tutorials/T07-MetricLandscape.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "911b67af-a7e0-434f-a441-0f12976065dc",
   "metadata": {},
   "source": [
    "# Tutorial 07 - Evaluation of  Metric Landscape\n",
    "\n",
    "This tutorial demonstrates how to run model predictions on a custom set of physics parameter values. From the predictions we can obtain the loss landscapes for a desired metric such as the log loss, auc or accuracy."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "44ee71ee-53bd-4849-8e1b-f90a1185aabf",
   "metadata": {},
   "source": [
    "To use the paws CLI:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "23990e7d-5725-4d21-b06e-42c54bd2f1b8",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Usage: paws compute_semi_weakly_landscape [OPTIONS]\n",
      "\n",
      "  Compute metric landscapes for a semi-weakly model\n",
      "\n",
      "Options:\n",
      "  -m, --mass-point TEXT           Signal mass point (in the form m1:m2) to use\n",
      "                                  for creating the dataset.  [required]\n",
      "  --min_mass FLOAT                Minimum value of the mass (in GeV) in the 2D\n",
      "                                  mass grid to scan for.  [default: 0]\n",
      "  --max_mass FLOAT                Maximum value of the mass (in GeV) in the 2D\n",
      "                                  mass grid to scan for.  [default: 600]\n",
      "  --mass_interval FLOAT           Mass interval (in GeV) between grid points\n",
      "                                  in the 2D mass grid to scan for.  [default:\n",
      "                                  50]\n",
      "  --mu FLOAT                      Signal fraction used in the dataset.\n",
      "                                  [required]\n",
      "  --mu_list FLOAT                 The list of signal fractions to scan over\n",
      "                                  (separated by commas). If None, the truth\n",
      "                                  value of the dataset will be used.\n",
      "  --alpha FLOAT                   Signal branching fraction in the dataset.\n",
      "                                  Ignored when only one signal decay mode is\n",
      "                                  considered.  [default: 0.5]\n",
      "  --alpha_list FLOAT              The list of branching fractions to scan over\n",
      "                                  (separated by commas). Only used when\n",
      "                                  evaluating mixed two-prong + three-prong\n",
      "                                  model.  If None, the truth value of the\n",
      "                                  dataset will be used.\n",
      "  --high-level / --low-level      Whether to do training with low-evel or\n",
      "                                  high-level features.  [default: high-level]\n",
      "  --decay-modes [qq|qqq|qq,qqq]   Which decay mode should the signal undergo\n",
      "                                  (qq or qqq).Use \"qq,qqq\" to include both\n",
      "                                  decay modes.  [default: qq]\n",
      "  --variables TEXT                Select certain high-level jet features to\n",
      "                                  include in the trainingby the indices they\n",
      "                                  appear in the feature vector. For\n",
      "                                  example,\"3,5,6\" means select the 4th, 6th\n",
      "                                  and 7th feature from the jetfeature vector\n",
      "                                  to be used in the training.\n",
      "  --noise INTEGER                 Number of noise dimension to add to the\n",
      "                                  train features.  [default: 0]\n",
      "  --dataset-index-path TEXT       Path to the dataset split configuration\n",
      "                                  file. It determines theshard indices for the\n",
      "                                  train, validation, and test datasets in\n",
      "                                  eachrandom realization of data. If None, a\n",
      "                                  default configuration will be created.\n",
      "  -i, --split-index INTEGER       Index for dataset split.  [default: 0]\n",
      "  --fs-version TEXT               Version of the supervised model to use.\n",
      "                                  [default: v1]\n",
      "  --fs-version-2 TEXT             When signals of mixed decay modes are\n",
      "                                  considered, it corresponds to the version of\n",
      "                                  the three-prone supervised model. If None,\n",
      "                                  the same version as `fs_version` will be\n",
      "                                  used.\n",
      "  --seed INTEGER                  The default seed used for all random\n",
      "                                  processes.  [default: 2023]\n",
      "  --batchsize INTEGER             Batch size for the dataset.\n",
      "  --cache-dataset / --no-cache-dataset\n",
      "                                  Whether to cache the dataset during\n",
      "                                  training.\n",
      "  -d, --datadir TEXT              input directory where the tfrecord datasets\n",
      "                                  are stored  [default: datasets]\n",
      "  -o, --outdir TEXT               base output directory  [default: outputs]\n",
      "  --version TEXT                  Version of the model.  [default: v1]\n",
