{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "3e0403c4",
   "metadata": {},
   "source": [
    "# Postprocessing upper line"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "7b11043c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "from pathlib import Path\n",
    "import numpy as np\n",
    "from matplotlib import pyplot as plt\n",
    "import pandas as pd\n",
    "from scipy.signal import savgol_filter\n",
    "from scipy.signal import medfilt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8fce6594",
   "metadata": {},
   "source": [
    "Import video"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "853bba52",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Opened: True, FPS: 59.94005994005994, Total Frames: 227.0\n"
     ]
    }
   ],
   "source": [
    "video_number = \"3\"\n",
    "# Define the relative path to the video file\n",
    "notebook_dir = Path().resolve()\n",
    "project_root = notebook_dir.parent.parent\n",
    "video_path = (\n",
    "    project_root\n",
    "    / \"data\"\n",
    "    / f\"recording_{video_number}\"\n",
    "    / f\"Recording_{video_number}.mp4\"\n",
    ")\n",
    "video_path = str(video_path)\n",
    "\n",
    "# Load the video\n",
    "cap = cv2.VideoCapture(video_path)\n",
    "\n",
    "# Check\n",
    "print(\n",
    "    f\"Opened: {cap.isOpened()}, FPS: {cap.get(cv2.CAP_PROP_FPS)}, Total Frames: {cap.get(cv2.CAP_PROP_FRAME_COUNT)}\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a3a38b6",
   "metadata": {},
   "source": [
    "Import data (lane points)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "3dc1d6c5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1320.0, 1049.0, 1537.0, 447.0], [1319.0, 1051.0, 1538.0, 446.0], [1316.0, 1053.0, 1536.0, 446.0], [1312.0, 1053.0, 1534.0, 445.0], [1308.0, 1052.0, 1530.0, 444.0], [1304.0, 1051.0, 1525.0, 442.0], [1299.0, 1049.0, 1521.0, 440.0], [1296.0, 1046.0, 1517.0, 439.0], [1292.0, 1044.0, 1512.0, 439.0], [1285.0, 1042.0, 1508.0, 436.0], [1279.0, 1041.0, 1503.0, 434.0], [1276.0, 1039.0, 1501.0, 432.0], [1275.0, 1037.0, 1499.0, 433.0], [1268.0, 1035.0, 1493.0, 430.0], [1262.0, 1033.0, 1488.0, 428.0], [1257.0, 1031.0, 1484.0, 426.0], [1253.0, 1030.0, 1480.0, 425.0], [1247.0, 1027.0, 1475.0, 422.0], [1244.0, 1025.0, 1471.0, 420.0], [1242.0, 1023.0, 1468.0, 418.0], [1238.0, 1021.0, 1463.0, 416.0], [1234.0, 1019.0, 1459.0, 417.0], [1234.0, 1016.0, 1456.0, 417.0], [1233.0, 1016.0, 1454.0, 415.0], [1232.0, 1016.0, 1452.0, 411.0], [1225.0, 1015.0, 1449.0, 406.0], [1218.0, 1014.0, 1446.0, 403.0], [1213.0, 1013.0, 1441.0, 401.0], [1216.0, 1012.0, 1441.0, 401.0], [1214.0, 1009.0, 1436.0, 399.0], [1207.0, 1006.0, 1429.0, 396.0], [1203.0, 1003.0, 1424.0, 394.0], [1201.0, 1002.0, 1422.0, 393.0], [1200.0, 1002.0, 1421.0, 392.0], [1197.0, 1003.0, 1418.0, 391.0], [1191.0, 1003.0, 1416.0, 389.0], [1185.0, 1003.0, 1415.0, 387.0], [1180.0, 1003.0, 1414.0, 387.0], [1180.0, 1001.0, 1412.0, 386.0], [1177.0, 1000.0, 1407.0, 383.0], [1174.0, 1000.0, 1405.0, 380.0], [1171.0, 998.0, 1402.0, 378.0], [1169.0, 997.0, 1400.0, 377.0], [1167.0, 995.0, 1395.0, 375.0], [1168.0, 993.0, 1393.0, 375.0], [1167.0, 991.0, 1392.0, 373.0], [1164.0, 989.0, 1391.0, 373.0], [1160.0, 987.0, 1388.0, 370.0], [1158.0, 986.0, 1385.0, 368.0], [1156.0, 984.0, 1381.0, 367.0], [1152.0, 983.0, 1380.0, 365.0], [1147.0, 982.0, 1381.0, 364.0], [1143.0, 982.0, 1380.0, 363.0], [1142.0, 982.0, 1377.0, 361.0], [1140.0, 982.0, 1372.0, 360.0], [1138.0, 982.0, 1369.0, 358.0], [1136.0, 981.0, 1366.0, 358.0], [1133.0, 980.0, 1363.0, 359.0], [1131.0, 979.0, 1362.0, 358.0], [1128.0, 978.0, 1361.0, 358.0], [1126.0, 977.0, 1359.0, 359.0], [1124.0, 976.0, 1358.0, 359.0], [1123.0, 976.0, 1356.0, 358.0], [1121.0, 976.0, 1352.0, 358.0], [1119.0, 976.0, 1348.0, 358.0], [1116.0, 977.0, 1346.0, 359.0], [1113.0, 979.0, 1345.0, 360.0], [1112.0, 979.0, 1343.0, 361.0], [1111.0, 979.0, 1342.0, 362.0], [1108.0, 981.0, 1340.0, 363.0], [1106.0, 982.0, 1336.0, 366.0], [1104.0, 983.0, 1333.0, 367.0], [1104.0, 986.0, 1332.0, 369.0], [1102.0, 989.0, 1328.0, 372.0], [1101.0, 990.0, 1326.0, 373.0], [1099.0, 992.0, 1325.0, 374.0], [1098.0, 995.0, 1323.0, 377.0], [1097.0, 996.0, 1322.0, 380.0], [1095.0, 999.0, 1319.0, 384.0], [1094.0, 1003.0, 1317.0, 387.0], [1092.0, 1007.0, 1316.0, 390.0], [1090.0, 1012.0, 1315.0, 391.0], [1087.0, 1018.0, 1313.0, 396.0], [1085.0, 1022.0, 1311.0, 400.0], [1083.0, 1028.0, 1309.0, 404.0], [1081.0, 1033.0, 1307.0, 410.0], [1079.0, 1037.0, 1305.0, 415.0], [1078.0, 1040.0, 1305.0, 416.0], [1077.0, 1043.0, 1303.0, 420.0], [1074.0, 1046.0, 1302.0, 422.0], [1072.0, 1047.0, 1300.0, 426.0], [1070.0, 1049.0, 1300.0, 426.0], [1069.0, 1051.0, 1297.0, 430.0], [1068.0, 1053.0, 1296.0, 432.0], [1066.0, 1054.0, 1296.0, 434.0], [1063.0, 1056.0, 1296.0, 435.0], [1061.0, 1057.0, 1295.0, 437.0], [1061.0, 1058.0, 1292.0, 438.0], [1060.0, 1059.0, 1288.0, 439.0], [1060.0, 1060.0, 1285.0, 441.0], [1057.0, 1061.0, 1285.0, 442.0], [1054.0, 1061.0, 1285.0, 444.0], [1052.0, 1063.0, 1285.0, 445.0], [1051.0, 1064.0, 1284.0, 445.0], [1049.0, 1065.0, 1283.0, 448.0], [1046.0, 1066.0, 1282.0, 449.0], [1044.0, 1067.0, 1282.0, 450.0], [1042.0, 1067.0, 1280.0, 450.0], [1041.0, 1068.0, 1278.0, 451.0], [1040.0, 1068.0, 1277.0, 451.0], [1039.0, 1070.0, 1275.0, 454.0], [1038.0, 1071.0, 1273.0, 455.0], [1036.0, 1073.0, 1271.0, 458.0], [1035.0, 1072.0, 1270.0, 456.0], [1033.0, 1072.0, 1269.0, 458.0], [1031.0, 1072.0, 1268.0, 457.0], [1029.0, 1071.0, 1266.0, 458.0], [1028.0, 1071.0, 1263.0, 458.0], [1027.0, 1073.0, 1262.0, 457.0], [1026.0, 1073.0, 1261.0, 457.0], [1025.0, 1074.0, 1260.0, 458.0], [1022.0, 1075.0, 1259.0, 458.0], [1020.0, 1075.0, 1257.0, 458.0], [1019.0, 1075.0, 1256.0, 460.0], [1018.0, 1075.0, 1255.0, 461.0], [1017.0, 1075.0, 1253.0, 462.0], [1013.0, 1076.0, 1251.0, 461.0], [1012.0, 1076.0, 1249.0, 461.0], [1011.0, 1077.0, 1248.0, 461.0], [1011.0, 1078.0, 1247.0, 461.0], [1010.0, 1079.0, 1246.0, 461.0], [1009.0, 1079.0, 1245.0, 462.0], [1009.0, 1078.0, 1244.0, 462.0], [1008.0, 1078.0, 1243.0, 462.0], [1010.0, 1078.0, 1243.0, 464.0], [1012.0, 1078.0, 1242.0, 462.0], [1014.0, 1078.0, 1244.0, 462.0], [1018.0, 1079.0, 1248.0, 461.0], [1024.0, 1079.0, 1253.0, 462.0], [1030.0, 1079.0, 1257.0, 462.0], [1035.0, 1079.0, 1262.0, 460.0], [1039.0, 1079.0, 1265.0, 463.0], [1042.0, 1079.0, 1267.0, 465.0], [1044.0, 1079.0, 1269.0, 463.0], [1046.0, 1079.0, 1271.0, 465.0], [1047.0, 1079.0, 1272.0, 464.0], [1050.0, 1079.0, 1272.0, 468.0], [1053.0, 1079.0, 1274.0, 472.0], [1058.0, 1079.0, 1276.0, 475.0], [1064.0, 1079.0, 1279.0, 478.0], [1067.0, 1079.0, 1283.0, 483.0], [1069.0, 1079.0, 1290.0, 486.0], [1072.0, 1079.0, 1295.0, 487.0], [1077.0, 1080.0, 1299.0, 487.0], [1080.0, 1080.0, 1299.0, 493.0], [1082.0, 1080.0, 1301.0, 494.0], [1084.0, 1080.0, 1300.0, 497.0], [1085.0, 1080.0, 1303.0, 496.0], [1086.0, 1080.0, 1306.0, 494.0], [1089.0, 1080.0, 1307.0, 495.0], [1089.0, 1080.0, 1307.0, 495.0], [1091.0, 1080.0, 1306.0, 502.0], [1092.0, 1080.0, 1309.0, 505.0], [1092.0, 1080.0, 1311.0, 505.0], [1094.0, 1080.0, 1313.0, 505.0], [1097.0, 1080.0, 1314.0, 501.0], [1102.0, 1080.0, 1313.0, 505.0], [1106.0, 1080.0, 1315.0, 506.0], [1109.0, 1080.0, 1318.0, 506.0], [1113.0, 1080.0, 1321.0, 509.0], [1115.0, 1080.0, 1327.0, 506.0], [1118.0, 1080.0, 1332.0, 505.0], [1120.0, 1080.0, 1335.0, 507.0], [1122.0, 1080.0, 1336.0, 508.0], [1125.0, 1080.0, 1336.0, 509.0], [1129.0, 1080.0, 1336.0, 509.0], [1133.0, 1080.0, 1337.0, 509.0], [1135.0, 1081.0, 1340.0, 510.0], [1134.0, 1081.0, 1345.0, 510.0], [1136.0, 1081.0, 1350.0, 512.0], [1138.0, 1081.0, 1354.0, 512.0], [1139.0, 1081.0, 1355.0, 512.0], [1143.0, 1081.0, 1357.0, 512.0], [1145.0, 1081.0, 1361.0, 508.0], [1147.0, 1081.0, 1360.0, 509.0], [1147.0, 1081.0, 1360.0, 511.0], [1149.0, 1081.0, 1362.0, 511.0], [1150.0, 1081.0, 1366.0, 511.0], [1151.0, 1081.0, 1367.0, 512.0], [1152.0, 1081.0, 1368.0, 512.0], [1154.0, 1081.0, 1367.0, 512.0], [1154.0, 1081.0, 1367.0, 514.0], [1155.0, 1081.0, 1368.0, 517.0], [1157.0, 1081.0, 1370.0, 515.0], [1158.0, 1081.0, 1499.0, 173.0], [1158.0, 1081.0, 1495.0, 187.0], [1159.0, 1081.0, 1495.0, 188.0], [1158.0, 1081.0, 1495.0, 188.0], [1158.0, 1081.0, 1496.0, 187.0], [1158.0, 1081.0, 1497.0, 187.0], [1158.0, 1081.0, 1497.0, 188.0], [1158.0, 1081.0, 1498.0, 188.0], [1159.0, 1081.0, 1498.0, 191.0], [1159.0, 1081.0, 1499.0, 191.0], [1160.0, 1081.0, 1499.0, 191.0], [1160.0, 1081.0, 1500.0, 189.0], [1161.0, 1081.0, 1505.0, 176.0], [1161.0, 1081.0, 1375.0, 518.0], [1161.0, 1081.0, 1374.0, 522.0], [1162.0, 1081.0, 1506.0, 175.0], [1161.0, 1081.0, 1506.0, 175.0], [1161.0, 1081.0, 1507.0, 177.0], [1163.0, 1081.0, 1509.0, 178.0], [1164.0, 1081.0, 1503.0, 190.0], [1166.0, 1081.0, 1500.0, 192.0], [1168.0, 1081.0, 1499.0, 192.0], [1166.0, 1081.0, 1499.0, 192.0], [1167.0, 1081.0, 1500.0, 193.0], [1169.0, 1081.0, 1502.0, 191.0], [1170.0, 1081.0, 1503.0, 193.0], [1171.0, 1081.0, 1509.0, 189.0], [1171.0, 1081.0, 1515.0, 183.0], [1173.0, 1081.0, 1518.0, 182.0], [1175.0, 1081.0, 1516.0, 183.0], [1180.0, 1081.0, 1517.0, 183.0], [1183.0, 1081.0, 1518.0, 184.0], [1184.0, 1081.0, 1509.0, 196.0]]\n"
     ]
    }
   ],
   "source": [
    "# Define the path to the CSV file\n",
    "input_data_path = (\n",
    "    project_root\n",
    "    / \"data\"\n",
    "    / \"auxiliary_data\"\n",
    "    / \"lane_points\"\n",
    "    / f\"lane_points_raw_{video_number}.csv\"\n",
    ")\n",
    "\n",
    "# Load the CSV file into a DataFrame\n",
    "lane_points = pd.read_csv(input_data_path)\n",
    "\n",
    "# get the upper lines from input data\n",
    "upper_lines = []\n",
    "for i in range(len(lane_points)):\n",
    "    if lane_points[\"up_left_x\"][i] == \"\":\n",
    "        upper_lines.append([np.nan, np.nan, np.nan, np.nan])\n",
    "    else:\n",
    "        upper_lines.append(\n",
    "            [\n",
    "                float(lane_points[\"up_left_x\"][i]),\n",
    "                float(lane_points[\"up_left_y\"][i]),\n",
    "                float(lane_points[\"up_right_x\"][i]),\n",
    "                float(lane_points[\"up_right_y\"][i]),\n",
    "            ]\n",
    "        )\n",
    "\n",
    "bottom_lines = []\n",
    "for i in range(len(lane_points)):\n",
    "    if lane_points[\"bottom_left_x\"][i] == \"\":\n",
    "        bottom_lines.append([np.nan, np.nan, np.nan, np.nan])\n",
    "    else:\n",
    "        bottom_lines.append(\n",
    "            [\n",
    "                float(lane_points[\"bottom_left_x\"][i]),\n",
    "                float(lane_points[\"bottom_left_y\"][i]),\n",
    "                float(lane_points[\"bottom_right_x\"][i]),\n",
    "                float(lane_points[\"bottom_right_y\"][i]),\n",
    "            ]\n",
    "        )\n",
    "\n",
    "left_lines = []\n",
    "for i in range(len(lane_points)):\n",
    "    if lane_points[\"bottom_left_x\"][i] == \"\":\n",
    "        left_lines.append([np.nan, np.nan, np.nan, np.nan])\n",
    "    else:\n",
    "        left_lines.append(\n",
    "            [\n",
    "                float(lane_points[\"bottom_left_x\"][i]),\n",
    "                float(lane_points[\"bottom_left_y\"][i]),\n",
    "                float(lane_points[\"up_left_x\"][i]),\n",
    "                float(lane_points[\"up_left_y\"][i]),\n",
    "            ]\n",
    "        )\n",
    "\n",
    "right_lines = []\n",
    "for i in range(len(lane_points)):\n",
    "    if lane_points[\"bottom_right_x\"][i] == \"\":\n",
    "        right_lines.append([np.nan, np.nan, np.nan, np.nan])\n",
    "    else:\n",
    "        right_lines.append(\n",
    "            [\n",
    "                float(lane_points[\"bottom_right_x\"][i]),\n",
    "                float(lane_points[\"bottom_right_y\"][i]),\n",
    "                float(lane_points[\"up_right_x\"][i]),\n",
    "                float(lane_points[\"up_right_y\"][i]),\n",
    "            ]\n",
    "        )\n",
    "print(right_lines)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fe4f6dc7",
   "metadata": {},
   "source": [
    "Import video movement"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "62e0e2ee",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Average movement video 3: 5.18\n"
     ]
    }
   ],
   "source": [
    "\"\"\" Import data of the movement from Camera_Motion_Test.ipynb \"\"\"\n",
