Digital-Twin/gwx/笔记/唐车会议/展示/csv.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "bbe6ec77",
   "metadata": {},
   "source": [
    "处理原始数据origin.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e77e804a",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-12-07T16:58:08.770045Z",
     "iopub.status.busy": "2022-12-07T16:58:08.769489Z",
     "iopub.status.idle": "2022-12-07T16:58:08.826735Z",
     "shell.execute_reply": "2022-12-07T16:58:08.825976Z"
    },
    "origin_pos": 1,
    "tab": [
     "pytorch"
    ]
   },
   "outputs": [],
   "source": [
    "import hashlib\n",
    "import os\n",
    "import tarfile\n",
    "import zipfile\n",
    "import requests\n",
    "import math\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5f97aaa0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-12-07T16:58:08.849212Z",
     "iopub.status.busy": "2022-12-07T16:58:08.848803Z",
     "iopub.status.idle": "2022-12-07T16:58:11.308665Z",
     "shell.execute_reply": "2022-12-07T16:58:11.307847Z"
    },
    "origin_pos": 8,
    "tab": [
     "pytorch"
    ]
   },
   "outputs": [],
   "source": [
    "\n",
    "%matplotlib inline\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "将位姿数据拆分为6个属性"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ebe45f59",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv(\"origin.csv\")\n",
    "data[\"TCP位姿\"] = data[\"TCP位姿\"].str.strip(\"[]\").str.split(\",\") \n",
    "# 使用apply(pd.Series)方法将列表展开为多列，并合并到原来的DataFrame对象中 \n",
    "data = data.join(data[\"TCP位姿\"].apply(pd.Series)) "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6100a284",
   "metadata": {},
   "source": [
    "将时间转化为时间戳"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7bb4fbce",
   "metadata": {},
   "outputs": [],
   "source": [
    "from datetime import datetime\n",
    " \n",
    "def toNum(x):\n",
    "    datetime_object = datetime.strptime(x, '%Y/%m/%d %H:%M:%S')\n",
    "    return datetime_object.timestamp()\n",
    "    # return x.replace(\":\",\"\").replace(\"/\",\"\").replace(\" \",\"\")\n",
    "data[\"createTime\"]=data[\"创建时间\"].map(toNum)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5edec8a4",
   "metadata": {},
   "source": [
    "提取有用的属性"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "08d63378",
   "metadata": {},
   "outputs": [],
   "source": [
    "data1=data[[\"createTime\",0,1,2,3,4,5,\"焊接速度\",\"焊接电压\",\"焊接电流\"]]\n",
    "data1.head()\n",
    "data1.to_csv(\"pos_time_cvv.csv\",index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "574f3b97",
   "metadata": {},
   "source": [
    "删除冗余和异常数据"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "fe01601c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(790966, 10)\n",
      "(185143, 10)\n"
     ]
    }
   ],
   "source": [
    "data=pd.read_csv(\"pos_time_cvv.csv\")\n",
    "print(data.shape)\n",
    "# data=data.drop_duplicates([\"0\",\"1\",\"2\",\"焊接电流\",\"焊接电压\"],keep='first')\n",
    "toDeleteList=[]\n",
    "x=data[\"1\"]\n",
    "y=data[\"2\"]\n",
    "z=data[\"3\"]\n",
    "v=data[\"焊接电压\"]\n",
    "c=data[\"焊接电流\"]\n",
    "time=data[\"createTime\"]\n",
    "x1=[]\n",
    "y1=[]\n",
    "z1=[]\n",
    "v1=[]\n",
    "c1=[]\n",
    "t1=[]\n",
    "count=0\n",
    "lastTime=time[0]\n",
    "lastV=0\n",
    "lastC=0\n",
    "lastX=0\n",
    "lastY=0\n",
    "lastZ=0\n",
    "thisTime=0\n",
    "colors=['b', 'g', 'r', 'c', 'm', 'y', 'k', 'w']\n",
    "colorCnt=0\n",
    "for tup in zip(x,y,z,time,v,c):\n",
    "    # print(tup,type(tup[1:]))\n",
    "\n",
    "    thisTime=tup[3]\n",
    "    if (tup[4]==lastV and tup[5]==lastC)or\\\n",
    "        (lastX==tup[0] and lastY==tup[1] and lastZ==tup[2])or tup[5]==400 or\\\n",
    "        abs(lastC-tup[5])>30:\n",
    "        # print(count)\n",