      "  --cache / --no-cache            Whether to cache the results.  [default:\n",
      "                                  cache]\n",
      "  --multi-gpu / --single-gpu      Whether to enable multi-GPU computation.\n",
      "                                  [default: multi-gpu]\n",
      "  -v, --verbosity TEXT            Verbosity level (\"DEBUG\", \"INFO\", \"WARNING\"\n",
      "                                  or \"ERROR\").  [default: INFO]\n",
      "  --help                          Show this message and exit.\n"
     ]
    }
   ],
   "source": [
    "# only the semi-weakly model landscape is implemented in CLI; for other models such as the parameterised supervised model, please use the API\n",
    "!paws compute_semi_weakly_landscape --help"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a2c9c88d-9206-4fdf-9dd3-00ba109debf5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# example command\n",
    "!paws compute_semi_weakly_landscape -m 300:300 --mu 0.005 --decay-modes qq,qqq --variables 3,5,6 -d datasets -o outputs"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8226d868-9818-49eb-92aa-9a1115364932",
   "metadata": {},
   "source": [
    "To use the paws API:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "6055e989-15f0-4227-aab7-c15e2950966e",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2024-06-02 07:06:54.421884: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
      "2024-06-02 07:06:54.421924: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
      "2024-06-02 07:06:54.423471: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
      "2024-06-02 07:06:54.443256: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
      "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
      "2024-06-02 07:06:56.433914: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:GPU:0',)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2024-06-02 07:06:58.836393: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1929] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 14091 MB memory:  -> device: 0, name: NVIDIA A100-PCIE-40GB, pci bus id: 0000:c3:00.0, compute capability: 8.0\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[INFO] Created MirroredStrategy for distributed training\n",
      "[INFO] Number of devices : 1\n",
      "[INFO]      aliad version : 0.0.3\n",
      "[INFO] tensorflow version : 2.15.0\n",
      "Sun Jun  2 07:06:59 2024       \n",
      "+-----------------------------------------------------------------------------+\n",
      "| NVIDIA-SMI 525.105.17   Driver Version: 525.105.17   CUDA Version: 12.2     |\n",
      "|-------------------------------+----------------------+----------------------+\n",
      "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
      "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
      "|                               |                      |               MIG M. |\n",
      "|===============================+======================+======================|\n",
      "|   0  NVIDIA A100-PCI...  On   | 00000000:C3:00.0 Off |                    0 |\n",
      "| N/A   35C    P0    37W / 250W |  38802MiB / 40960MiB |      3%      Default |\n",
      "|                               |                      |             Disabled |\n",
      "+-------------------------------+----------------------+----------------------+\n",
      "                                                                               \n",
      "+-----------------------------------------------------------------------------+\n",
      "| Processes:                                                                  |\n",
      "|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |\n",
      "|        ID   ID                                                   Usage      |\n",
      "|=============================================================================|\n",
      "|    0   N/A  N/A    291095      C   ...da/envs/ml-gpu/bin/python     1312MiB |\n",
      "|    0   N/A  N/A    417736      C   ...da/envs/ml-gpu/bin/python    14506MiB |\n",
      "|    0   N/A  N/A    685939      C   ...da/envs/ml-gpu/bin/python    22982MiB |\n",
      "+-----------------------------------------------------------------------------+\n",
      "nvcc: NVIDIA (R) Cuda compiler driver\n",
      "Copyright (c) 2005-2023 NVIDIA Corporation\n",
      "Built on Tue_Jun_13_19:16:58_PDT_2023\n",
      "Cuda compilation tools, release 12.2, V12.2.91\n",
      "Build cuda_12.2.r12.2/compiler.32965470_0\n",
      "[INFO] Number of events in each dataset split:\n",
      "                              train     val    test\n",
      "QCD + extra_QCD (label = 0)  183530   91787       0\n",
      "QCD + extra_QCD (label = 1)  183530   91787       0\n",
      "W_qq                           4829    2415   18625\n",
      "W_qqq                          4829    2415   19050\n",
      "QCD                               0       0   30350\n",
      "extra_QCD                         0       0  153225\n",
      "total                        376718  188404  221250\n",
      "num_batch                       368     184     217\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from quickstats.maths.numerics import cartesian_product\n",
    "from paws.components import ModelTrainer, MetricLandscape\n",
    "\n",
    "datadir = \"datasets\"\n",
    "outdir = \"outputs\"\n",
    "\n",
    "# declare options to create the weakly datasets\n",
    "model_options = {\n",
    "    \"mass_point\": [300, 300],\n",
    "    \"mu\": 0.05,\n",
    "    \"alpha\": 0.5\n",
    "}\n",
    "\n",