    "avg_movement_list = [0.57, 3.86, 5.18, 0.10, 0.16, 3.26, 0.52]\n",
    "avg_movement = avg_movement_list[int(video_number) - 1]\n",
    "print(f\"Average movement video {int(video_number)}: {avg_movement}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bf64b652",
   "metadata": {},
   "source": [
    "## Functions"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "add13ea0",
   "metadata": {},
   "source": [
    "Extend the input lines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "250242b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Funzione per estendere una linea\n",
    "def extend_line(x1, y1, x2, y2, length=1000):\n",
    "    # Calcola la lunghezza originale della linea\n",
    "    dx, dy = x2 - x1, y2 - y1\n",
    "    norm = np.sqrt(dx**2 + dy**2)  # Distanza euclidea tra i due punti\n",
    "\n",
    "    # Evita divisioni per zero\n",
    "    if norm == 0:\n",
    "        return x1, y1, x2, y2\n",
    "\n",
    "    # Calcola i punti estesi\n",
    "    x1_ext = int(x1 - length * (dx / norm))\n",
    "    y1_ext = int(y1 - length * (dy / norm))\n",
    "    x2_ext = int(x2 + length * (dx / norm))\n",
    "    y2_ext = int(y2 + length * (dy / norm))\n",
    "\n",
    "    return x1_ext, y1_ext, x2_ext, y2_ext"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f699a316",
   "metadata": {},
   "source": [
    "Draw line-lines on a frame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "id": "8e420420",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"Disegna la linea sul frame\"\"\"\n",
    "\n",
    "\n",
    "def write_line_on_frame(frame, line):\n",
    "    # Create a copy of the original frame to draw the first line\n",
    "    modified_frame = np.copy(frame)\n",
    "\n",
    "    if line is not None:\n",
    "        print(line)\n",
    "        x1, y1, x2, y2 = line\n",
    "\n",
    "        # Allunga la linea di 1000 pixel da entrambe le estremità\n",
    "        x1_ext, y1_ext, x2_ext, y2_ext = extend_line(x1, y1, x2, y2, length=1000)\n",
    "\n",
    "        # Disegna la linea estesa\n",
    "        cv2.line(modified_frame, (x1_ext, y1_ext), (x2_ext, y2_ext), (0, 255, 0), 2)\n",
    "\n",
    "    # return the modified frame\n",
    "    return modified_frame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "id": "bb85c260",
   "metadata": {},
   "outputs": [],
   "source": [
    "def write_lines_on_frame(frame, lines):\n",
    "    for i in range(len(lines)):\n",
    "        # print('linea', i, ':', lines[i])\n",
    "        frame = write_line_on_frame(frame, lines[i])\n",
    "    return frame"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d5401a53",
   "metadata": {},
   "source": [
    "plot the trajectory of the points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "ed722a4f",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\" Plot the trajectory of the points\"\"\"  # DA CANCELLARE!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n",
    "\n",
    "\n",
    "def plot_trajectory(df, title=\"Trajectory\"):\n",
    "    plt.figure(figsize=(8, 6))\n",
    "    plt.plot(df[\"X\"], -df[\"Y\"], \"o-\", label=\"Cleaned Trajectory\")\n",
    "    plt.xlabel(\"X Coordinate\")\n",
    "    plt.ylabel(\"Y Coordinate\")\n",
    "    plt.title(title)\n",
    "    plt.legend()\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b582209b",
   "metadata": {},
   "source": [
    "Get the points to process"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "28285f12",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\" get the intersection of each line with the orthogonal line passing through the origin\"\"\"\n",
    "\n",
    "\n",
    "def get_relevant_points(lines):\n",
    "    # initialize the list of intersection points\n",
    "    intersection_points = []\n",
    "    for line in lines:\n",
    "        if line is not None:\n",
    "            x1, y1, x2, y2 = line\n",
    "            # Calculate the line coefficients (a, b, c) for ax + by + c = 0\n",
    "            a = y2 - y1\n",
    "            b = x1 - x2\n",
    "            c = x2 * y1 - x1 * y2\n",
    "\n",
    "            # Calculate the intersection with the orthogonal line passing through the origin\n",
    "            # The orthogonal line has equation bx - ay = 0\n",
    "            denominator = a**2 + b**2\n",
    "            if denominator == 0:\n",
    "                intersection_points.append((0, 0))\n",
    "                continue  # Skip degenerate lines\n",
    "\n",
    "            x = -a * c / denominator\n",
    "            y = -b * c / denominator\n",
    "\n",
    "            # Append the intersection point\n",
    "            intersection_points.append((x, y))\n",
    "        else:\n",
    "            # Append a default point if the line is None\n",
    "            intersection_points.append((0, 0))\n",
    "\n",
    "    return intersection_points"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3f67d32f",
   "metadata": {},
   "source": [
    "Remove outliers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "0f6c89a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\" execute an iterated algorithm for removing outliers,\n",
    "    the exit threshold is set as two times the mean of the distances between points at the first iteration\"\"\"\n",
    "\n",
    "\n",
    "def remove_outliers_iterated(df, threshold_factor=1):\n",
    "    # Ensure 'X' and 'Y' are numeric\n",
    "    df[[\"X\", \"Y\"]] = df[[\"X\", \"Y\"]].apply(pd.to_numeric, errors=\"coerce\")\n",
    "\n",
    "    first_iteration = True\n",
    "    exit_threshold = 10000\n",
    "    max_dist = np.inf\n",
    "\n",
    "    # Compute the distance between consecutive points\n",
    "    dx = df[\"X\"].diff()\n",
    "    dy = df[\"Y\"].diff()\n",
    "\n",
    "    # compute distances\n",
    "    df[\"distance\"] = np.sqrt(dx**2 + dy**2)\n",
    "    print(df[\"distance\"])\n",
    "\n",
    "    # remove 0,0 points\n",
    "    df = df[(df[\"X\"] != 0) | (df[\"Y\"] != 0)]\n",
    "\n",
    "    while max_dist > exit_threshold:\n",
    "        # set the mean to exit the while\n",
    "        if first_iteration:\n",
    "            first_iteration = False\n",
    "            mean_dist = np.mean(df[\"distance\"])\n",
    "            std = np.std(df[\"distance\"])\n",
    "            print(\"mean:\", mean_dist, \"std:\", std)\n",
    "            if std > mean_dist:\n",
    "                exit_threshold = threshold_factor * std\n",
    "            else:\n",
    "                exit_threshold = threshold_factor * 2 * mean_dist\n",
    "\n",
    "        # set the threshold\n",
    "        threshold_dist = 2 * np.mean(df[\"distance\"])\n",
    "        # remove outliers\n",
    "        df = df[\n",
    "            (df[\"distance\"] < threshold_dist) & df[\"distance\"].notna()\n",
    "        ]  # the first value is considered as correct\n",
    "\n",
    "        # Compute the distance between consecutive points\n",
    "        dx = df[\"X\"].diff()\n",
    "        dy = df[\"Y\"].diff()\n",
    "\n",
    "        # compute distances\n",
    "        df[\"distance\"] = np.sqrt(dx**2 + dy**2)\n",
    "\n",
    "        # get the max distance\n",
    "        max_dist = np.max(df[\"distance\"])\n",
    "\n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "id": "379c9c65",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\" Removes the outliers from the bottom line detection,\n",
    "    The outliers are defined as the points which distance is too far from the std of the distances\"\"\"\n",
    "\n",
    "\n",
    "def remove_outliers_up(df, threshold=2):\n",
    "    # Ensure 'X' and 'Y' are numeric\n",
    "    df[[\"X\", \"Y\"]] = df[[\"X\", \"Y\"]].apply(pd.to_numeric, errors=\"coerce\")\n",
    "    # Compute the distance between consecutive points\n",
    "    dx = df[\"X\"].diff()\n",
    "    dy = df[\"Y\"].diff()\n",
    "    distances = np.sqrt(dx**2 + dy**2)\n",
    "\n",
    "    # Define outlier threshold\n",
    "    median_dist = distances.mean()\n",
    "    std_dist = distances.std()\n",
    "\n",
    "    outlier_threshold = threshold * std_dist\n",
    "\n",
    "    mask = []\n",
    "\n",
    "    for i in range(0, len(distances) - 1):\n",
    "        # Remove points that are  (0, 0)  (the ones that I set when it doesn't detect any line)\n",
    "        if df[\"X\"].iloc[i] == 0 and df[\"Y\"].iloc[i] == 0:\n",
    "            mask.append(i)\n",
    "            prev_index = i - 1\n",
    "            while prev_index in mask and prev_index >= 0:\n",
    "                prev_index -= 1\n",
    "            if prev_index < 0:\n",
    "                print(\"No valid previous index found. Breaking.\")\n",
    "                break\n",
    "            distances[i + 1] = np.sqrt(\n",
    "                (df[\"X\"].iloc[i + 1] - df[\"X\"].iloc[prev_index]) ** 2\n",
    "                + (df[\"Y\"].iloc[i + 1] - df[\"Y\"].iloc[prev_index]) ** 2\n",
    "            )\n",
    "            continue\n",
    "        if distances[i] > outlier_threshold:\n",
    "            # Create a mask to identify the outlier point\n",
    "            mask.append(i + 1)\n",
    "            # convert the next point distance in the distance with respect to the previous point\n",
    "            if i < len(distances) - 2 and i > 0:\n",
    "                # select the previous point as the last point evaluated non present in the mask\n",
    "                prev_index = i\n",
    "                while prev_index in mask and prev_index >= 0:\n",
    "                    prev_index -= 1\n",
    "                if prev_index < 0:\n",
    "                    print(\"No valid previous index found. Breaking.\")\n",
    "                    break\n",
    "                distances[i + 1] = np.sqrt(\n",
    "                    (df[\"X\"].iloc[i + 2] - df[\"X\"].iloc[prev_index]) ** 2\n",
    "                    + (df[\"Y\"].iloc[i + 2] - df[\"Y\"].iloc[prev_index]) ** 2\n",
    "                )\n",
    "    # Remove the outlier points from the DataFrame\n",
    "    df = df.drop(mask)\n",
    "\n",
    "    # compute means and standard deviations of points\n",
    "    mean_x = df[\"X\"].mean()\n",
    "    mean_y = df[\"Y\"].mean()\n",
    "    std_x = df[\"X\"].std()\n",
    "    std_y = df[\"Y\"].std()\n",
    "\n",
    "    # threshold_std = 1\n",
    "    # if std_x > 1 and std_y > 1:\n",
    "    #     # Remove points too far from the mean\n",
    "    #     df = df[(df['X'] > mean_x - threshold_std*std_x) & (df['X'] < mean_x + threshold_std*std_x) & (df['Y'] > mean_y - threshold_std*std_y) & (df['Y'] < mean_y + threshold_std*std_y)]\n",
    "    # elif std_x > 1:\n",
    "    #     df = df[(df['X'] > mean_x - threshold_std*std_x) & (df['X'] < mean_x + threshold_std*std_x)]\n",
    "    # elif std_y > 1:\n",
    "    #     df = df[(df['Y'] > mean_y - threshold_std*std_y) & (df['Y'] < mean_y + threshold_std*std_y)]\n",
    "\n",
    "    return df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "31e41424",
   "metadata": {},
   "source": [
    "Smoothing with median filter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "id": "69d0fcb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\" Smooths the X and Y coordinates using a median filter to reduce noise.\"\"\"\n",
    "\n",
    "\n",
    "def median_filter(df, kernel_size=3):\n",
    "    df[\"X\"] = medfilt(df[\"X\"], kernel_size=kernel_size)\n",
    "    df[\"Y\"] = medfilt(df[\"Y\"], kernel_size=kernel_size)\n",
    "    return df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "78421c15",
   "metadata": {},
   "source": [
    "Smoothing with savitzky-golay filter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "id": "2bed08c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\" Smooths the X and Y coordinates using Savitzky-Golay filter to reduce noise.\"\"\"\n",
    "\n",
    "\n",
    "def Savitzky_Golay_filter(df, window_length=25, polyorder=1):\n",
    "    df[\"X\"] = savgol_filter(df[\"X\"], window_length=window_length, polyorder=polyorder)\n",
    "    df[\"Y\"] = savgol_filter(df[\"Y\"], window_length=window_length, polyorder=polyorder)\n",
    "\n",