    "        colorCnt+=1\n",
    "        toDeleteList.append(count)\n",
    "        \n",
    "       \n",
    "        \n",
    "        # print(len(x1))\n",
    " \n",
    "        x1=[]\n",
    "        y1=[]\n",
    "        z1=[]\n",
    "        v1=[]\n",
    "        c1=[]\n",
    "        t1=[]\n",
    "    count+=1    \n",
    "    lastV=tup[4]\n",
    "    lastC=tup[5]\n",
    "    lastX=tup[0]\n",
    "    lastY=tup[1]\n",
    "    lastZ=tup[2]\n",
    "    lastTime=thisTime\n",
    "data=data.drop(toDeleteList)\n",
    "print(data.values.shape)\n",
    "data.to_csv(\"delete_same_and_sharp.csv\",index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "92aba770",
   "metadata": {},
   "source": [
    "提取line(因为轨迹是一条条的线，所以可以把轨迹投影到xoy平面)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "b02274bc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(183427, 10)\n",
      "(1320, 10)\n"
     ]
    }
   ],
   "source": [
    "\n",
    "# data=data.drop_duplicates([\"0\",\"1\",\"2\",\"焊接电流\",\"焊接电压\"],keep='first')\n",
    "def dis(x1,y1,x2,y2):\n",
    "    return math.sqrt((x1-x2)**2+(y1-y2)**2)\n",
    "data=pd.read_csv(\"delete_same_and_sharp3.csv\")\n",
    "x=data[\"1\"]\n",
    "y=data[\"2\"]\n",
    "z=data[\"3\"]\n",
    "v=data[\"焊接电压\"]\n",
    "c=data[\"焊接电流\"]\n",
    "time=data[\"createTime\"]\n",
    "toDeleteList=[]\n",
    "x1=[]\n",
    "y1=[]\n",
    "z1=[]\n",
    "v1=[]\n",
    "c1=[]\n",
    "t1=[]\n",
    "count=0\n",
    "lastTime=0\n",
    "lastV=0\n",
    "lastC=0\n",
    "lastX=0\n",
    "lastY=0\n",
    "lastZ=0\n",
    "thisTime=0\n",
    "colors=['b', 'g', 'r', 'c', 'm', 'y', 'k', 'w']\n",
    "colorCnt=0\n",
    "for tup in zip(x,y,z,time,v,c):\n",
    "    # print(tup,type(tup[1:]))\n",
    "\n",
    "    thisTime=tup[3]\n",
    "    if  dis(lastY,lastZ,tup[1],tup[2])<1:\n",
    "        # print(count)\n",
    "        colorCnt+=1\n",
    "        toDeleteList.append(count)\n",
    "        \n",
    "    \n",
    "        \n",
    "        # print(len(x1))\n",
    "\n",
    "        x1=[]\n",
    "        y1=[]\n",
    "        z1=[]\n",
    "        v1=[]\n",
    "        c1=[]\n",
    "        t1=[]\n",
    "    count+=1    \n",
    "    lastV=tup[4]\n",
    "    lastC=tup[5]\n",
    "    lastX=tup[0]\n",
    "    lastY=tup[1]\n",
    "    lastZ=tup[2]\n",
    "    lastTime=thisTime\n",
    "# print(toDeleteList)\n",
    "print(data.shape)\n",
    "data=data.drop(toDeleteList)\n",
    "# print(data['createTime'])\n",
    "\n",
    "data.to_csv(\"line.csv\",index=False)\n",
    "\n",
    "print(data.shape)\n",
    "# data.to_csv(\"delete_same_and_sharp7.csv\",index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b937fa76",
   "metadata": {},
   "source": [
    "合并相近的line（离得太近的合并到一起，减少点的数量）"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "37a9a5b7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1320, 10)\n",
      "(872, 10)\n"
     ]
    }
   ],
   "source": [
    "def dis(x1,y1,x2,y2):\n",
    "    return math.sqrt((x1-x2)**2+(y1-y2)**2)\n",
    "data=pd.read_csv(\"line.csv\")\n",
    "x=data[\"1\"]\n",
    "y=data[\"2\"]\n",
    "z=data[\"3\"]\n",
    "v=data[\"焊接电压\"]\n",
    "c=data[\"焊接电流\"]\n",
    "time=data[\"createTime\"]\n",
    "toDeleteList=[]\n",
    "x1=[]\n",
    "y1=[]\n",
    "z1=[]\n",
    "v1=[]\n",
    "c1=[]\n",
    "t1=[]\n",
    "count=0\n",
    "lastTime=0\n",
    "lastV=0\n",
    "lastC=0\n",
    "lastX=0\n",
    "lastY=0\n",
    "lastZ=0\n",
    "thisTime=0\n",
    "colors=['b', 'g', 'r', 'c', 'm', 'y', 'k', 'w']\n",
    "colorCnt=0\n",
    "for tup in zip(x,y,z,time,v,c):\n",
    "    # print(tup,type(tup[1:]))\n",
    "\n",
    "    thisTime=tup[3]\n",
    "    if  abs(lastTime-tup[3])<100:\n",
    "        # print(count)\n",
