keras_g3_ae_simple.ana.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import uproot4\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.patches as patches\n",
    "from matplotlib.collections import PatchCollection\n",
    "from matplotlib import cm\n",
    "from matplotlib.colors import LogNorm, Normalize\n",
    "import awkward1 as ak\n",
    "from lxml import etree as ET\n",
    "import os\n",
    "from pathlib import Path\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "from event_display import get_module_geometry, get_module_positions, plot_calorimeter_hits, build_calorimeter_section"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Time open 9.577701091766357\n",
      "Time split 1.2636222839355469\n"
     ]
    }
   ],
   "source": [
    "from geant3_parser import build_train_set\n",
    "from geant3_parser import Geant3DataFile\n",
    "\n",
    "file_name = os.path.join('data', 'shower_geant3_new.dat')\n",
    "data_file = Geant3DataFile(file_name, skip_lines=3)\n",
    "input_data, true_e, sum_e = build_train_set(data_file, 10, add_real_xy=False, normalize=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def display_event(event_data):\n",
    "    # constants\n",
    "    cal_size = 11\n",
    "    cell_size = 1    \n",
    "    size_x = cell_size\n",
    "    size_y = cell_size\n",
    "    dx = size_x / 2.0\n",
    "    dy = size_y / 2.0\n",
    "\n",
    "    # go through all cells and calculate their centers\n",
    "    centers = np.arange(-cal_size/2.0 + cell_size/2, cal_size/2 + cell_size/2, 1)\n",
    "    positions = []\n",
    "    for y_iter in range(cal_size):\n",
    "        for x_iter in range(cal_size):\n",
    "            positions.append((centers[x_iter], centers[y_iter]))\n",
    "\n",
    "    # plot calorimeter with empty cells\n",
    "    fig, ax = plt.subplots()\n",
    "    build_calorimeter_section(ax, positions, 1, 1)\n",
    "\n",
    "    # Create a heat map\n",
    "    norm = LogNorm()\n",
    "    norm.autoscale(event_data)\n",
    "    cmap = cm.get_cmap('inferno')\n",
    "\n",
    "    # Convert data to rectangular patches    \n",
    "    module_rects = []\n",
    "    for y_iter in range(cal_size):\n",
    "        for x_iter in range(cal_size):\n",
    "            data_iter = y_iter*cal_size + x_iter\n",
    "            x = centers[x_iter]\n",
    "            y = centers[y_iter]\n",
    "            weight = event_data[data_iter]\n",
    "            #print(x,y,weight)\n",
    "            patch = patches.Rectangle((x-dx, y-dy), size_x, size_y, edgecolor='black', facecolor=cmap(norm(weight)))\n",
    "            module_rects.append(patch)\n",
    "\n",
    "    # plot rectangles with data\n",
    "    col = PatchCollection(module_rects, match_original=True)\n",
    "    ax.add_collection(col)\n",
    "\n",
    "    # plot heatmap legend\n",
    "    sm = plt.cm.ScalarMappable(cmap=cmap, norm=norm)\n",
    "    sm.set_array(event_data)\n",
    "    fig.colorbar(sm)\n",
    "    \n",
    "    return fig, ax"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(<Figure size 432x288 with 2 Axes>, <AxesSubplot:>)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "display_event(input_data[0][2:])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(<Figure size 432x288 with 2 Axes>, <AxesSubplot:>)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "display_event(input_data[1][2:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(<Figure size 432x288 with 2 Axes>, <AxesSubplot:>)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "display_event(input_data[2][2:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(<Figure size 432x288 with 2 Axes>, <AxesSubplot:>)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "display_event(input_data[3][2:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(<Figure size 432x288 with 2 Axes>, <AxesSubplot:>)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "display_event(input_data[4][2:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-06-21 17:52:50.503538: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0\n"