    "    return df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "05e248f9",
   "metadata": {},
   "source": [
    "Interpolate the missing coordinates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "id": "c35393f5",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"Interpolate the missing coordinates between the frames from start_frame to end_frame.\n",
    "    Ensures a smooth trajectory by interpolating both X and Y coordinates.\"\"\"\n",
    "\n",
    "\n",
    "def interpolate_missing_coordinates(df, end_frame=100, start_frame=0, polyorder=1):\n",
    "    # Create a DataFrame with all frames from start_frame to end_frame\n",
    "    all_frames = pd.DataFrame({\"Frame\": range(start_frame, end_frame + 1)})\n",
    "\n",
    "    # Merge with the original dataframe\n",
    "    df_full = pd.merge(all_frames, df, on=\"Frame\", how=\"left\")\n",
    "\n",
    "    # Interpolate the missing 'X' and 'Y' coordinates (linear interpolation)\n",
    "    df_full[\"X\"] = df_full[\"X\"].interpolate(method=\"linear\")\n",
    "    df_full[\"Y\"] = df_full[\"Y\"].interpolate(method=\"linear\")\n",
    "\n",
    "    # Fill any remaining NaN values using forward and backward filling\n",
    "    df_full[\"X\"] = df_full[\"X\"].bfill().ffill()\n",
    "    df_full[\"Y\"] = df_full[\"Y\"].bfill().ffill()\n",
    "\n",
    "    # Apply smoothing to ensure a smooth trajectory\n",
    "    # df_full = Savitzky_Golay_filter(df_full, polyorder=polyorder)\n",
    "\n",
    "    return df_full"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e35ca9cb",
   "metadata": {},
   "source": [
    "Recover the lines from the points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "id": "acce1ab7",
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\" Get the lines from the intersection points\"\"\"\n",
    "\n",
    "\n",
    "def points_to_lines(df, line_length=10):\n",
    "    lines = []\n",
    "    for i in range(0, len(df)):\n",
    "        x, y = df.iloc[i][\"X\"], df.iloc[i][\"Y\"]\n",
    "        # Compute the direction vector orthogonal to the line connecting the point to the origin\n",
    "        dx, dy = (\n",
    "            -y,\n",
    "            x,\n",
    "        )  # Rotate the vector (x, y) by 90 degrees to get orthogonal direction\n",
    "\n",
    "        # Append the line as a pair of points\n",
    "        lines.append(\n",
    "            [\n",
    "                x + line_length * dx,\n",
    "                y + line_length * dy,\n",
    "                x - line_length * dx,\n",
    "                y - line_length * dy,\n",
    "            ]\n",
    "        )\n",
    "\n",
    "    return lines"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e6094306",
   "metadata": {},
   "source": [
    "Postprocessing Main"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d11afc34",
   "metadata": {},
   "outputs": [],
   "source": [
    "def postprocessing_upper(upper_lines_raw):\n",
    "    # get the intersection points\n",
    "    intersection_points = get_relevant_points(upper_lines_raw)\n",
    "\n",
    "    # Create a DataFrame from intersection_points\n",
    "    points_df = pd.DataFrame(intersection_points, columns=[\"X\", \"Y\"])\n",
    "    points_df[\"Frame\"] = range(len(points_df))\n",
    "    # Reorder columns to have 'Frame', 'X', 'Y'\n",
    "    points_df = points_df[[\"Frame\", \"X\", \"Y\"]]\n",
    "\n",
    "    plot_trajectory(points_df, title=\"Trajectory before filtering\")\n",
    "\n",
    "    # Remove outliers\n",
    "    points_cleaned = remove_outliers_iterated(points_df, threshold_factor=8)\n",
    "    plot_trajectory(points_cleaned, title=\"Trajectory after removing outliers\")\n",
    "\n",
    "    if avg_movement > 1:\n",
    "        # Smooth the trajectory to reduce noise\n",
    "        points_smoothed = median_filter(points_cleaned)\n",
    "        plot_trajectory(points_smoothed, title=\"Trajectory after smoothing\")\n",
    "\n",
    "        # Interpolate missing coordinates\n",
    "        points_interpolated = interpolate_missing_coordinates(\n",
    "            points_smoothed, end_frame=len(points_df) - 1, polyorder=1\n",
    "        )\n",
    "        plot_trajectory(points_interpolated, title=\"Trajectory after interpolation\")\n",
    "\n",
    "        # recover the lines from the points\n",
    "        upper_lines = points_to_lines(points_interpolated)\n",
    "\n",
    "    else:\n",
    "        # get the mean point because I'm assuming the video still\n",
    "        mean_point = points_cleaned.mean()\n",
    "        # print('mean point:', mean_point)\n",
    "\n",
    "        # create a list of length of the original df where each element is mean_point\n",
    "        mean_point_list = [mean_point] * len(intersection_points)\n",
    "        mean_point_df = pd.DataFrame(mean_point_list, columns=[\"X\", \"Y\"])\n",
    "\n",
    "        # recover the lines from the points\n",
    "        upper_lines = points_to_lines(mean_point_df)\n",
    "\n",
    "    return upper_lines"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5c1f93ce",
   "metadata": {},
   "source": [
    "Generate video"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "id": "63b5cf93",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0            NaN\n",
      "1       1.114503\n",
      "2       0.050706\n",
      "3       4.584456\n",
      "4       1.003959\n",
      "         ...    \n",
      "222     1.000000\n",
      "223     1.000000\n",
      "224     0.000000\n",
      "225     1.000000\n",
      "226    12.000000\n",
      "Name: distance, Length: 227, dtype: float64\n",
      "mean: 6.6340055257395685 std: 38.461422535205436\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[625.0, 1041.0, 1320.0, 1049.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[625.0, 1041.0, 1242.0, 445.0]\n",
      "[1320.0, 1049.0, 1537.0, 447.0]\n",
      "[627.0, 1041.0, 1319.0, 1051.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[627.0, 1041.0, 1246.0, 444.0]\n",
      "[1319.0, 1051.0, 1538.0, 446.0]\n",
      "[624.0, 1042.0, 1316.0, 1053.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[624.0, 1042.0, 1243.0, 444.0]\n",
      "[1316.0, 1053.0, 1536.0, 446.0]\n",
      "[620.0, 1042.0, 1312.0, 1053.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[620.0, 1042.0, 1237.0, 444.0]\n",
      "[1312.0, 1053.0, 1534.0, 445.0]\n",
      "[618.0, 1041.0, 1308.0, 1052.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[618.0, 1041.0, 1234.0, 443.0]\n",
      "[1308.0, 1052.0, 1530.0, 444.0]\n",
      "[616.0, 1039.0, 1304.0, 1051.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[616.0, 1039.0, 1232.0, 441.0]\n",
      "[1304.0, 1051.0, 1525.0, 442.0]\n",
      "[611.0, 1038.0, 1299.0, 1049.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[611.0, 1038.0, 1226.0, 439.0]\n",
      "[1299.0, 1049.0, 1521.0, 440.0]\n",
      "[604.0, 1036.0, 1296.0, 1046.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[604.0, 1036.0, 1218.0, 438.0]\n",
      "[1296.0, 1046.0, 1517.0, 439.0]\n",
      "[599.0, 1034.0, 1292.0, 1044.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[599.0, 1034.0, 1212.0, 438.0]\n",
      "[1292.0, 1044.0, 1512.0, 439.0]\n",
      "[596.0, 1032.0, 1285.0, 1042.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[596.0, 1032.0, 1211.0, 435.0]\n",
      "[1285.0, 1042.0, 1508.0, 436.0]\n",
      "[592.0, 1030.0, 1279.0, 1041.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[592.0, 1030.0, 1208.0, 433.0]\n",
      "[1279.0, 1041.0, 1503.0, 434.0]\n",
      "[589.0, 1028.0, 1276.0, 1039.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[589.0, 1028.0, 1207.0, 431.0]\n",
      "[1276.0, 1039.0, 1501.0, 432.0]\n",
      "[586.0, 1027.0, 1275.0, 1037.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[586.0, 1027.0, 1200.0, 432.0]\n",
      "[1275.0, 1037.0, 1499.0, 433.0]\n",
      "[581.0, 1024.0, 1268.0, 1035.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[581.0, 1024.0, 1196.0, 429.0]\n",
      "[1268.0, 1035.0, 1493.0, 430.0]\n",
      "[576.0, 1023.0, 1262.0, 1033.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[576.0, 1023.0, 1191.0, 427.0]\n",
      "[1262.0, 1033.0, 1488.0, 428.0]\n",
      "[571.0, 1021.0, 1257.0, 1031.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[571.0, 1021.0, 1187.0, 425.0]\n",
      "[1257.0, 1031.0, 1484.0, 426.0]\n",
      "[567.0, 1020.0, 1253.0, 1030.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[567.0, 1020.0, 1183.0, 424.0]\n",
      "[1253.0, 1030.0, 1480.0, 425.0]\n",
      "[564.0, 1018.0, 1247.0, 1027.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[564.0, 1018.0, 1181.0, 421.0]\n",
      "[1247.0, 1027.0, 1475.0, 422.0]\n",
      "[562.0, 1016.0, 1244.0, 1025.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[562.0, 1016.0, 1179.0, 419.0]\n",
      "[1244.0, 1025.0, 1471.0, 420.0]\n",
      "[560.0, 1014.0, 1242.0, 1023.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[560.0, 1014.0, 1176.0, 417.0]\n",
      "[1242.0, 1023.0, 1468.0, 418.0]\n",
      "[556.0, 1012.0, 1238.0, 1021.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[556.0, 1012.0, 1170.0, 415.0]\n",
      "[1238.0, 1021.0, 1463.0, 416.0]\n",
      "[549.0, 1011.0, 1234.0, 1019.0]\n",
      "[np.float64(-4079.323625070496), np.float64(394.32615662689534), np.float64(4076.6293268764057), np.float64(421.2691385677948)]\n",
      "[549.0, 1011.0, 1153.0, 416.0]\n",
      "[1234.0, 1019.0, 1459.0, 417.0]\n",
      "[545.0, 1008.0, 1234.0, 1016.0]\n",
      "[np.float64(-4080.549331794254), np.float64(382.0690893893107), np.float64(4075.4036201526474), np.float64(433.52620580537945)]\n",
      "[545.0, 1008.0, 1139.0, 415.0]\n",
      "[1234.0, 1016.0, 1456.0, 417.0]\n",
      "[541.0, 1007.0, 1233.0, 1016.0]\n",
      "[np.float64(-4060.0951737899204), np.float64(379.989871912445), np.float64(4054.9427687470397), np.float64(431.51392234125103)]\n",
      "[541.0, 1007.0, 1139.0, 413.0]\n",
      "[1233.0, 1016.0, 1454.0, 415.0]\n",
      "[539.0, 1007.0, 1232.0, 1016.0]\n",
      "[np.float64(-4016.8761376004272), np.float64(375.6679682934957), np.float64(4011.7237325575466), np.float64(427.1920187223017)]\n",
      "[539.0, 1007.0, 1148.0, 409.0]\n",
      "[1232.0, 1016.0, 1452.0, 411.0]\n",
      "[537.0, 1006.0, 1225.0, 1015.0]\n",
      "[np.float64(-4011.7068122307546), np.float64(387.2616261238201), np.float64(4008.9525438942683), np.float64(414.8043094886821)]\n",
      "[537.0, 1006.0, 1157.0, 405.0]\n",
      "[1225.0, 1015.0, 1449.0, 406.0]\n",
      "[532.0, 1005.0, 1218.0, 1014.0]\n",
      "[np.float64(-3981.2948803907952), np.float64(384.2204329398242), np.float64(3978.540612054309), np.float64(411.7631163046862)]\n",
      "[532.0, 1005.0, 1157.0, 402.0]\n",
      "[1218.0, 1014.0, 1446.0, 403.0]\n",
      "[524.0, 1003.0, 1213.0, 1013.0]\n",
      "[np.float64(-3961.1225688964423), np.float64(382.17727327910643), np.float64(3958.3631662012867), np.float64(409.7713002306665)]\n",
      "[524.0, 1003.0, 1154.0, 400.0]\n",
      "[1213.0, 1013.0, 1441.0, 401.0]\n",
      "[520.0, 1001.0, 1216.0, 1012.0]\n",
      "[np.float64(-3914.4482806084393), np.float64(364.61400094938597), np.float64(3909.1352455368637), np.float64(417.74435166514434)]\n",
      "[520.0, 1001.0, 1147.0, 399.0]\n",
      "[1216.0, 1012.0, 1441.0, 401.0]\n",
      "[519.0, 999.0, 1214.0, 1009.0]\n",
      "[np.float64(-3894.45927276132), np.float64(362.5689906727076), np.float64(3889.1371070972755), np.float64(415.7906473131519)]\n",
      "[519.0, 999.0, 1143.0, 397.0]\n",
      "[1214.0, 1009.0, 1436.0, 399.0]\n",
      "[518.0, 995.0, 1207.0, 1006.0]\n",
      "[np.float64(-3863.9211422860967), np.float64(359.5612871171517), np.float64(3858.608107214521), np.float64(412.6916378329101)]\n",
      "[518.0, 995.0, 1139.0, 394.0]\n",
      "[1207.0, 1006.0, 1429.0, 396.0]\n",
      "[520.0, 993.0, 1203.0, 1003.0]\n",
      "[np.float64(-3844.5896203577963), np.float64(357.7897620593966), np.float64(3839.308590659503), np.float64(410.6000590423333)]\n",
      "[520.0, 993.0, 1133.0, 392.0]\n",
      "[1203.0, 1003.0, 1424.0, 394.0]\n",
      "[527.0, 991.0, 1201.0, 1002.0]\n",
      "[np.float64(-3835.0478960454097), np.float64(356.992822629826), np.float64(3829.798001594971), np.float64(409.4917671342121)]\n",