    "        colorCnt+=1\n",
    "        toDeleteList.append(count)\n",
    "        \n",
    "    \n",
    "        \n",
    "        # print(len(x1))\n",
    "\n",
    "        x1=[]\n",
    "        y1=[]\n",
    "        z1=[]\n",
    "        v1=[]\n",
    "        c1=[]\n",
    "        t1=[]\n",
    "    count+=1    \n",
    "    lastV=tup[4]\n",
    "    lastC=tup[5]\n",
    "    lastX=tup[0]\n",
    "    lastY=tup[1]\n",
    "    lastZ=tup[2]\n",
    "    lastTime=thisTime\n",
    "# print(toDeleteList)\n",
    "print(data.shape)\n",
    "data=data.drop(toDeleteList)\n",
    "# print(data['createTime'])\n",
    "\n",
    "data.to_csv(\"line0.csv\",index=False)\n",
    "\n",
    "print(data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "96afb190",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>创建时间</th>\n",
       "      <th>在线</th>\n",
       "      <th>驱动已打开</th>\n",
       "      <th>操作模式</th>\n",
       "      <th>当前程序号</th>\n",
       "      <th>当前程序步</th>\n",
       "      <th>TCP位姿</th>\n",
       "      <th>焊接电流</th>\n",
       "      <th>驱动打开时间</th>\n",
       "      <th>停止采集日期</th>\n",
       "      <th>...</th>\n",
       "      <th>焊接状态.1</th>\n",
       "      <th>保护气流量</th>\n",
       "      <th>焊接速度</th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>createTime</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2022/8/1 8:08:38</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0.0</td>\n",
       "      <td>[-3.101456, -622.703380, -527.500837, -0.50521...</td>\n",
       "      <td>329.0</td>\n",
       "      <td>42806478193644</td>\n",
       "      <td>2022-8-2 0:47:18.003</td>\n",
       "      <td>...</td>\n",
       "      <td>False</td>\n",
       "      <td>0.029388</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-3.101456</td>\n",
       "      <td>-622.703380</td>\n",
       "      <td>-527.500837</td>\n",
       "      <td>-0.505214</td>\n",
       "      <td>108.646219</td>\n",
       "      <td>-4.107130</td>\n",
       "      <td>1.659313e+09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2022/8/1 8:08:39</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0.0</td>\n",
       "      <td>[-3.101456, -622.703380, -527.500837, -0.50521...</td>\n",
       "      <td>329.0</td>\n",
       "      <td>42806478193644</td>\n",
       "      <td>2022-8-2 0:47:18.003</td>\n",
       "      <td>...</td>\n",
       "      <td>False</td>\n",
       "      <td>0.029388</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-3.101456</td>\n",
       "      <td>-622.703380</td>\n",
       "      <td>-527.500837</td>\n",
       "      <td>-0.505214</td>\n",
       "      <td>108.646219</td>\n",
       "      <td>-4.107130</td>\n",
       "      <td>1.659313e+09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2022/8/1 8:08:40</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0.0</td>\n",
       "      <td>[-3.101456, -622.703380, -527.500837, -0.50521...</td>\n",
       "      <td>329.0</td>\n",
       "      <td>42806478193644</td>\n",
       "      <td>2022-8-2 0:47:18.003</td>\n",
       "      <td>...</td>\n",
       "      <td>False</td>\n",
       "      <td>0.029388</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-3.101456</td>\n",
       "      <td>-622.703380</td>\n",
       "      <td>-527.500837</td>\n",
       "      <td>-0.505214</td>\n",
       "      <td>108.646219</td>\n",
       "      <td>-4.107130</td>\n",
       "      <td>1.659313e+09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2022/8/1 8:08:41</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0.0</td>\n",
       "      <td>[-3.101456, -622.703380, -527.500837, -0.50521...</td>\n",
       "      <td>329.0</td>\n",
       "      <td>42806478193644</td>\n",