     ]
    }
   ],
   "source": [
    "import math\n",
    "from keras.models import load_model\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from geant3_parser import build_train_set\n",
    "from geant3_parser import Geant3DataFile\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-06-21 17:53:02.597829: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcuda.so.1\n",
      "2022-06-21 17:53:02.768433: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:923] could not open file to read NUMA node: /sys/bus/pci/devices/0000:01:00.0/numa_node\n",
      "Your kernel may have been built without NUMA support.\n",
      "2022-06-21 17:53:02.768810: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties: \n",
      "pciBusID: 0000:01:00.0 name: Quadro P1000 computeCapability: 6.1\n",
      "coreClock: 1.5185GHz coreCount: 4 deviceMemorySize: 4.00GiB deviceMemoryBandwidth: 89.53GiB/s\n",
      "2022-06-21 17:53:02.768997: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0\n",
      "2022-06-21 17:53:02.806321: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcublas.so.11\n",
      "2022-06-21 17:53:02.806467: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcublasLt.so.11\n",
      "2022-06-21 17:53:02.818948: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcufft.so.10\n",
      "2022-06-21 17:53:02.821556: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcurand.so.10\n",
      "2022-06-21 17:53:02.827899: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcusolver.so.11\n",
      "2022-06-21 17:53:02.833596: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcusparse.so.11\n",
      "2022-06-21 17:53:02.835281: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudnn.so.8\n",
      "2022-06-21 17:53:02.836582: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:923] could not open file to read NUMA node: /sys/bus/pci/devices/0000:01:00.0/numa_node\n",
      "Your kernel may have been built without NUMA support.\n",
      "2022-06-21 17:53:02.837821: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:923] could not open file to read NUMA node: /sys/bus/pci/devices/0000:01:00.0/numa_node\n",
      "Your kernel may have been built without NUMA support.\n",
      "2022-06-21 17:53:02.838136: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1871] Adding visible gpu devices: 0\n",
      "2022-06-21 17:53:02.840298: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
      "2022-06-21 17:53:02.844738: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:923] could not open file to read NUMA node: /sys/bus/pci/devices/0000:01:00.0/numa_node\n",
      "Your kernel may have been built without NUMA support.\n",
      "2022-06-21 17:53:02.844789: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties: \n",
      "pciBusID: 0000:01:00.0 name: Quadro P1000 computeCapability: 6.1\n",
      "coreClock: 1.5185GHz coreCount: 4 deviceMemorySize: 4.00GiB deviceMemoryBandwidth: 89.53GiB/s\n",
      "2022-06-21 17:53:02.845573: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:923] could not open file to read NUMA node: /sys/bus/pci/devices/0000:01:00.0/numa_node\n",
      "Your kernel may have been built without NUMA support.\n",
      "2022-06-21 17:53:02.846517: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:923] could not open file to read NUMA node: /sys/bus/pci/devices/0000:01:00.0/numa_node\n",
      "Your kernel may have been built without NUMA support.\n",
      "2022-06-21 17:53:02.846550: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1871] Adding visible gpu devices: 0\n",
      "2022-06-21 17:53:02.846805: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0\n",
      "2022-06-21 17:53:05.668583: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix:\n",
      "2022-06-21 17:53:05.668654: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264]      0 \n",
      "2022-06-21 17:53:05.668673: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0:   N \n",
      "2022-06-21 17:53:05.670156: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:923] could not open file to read NUMA node: /sys/bus/pci/devices/0000:01:00.0/numa_node\n",