      "[527.0, 991.0, 1130.0, 391.0]\n",
      "[1201.0, 1002.0, 1422.0, 393.0]\n",
      "[524.0, 989.0, 1200.0, 1002.0]\n",
      "[np.float64(-3825.781356295094), np.float64(356.0661686547944), np.float64(3820.5314618446555), np.float64(408.56511315918056)]\n",
      "[524.0, 989.0, 1127.0, 390.0]\n",
      "[1200.0, 1002.0, 1421.0, 392.0]\n",
      "[515.0, 987.0, 1197.0, 1003.0]\n",
      "[np.float64(-3805.601426066065), np.float64(352.96848199786336), np.float64(3800.1377308960164), np.float64(407.60543369834477)]\n",
      "[515.0, 987.0, 1129.0, 387.0]\n",
      "[1197.0, 1003.0, 1418.0, 391.0]\n",
      "[508.0, 986.0, 1191.0, 1003.0]\n",
      "[np.float64(-3785.4214958370358), np.float64(349.8707953409324), np.float64(3779.743999947378), np.float64(406.64575423750904)]\n",
      "[508.0, 986.0, 1130.0, 385.0]\n",
      "[1191.0, 1003.0, 1416.0, 389.0]\n",
      "[507.0, 984.0, 1185.0, 1003.0]\n",
      "[np.float64(-3765.2415656080066), np.float64(346.77310868400133), np.float64(3759.350268998739), np.float64(405.68607477667325)]\n",
      "[507.0, 984.0, 1126.0, 383.0]\n",
      "[1185.0, 1003.0, 1415.0, 387.0]\n",
      "[508.0, 983.0, 1180.0, 1003.0]\n",
      "[np.float64(-3745.0616353789774), np.float64(343.67542202707034), np.float64(3738.956538050101), np.float64(404.7263953158375)]\n",
      "[508.0, 983.0, 1119.0, 383.0]\n",
      "[1180.0, 1003.0, 1414.0, 387.0]\n",
      "[504.0, 982.0, 1180.0, 1001.0]\n",
      "[np.float64(-3724.881705149948), np.float64(340.5777353701393), np.float64(3718.5628071014617), np.float64(403.76671585500173)]\n",
      "[504.0, 982.0, 1113.0, 382.0]\n",
      "[1180.0, 1001.0, 1412.0, 386.0]\n",
      "[500.0, 982.0, 1177.0, 1000.0]\n",
      "[np.float64(-3704.7017749209194), np.float64(337.4800487132083), np.float64(3698.169076152824), np.float64(402.807036394166)]\n",
      "[500.0, 982.0, 1114.0, 379.0]\n",
      "[1177.0, 1000.0, 1407.0, 383.0]\n",
      "[494.0, 981.0, 1174.0, 1000.0]\n",
      "[np.float64(-3684.5218446918902), np.float64(334.38236205627726), np.float64(3677.7753452041848), np.float64(401.8473569333302)]\n",
      "[494.0, 981.0, 1114.0, 376.0]\n",
      "[1174.0, 1000.0, 1405.0, 380.0]\n",
      "[492.0, 980.0, 1171.0, 998.0]\n",
      "[np.float64(-3664.341914462861), np.float64(331.28467539934627), np.float64(3657.3816142555465), np.float64(400.8876774724945)]\n",
      "[492.0, 980.0, 1116.0, 374.0]\n",
      "[1171.0, 998.0, 1402.0, 378.0]\n",
      "[489.0, 977.0, 1169.0, 997.0]\n",
      "[np.float64(-3644.161984233832), np.float64(328.1869887424152), np.float64(3636.9878833069074), np.float64(399.9279980116587)]\n",
      "[489.0, 977.0, 1114.0, 372.0]\n",
      "[1169.0, 997.0, 1400.0, 377.0]\n",
      "[485.0, 975.0, 1167.0, 995.0]\n",
      "[np.float64(-3623.982054004802), np.float64(325.0893020854842), np.float64(3616.5941523582687), np.float64(398.9683185508229)]\n",
      "[485.0, 975.0, 1110.0, 370.0]\n",
      "[1167.0, 995.0, 1395.0, 375.0]\n",
      "[483.0, 973.0, 1168.0, 993.0]\n",
      "[np.float64(-3603.8021237757735), np.float64(321.99161542855325), np.float64(3596.20042140963), np.float64(398.0086390899871)]\n",
      "[483.0, 973.0, 1106.0, 370.0]\n",
      "[1168.0, 993.0, 1393.0, 375.0]\n",
      "[483.0, 971.0, 1167.0, 991.0]\n",
      "[np.float64(-3583.6221935467443), np.float64(318.8939287716222), np.float64(3575.806690460991), np.float64(397.04895962915134)]\n",
      "[483.0, 971.0, 1104.0, 368.0]\n",
      "[1167.0, 991.0, 1392.0, 373.0]\n",
      "[481.0, 970.0, 1164.0, 989.0]\n",
      "[np.float64(-3563.4422633177155), np.float64(315.7962421146912), np.float64(3555.412959512353), np.float64(396.0892801683156)]\n",
      "[481.0, 970.0, 1099.0, 368.0]\n",
      "[1164.0, 989.0, 1391.0, 373.0]\n",
      "[477.0, 968.0, 1160.0, 987.0]\n",
      "[np.float64(-3543.2623330886863), np.float64(312.69855545776016), np.float64(3535.019228563714), np.float64(395.1296007074798)]\n",
      "[477.0, 968.0, 1096.0, 366.0]\n",
      "[1160.0, 987.0, 1388.0, 370.0]\n",
      "[476.0, 967.0, 1158.0, 986.0]\n",
      "[np.float64(-3523.082402859657), np.float64(309.6008688008292), np.float64(3514.625497615076), np.float64(394.1699212466441)]\n",
      "[476.0, 967.0, 1097.0, 364.0]\n",
      "[1158.0, 986.0, 1385.0, 368.0]\n",
      "[476.0, 965.0, 1156.0, 984.0]\n",
      "[np.float64(-3502.902472630628), np.float64(306.50318214389813), np.float64(3494.2317666664367), np.float64(393.2102417858083)]\n",
      "[476.0, 965.0, 1096.0, 363.0]\n",
      "[1156.0, 984.0, 1381.0, 367.0]\n",
      "[474.0, 964.0, 1152.0, 983.0]\n",
      "[np.float64(-3482.7225424015987), np.float64(303.40549548696714), np.float64(3473.8380357177984), np.float64(392.2505623249726)]\n",
      "[474.0, 964.0, 1093.0, 361.0]\n",
      "[1152.0, 983.0, 1380.0, 365.0]\n",
      "[472.0, 962.0, 1147.0, 982.0]\n",
      "[np.float64(-3462.5426121725695), np.float64(300.3078088300361), np.float64(3453.4443047691593), np.float64(391.2908828641368)]\n",
      "[472.0, 962.0, 1091.0, 360.0]\n",
      "[1147.0, 982.0, 1381.0, 364.0]\n",
      "[472.0, 961.0, 1143.0, 982.0]\n",
      "[np.float64(-3442.3626819435403), np.float64(297.2101221731051), np.float64(3433.050573820521), np.float64(390.33120340330106)]\n",
      "[472.0, 961.0, 1091.0, 359.0]\n",
      "[1143.0, 982.0, 1380.0, 363.0]\n",
      "[469.0, 960.0, 1142.0, 982.0]\n",
      "[np.float64(-3422.182751714511), np.float64(294.11243551617406), np.float64(3412.656842871882), np.float64(389.3715239424653)]\n",
      "[469.0, 960.0, 1090.0, 357.0]\n",
      "[1142.0, 982.0, 1377.0, 361.0]\n",
      "[462.0, 960.0, 1140.0, 982.0]\n",
      "[np.float64(-3411.5372530960753), np.float64(292.9794095618884), np.float64(3401.997784631181), np.float64(388.3740942108372)]\n",
      "[462.0, 960.0, 1087.0, 356.0]\n",
      "[1140.0, 982.0, 1372.0, 360.0]\n",
      "[458.0, 959.0, 1138.0, 982.0]\n",
      "[np.float64(-3391.704085680286), np.float64(290.99008330027766), np.float64(3382.1634272114243), np.float64(386.39666798889334)]\n",
      "[458.0, 959.0, 1085.0, 354.0]\n",
      "[1138.0, 982.0, 1369.0, 358.0]\n",
      "[456.0, 958.0, 1136.0, 981.0]\n",
      "[np.float64(-3391.7034906783024), np.float64(290.9960333201111), np.float64(3382.164022213408), np.float64(386.3907179690599)]\n",
      "[456.0, 958.0, 1082.0, 354.0]\n",
      "[1136.0, 981.0, 1366.0, 358.0]\n",
      "[454.0, 958.0, 1133.0, 980.0]\n",
      "[np.float64(-3394.9327982526534), np.float64(291.48358931531567), np.float64(3385.4259288447424), np.float64(386.5522833944239)]\n",
      "[454.0, 958.0, 1077.0, 355.0]\n",
      "[1133.0, 980.0, 1363.0, 359.0]\n",
      "[451.0, 958.0, 1131.0, 979.0]\n",
      "[np.float64(-3395.685275411773), np.float64(292.01184480250805), np.float64(3386.2681105130264), np.float64(386.1834937899719)]\n",
      "[451.0, 958.0, 1074.0, 354.0]\n",
      "[1131.0, 979.0, 1362.0, 358.0]\n",
      "[449.0, 958.0, 1128.0, 978.0]\n",
      "[np.float64(-3395.6700863090605), np.float64(292.1637358296324), np.float64(3386.283299615739), np.float64(386.03160276284757)]\n",
      "[449.0, 958.0, 1072.0, 354.0]\n",
      "[1128.0, 978.0, 1361.0, 358.0]\n",
      "[447.0, 958.0, 1126.0, 977.0]\n",
      "[np.float64(-3407.230031760275), np.float64(293.4848105599962), np.float64(3397.875934212546), np.float64(387.02578603728585)]\n",
      "[447.0, 958.0, 1068.0, 355.0]\n",
      "[1126.0, 977.0, 1359.0, 359.0]\n",
      "[445.0, 959.0, 1124.0, 976.0]\n",
      "[np.float64(-3407.230031760275), np.float64(293.4848105599962), np.float64(3397.875934212546), np.float64(387.02578603728585)]\n",
      "[445.0, 959.0, 1066.0, 355.0]\n",
      "[1124.0, 976.0, 1358.0, 359.0]\n",
      "[444.0, 960.0, 1123.0, 976.0]\n",
      "[np.float64(-3396.9991915925625), np.float64(292.4413904607922), np.float64(3387.641067097817), np.float64(386.0226354082458)]\n",
      "[444.0, 960.0, 1066.0, 354.0]\n",
      "[1123.0, 976.0, 1356.0, 358.0]\n",
      "[443.0, 960.0, 1121.0, 976.0]\n",
      "[np.float64(-3396.1926564301757), np.float64(291.8866055714026), np.float64(3386.740644534806), np.float64(386.40672452509557)]\n",
      "[443.0, 960.0, 1065.0, 354.0]\n",
      "[1121.0, 976.0, 1352.0, 358.0]\n",
      "[438.0, 960.0, 1119.0, 976.0]\n",
      "[np.float64(-3396.1926564301757), np.float64(291.8866055714026), np.float64(3386.740644534806), np.float64(386.40672452509557)]\n",
      "[438.0, 960.0, 1061.0, 354.0]\n",
      "[1119.0, 976.0, 1348.0, 358.0]\n",
      "[433.0, 960.0, 1116.0, 977.0]\n",
      "[np.float64(-3407.7606090714294), np.float64(293.20400541077606), np.float64(3398.340400062248), np.float64(387.4060955025917)]\n",
      "[433.0, 960.0, 1057.0, 355.0]\n",
      "[1116.0, 977.0, 1346.0, 359.0]\n",
      "[433.0, 960.0, 1113.0, 979.0]\n",
      "[np.float64(-3418.5433823589824), np.float64(294.28228273953135), np.float64(3409.123173349801), np.float64(388.484372831347)]\n",
      "[433.0, 960.0, 1055.0, 356.0]\n",
      "[1113.0, 979.0, 1345.0, 360.0]\n",
      "[430.0, 961.0, 1112.0, 979.0]\n",
      "[np.float64(-3428.8286748606006), np.float64(295.19582308070926), np.float64(3419.385695770432), np.float64(389.62561398239404)]\n",
      "[430.0, 961.0, 1053.0, 357.0]\n",
      "[1112.0, 979.0, 1343.0, 361.0]\n",
      "[430.0, 962.0, 1111.0, 979.0]\n",
      "[np.float64(-3439.6065505112897), np.float64(296.25929977983697), np.float64(3430.160737586282), np.float64(390.71742902992014)]\n",
      "[430.0, 962.0, 1051.0, 358.0]\n",
      "[1111.0, 979.0, 1342.0, 362.0]\n",
      "[428.0, 963.0, 1108.0, 981.0]\n",
      "[np.float64(-3439.65025046271), np.float64(295.82230026563485), np.float64(3430.1170376348614), np.float64(391.15442854412225)]\n",
      "[428.0, 963.0, 1051.0, 359.0]\n",
      "[1108.0, 981.0, 1340.0, 363.0]\n",
      "[426.0, 965.0, 1106.0, 982.0]\n",
      "[np.float64(-3439.4043205436446), np.float64(283.4572064765788), np.float64(3427.4274441916077), np.float64(403.22596999694645)]\n",
      "[426.0, 965.0, 1050.0, 361.0]\n",
      "[1106.0, 982.0, 1336.0, 366.0]\n",
      "[421.0, 968.0, 1104.0, 983.0]\n",
      "[np.float64(-3439.4819881668623), np.float64(282.6805302444017), np.float64(3427.34977656839), np.float64(404.0026462291235)]\n",
      "[421.0, 968.0, 1050.0, 362.0]\n",
      "[1104.0, 983.0, 1333.0, 367.0]\n",
      "[418.0, 971.0, 1104.0, 986.0]\n",
      "[np.float64(-3460.503960040158), np.float64(284.6249302809831), np.float64(3448.3405014811415), np.float64(406.25951587114685)]\n",
      "[418.0, 971.0, 1048.0, 364.0]\n",
      "[1104.0, 986.0, 1332.0, 369.0]\n",
      "[417.0, 974.0, 1102.0, 989.0]\n",
      "[np.float64(-3490.3651254399797), np.float64(287.61104682096527), np.float64(3478.2016668809633), np.float64(409.245632411129)]\n",
      "[417.0, 974.0, 1045.0, 367.0]\n",
      "[1102.0, 989.0, 1328.0, 372.0]\n",
      "[416.0, 977.0, 1101.0, 990.0]\n",
      "[np.float64(-3518.2902437951443), np.float64(291.7171945763867), np.float64(3506.386911160862), np.float64(410.7505209192139)]\n",
      "[416.0, 977.0, 1041.0, 372.0]\n",
      "[1101.0, 990.0, 1326.0, 373.0]\n",
      "[414.0, 981.0, 1099.0, 992.0]\n",
      "[np.float64(-3546.21536215031), np.float64(295.8233423318082), np.float64(3534.5721554407605), np.float64(412.25540942729884)]\n",
      "[414.0, 981.0, 1040.0, 373.0]\n",
      "[1099.0, 992.0, 1325.0, 374.0]\n",
      "[413.0, 983.0, 1098.0, 995.0]\n",
      "[np.float64(-3574.1404805054744), np.float64(299.9294900872296), np.float64(3562.757399720659), np.float64(413.76029793538373)]\n",
      "[413.0, 983.0, 1038.0, 376.0]\n",
      "[1098.0, 995.0, 1323.0, 377.0]\n",
      "[414.0, 985.0, 1097.0, 996.0]\n",
      "[np.float64(-3602.0655988606395), np.float64(304.03563784265117), np.float64(3590.942644000558), np.float64(415.2651864434686)]\n",
      "[414.0, 985.0, 1036.0, 379.0]\n",
      "[1097.0, 996.0, 1322.0, 380.0]\n",
      "[411.0, 988.0, 1095.0, 999.0]\n",
      "[np.float64(-3629.9907172158046), np.float64(308.1417855980726), np.float64(3619.1278882804563), np.float64(416.7700749515535)]\n",
      "[411.0, 988.0, 1033.0, 383.0]\n",
      "[1095.0, 999.0, 1319.0, 384.0]\n",
      "[409.0, 992.0, 1094.0, 1003.0]\n",