       "      <td>2022-8-2 0:47:18.003</td>\n",
       "      <td>...</td>\n",
       "      <td>False</td>\n",
       "      <td>0.029388</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-3.101456</td>\n",
       "      <td>-622.703380</td>\n",
       "      <td>-527.500837</td>\n",
       "      <td>-0.505214</td>\n",
       "      <td>108.646219</td>\n",
       "      <td>-4.107130</td>\n",
       "      <td>1.659313e+09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2022/8/1 8:08:42</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0.0</td>\n",
       "      <td>[-3.101456, -622.703380, -527.500837, -0.50521...</td>\n",
       "      <td>329.0</td>\n",
       "      <td>42806478193644</td>\n",
       "      <td>2022-8-2 0:47:18.003</td>\n",
       "      <td>...</td>\n",
       "      <td>False</td>\n",
       "      <td>0.029388</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-3.101456</td>\n",
       "      <td>-622.703380</td>\n",
       "      <td>-527.500837</td>\n",
       "      <td>-0.505214</td>\n",
       "      <td>108.646219</td>\n",
       "      <td>-4.107130</td>\n",
       "      <td>1.659313e+09</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 37 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               创建时间    在线  驱动已打开  操作模式 当前程序号  当前程序步  \\\n",
       "0  2022/8/1 8:08:38  True   True   1.0   NaN  0.0.0   \n",
       "1  2022/8/1 8:08:39  True   True   1.0   NaN  0.0.0   \n",
       "2  2022/8/1 8:08:40  True   True   1.0   NaN  0.0.0   \n",
       "3  2022/8/1 8:08:41  True   True   1.0   NaN  0.0.0   \n",
       "4  2022/8/1 8:08:42  True   True   1.0   NaN  0.0.0   \n",
       "\n",
       "                                               TCP位姿   焊接电流          驱动打开时间  \\\n",
       "0  [-3.101456, -622.703380, -527.500837, -0.50521...  329.0  42806478193644   \n",
       "1  [-3.101456, -622.703380, -527.500837, -0.50521...  329.0  42806478193644   \n",
       "2  [-3.101456, -622.703380, -527.500837, -0.50521...  329.0  42806478193644   \n",
       "3  [-3.101456, -622.703380, -527.500837, -0.50521...  329.0  42806478193644   \n",
       "4  [-3.101456, -622.703380, -527.500837, -0.50521...  329.0  42806478193644   \n",
       "\n",
       "                 停止采集日期  ...  焊接状态.1     保护气流量  焊接速度          0            1  \\\n",
       "0  2022-8-2 0:47:18.003  ...   False  0.029388   0.0  -3.101456  -622.703380   \n",
       "1  2022-8-2 0:47:18.003  ...   False  0.029388   0.0  -3.101456  -622.703380   \n",
       "2  2022-8-2 0:47:18.003  ...   False  0.029388   0.0  -3.101456  -622.703380   \n",
       "3  2022-8-2 0:47:18.003  ...   False  0.029388   0.0  -3.101456  -622.703380   \n",
       "4  2022-8-2 0:47:18.003  ...   False  0.029388   0.0  -3.101456  -622.703380   \n",
       "\n",
       "             2          3           4          5    createTime  \n",
       "0  -527.500837  -0.505214  108.646219  -4.107130  1.659313e+09  \n",
       "1  -527.500837  -0.505214  108.646219  -4.107130  1.659313e+09  \n",
       "2  -527.500837  -0.505214  108.646219  -4.107130  1.659313e+09  \n",
       "3  -527.500837  -0.505214  108.646219  -4.107130  1.659313e+09  \n",
       "4  -527.500837  -0.505214  108.646219  -4.107130  1.659313e+09  \n",
       "\n",
       "[5 rows x 37 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print(data.iloc[[0,1,2], :])\n",
    "data.head()\n",
    "# data.to_csv(\"origin_TimePos.csv\",index=False)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.16 ('torch_py3.9')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.16"
  },
  "vscode": {
   "interpreter": {
    "hash": "2c93e8e09754cf1cd40b55c7c8fefeaff6ac58d6a85dd394fdad2eae466f5690"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}