      "Your kernel may have been built without NUMA support.\n",
      "2022-06-21 17:53:05.671352: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:923] could not open file to read NUMA node: /sys/bus/pci/devices/0000:01:00.0/numa_node\n",
      "Your kernel may have been built without NUMA support.\n",
      "2022-06-21 17:53:05.671394: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1501] Could not identify NUMA node of platform GPU id 0, defaulting to 0.  Your kernel may not have been built with NUMA support.\n",
      "2022-06-21 17:53:05.672586: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:923] could not open file to read NUMA node: /sys/bus/pci/devices/0000:01:00.0/numa_node\n",
      "Your kernel may have been built without NUMA support.\n",
      "2022-06-21 17:53:05.673287: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1418] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2763 MB memory) -> physical GPU (device: 0, name: Quadro P1000, pci bus id: 0000:01:00.0, compute capability: 6.1)\n",
      "2022-06-21 17:53:07.483603: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:176] None of the MLIR Optimization Passes are enabled (registered 2)\n",
      "2022-06-21 17:53:07.488303: I tensorflow/core/platform/profile_utils/cpu_utils.cc:114] CPU Frequency: 2904005000 Hz\n",
      "2022-06-21 17:53:13.362706: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcublas.so.11\n",
      "2022-06-21 17:53:15.760000: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcublasLt.so.11\n"
     ]
    }
   ],
   "source": [
    "model = load_model('g3_autoencoder_no_xy.hd5')\n",
    "\n",
    "# Run ML on data\n",
    "eval_e = model.predict(input_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-1.9960003e-03,  2.6597895e-03,  4.1544214e-03, -3.2817305e-03,\n",
       "        7.3247380e-04,  2.3067743e-04, -2.0754829e-03,  2.7470442e-03,\n",
       "        1.5396070e-03,  2.0557425e-03, -2.3193203e-03,  1.1675650e-03,\n",
       "       -2.4239277e-03,  4.5402604e-03, -1.9827457e-03, -1.0788837e-03,\n",
       "        1.2871429e-03,  2.2917986e-05, -1.4010788e-03, -4.7252793e-03,\n",
       "        4.5386696e-04, -2.1698698e-04,  1.2072616e-03, -1.8261184e-03,\n",
       "       -1.9758944e-03, -7.2754659e-03,  1.1764593e-02,  2.0981573e-02,\n",
       "        4.9877591e-02,  6.1963007e-02,  5.3096797e-02,  3.5997208e-02,\n",
       "        2.2213180e-02,  1.7208699e-03,  4.6374681e-03, -1.8038653e-03,\n",
       "       -3.1976146e-03,  3.4851503e-02,  8.4846817e-02,  1.3725215e-01,\n",
       "        1.7623037e-01,  1.4429806e-01,  6.8543829e-02,  2.8800506e-02,\n",
       "        3.7936382e-03, -1.4696686e-03, -3.8835846e-03, -2.5930270e-03,\n",
       "        4.4461567e-02,  1.4689879e-01,  2.9023719e-01,  3.8833317e-01,\n",
       "        2.9048166e-01,  1.3676400e-01,  4.9636669e-02,  1.0031830e-03,\n",
       "        2.0337189e-03,  2.2681910e-03, -6.5909221e-04,  5.1267333e-02,\n",
       "        1.7579821e-01,  3.9005244e-01,  6.4210796e-01,  3.9058736e-01,\n",
       "        1.7298226e-01,  5.5716567e-02, -9.7696949e-03,  3.2212711e-03,\n",
       "       -1.0269820e-03,  1.8292812e-03,  4.9127445e-02,  1.3815406e-01,\n",
       "        2.9516235e-01,  3.9425087e-01,  2.9004040e-01,  1.4216678e-01,\n",
       "        4.7003761e-02, -1.2794967e-03,  4.1337367e-03, -9.4607810e-04,\n",
       "        4.0529626e-03,  2.3787277e-02,  7.7811398e-02,  1.4016950e-01,\n",
       "        1.8337992e-01,  1.5163377e-01,  7.8128390e-02,  2.5108865e-02,\n",
       "        5.6425775e-03,  5.6143547e-03,  5.8889757e-03,  4.2230678e-03,\n",
       "        1.4749920e-02,  3.0738778e-02,  4.8337292e-02,  6.0079060e-02,\n",
       "        5.2195836e-02,  2.5198244e-02,  9.3148248e-03, -4.0520611e-03,\n",
       "        1.8473394e-03,  3.4697768e-03,  8.0570597e-03,  4.2285882e-03,\n",
       "       -7.0427905e-04, -1.9799815e-03,  2.8448619e-03,  3.7618782e-03,\n",
       "        1.4318236e-03, -1.3114266e-03, -1.7463416e-04, -4.9535111e-03,\n",