      "[np.float64(-3657.9158355709696), np.float64(312.2479333534941), np.float64(3647.3131325603554), np.float64(418.27496345963846)]\n",
      "[409.0, 992.0, 1031.0, 386.0]\n",
      "[1094.0, 1003.0, 1317.0, 387.0]\n",
      "[405.0, 997.0, 1092.0, 1007.0]\n",
      "[np.float64(-3685.8409539261347), np.float64(316.3540811089155), np.float64(3675.4983768402535), np.float64(419.77985196772335)]\n",
      "[405.0, 997.0, 1029.0, 389.0]\n",
      "[1092.0, 1007.0, 1316.0, 390.0]\n",
      "[401.0, 1002.0, 1090.0, 1012.0]\n",
      "[np.float64(-3713.7660722813002), np.float64(320.460228864337), np.float64(3703.683621120153), np.float64(421.2847404758083)]\n",
      "[401.0, 1002.0, 1030.0, 390.0]\n",
      "[1090.0, 1012.0, 1315.0, 391.0]\n",
      "[399.0, 1006.0, 1087.0, 1018.0]\n",
      "[np.float64(-3741.691190636465), np.float64(324.56637661975844), np.float64(3731.8688654000516), np.float64(422.7896289838932)]\n",
      "[399.0, 1006.0, 1027.0, 395.0]\n",
      "[1087.0, 1018.0, 1313.0, 396.0]\n",
      "[399.0, 1011.0, 1085.0, 1022.0]\n",
      "[np.float64(-3769.6163089916304), np.float64(328.67252437517993), np.float64(3760.05410967995), np.float64(424.2945174919781)]\n",
      "[399.0, 1011.0, 1026.0, 399.0]\n",
      "[1085.0, 1022.0, 1311.0, 400.0]\n",
      "[400.0, 1015.0, 1083.0, 1028.0]\n",
      "[np.float64(-3797.541427346795), np.float64(332.7786721306014), np.float64(3788.239353959849), np.float64(425.79940600006296)]\n",
      "[400.0, 1015.0, 1024.0, 403.0]\n",
      "[1083.0, 1028.0, 1309.0, 404.0]\n",
      "[399.0, 1019.0, 1081.0, 1033.0]\n",
      "[np.float64(-3825.4665457019596), np.float64(336.88481988602285), np.float64(3816.4245982397474), np.float64(427.30429450814785)]\n",
      "[399.0, 1019.0, 1024.0, 406.0]\n",
      "[1081.0, 1033.0, 1307.0, 410.0]\n",
      "[397.0, 1023.0, 1079.0, 1037.0]\n",
      "[np.float64(-3853.391664057125), np.float64(340.99096764144434), np.float64(3844.609842519646), np.float64(428.8091830162328)]\n",
      "[397.0, 1023.0, 1022.0, 411.0]\n",
      "[1079.0, 1037.0, 1305.0, 415.0]\n",
      "[394.0, 1026.0, 1078.0, 1040.0]\n",
      "[np.float64(-3881.3167824122906), np.float64(345.09711539686583), np.float64(3872.7950867995455), np.float64(430.31407152431774)]\n",
      "[394.0, 1026.0, 1018.0, 415.0]\n",
      "[1078.0, 1040.0, 1305.0, 416.0]\n",
      "[391.0, 1030.0, 1077.0, 1043.0]\n",
      "[np.float64(-3909.2419007674553), np.float64(349.20326315228726), np.float64(3900.980331079444), np.float64(431.81896003240263)]\n",
      "[391.0, 1030.0, 1012.0, 419.0]\n",
      "[1077.0, 1043.0, 1303.0, 420.0]\n",
      "[387.0, 1033.0, 1074.0, 1046.0]\n",
      "[np.float64(-3937.1670191226203), np.float64(353.3094109077087), np.float64(3929.1655753593423), np.float64(433.3238485404875)]\n",
      "[387.0, 1033.0, 1012.0, 421.0]\n",
      "[1074.0, 1046.0, 1302.0, 422.0]\n",
      "[384.0, 1036.0, 1072.0, 1047.0]\n",
      "[np.float64(-3965.0921374777854), np.float64(357.41555866313024), np.float64(3957.3508196392413), np.float64(434.8287370485724)]\n",
      "[384.0, 1036.0, 1011.0, 425.0]\n",
      "[1072.0, 1047.0, 1300.0, 426.0]\n",
      "[383.0, 1038.0, 1070.0, 1049.0]\n",
      "[np.float64(-3993.0172558329505), np.float64(361.5217064185517), np.float64(3985.5360639191395), np.float64(436.3336255566573)]\n",
      "[383.0, 1038.0, 1014.0, 425.0]\n",
      "[1070.0, 1049.0, 1300.0, 426.0]\n",
      "[381.0, 1040.0, 1069.0, 1051.0]\n",
      "[np.float64(-4020.9423741881155), np.float64(365.62785417397316), np.float64(4013.7213081990385), np.float64(437.83851406474224)]\n",
      "[381.0, 1040.0, 1009.0, 429.0]\n",
      "[1069.0, 1051.0, 1297.0, 430.0]\n",
      "[381.0, 1042.0, 1068.0, 1053.0]\n",
      "[np.float64(-4048.86749254328), np.float64(369.7340019293946), np.float64(4041.906552478937), np.float64(439.34340257282713)]\n",
      "[381.0, 1042.0, 1008.0, 431.0]\n",
      "[1068.0, 1053.0, 1296.0, 432.0]\n",
      "[380.0, 1044.0, 1066.0, 1054.0]\n",
      "[np.float64(-4076.7926108984457), np.float64(373.8401496848161), np.float64(4070.0917967588357), np.float64(440.8482910809121)]\n",
      "[380.0, 1044.0, 1007.0, 433.0]\n",
      "[1066.0, 1054.0, 1296.0, 434.0]\n",
      "[379.0, 1045.0, 1063.0, 1056.0]\n",
      "[np.float64(-4104.717729253611), np.float64(377.9462974402375), np.float64(4098.277041038735), np.float64(442.35317958899697)]\n",
      "[379.0, 1045.0, 1007.0, 434.0]\n",
      "[1063.0, 1056.0, 1296.0, 435.0]\n",
      "[377.0, 1047.0, 1061.0, 1057.0]\n",
      "[np.float64(-4132.642847608776), np.float64(382.052445195659), np.float64(4126.462285318633), np.float64(443.8580680970819)]\n",
      "[377.0, 1047.0, 1004.0, 436.0]\n",
      "[1061.0, 1057.0, 1295.0, 437.0]\n",
      "[376.0, 1048.0, 1061.0, 1058.0]\n",
      "[np.float64(-4160.56796596394), np.float64(386.15859295108044), np.float64(4154.647529598532), np.float64(445.3629566051668)]\n",
      "[376.0, 1048.0, 1003.0, 437.0]\n",
      "[1061.0, 1058.0, 1292.0, 438.0]\n",
      "[373.0, 1049.0, 1060.0, 1059.0]\n",
      "[np.float64(-4188.493084319105), np.float64(390.2647407065019), np.float64(4182.83277387843), np.float64(446.86784511325163)]\n",
      "[373.0, 1049.0, 1001.0, 438.0]\n",
      "[1060.0, 1059.0, 1288.0, 439.0]\n",
      "[370.0, 1050.0, 1060.0, 1060.0]\n",
      "[np.float64(-4216.418202674271), np.float64(394.3708884619234), np.float64(4211.018018158329), np.float64(448.3727336213366)]\n",
      "[370.0, 1050.0, 999.0, 440.0]\n",
      "[1060.0, 1060.0, 1285.0, 441.0]\n",
      "[369.0, 1051.0, 1057.0, 1061.0]\n",
      "[np.float64(-4244.343321029436), np.float64(398.4770362173449), np.float64(4239.203262438229), np.float64(449.8776221294215)]\n",
      "[369.0, 1051.0, 998.0, 441.0]\n",
      "[1057.0, 1061.0, 1285.0, 442.0]\n",
      "[368.0, 1052.0, 1054.0, 1061.0]\n",
      "[np.float64(-4272.268439384601), np.float64(402.58318397276634), np.float64(4267.388506718127), np.float64(451.3825106375064)]\n",
      "[368.0, 1052.0, 996.0, 443.0]\n",
      "[1054.0, 1061.0, 1285.0, 444.0]\n",
      "[367.0, 1053.0, 1052.0, 1063.0]\n",
      "[np.float64(-4300.193557739766), np.float64(406.68933172818777), np.float64(4295.573750998025), np.float64(452.8873991455913)]\n",
      "[367.0, 1053.0, 995.0, 444.0]\n",
      "[1052.0, 1063.0, 1285.0, 445.0]\n",
      "[365.0, 1054.0, 1051.0, 1064.0]\n",
      "[np.float64(-4328.11867609493), np.float64(410.79547948360926), np.float64(4323.758995277924), np.float64(454.39228765367625)]\n",
      "[365.0, 1054.0, 994.0, 444.0]\n",
      "[1051.0, 1064.0, 1284.0, 445.0]\n",
      "[363.0, 1055.0, 1049.0, 1065.0]\n",
      "[np.float64(-4356.043794450095), np.float64(414.90162723903074), np.float64(4351.944239557823), np.float64(455.8971761617611)]\n",
      "[363.0, 1055.0, 990.0, 447.0]\n",
      "[1049.0, 1065.0, 1283.0, 448.0]\n",
      "[362.0, 1056.0, 1046.0, 1066.0]\n",
      "[np.float64(-4383.968912805261), np.float64(419.00777499445223), np.float64(4380.129483837722), np.float64(457.402064669846)]\n",
      "[362.0, 1056.0, 989.0, 448.0]\n",
      "[1046.0, 1066.0, 1282.0, 449.0]\n",
      "[359.0, 1057.0, 1044.0, 1067.0]\n",
      "[np.float64(-4411.894031160426), np.float64(423.11392274987367), np.float64(4408.314728117621), np.float64(458.9069531779309)]\n",
      "[359.0, 1057.0, 987.0, 449.0]\n",
      "[1044.0, 1067.0, 1282.0, 450.0]\n",
      "[359.0, 1058.0, 1042.0, 1067.0]\n",
      "[np.float64(-4439.819149515591), np.float64(427.22007050529515), np.float64(4436.499972397519), np.float64(460.41184168601586)]\n",
      "[359.0, 1058.0, 987.0, 449.0]\n",
      "[1042.0, 1067.0, 1280.0, 450.0]\n",
      "[358.0, 1058.0, 1041.0, 1068.0]\n",
      "[np.float64(-4467.744267870756), np.float64(431.3262182607166), np.float64(4464.685216677417), np.float64(461.91673019410075)]\n",
      "[358.0, 1058.0, 985.0, 450.0]\n",
      "[1041.0, 1068.0, 1278.0, 451.0]\n",
      "[357.0, 1058.0, 1040.0, 1068.0]\n",
      "[np.float64(-4467.854571927781), np.float64(431.3895748398369), np.float64(4464.805882352941), np.float64(461.8764705882353)]\n",
      "[357.0, 1058.0, 985.0, 450.0]\n",
      "[1040.0, 1068.0, 1277.0, 451.0]\n",
      "[355.0, 1059.0, 1039.0, 1070.0]\n",
      "[np.float64(-4498.949178342463), np.float64(434.75350273885846), np.float64(4495.950878323573), np.float64(464.7365029277452)]\n",
      "[355.0, 1059.0, 975.0, 453.0]\n",
      "[1039.0, 1070.0, 1275.0, 454.0]\n",
      "[353.0, 1059.0, 1038.0, 1071.0]\n",
      "[np.float64(-4509.559139552247), np.float64(435.97842388305185), np.float64(4506.593299933996), np.float64(465.63682006557235)]\n",
      "[353.0, 1059.0, 969.0, 454.0]\n",
      "[1038.0, 1071.0, 1273.0, 455.0]\n",
      "[352.0, 1060.0, 1036.0, 1073.0]\n",
      "[np.float64(-4519.240364457147), np.float64(436.9465463735418), np.float64(4516.274524838896), np.float64(466.6049425560623)]\n",
      "[352.0, 1060.0, 964.0, 457.0]\n",
      "[1036.0, 1073.0, 1271.0, 458.0]\n",
      "[350.0, 1060.0, 1035.0, 1072.0]\n",
      "[np.float64(-4539.291362221585), np.float64(438.7698836670272), np.float64(4536.28953003245), np.float64(468.78820555837615)]\n",
      "[350.0, 1060.0, 969.0, 455.0]\n",
      "[1035.0, 1072.0, 1270.0, 456.0]\n",
      "[347.0, 1061.0, 1033.0, 1072.0]\n",
      "[np.float64(-4529.464514581493), np.float64(437.78719890301807), np.float64(4526.462682392358), np.float64(467.805520794367)]\n",
      "[347.0, 1061.0, 968.0, 457.0]\n",
      "[1033.0, 1072.0, 1269.0, 458.0]\n",
      "[343.0, 1061.0, 1031.0, 1072.0]\n",
      "[np.float64(-4539.298017703803), np.float64(438.7033288448378), np.float64(4536.282874550231), np.float64(468.85476038056555)]\n",
      "[343.0, 1061.0, 966.0, 456.0]\n",
      "[1031.0, 1072.0, 1268.0, 457.0]\n",
      "[341.0, 1061.0, 1029.0, 1071.0]\n",
      "[np.float64(-4539.357184137755), np.float64(438.7089110585295), np.float64(4536.341974760479), np.float64(468.8610048312939)]\n",
      "[341.0, 1061.0, 965.0, 457.0]\n",
      "[1029.0, 1071.0, 1266.0, 458.0]\n",
      "[340.0, 1061.0, 1028.0, 1071.0]\n",
      "[np.float64(-4539.3621959756), np.float64(438.6587926800813), np.float64(4536.3369629226345), np.float64(468.9111232097421)]\n",
      "[340.0, 1061.0, 963.0, 457.0]\n",
      "[1028.0, 1071.0, 1263.0, 458.0]\n",
      "[339.0, 1061.0, 1027.0, 1073.0]\n",
      "[np.float64(-4528.84269034548), np.float64(437.43634226234633), np.float64(4525.783694945045), np.float64(468.02629626670625)]\n",
      "[339.0, 1061.0, 966.0, 456.0]\n",
      "[1027.0, 1073.0, 1262.0, 457.0]\n",
      "[338.0, 1061.0, 1026.0, 1073.0]\n",
      "[np.float64(-4528.847837464053), np.float64(437.38487107662843), np.float64(4525.778547826472), np.float64(468.07776745242415)]\n",
      "[338.0, 1061.0, 966.0, 456.0]\n",
      "[1026.0, 1073.0, 1261.0, 457.0]\n",
      "[338.0, 1062.0, 1025.0, 1074.0]\n",
      "[np.float64(-4538.378797392801), np.float64(438.19858562163296), np.float64(4535.281907468514), np.float64(469.1674848644985)]\n",
      "[338.0, 1062.0, 967.0, 457.0]\n",
      "[1025.0, 1074.0, 1260.0, 458.0]\n",
      "[340.0, 1062.0, 1022.0, 1075.0]\n",
      "[np.float64(-4538.384061455463), np.float64(438.1459449950155), np.float64(4535.276643405852), np.float64(469.22012549111594)]\n",
      "[340.0, 1062.0, 967.0, 457.0]\n",
      "[1022.0, 1075.0, 1259.0, 458.0]\n",
      "[340.0, 1063.0, 1020.0, 1075.0]\n",
      "[np.float64(-4538.384061455463), np.float64(438.1459449950155), np.float64(4535.276643405852), np.float64(469.22012549111594)]\n",
      "[340.0, 1063.0, 966.0, 457.0]\n",
      "[1020.0, 1075.0, 1257.0, 458.0]\n",
      "[337.0, 1064.0, 1019.0, 1075.0]\n",
      "[np.float64(-4538.309569920408), np.float64(438.0848468387615), np.float64(4535.191528305897), np.float64(469.26526298386904)]\n",
      "[337.0, 1064.0, 962.0, 459.0]\n",
      "[1019.0, 1075.0, 1256.0, 460.0]\n",
      "[337.0, 1064.0, 1018.0, 1075.0]\n",
      "[np.float64(-4539.018444158604), np.float64(423.2574017113137), np.float64(4532.950237682457), np.float64(483.93946647279233)]\n",
      "[337.0, 1064.0, 959.0, 459.0]\n",
      "[1018.0, 1075.0, 1255.0, 461.0]\n",
      "[334.0, 1065.0, 1017.0, 1075.0]\n",
      "[np.float64(-4528.5998662328675), np.float64(422.0801355809234), np.float64(4522.5048462244795), np.float64(483.03033566481133)]\n",