    "model_trainer = ModelTrainer(\"semi_weakly\", model_options=model_options, decay_modes=\"qq,qqq\",\n",
    "                             variables=\"3,5,6\", datadir=datadir, outdir=outdir)\n",
    "datasets = model_trainer.get_datasets()\n",
    "model = model_trainer.get_model()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "debab92b-87b3-40bf-8649-e5ded47d4c7c",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2024-06-02 07:07:11.932483: I tensorflow/core/kernels/data/shuffle_dataset_op.cc:422] ShuffleDatasetV3:30: Filling up shuffle buffer (this may take a while): 371890 of 376718\n",
      "2024-06-02 07:07:12.011311: I tensorflow/core/kernels/data/shuffle_dataset_op.cc:452] Shuffle buffer filled.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 0, 0.01)\n",
      "368/368 [==============================] - 2s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (0, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (50, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (100, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (150, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (200, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (250, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (300, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (350, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (400, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (450, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (500, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (550, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 0, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 50, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 100, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 150, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 200, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 250, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 300, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 350, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 400, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 450, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 500, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 550, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n",
      "[INFO] Running model prediction with (m1, m2, mu) = (600, 600, 0.01)\n",
      "368/368 [==============================] - 1s 2ms/step\n"
     ]
    }
   ],
   "source": [
    "landscape = MetricLandscape()\n",
    "\n",
    "masses = np.arange(0, 600 + 50, 50)\n",
    "mass_points = cartesian_product(masses, masses)\n",
    "mu_points = [0.01]\n",
    "alpha_points = [0.5]\n",
    "\n",
    "result = landscape.predict_semiweakly(model, datasets['train'], mass_points=mass_points,\n",
    "                                       mu_points=mu_points, alpha_points=alpha_points)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "fddda462-3363-4fd4-851c-37fa78afb3e0",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.49748763, 0.49748752, 0.49751624, ..., 0.49748743, 0.49749145,\n",
       "        0.49748743],\n",
       "       [0.4974941 , 0.49757928, 0.49832648, ..., 0.49748743, 0.49787843,\n",
       "        0.49749604],\n",
       "       [0.49749324, 0.49753064, 0.50252944, ..., 0.49748743, 0.497965  ,\n",
       "        0.49752173],\n",
       "       ...,\n",
       "       [0.49748975, 0.4975535 , 0.49748933, ..., 0.49749005, 0.4974926 ,\n",
       "        0.49748865],\n",
       "       [0.4974891 , 0.49754545, 0.4974886 , ..., 0.49749053, 0.49749202,\n",
       "        0.49748826],\n",
       "       [0.49748832, 0.49753255, 0.49748838, ..., 0.4974934 , 0.49749127,\n",
       "        0.4974881 ]], dtype=float32)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result['predictions']['y_pred']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "8e8dbff0-6a6d-44d5-9f69-d829bd8e380f",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 0, 0, ..., 0, 0, 0])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result['y_true']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "fd8b2d20-3e53-4c5b-a4b2-063c722a4788",
   "metadata": {},
   "outputs": [],
   "source": [
    "# saving the results to a json fle (this can be quite large)\n",
    "import json\n",
    "from quickstats.utils.common_utils import NpEncoder\n",
    "outname = \"landscape_result.json\"\n",
    "with open(outname, 'w') as file:\n",
    "    json.dump(result, file, cls=NpEncoder)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "8f13291e-caa1-473e-a6a7-986021ae7231",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# now get the metric landscape based on the predictions\n",
    "\n",
    "loss_landscape = landscape.get_loss_landscape(result)\n",
    "loss_df = pd.DataFrame(loss_landscape)\n",
    "\n",
    "auc_landscape = landscape.get_auc_landscape(result)\n",
    "auc_df = pd.DataFrame(auc_landscape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1cad29ee-f7fb-44ff-85ad-483396ed65ad",
   "metadata": {},
   "source": [
    "### Landscape Plots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "cb0d2cf9-d3ab-4316-8ef0-d9db7652bd23",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 799.992x599.976 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 799.992x599.976 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from paws.plotting import plot_metric_landscape\n",
    "\n",
    "plot_metric_landscape(loss_df, metric='log_loss')\n",
    "plt.show()\n",
    "plot_metric_landscape(auc_df, metric='auc')\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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
}