       "        2.0216212e-03, -1.1636273e-03,  3.5810098e-04, -5.3323666e-03,\n",
       "        3.3775717e-04, -1.4070066e-03,  1.2705541e-03, -3.1880010e-04,\n",
       "       -8.9268491e-04,  2.8703355e-03,  1.6753768e-03], dtype=float32)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "eval_e[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.0000000e+00, 2.6597895e-03, 4.1544214e-03, 0.0000000e+00,\n",
       "       7.3247380e-04, 2.3067743e-04, 0.0000000e+00, 2.7470442e-03,\n",
       "       1.5396070e-03, 2.0557425e-03, 0.0000000e+00, 1.1675650e-03,\n",
       "       0.0000000e+00, 4.5402604e-03, 0.0000000e+00, 0.0000000e+00,\n",
       "       1.2871429e-03, 2.2917986e-05, 0.0000000e+00, 0.0000000e+00,\n",
       "       4.5386696e-04, 0.0000000e+00, 1.2072616e-03, 0.0000000e+00,\n",
       "       0.0000000e+00, 0.0000000e+00, 1.1764593e-02, 2.0981573e-02,\n",
       "       4.9877591e-02, 6.1963007e-02, 5.3096797e-02, 3.5997208e-02,\n",
       "       2.2213180e-02, 1.7208699e-03, 4.6374681e-03, 0.0000000e+00,\n",
       "       0.0000000e+00, 3.4851503e-02, 8.4846817e-02, 1.3725215e-01,\n",
       "       1.7623037e-01, 1.4429806e-01, 6.8543829e-02, 2.8800506e-02,\n",
       "       3.7936382e-03, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
       "       4.4461567e-02, 1.4689879e-01, 2.9023719e-01, 3.8833317e-01,\n",
       "       2.9048166e-01, 1.3676400e-01, 4.9636669e-02, 1.0031830e-03,\n",
       "       2.0337189e-03, 2.2681910e-03, 0.0000000e+00, 5.1267333e-02,\n",
       "       1.7579821e-01, 3.9005244e-01, 6.4210796e-01, 3.9058736e-01,\n",
       "       1.7298226e-01, 5.5716567e-02, 0.0000000e+00, 3.2212711e-03,\n",
       "       0.0000000e+00, 1.8292812e-03, 4.9127445e-02, 1.3815406e-01,\n",
       "       2.9516235e-01, 3.9425087e-01, 2.9004040e-01, 1.4216678e-01,\n",
       "       4.7003761e-02, 0.0000000e+00, 4.1337367e-03, 0.0000000e+00,\n",
       "       4.0529626e-03, 2.3787277e-02, 7.7811398e-02, 1.4016950e-01,\n",
       "       1.8337992e-01, 1.5163377e-01, 7.8128390e-02, 2.5108865e-02,\n",
       "       5.6425775e-03, 5.6143547e-03, 5.8889757e-03, 4.2230678e-03,\n",
       "       1.4749920e-02, 3.0738778e-02, 4.8337292e-02, 6.0079060e-02,\n",
       "       5.2195836e-02, 2.5198244e-02, 9.3148248e-03, 0.0000000e+00,\n",
       "       1.8473394e-03, 3.4697768e-03, 8.0570597e-03, 4.2285882e-03,\n",
       "       0.0000000e+00, 0.0000000e+00, 2.8448619e-03, 3.7618782e-03,\n",
       "       1.4318236e-03, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
       "       2.0216212e-03, 0.0000000e+00, 3.5810098e-04, 0.0000000e+00,\n",
       "       3.3775717e-04, 0.0000000e+00, 1.2705541e-03, 0.0000000e+00,\n",
       "       0.0000000e+00, 2.8703355e-03, 1.6753768e-03], dtype=float32)"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "eval_e[eval_e<0]=0\n",
    "eval_e[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'keras_g3_ae_simple_event 2')"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "i=2\n",
    "plt.plot(input_data[i],label='true',color='red')\n",
    "plt.plot(eval_e[i],label='pred',color='blue')\n",
    "plt.legend()\n",
    "plt.title('keras_g3_ae_simple_event {}'.format(i))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(<Figure size 432x288 with 2 Axes>, <AxesSubplot:>)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "display_event(eval_e[0][2:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(<Figure size 432x288 with 2 Axes>, <AxesSubplot:>)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "display_event(eval_e[1][2:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(<Figure size 432x288 with 2 Axes>, <AxesSubplot:>)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "display_event(eval_e[2][2:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.12 ('dl')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.13"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "e792f99ca924ac5da9af932bc557d69820b5853464ee68b1079b8b9e6589c389"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}