      "[334.0, 1065.0, 954.0, 460.0]\n",
      "[1017.0, 1075.0, 1253.0, 462.0]\n",
      "[330.0, 1065.0, 1013.0, 1076.0]\n",
      "[np.float64(-4528.734540260505), np.float64(422.0936029836872), np.float64(4522.639520252117), np.float64(483.043803067575)]\n",
      "[330.0, 1065.0, 954.0, 459.0]\n",
      "[1013.0, 1076.0, 1251.0, 461.0]\n",
      "[327.0, 1066.0, 1012.0, 1076.0]\n",
      "[np.float64(-4528.599956922449), np.float64(422.07922868511446), np.float64(4522.504755534898), np.float64(483.0312425606203)]\n",
      "[327.0, 1066.0, 952.0, 459.0]\n",
      "[1012.0, 1076.0, 1249.0, 461.0]\n",
      "[328.0, 1067.0, 1011.0, 1077.0]\n",
      "[np.float64(-4528.249755828517), np.float64(421.83898470624735), np.float64(4522.113916050971), np.float64(483.1973824817015)]\n",
      "[328.0, 1067.0, 953.0, 459.0]\n",
      "[1011.0, 1077.0, 1248.0, 461.0]\n",
      "[327.0, 1067.0, 1011.0, 1078.0]\n",
      "[np.float64(-4528.1068949560395), np.float64(421.7208236927349), np.float64(4521.950485886164), np.float64(483.2849143914854)]\n",
      "[327.0, 1067.0, 953.0, 459.0]\n",
      "[1011.0, 1078.0, 1247.0, 461.0]\n",
      "[326.0, 1067.0, 1010.0, 1079.0]\n",
      "[np.float64(-4528.1068949560395), np.float64(421.7208236927349), np.float64(4521.950485886164), np.float64(483.2849143914854)]\n",
      "[326.0, 1067.0, 952.0, 459.0]\n",
      "[1010.0, 1079.0, 1246.0, 461.0]\n",
      "[326.0, 1067.0, 1009.0, 1079.0]\n",
      "[np.float64(-4538.459639890151), np.float64(422.7896448310333), np.float64(4532.309873720254), np.float64(484.28730653000724)]\n",
      "[326.0, 1067.0, 950.0, 460.0]\n",
      "[1009.0, 1079.0, 1245.0, 462.0]\n",
      "[326.0, 1067.0, 1009.0, 1078.0]\n",
      "[np.float64(-4538.459639890151), np.float64(422.7896448310333), np.float64(4532.309873720254), np.float64(484.28730653000724)]\n",
      "[326.0, 1067.0, 949.0, 460.0]\n",
      "[1009.0, 1078.0, 1244.0, 462.0]\n",
      "[327.0, 1067.0, 1008.0, 1078.0]\n",
      "[np.float64(-4538.54103804479), np.float64(422.660377575291), np.float64(4532.364062553861), np.float64(484.4301324845741)]\n",
      "[327.0, 1067.0, 950.0, 460.0]\n",
      "[1008.0, 1078.0, 1243.0, 462.0]\n",
      "[326.0, 1067.0, 1010.0, 1078.0]\n",
      "[np.float64(-4538.037808812737), np.float64(422.53899106612465), np.float64(4531.846761324589), np.float64(484.4494659476081)]\n",
      "[326.0, 1067.0, 948.0, 462.0]\n",
      "[1010.0, 1078.0, 1243.0, 464.0]\n",
      "[329.0, 1067.0, 1012.0, 1078.0]\n",
      "[np.float64(-4537.256159041187), np.float64(422.1430609721297), np.float64(4531.002187767525), np.float64(484.68277370874154)]\n",
      "[329.0, 1067.0, 952.0, 460.0]\n",
      "[1012.0, 1078.0, 1242.0, 462.0]\n",
      "[334.0, 1067.0, 1014.0, 1078.0]\n",
      "[np.float64(-4537.256159041187), np.float64(422.1430609721297), np.float64(4531.002187767525), np.float64(484.68277370874154)]\n",
      "[334.0, 1067.0, 957.0, 460.0]\n",
      "[1014.0, 1078.0, 1244.0, 462.0]\n",
      "[338.0, 1067.0, 1018.0, 1079.0]\n",
      "[np.float64(-4567.756469603329), np.float64(440.59383694876027), np.float64(4564.552150789156), np.float64(472.6370250904883)]\n",
      "[338.0, 1067.0, 963.0, 460.0]\n",
      "[1018.0, 1079.0, 1248.0, 461.0]\n",
      "[341.0, 1067.0, 1024.0, 1079.0]\n",
      "[np.float64(-4577.741010076484), np.float64(441.669891950953), np.float64(4574.55205778803), np.float64(473.5594148354984)]\n",
      "[341.0, 1067.0, 965.0, 461.0]\n",
      "[1024.0, 1079.0, 1253.0, 462.0]\n",
      "[346.0, 1067.0, 1030.0, 1079.0]\n",
      "[np.float64(-4577.741010076484), np.float64(441.669891950953), np.float64(4574.55205778803), np.float64(473.5594148354984)]\n",
      "[346.0, 1067.0, 970.0, 461.0]\n",
      "[1030.0, 1079.0, 1257.0, 462.0]\n",
      "[351.0, 1067.0, 1035.0, 1079.0]\n",
      "[np.float64(-4577.741010076484), np.float64(441.669891950953), np.float64(4574.55205778803), np.float64(473.5594148354984)]\n",
      "[351.0, 1067.0, 977.0, 459.0]\n",
      "[1035.0, 1079.0, 1262.0, 460.0]\n",
      "[355.0, 1067.0, 1039.0, 1079.0]\n",
      "[np.float64(-4587.761827270051), np.float64(442.73370641875675), np.float64(4584.585099288221), np.float64(474.50098623707044)]\n",
      "[355.0, 1067.0, 976.0, 462.0]\n",
      "[1039.0, 1079.0, 1265.0, 463.0]\n",
      "[358.0, 1067.0, 1042.0, 1079.0]\n",
      "[np.float64(-4587.761827270051), np.float64(442.73370641875675), np.float64(4584.585099288221), np.float64(474.50098623707044)]\n",
      "[358.0, 1067.0, 977.0, 464.0]\n",
      "[1042.0, 1079.0, 1267.0, 465.0]\n",
      "[359.0, 1067.0, 1044.0, 1079.0]\n",
      "[np.float64(-4607.112054138471), np.float64(444.4611303147409), np.float64(4603.894217485183), np.float64(476.6394968476245)]\n",
      "[359.0, 1067.0, 984.0, 462.0]\n",
      "[1044.0, 1079.0, 1269.0, 463.0]\n",
      "[361.0, 1067.0, 1046.0, 1079.0]\n",
      "[np.float64(-4596.764611131195), np.float64(443.41227171742037), np.float64(4593.54397956769), np.float64(475.6185873524681)]\n",
      "[361.0, 1067.0, 985.0, 464.0]\n",
      "[1046.0, 1079.0, 1271.0, 465.0]\n",
      "[366.0, 1067.0, 1047.0, 1079.0]\n",
      "[np.float64(-4607.121147887654), np.float64(444.37019282291004), np.float64(4603.8851237359995), np.float64(476.73043433945537)]\n",
      "[366.0, 1067.0, 988.0, 463.0]\n",
      "[1047.0, 1079.0, 1272.0, 464.0]\n",
      "[371.0, 1068.0, 1050.0, 1079.0]\n",
      "[np.float64(-4636.9377785438155), np.float64(447.26688498756556), np.float64(4633.684928471179), np.float64(479.79538571393397)]\n",
      "[371.0, 1068.0, 987.0, 467.0]\n",
      "[1050.0, 1079.0, 1272.0, 468.0]\n",
      "[377.0, 1068.0, 1053.0, 1079.0]\n",
      "[np.float64(-4677.1821051353645), np.float64(451.26417384970256), np.float64(4673.923880053418), np.float64(483.84642466917563)]\n",
      "[377.0, 1068.0, 987.0, 471.0]\n",
      "[1053.0, 1079.0, 1274.0, 472.0]\n",
      "[383.0, 1068.0, 1058.0, 1079.0]\n",
      "[np.float64(-4707.271613719935), np.float64(454.2247513412502), np.float64(4704.003809753451), np.float64(486.90279100608836)]\n",
      "[383.0, 1068.0, 988.0, 474.0]\n",
      "[1058.0, 1079.0, 1276.0, 475.0]\n",
      "[389.0, 1068.0, 1064.0, 1079.0]\n",
      "[np.float64(-4736.877501619863), np.float64(456.96546328104944), np.float64(4733.566157683044), np.float64(490.0789026492414)]\n",
      "[389.0, 1068.0, 993.0, 477.0]\n",
      "[1064.0, 1079.0, 1279.0, 478.0]\n",
      "[395.0, 1068.0, 1067.0, 1079.0]\n",
      "[np.float64(-4787.055289649768), np.float64(461.9234191331605), np.float64(4783.732099584062), np.float64(495.15531979022245)]\n",
      "[395.0, 1068.0, 995.0, 482.0]\n",
      "[1067.0, 1079.0, 1283.0, 483.0]\n",
      "[403.0, 1068.0, 1069.0, 1079.0]\n",
      "[np.float64(-4816.971863700582), np.float64(464.8686094681641), np.float64(4813.6394722348605), np.float64(498.19252412538015)]\n",
      "[403.0, 1068.0, 1001.0, 485.0]\n",
      "[1069.0, 1079.0, 1290.0, 486.0]\n",
      "[409.0, 1068.0, 1072.0, 1079.0]\n",
      "[np.float64(-4826.663681425253), np.float64(465.8039318981825), np.float64(4823.324585139245), np.float64(499.19489475826725)]\n",
      "[409.0, 1068.0, 1006.0, 486.0]\n",
      "[1072.0, 1079.0, 1295.0, 487.0]\n",
      "[413.0, 1068.0, 1077.0, 1080.0]\n",
      "[np.float64(-4826.8020880726035), np.float64(465.8177725629176), np.float64(4823.462991786595), np.float64(499.20873542300234)]\n",
      "[413.0, 1068.0, 1010.0, 486.0]\n",
      "[1077.0, 1080.0, 1299.0, 487.0]\n",
      "[417.0, 1068.0, 1080.0, 1080.0]\n",
      "[np.float64(-4887.278167828502), np.float64(471.8653805385074), np.float64(4883.939071542493), np.float64(505.25634339859215)]\n",
      "[417.0, 1068.0, 1006.0, 492.0]\n",
      "[1080.0, 1080.0, 1299.0, 493.0]\n",
      "[422.0, 1068.0, 1082.0, 1080.0]\n",
      "[np.float64(-4896.916499374129), np.float64(472.7013178715666), np.float64(4893.552077182872), np.float64(506.34553978413356)]\n",
      "[422.0, 1068.0, 1010.0, 493.0]\n",
      "[1082.0, 1080.0, 1301.0, 494.0]\n",
      "[424.0, 1068.0, 1084.0, 1080.0]\n",
      "[np.float64(-4916.55529082158), np.float64(474.47904743660354), np.float64(4913.15400732741), np.float64(508.4918823782955)]\n",
      "[424.0, 1068.0, 1011.0, 496.0]\n",
      "[1084.0, 1080.0, 1300.0, 497.0]\n",
      "[425.0, 1068.0, 1085.0, 1080.0]\n",
      "[np.float64(-4916.55529082158), np.float64(474.47904743660354), np.float64(4913.15400732741), np.float64(508.4918823782955)]\n",
      "[425.0, 1068.0, 1014.0, 495.0]\n",
      "[1085.0, 1080.0, 1303.0, 496.0]\n",
      "[427.0, 1069.0, 1086.0, 1080.0]\n",
      "[np.float64(-4905.780616139521), np.float64(473.40157996839764), np.float64(4902.3793326453515), np.float64(507.4144149100896)]\n",
      "[427.0, 1069.0, 1018.0, 493.0]\n",
      "[1086.0, 1080.0, 1306.0, 494.0]\n",
      "[429.0, 1069.0, 1089.0, 1080.0]\n",
      "[np.float64(-4905.638802642485), np.float64(473.18450912692794), np.float64(4902.197343011332), np.float64(507.5991054384538)]\n",
      "[429.0, 1069.0, 1022.0, 494.0]\n",
      "[1089.0, 1080.0, 1307.0, 495.0]\n",
      "[436.0, 1069.0, 1089.0, 1080.0]\n",
      "[np.float64(-4905.800704208013), np.float64(473.2006992834807), np.float64(4902.35924457686), np.float64(507.61529559500656)]\n",
      "[436.0, 1069.0, 1023.0, 494.0]\n",
      "[1089.0, 1080.0, 1307.0, 495.0]\n",
      "[441.0, 1069.0, 1091.0, 1080.0]\n",
      "[np.float64(-4977.066744321491), np.float64(480.55608619685495), np.float64(4973.6705882352935), np.float64(514.5176470588235)]\n",
      "[441.0, 1069.0, 1013.0, 501.0]\n",
      "[1091.0, 1080.0, 1306.0, 502.0]\n",
      "[445.0, 1069.0, 1092.0, 1080.0]\n",
      "[np.float64(-5007.913145409495), np.float64(483.9367340362885), np.float64(5004.575604715503), np.float64(517.3121409762114)]\n",
      "[445.0, 1069.0, 1009.0, 504.0]\n",
      "[1092.0, 1080.0, 1309.0, 505.0]\n",
      "[445.0, 1069.0, 1092.0, 1080.0]\n",
      "[np.float64(-5007.91312318752), np.float64(483.9369562560416), np.float64(5004.575626937478), np.float64(517.3119187564582)]\n",
      "[445.0, 1069.0, 1011.0, 504.0]\n",
      "[1092.0, 1080.0, 1311.0, 505.0]\n",
      "[446.0, 1069.0, 1094.0, 1080.0]\n",
      "[np.float64(-5007.846457261586), np.float64(483.93028966344815), np.float64(5004.508961011544), np.float64(517.3052521638648)]\n",
      "[446.0, 1069.0, 1013.0, 504.0]\n",
      "[1094.0, 1080.0, 1313.0, 505.0]\n",
      "[447.0, 1069.0, 1097.0, 1080.0]\n",
      "[np.float64(-5006.04971067267), np.float64(483.43171357591643), np.float64(5002.649065624878), np.float64(517.4381640538382)]\n",
      "[447.0, 1069.0, 1022.0, 500.0]\n",
      "[1097.0, 1080.0, 1314.0, 501.0]\n",
      "[448.0, 1069.0, 1102.0, 1080.0]\n",
      "[np.float64(-5006.087009464103), np.float64(483.05872566158297), np.float64(5002.611766833445), np.float64(517.8111519681717)]\n",
      "[448.0, 1069.0, 1025.0, 504.0]\n",
      "[1102.0, 1080.0, 1313.0, 505.0]\n",
      "[450.0, 1069.0, 1106.0, 1080.0]\n",
      "[np.float64(-5015.288617226564), np.float64(483.7606655785646), np.float64(5011.770162544566), np.float64(518.9452123985484)]\n",
      "[450.0, 1069.0, 1030.0, 505.0]\n",
      "[1106.0, 1080.0, 1315.0, 506.0]\n",
      "[454.0, 1069.0, 1109.0, 1080.0]\n",
      "[np.float64(-5015.557149188683), np.float64(483.7875187747765), np.float64(5012.038694506685), np.float64(518.9720655947602)]\n",
      "[454.0, 1069.0, 1034.0, 505.0]\n",
      "[1109.0, 1080.0, 1318.0, 506.0]\n",
      "[457.0, 1069.0, 1113.0, 1080.0]\n",
      "[np.float64(-5015.297565623216), np.float64(483.779408134496), np.float64(5011.782645142459), np.float64(518.9286129420716)]\n",
      "[457.0, 1069.0, 1034.0, 508.0]\n",
      "[1113.0, 1080.0, 1321.0, 509.0]\n",
      "[461.0, 1069.0, 1115.0, 1080.0]\n",
      "[np.float64(-5015.295614702513), np.float64(483.7989173415241), np.float64(5011.784596063161), np.float64(518.9091037350435)]\n",
      "[461.0, 1069.0, 1041.0, 505.0]\n",
      "[1115.0, 1080.0, 1327.0, 506.0]\n",
      "[466.0, 1069.0, 1118.0, 1080.0]\n",
      "[np.float64(-5015.295614702513), np.float64(483.7989173415241), np.float64(5011.784596063161), np.float64(518.9091037350435)]\n",
      "[466.0, 1069.0, 1047.0, 504.0]\n",
      "[1118.0, 1080.0, 1332.0, 505.0]\n",
      "[470.0, 1069.0, 1120.0, 1080.0]\n",
