert 'disk' in resources
+        assert len(resources['disk']) > 0
+        for mount_point, disk_info in resources['disk'].items():
+            assert 'total' in disk_info
+            assert 'used' in disk_info
+            assert 'free' in disk_info
+            assert 'percent' in disk_info
+            assert disk_info['total'] > 0
+            assert 0 <= disk_info['percent'] <= 100
+        
+        # 验证进程信息
+        assert 'processes' in resources
+        processes = resources['processes']
+        assert 'total' in processes
+        assert 'running' in processes
+        assert 'sleeping' in processes
+        assert processes['total'] > 0
+        assert processes['running'] >= 0
+        assert processes['sleeping'] >= 0
+        
+    def test_error_handling(self, system_monitor, monkeypatch):
+        """测试错误处理"""
+        def mock_gpu_error(*args, **kwargs):
+            raise Exception("GPU query failed")
+            
+        # 模拟GPU查询错误
+        monkeypatch.setattr(system_monitor, '_get_gpu_info', mock_gpu_error)
+        
+        result = system_monitor.get_system_resources()
+        assert result['status'] == 'success'  # 即使GPU查询失败，其他资源信息仍应返回
+        assert result['resources']['gpu'] == []  # GPU信息应为空列表
+        
+        # 验证其他资源信息仍然可用
+        assert 'cpu' in result['resources']
+        assert 'disk' in result['resources']
+        assert 'processes' in result['resources'] 
\ No newline at end of file
diff --git a/function_old/处理乳腺癌数据集.py b/function_old/处理乳腺癌数据集.py
new file mode 100644
index 0000000..a84aa3b
--- /dev/null
+++ b/function_old/处理乳腺癌数据集.py
@@ -0,0 +1,6 @@
+import pandas as pd
+from sklearn.datasets import load_breast_cancer
+cancer = load_breast_cancer()
+df = pd.DataFrame(cancer.data, columns=cancer.feature_names)
+df['target'] = cancer.target
+df.to_csv('./dataset/breast_cancer.csv', index=False)