      "[np.float64(-5025.01577558861), np.float64(484.7709334301337), np.float64(5021.504756949258), np.float64(519.8811198236531)]\n",
      "[470.0, 1069.0, 1049.0, 506.0]\n",
      "[1120.0, 1080.0, 1335.0, 507.0]\n",
      "[473.0, 1069.0, 1122.0, 1080.0]\n",
      "[np.float64(-5035.1447542605065), np.float64(485.7749898703457), np.float64(5031.631984843535), np.float64(520.9026840400585)]\n",
      "[473.0, 1069.0, 1049.0, 507.0]\n",
      "[1122.0, 1080.0, 1336.0, 508.0]\n",
      "[475.0, 1069.0, 1125.0, 1080.0]\n",
      "[np.float64(-5044.658588385866), np.float64(486.6558682521347), np.float64(5041.131857576667), np.float64(521.9231763441186)]\n",
      "[475.0, 1069.0, 1050.0, 508.0]\n",
      "[1125.0, 1080.0, 1336.0, 509.0]\n",
      "[477.0, 1069.0, 1129.0, 1080.0]\n",
      "[np.float64(-5044.670890313302), np.float64(486.5328489777701), np.float64(5041.119555649231), np.float64(522.0461956184832)]\n",
      "[477.0, 1069.0, 1052.0, 508.0]\n",
      "[1129.0, 1080.0, 1336.0, 509.0]\n",
      "[480.0, 1069.0, 1133.0, 1080.0]\n",
      "[np.float64(-5044.689655746394), np.float64(486.3451946468514), np.float64(5041.100790216139), np.float64(522.2338499494019)]\n",
      "[480.0, 1069.0, 1056.0, 508.0]\n",
      "[1133.0, 1080.0, 1337.0, 509.0]\n",
      "[484.0, 1069.0, 1135.0, 1081.0]\n",
      "[np.float64(-5044.160383728847), np.float64(486.19246979595323), np.float64(5040.5517562878695), np.float64(522.2787442057185)]\n",
      "[484.0, 1069.0, 1060.0, 509.0]\n",
      "[1135.0, 1081.0, 1340.0, 510.0]\n",
      "[487.0, 1070.0, 1134.0, 1081.0]\n",
      "[np.float64(-5029.497902300236), np.float64(467.6979312340261), np.float64(5022.517336162415), np.float64(537.503592612239)]\n",
      "[487.0, 1070.0, 1064.0, 508.0]\n",
      "[1134.0, 1081.0, 1345.0, 510.0]\n",
      "[487.0, 1070.0, 1136.0, 1081.0]\n",
      "[np.float64(-5029.497902300236), np.float64(467.6979312340261), np.float64(5022.517336162415), np.float64(537.503592612239)]\n",
      "[487.0, 1070.0, 1062.0, 510.0]\n",
      "[1136.0, 1081.0, 1350.0, 512.0]\n",
      "[490.0, 1070.0, 1138.0, 1081.0]\n",
      "[np.float64(-5029.497902300236), np.float64(467.6979312340261), np.float64(5022.517336162415), np.float64(537.503592612239)]\n",
      "[490.0, 1070.0, 1065.0, 510.0]\n",
      "[1138.0, 1081.0, 1354.0, 512.0]\n",
      "[494.0, 1070.0, 1139.0, 1081.0]\n",
      "[np.float64(-5029.535109248728), np.float64(467.8232864411853), np.float64(5022.578629152948), np.float64(537.3880873989824)]\n",
      "[494.0, 1070.0, 1069.0, 510.0]\n",
      "[1139.0, 1081.0, 1355.0, 512.0]\n",
      "[494.0, 1070.0, 1143.0, 1081.0]\n",
      "[np.float64(-5028.493783637949), np.float64(467.55228586989523), np.float64(5021.50426037183), np.float64(537.4475185310828)]\n",
      "[494.0, 1070.0, 1070.0, 511.0]\n",
      "[1143.0, 1081.0, 1357.0, 512.0]\n",
      "[498.0, 1070.0, 1145.0, 1081.0]\n",
      "[np.float64(-5025.155090783054), np.float64(467.21841658440576), np.float64(5018.165567516936), np.float64(537.1136492455933)]\n",
      "[498.0, 1070.0, 1074.0, 506.0]\n",
      "[1145.0, 1081.0, 1361.0, 508.0]\n",
      "[506.0, 1070.0, 1147.0, 1081.0]\n",
      "[np.float64(-5021.816397928159), np.float64(466.88454729891623), np.float64(5014.826874662041), np.float64(536.7797799601037)]\n",
      "[506.0, 1070.0, 1071.0, 507.0]\n",
      "[1147.0, 1081.0, 1360.0, 509.0]\n",
      "[510.0, 1070.0, 1147.0, 1081.0]\n",
      "[np.float64(-5018.477705073265), np.float64(466.55067801342676), np.float64(5011.488181807146), np.float64(536.4459106746143)]\n",
      "[510.0, 1070.0, 1073.0, 509.0]\n",
      "[1147.0, 1081.0, 1360.0, 511.0]\n",
      "[507.0, 1070.0, 1149.0, 1081.0]\n",
      "[np.float64(-5017.038093216636), np.float64(465.9204549710961), np.float64(5009.952280473949), np.float64(536.7785823979624)]\n",
      "[507.0, 1070.0, 1079.0, 509.0]\n",
      "[1149.0, 1081.0, 1362.0, 511.0]\n",
      "[505.0, 1070.0, 1150.0, 1081.0]\n",
      "[np.float64(-5017.038093216636), np.float64(465.9204549710961), np.float64(5009.952280473949), np.float64(536.7785823979624)]\n",
      "[505.0, 1070.0, 1083.0, 509.0]\n",
      "[1150.0, 1081.0, 1366.0, 511.0]\n",
      "[506.0, 1070.0, 1151.0, 1081.0]\n",
      "[np.float64(-5026.950458715596), np.float64(466.9651376146789), np.float64(5019.875229357797), np.float64(537.7174311926606)]\n",
      "[506.0, 1070.0, 1081.0, 510.0]\n",
      "[1151.0, 1081.0, 1367.0, 512.0]\n",
      "[507.0, 1070.0, 1152.0, 1081.0]\n",
      "[np.float64(-5027.348262320107), np.float64(467.12738061529745), np.float64(5020.297282990065), np.float64(537.6371739157197)]\n",
      "[507.0, 1070.0, 1084.0, 510.0]\n",
      "[1152.0, 1081.0, 1368.0, 512.0]\n",
      "[510.0, 1070.0, 1154.0, 1081.0]\n",
      "[np.float64(-5027.348262320107), np.float64(467.12738061529745), np.float64(5020.297282990065), np.float64(537.6371739157197)]\n",
      "[510.0, 1070.0, 1082.0, 510.0]\n",
      "[1154.0, 1081.0, 1367.0, 512.0]\n",
      "[516.0, 1070.0, 1154.0, 1081.0]\n",
      "[np.float64(-5048.647758156241), np.float64(469.60105357677344), np.float64(5041.664842861419), np.float64(539.4302065249925)]\n",
      "[516.0, 1070.0, 1078.0, 512.0]\n",
      "[1154.0, 1081.0, 1367.0, 514.0]\n",
      "[519.0, 1070.0, 1155.0, 1081.0]\n",
      "[np.float64(-5059.702593642664), np.float64(471.0895050838408), np.float64(5052.795513587135), np.float64(540.1603056391392)]\n",
      "[519.0, 1070.0, 1074.0, 515.0]\n",
      "[1155.0, 1081.0, 1368.0, 517.0]\n",
      "[520.0, 1070.0, 1157.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[520.0, 1070.0, 1077.0, 513.0]\n",
      "[1157.0, 1081.0, 1370.0, 515.0]\n",
      "[519.0, 1070.0, 1158.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[519.0, 1070.0, 1424.0, 173.0]\n",
      "[1158.0, 1081.0, 1499.0, 173.0]\n",
      "[517.0, 1070.0, 1158.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[517.0, 1070.0, 1418.0, 187.0]\n",
      "[1158.0, 1081.0, 1495.0, 187.0]\n",
      "[514.0, 1070.0, 1159.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[514.0, 1070.0, 1420.0, 188.0]\n",
      "[1159.0, 1081.0, 1495.0, 188.0]\n",
      "[514.0, 1070.0, 1158.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[514.0, 1070.0, 1419.0, 188.0]\n",
      "[1158.0, 1081.0, 1495.0, 188.0]\n",
      "[515.0, 1070.0, 1158.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[515.0, 1070.0, 1421.0, 187.0]\n",
      "[1158.0, 1081.0, 1496.0, 187.0]\n",
      "[516.0, 1070.0, 1158.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[516.0, 1070.0, 1420.0, 187.0]\n",
      "[1158.0, 1081.0, 1497.0, 187.0]\n",
      "[515.0, 1070.0, 1158.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[515.0, 1070.0, 1420.0, 188.0]\n",
      "[1158.0, 1081.0, 1497.0, 188.0]\n",
      "[516.0, 1070.0, 1158.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[516.0, 1070.0, 1422.0, 188.0]\n",
      "[1158.0, 1081.0, 1498.0, 188.0]\n",
      "[517.0, 1070.0, 1159.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[517.0, 1070.0, 1422.0, 191.0]\n",
      "[1159.0, 1081.0, 1498.0, 191.0]\n",
      "[518.0, 1070.0, 1159.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[518.0, 1070.0, 1424.0, 191.0]\n",
      "[1159.0, 1081.0, 1499.0, 191.0]\n",
      "[518.0, 1070.0, 1160.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[518.0, 1070.0, 1424.0, 191.0]\n",
      "[1160.0, 1081.0, 1499.0, 191.0]\n",
      "[519.0, 1070.0, 1160.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[519.0, 1070.0, 1424.0, 189.0]\n",
      "[1160.0, 1081.0, 1500.0, 189.0]\n",
      "[521.0, 1070.0, 1161.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[521.0, 1070.0, 1435.0, 176.0]\n",
      "[1161.0, 1081.0, 1505.0, 176.0]\n",
      "[525.0, 1070.0, 1161.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[525.0, 1070.0, 1086.0, 517.0]\n",
      "[1161.0, 1081.0, 1375.0, 518.0]\n",
      "[528.0, 1070.0, 1161.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[528.0, 1070.0, 1081.0, 521.0]\n",
      "[1161.0, 1081.0, 1374.0, 522.0]\n",
      "[529.0, 1070.0, 1162.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[529.0, 1070.0, 1431.0, 175.0]\n",
      "[1162.0, 1081.0, 1506.0, 175.0]\n",
      "[527.0, 1070.0, 1161.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[527.0, 1070.0, 1436.0, 175.0]\n",
      "[1161.0, 1081.0, 1506.0, 175.0]\n",
      "[527.0, 1070.0, 1161.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[527.0, 1070.0, 1438.0, 177.0]\n",
      "[1161.0, 1081.0, 1507.0, 177.0]\n",
      "[527.0, 1070.0, 1163.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[527.0, 1070.0, 1437.0, 178.0]\n",
      "[1163.0, 1081.0, 1509.0, 178.0]\n",
      "[526.0, 1070.0, 1164.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1427.0, 190.0]\n",
      "[1164.0, 1081.0, 1503.0, 190.0]\n",
      "[525.0, 1070.0, 1166.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[525.0, 1070.0, 1427.0, 192.0]\n",
      "[1166.0, 1081.0, 1500.0, 192.0]\n",
      "[525.0, 1070.0, 1168.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[525.0, 1070.0, 1429.0, 192.0]\n",
      "[1168.0, 1081.0, 1499.0, 192.0]\n",
      "[526.0, 1070.0, 1166.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1431.0, 192.0]\n",
      "[1166.0, 1081.0, 1499.0, 192.0]\n",
      "[526.0, 1070.0, 1167.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1431.0, 193.0]\n",
      "[1167.0, 1081.0, 1500.0, 193.0]\n",
      "[527.0, 1070.0, 1169.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[527.0, 1070.0, 1434.0, 191.0]\n",
      "[1169.0, 1081.0, 1502.0, 191.0]\n",
      "[526.0, 1070.0, 1170.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1431.0, 193.0]\n",
      "[1170.0, 1081.0, 1503.0, 193.0]\n",
      "[526.0, 1070.0, 1171.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1435.0, 189.0]\n",
      "[1171.0, 1081.0, 1509.0, 189.0]\n",
      "[526.0, 1070.0, 1171.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1441.0, 183.0]\n",
      "[1171.0, 1081.0, 1515.0, 183.0]\n",
      "[526.0, 1070.0, 1173.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1442.0, 182.0]\n",
      "[1173.0, 1081.0, 1518.0, 182.0]\n",
      "[526.0, 1070.0, 1175.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1441.0, 183.0]\n",
      "[1175.0, 1081.0, 1516.0, 183.0]\n",
      "[526.0, 1070.0, 1180.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1441.0, 183.0]\n",
      "[1180.0, 1081.0, 1517.0, 183.0]\n",
      "[526.0, 1070.0, 1183.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1440.0, 184.0]\n",
      "[1183.0, 1081.0, 1518.0, 184.0]\n",
      "[526.0, 1070.0, 1184.0, 1081.0]\n",
      "[np.float64(-5059.700418156616), np.float64(471.1112599443234), np.float64(5052.797689073183), np.float64(540.1385507786565)]\n",
      "[526.0, 1070.0, 1428.0, 196.0]\n",
      "[1184.0, 1081.0, 1509.0, 196.0]\n",
      "Adjusted video saved to C:\\Users\\miche\\OneDrive\\Documenti\\GitHub\\bowling-analysis\\data\\recording_3\\All_Lines_video_processed.mp4\n"
     ]
    }
   ],
   "source": [
    "# Reset the video to the beginning\n",
    "cap.set(cv2.CAP_PROP_POS_FRAMES, 0)\n",
    "\n",
    "# Define the codec and create a VideoWriter object to save the modified frames\n",
    "output_path = (\n",
    "    project_root\n",
    "    / \"data\"\n",
    "    / f\"recording_{video_number}\"\n",
    "    / \"All_Lines_video_processed.mp4\"\n",
    ")\n",
    "fourcc = cv2.VideoWriter_fourcc(*\"mp4v\")  # Use 'mp4v' codec for MP4 format\n",
    "fps = int(cap.get(cv2.CAP_PROP_FPS))\n",
    "frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))\n",
    "frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))\n",
    "out = cv2.VideoWriter(str(output_path), fourcc, fps, (frame_width, frame_height))\n",
    "\n",
    "# Process the lines\n",
    "upper_processed = postprocessing_upper(upper_lines)\n",
    "# print('Processed lines:', upper_processed)\n",
    "\n",
    "# initializing df\n",
    "# output_df = pd.DataFrame(columns=['frame_number', 'horizontal', 'left', 'right'])\n",
    "\n",
    "# Loop through each frame in the video\n",
    "frame_index = 0\n",
    "while frame_index < len(upper_processed):\n",
    "    ret, video_frame = cap.read()\n",
    "    if not ret:\n",
    "        print(\"End of video or failed to read the frame at iteration\", frame_index)\n",
    "        break\n",
    "    # print(f\"Processing frame {frame_index}\")\n",
    "\n",
    "    # draw the lines on the frame\n",
    "    modified_frame = write_lines_on_frame(\n",
    "        video_frame,\n",
    "        [\n",
    "            bottom_lines[frame_index],\n",
    "            upper_processed[frame_index],\n",
    "            left_lines[frame_index],\n",
    "            right_lines[frame_index],\n",
    "        ],\n",
    "    )\n",
    "\n",
    "    # add lines to the output df\n",
    "    # output_df.loc[len(output_df)] = [frame_index, processed_lines[frame_index][0], processed_lines[frame_index][1], processed_lines[frame_index][2]]\n",
    "\n",
    "    # Write the modified frame to the output video\n",
    "    out.write(modified_frame)\n",
    "\n",
    "    # Increment the frame index\n",
    "    frame_index += 1\n",
    "\n",
    "# Release the video capture and writer objects\n",
    "# cap.release()\n",
    "out.release()\n",
    "\n",
    "print(f\"Adjusted video saved to {output_path}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "63f11c37",
   "metadata": {},
   "source": [
    "Compute the determinant"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "id": "b29c7359",
   "metadata": {},
   "outputs": [],
   "source": [
    "def det(a, b):\n",
    "    return a[0] * b[1] - a[1] * b[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "604fcbdc",
   "metadata": {},
   "source": [
    "Get the intersection of 2 lines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "id": "887855eb",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_intersection(line_1, line_2):\n",
    "    \"\"\"Find the intersection point of two lines.\"\"\"\n",
    "    xdiff = (line_1[0] - line_1[2], line_2[0] - line_2[2])\n",
    "    ydiff = (line_1[1] - line_1[3], line_2[1] - line_2[3])\n",
    "\n",
    "    div = det(xdiff, ydiff)\n",
    "    if div == 0:\n",
    "        return None\n",
    "\n",
    "    d = (\n",
    "        det((line_1[0], line_1[1]), (line_1[2], line_1[3])),\n",
    "        det((line_2[0], line_2[1]), (line_2[2], line_2[3])),\n",
    "    )\n",
    "    x = int(det(d, xdiff) / div)\n",
    "    y = int(det(d, ydiff) / div)\n",
    "    return x, y"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "df303b00",
   "metadata": {},
   "source": [
    "save the 4 points in a csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "id": "c5022c0d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1320.0, 1049.0, 1537.0, 447.0], [1319.0, 1051.0, 1538.0, 446.0], [1316.0, 1053.0, 1536.0, 446.0], [1312.0, 1053.0, 1534.0, 445.0], [1308.0, 1052.0, 1530.0, 444.0], [1304.0, 1051.0, 1525.0, 442.0], [1299.0, 1049.0, 1521.0, 440.0], [1296.0, 1046.0, 1517.0, 439.0], [1292.0, 1044.0, 1512.0, 439.0], [1285.0, 1042.0, 1508.0, 436.0], [1279.0, 1041.0, 1503.0, 434.0], [1276.0, 1039.0, 1501.0, 432.0], [1275.0, 1037.0, 1499.0, 433.0], [1268.0, 1035.0, 1493.0, 430.0], [1262.0, 1033.0, 1488.0, 428.0], [1257.0, 1031.0, 1484.0, 426.0], [1253.0, 1030.0, 1480.0, 425.0], [1247.0, 1027.0, 1475.0, 422.0], [1244.0, 1025.0, 1471.0, 420.0], [1242.0, 1023.0, 1468.0, 418.0], [1238.0, 1021.0, 1463.0, 416.0], [1234.0, 1019.0, 1459.0, 417.0], [1234.0, 1016.0, 1456.0, 417.0], [1233.0, 1016.0, 1454.0, 415.0], [1232.0, 1016.0, 1452.0, 411.0], [1225.0, 1015.0, 1449.0, 406.0], [1218.0, 1014.0, 1446.0, 403.0], [1213.0, 1013.0, 1441.0, 401.0], [1216.0, 1012.0, 1441.0, 401.0], [1214.0, 1009.0, 1436.0, 399.0], [1207.0, 1006.0, 1429.0, 396.0], [1203.0, 1003.0, 1424.0, 394.0], [1201.0, 1002.0, 1422.0, 393.0], [1200.0, 1002.0, 1421.0, 392.0], [1197.0, 1003.0, 1418.0, 391.0], [1191.0, 1003.0, 1416.0, 389.0], [1185.0, 1003.0, 1415.0, 387.0], [1180.0, 1003.0, 1414.0, 387.0], [1180.0, 1001.0, 1412.0, 386.0], [1177.0, 1000.0, 1407.0, 383.0], [1174.0, 1000.0, 1405.0, 380.0], [1171.0, 998.0, 1402.0, 378.0], [1169.0, 997.0, 1400.0, 377.0], [1167.0, 995.0, 1395.0, 375.0], [1168.0, 993.0, 1393.0, 375.0], [1167.0, 991.0, 1392.0, 373.0], [1164.0, 989.0, 1391.0, 373.0], [1160.0, 987.0, 1388.0, 370.0], [1158.0, 986.0, 1385.0, 368.0], [1156.0, 984.0, 1381.0, 367.0], [1152.0, 983.0, 1380.0, 365.0], [1147.0, 982.0, 1381.0, 364.0], [1143.0, 982.0, 1380.0, 363.0], [1142.0, 982.0, 1377.0, 361.0], [1140.0, 982.0, 1372.0, 360.0], [1138.0, 982.0, 1369.0, 358.0], [1136.0, 981.0, 1366.0, 358.0], [1133.0, 980.0, 1363.0, 359.0], [1131.0, 979.0, 1362.0, 358.0], [1128.0, 978.0, 1361.0, 358.0], [1126.0, 977.0, 1359.0, 359.0], [1124.0, 976.0, 1358.0, 359.0], [1123.0, 976.0, 1356.0, 358.0], [1121.0, 976.0, 1352.0, 358.0], [1119.0, 976.0, 1348.0, 358.0], [1116.0, 977.0, 1346.0, 359.0], [1113.0, 979.0, 1345.0, 360.0], [1112.0, 979.0, 1343.0, 361.0], [1111.0, 979.0, 1342.0, 362.0], [1108.0, 981.0, 1340.0, 363.0], [1106.0, 982.0, 1336.0, 366.0], [1104.0, 983.0, 1333.0, 367.0], [1104.0, 986.0, 1332.0, 369.0], [1102.0, 989.0, 1328.0, 372.0], [1101.0, 990.0, 1326.0, 373.0], [1099.0, 992.0, 1325.0, 374.0], [1098.0, 995.0, 1323.0, 377.0], [1097.0, 996.0, 1322.0, 380.0], [1095.0, 999.0, 1319.0, 384.0], [1094.0, 1003.0, 1317.0, 387.0], [1092.0, 1007.0, 1316.0, 390.0], [1090.0, 1012.0, 1315.0, 391.0], [1087.0, 1018.0, 1313.0, 396.0], [1085.0, 1022.0, 1311.0, 400.0], [1083.0, 1028.0, 1309.0, 404.0], [1081.0, 1033.0, 1307.0, 410.0], [1079.0, 1037.0, 1305.0, 415.0], [1078.0, 1040.0, 1305.0, 416.0], [1077.0, 1043.0, 1303.0, 420.0], [1074.0, 1046.0, 1302.0, 422.0], [1072.0, 1047.0, 1300.0, 426.0], [1070.0, 1049.0, 1300.0, 426.0], [1069.0, 1051.0, 1297.0, 430.0], [1068.0, 1053.0, 1296.0, 432.0], [1066.0, 1054.0, 1296.0, 434.0], [1063.0, 1056.0, 1296.0, 435.0], [1061.0, 1057.0, 1295.0, 437.0], [1061.0, 1058.0, 1292.0, 438.0], [1060.0, 1059.0, 1288.0, 439.0], [1060.0, 1060.0, 1285.0, 441.0], [1057.0, 1061.0, 1285.0, 442.0], [1054.0, 1061.0, 1285.0, 444.0], [1052.0, 1063.0, 1285.0, 445.0], [1051.0, 1064.0, 1284.0, 445.0], [1049.0, 1065.0, 1283.0, 448.0], [1046.0, 1066.0, 1282.0, 449.0], [1044.0, 1067.0, 1282.0, 450.0], [1042.0, 1067.0, 1280.0, 450.0], [1041.0, 1068.0, 1278.0, 451.0], [1040.0, 1068.0, 1277.0, 451.0], [1039.0, 1070.0, 1275.0, 454.0], [1038.0, 1071.0, 1273.0, 455.0], [1036.0, 1073.0, 1271.0, 458.0], [1035.0, 1072.0, 1270.0, 456.0], [1033.0, 1072.0, 1269.0, 458.0], [1031.0, 1072.0, 1268.0, 457.0], [1029.0, 1071.0, 1266.0, 458.0], [1028.0, 1071.0, 1263.0, 458.0], [1027.0, 1073.0, 1262.0, 457.0], [1026.0, 1073.0, 1261.0, 457.0], [1025.0, 1074.0, 1260.0, 458.0], [1022.0, 1075.0, 1259.0, 458.0], [1020.0, 1075.0, 1257.0, 458.0], [1019.0, 1075.0, 1256.0, 460.0], [1018.0, 1075.0, 1255.0, 461.0], [1017.0, 1075.0, 1253.0, 462.0], [1013.0, 1076.0, 1251.0, 461.0], [1012.0, 1076.0, 1249.0, 461.0], [1011.0, 1077.0, 1248.0, 461.0], [1011.0, 1078.0, 1247.0, 461.0], [1010.0, 1079.0, 1246.0, 461.0], [1009.0, 1079.0, 1245.0, 462.0], [1009.0, 1078.0, 1244.0, 462.0], [1008.0, 1078.0, 1243.0, 462.0], [1010.0, 1078.0, 1243.0, 464.0], [1012.0, 1078.0, 1242.0, 462.0], [1014.0, 1078.0, 1244.0, 462.0], [1018.0, 1079.0, 1248.0, 461.0], [1024.0, 1079.0, 1253.0, 462.0], [1030.0, 1079.0, 1257.0, 462.0], [1035.0, 1079.0, 1262.0, 460.0], [1039.0, 1079.0, 1265.0, 463.0], [1042.0, 1079.0, 1267.0, 465.0], [1044.0, 1079.0, 1269.0, 463.0], [1046.0, 1079.0, 1271.0, 465.0], [1047.0, 1079.0, 1272.0, 464.0], [1050.0, 1079.0, 1272.0, 468.0], [1053.0, 1079.0, 1274.0, 472.0], [1058.0, 1079.0, 1276.0, 475.0], [1064.0, 1079.0, 1279.0, 478.0], [1067.0, 1079.0, 1283.0, 483.0], [1069.0, 1079.0, 1290.0, 486.0], [1072.0, 1079.0, 1295.0, 487.0], [1077.0, 1080.0, 1299.0, 487.0], [1080.0, 1080.0, 1299.0, 493.0], [1082.0, 1080.0, 1301.0, 494.0], [1084.0, 1080.0, 1300.0, 497.0], [1085.0, 1080.0, 1303.0, 496.0], [1086.0, 1080.0, 1306.0, 494.0], [1089.0, 1080.0, 1307.0, 495.0], [1089.0, 1080.0, 1307.0, 495.0], [1091.0, 1080.0, 1306.0, 502.0], [1092.0, 1080.0, 1309.0, 505.0], [1092.0, 1080.0, 1311.0, 505.0], [1094.0, 1080.0, 1313.0, 505.0], [1097.0, 1080.0, 1314.0, 501.0], [1102.0, 1080.0, 1313.0, 505.0], [1106.0, 1080.0, 1315.0, 506.0], [1109.0, 1080.0, 1318.0, 506.0], [1113.0, 1080.0, 1321.0, 509.0], [1115.0, 1080.0, 1327.0, 506.0], [1118.0, 1080.0, 1332.0, 505.0], [1120.0, 1080.0, 1335.0, 507.0], [1122.0, 1080.0, 1336.0, 508.0], [1125.0, 1080.0, 1336.0, 509.0], [1129.0, 1080.0, 1336.0, 509.0], [1133.0, 1080.0, 1337.0, 509.0], [1135.0, 1081.0, 1340.0, 510.0], [1134.0, 1081.0, 1345.0, 510.0], [1136.0, 1081.0, 1350.0, 512.0], [1138.0, 1081.0, 1354.0, 512.0], [1139.0, 1081.0, 1355.0, 512.0], [1143.0, 1081.0, 1357.0, 512.0], [1145.0, 1081.0, 1361.0, 508.0], [1147.0, 1081.0, 1360.0, 509.0], [1147.0, 1081.0, 1360.0, 511.0], [1149.0, 1081.0, 1362.0, 511.0], [1150.0, 1081.0, 1366.0, 511.0], [1151.0, 1081.0, 1367.0, 512.0], [1152.0, 1081.0, 1368.0, 512.0], [1154.0, 1081.0, 1367.0, 512.0], [1154.0, 1081.0, 1367.0, 514.0], [1155.0, 1081.0, 1368.0, 517.0], [1157.0, 1081.0, 1370.0, 515.0], [1158.0, 1081.0, 1499.0, 173.0], [1158.0, 1081.0, 1495.0, 187.0], [1159.0, 1081.0, 1495.0, 188.0], [1158.0, 1081.0, 1495.0, 188.0], [1158.0, 1081.0, 1496.0, 187.0], [1158.0, 1081.0, 1497.0, 187.0], [1158.0, 1081.0, 1497.0, 188.0], [1158.0, 1081.0, 1498.0, 188.0], [1159.0, 1081.0, 1498.0, 191.0], [1159.0, 1081.0, 1499.0, 191.0], [1160.0, 1081.0, 1499.0, 191.0], [1160.0, 1081.0, 1500.0, 189.0], [1161.0, 1081.0, 1505.0, 176.0], [1161.0, 1081.0, 1375.0, 518.0], [1161.0, 1081.0, 1374.0, 522.0], [1162.0, 1081.0, 1506.0, 175.0], [1161.0, 1081.0, 1506.0, 175.0], [1161.0, 1081.0, 1507.0, 177.0], [1163.0, 1081.0, 1509.0, 178.0], [1164.0, 1081.0, 1503.0, 190.0], [1166.0, 1081.0, 1500.0, 192.0], [1168.0, 1081.0, 1499.0, 192.0], [1166.0, 1081.0, 1499.0, 192.0], [1167.0, 1081.0, 1500.0, 193.0], [1169.0, 1081.0, 1502.0, 191.0], [1170.0, 1081.0, 1503.0, 193.0], [1171.0, 1081.0, 1509.0, 189.0], [1171.0, 1081.0, 1515.0, 183.0], [1173.0, 1081.0, 1518.0, 182.0], [1175.0, 1081.0, 1516.0, 183.0], [1180.0, 1081.0, 1517.0, 183.0], [1183.0, 1081.0, 1518.0, 184.0], [1184.0, 1081.0, 1509.0, 196.0]]\n",
      "Updated lane points saved to C:\\Users\\miche\\OneDrive\\Documenti\\GitHub\\bowling-analysis\\data\\auxiliary_data\\lane_points\\lane_points_processed_3.csv\n"
     ]
    }
   ],
   "source": [
    "up_left_points = []\n",
    "up_right_points = []\n",
    "for i in range(len(upper_processed)):\n",
    "    if upper_processed[i] is not None and left_lines[i] is not None:\n",
    "        intersection = get_intersection(upper_processed[i], left_lines[i])\n",
    "        if intersection is not None:\n",
    "            up_left_points.append(intersection)\n",
    "        else:\n",
    "            up_left_points.append(None)\n",
    "    else:\n",
    "        up_left_points.append(None)\n",
    "\n",
    "print(right_lines)\n",
    "\n",
    "for i in range(len(upper_processed)):\n",
    "    if upper_processed[i] is not None and right_lines[i] is not None:\n",
    "        intersection = get_intersection(upper_processed[i], right_lines[i])\n",
    "        if intersection is not None:\n",
    "            up_right_points.append(intersection)\n",
    "        else:\n",
    "            up_right_points.append(None)\n",
    "    else:\n",
    "        up_right_points.append(None)\n",
    "\n",
    "\n",
    "lane_points[\"up_left_x\"] = [point[0] if point else np.nan for point in up_left_points]\n",
    "lane_points[\"up_left_y\"] = [point[1] if point else np.nan for point in up_left_points]\n",
    "lane_points[\"up_right_x\"] = [point[0] if point else np.nan for point in up_right_points]\n",
    "lane_points[\"up_right_y\"] = [point[1] if point else np.nan for point in up_right_points]\n",
    "\n",
    "# print(lane_points[['up_left_x', 'up_left_y', 'up_right_x', 'up_right_y']])\n",
    "# print(lane_points[['bottom_left_x', 'bottom_left_y', 'bottom_right_x', 'bottom_right_y']])\n",
    "\n",
    "# Save the updated DataFrame to a new CSV file\n",
    "output_csv_path = (\n",
    "    project_root\n",
    "    / \"data\"\n",
    "    / \"auxiliary_data\"\n",
    "    / \"lane_points\"\n",
    "    / f\"lane_points_processed_{video_number}.csv\"\n",
    ")\n",
    "lane_points.to_csv(output_csv_path, index=False)\n",
    "print(f\"Updated lane points saved to {output_csv_path}\")\n",
    "# Close the video capture\n",
    "cap.release()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}