classifier_species_expt2_eval.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "official-plymouth",
   "metadata": {},
   "source": [
    "# Training species classifier Expt 2\n",
    "## Trained on all except Gillispie 96 kHz data\n",
    "## Four datasets: Oswald, Gillispie, DCLDE 2011 & Watkin"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "greatest-threat",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from itertools import permutations\n",
    "import random\n",
    "import os\n",
    "import glob\n",
    "import pickle\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.patheffects as PathEffects\n",
    "import pandas as pd\n",
    "from os import makedirs\n",
    "from datetime import datetime\n",
    "\n",
    "from math import floor\n",
    "from collections import Counter\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.utils import shuffle\n",
    "from sklearn.utils.class_weight import compute_class_weight\n",
    "from sklearn.metrics import roc_curve\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.metrics import confusion_matrix, classification_report\n",
    "\n",
    "# from MulticoreTSNE import MulticoreTSNE as TSNE\n",
    "# from sklearn.manifold import TSNE\n",
    "import seaborn as sns\n",
    "\n",
    "from tensorflow.keras.utils import Sequence\n",
    "from tensorflow.keras.layers import Input, Dense, BatchNormalization, Dropout, Activation\n",
    "from tensorflow.keras.layers import Conv2D, Lambda, Flatten, MaxPooling2D, Concatenate, LSTM, Reshape, Lambda, ConvLSTM2D, GlobalAveragePooling2D, GlobalMaxPooling2D\n",
    "from tensorflow.keras.layers import Bidirectional, LSTM, GRU\n",
    "from tensorflow.keras.models import Model, Sequential\n",
    "from tensorflow.keras.regularizers import l2\n",
    "from tensorflow.keras import backend as K\n",
    "\n",
    "from tensorflow.keras.optimizers.schedules import ExponentialDecay\n",
    "from tensorflow.keras.optimizers import SGD,Adam\n",
    "from tensorflow.keras.losses import binary_crossentropy, CategoricalCrossentropy\n",
    "from tensorflow.keras.callbacks import ModelCheckpoint, TensorBoard, EarlyStopping\n",
    "from tensorflow.keras.utils import to_categorical\n",
    "from tensorflow.keras.models import load_model\n",
    "# import tensorflow_addons as tfa\n",
    "# import tensorflow_datasets as tfds\n",
    "from tensorflow.math import l2_normalize\n",
    "\n",
    "from tensorflow.keras.optimizers.schedules import PiecewiseConstantDecay\n",
    "\n",
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "sonic-posting",
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\", category=DeprecationWarning)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "impossible-serum",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Hyper parameters\n",
    "learning_rate = 1.0e-4\n",
    "conv_dim = 16\n",
    "rnn_dim = 16\n",
    "pool_size = 2\n",
    "pool_stride = 2\n",
    "l2_regu = 0.000\n",
    "drop_rate = 0.2\n",
    "hidden_units = 512\n",
    "fcn_dim = 512\n",
    "\n",
    "# learning_rate = 1.e-4\n",
    "# conv_dim = 64\n",
    "# rnn_dim = 16\n",
    "# pool_size = 2\n",
    "# pool_stride = 2\n",
    "# l2_regu = 0.00\n",
    "# drop_rate = 0.2\n",
    "# # drop_rate = 0.5\n",
    "# hidden_units = 512\n",
    "# fcn_dim = 512\n",
    "\n",
    "num_epoch = 200\n",
    "# batch_size = 128\n",
    "batch_size = 32  # for cnn14+attention\n",
    "\n",
    "num_species = 21\n",
    "num_patience = 20"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "alert-louis",
   "metadata": {},
   "outputs": [],
   "source": [
    "# data_type_dict = {1: 'universal', 2: 'file', 3: 'encounter', 4: 'domain'}\n",
    "# data_type = 2\n",
    "\n",
    "work_path = '/home/ys587/__Data/__whistle/__whislte_30_species'\n",
    "fit_result_path =  os.path.join(work_path, '__fit_result_species')\n",
    "# feature_path = os.path.join(work_path, '__feature_species')\n",
    "feature_path = os.path.join(work_path, '__dataset/20210210')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "prescribed-outreach",
   "metadata": {},
   "outputs": [],
   "source": [
    "# species_dict = {'BD': 0, 'MH': 1, 'CD': 2, 'STR': 3, 'SPT': 4, 'SPIN': 5, 'PLT': 6, 'RD': 7, 'RT': 8,\n",
    "#                 'WSD': 9, 'FKW': 10, 'BEL': 11, 'KW': 12, 'WBD': 13, 'DUSK': 14, 'FRA': 15, 'PKW': 16, 'LPLT': 17, }\n",
    "species_dict = {'BD': 0, 'MH': 1, 'CD': 2, 'STR': 3, 'SPT': 4, 'SPIN': 5, 'PLT': 6, 'RD': 7, 'RT': 8,\n",
    "                'WSD': 9, 'FKW': 10, 'BEL': 11, 'KW': 12, 'WBD': 13, 'DUSK': 14, 'FRA': 15, 'PKW': 16, 'LPLT': 17,\n",
    "                'CLY': 18, 'SPE': 19, 'ASP': 20}\n",
    "species_list = list(species_dict.keys())\n",
    "species_id = list(species_dict.values())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "seven-amber",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Testing data\n",
    "fea_temp = np.load(os.path.join(feature_path, 'gillispie_96kHz_orig.npz'))\n",
    "fea_test = fea_temp['feas_orig']\n",
    "label_test_list = fea_temp['labels_orig']\n",
    "\n",
    "fea_test = fea_test[:,:100,:]\n",
    "label_test = np.zeros(len(label_test_list))\n",
    "for ii in range(len(label_test_list)):\n",
    "    label_test[ii] = species_dict[label_test_list[ii]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "confident-equilibrium",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({0.0: 26,\n",
       "         2.0: 520,\n",
       "         12.0: 1351,\n",
       "         6.0: 148,\n",
       "         4.0: 120,\n",
       "         3.0: 935,\n",
       "         13.0: 268})"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Counter(label_test.tolist())"
   ]
  },
  {
   "cell_type": "raw",
   "id": "italic-producer",
   "metadata": {},
   "source": [
    "# create a folder based on date & time\n",
    "today = datetime.now()\n",
    "\n",
    "fit_result_path1 = os.path.join(fit_result_path, today.strftime('%Y%m%d_%H%M%S'))\n",
    "\n",
    "if not os.path.exists(fit_result_path1):\n",
    "    makedirs(fit_result_path1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "objective-commercial",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "feature test shape: (3368, 100, 128)\n",
      "label test shape: (3368,)\n",
      "dim_time: 100\n",
      "dim_freq: 128\n"
     ]
    }
   ],
   "source": [
    "print('feature test shape: '+str(fea_test.shape))\n",
    "print('label test shape: '+str(label_test.shape))\n",
    "\n",
    "dim_time = fea_test.shape[1]\n",
    "dim_freq = fea_test.shape[2]\n",
    "print('dim_time: '+str(dim_time))\n",
    "print('dim_freq: '+str(dim_freq))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "widespread-arbitration",
   "metadata": {},
   "outputs": [],
   "source": [
    "# shuffle features & labels\n",
    "fea_test, label_test = shuffle(fea_test, label_test, random_state=0)\n",
    "fea_test = np.expand_dims(fea_test, axis=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "convinced-london",
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "\n",
    "def find_best_model(classifier_path, fmt='epoch_\\d+_valloss_(\\d+.\\d{4})_valacc_\\d+.\\d{4}.hdf5', is_max=False, purge=True):\n",
    "    \"\"\"\n",
    "    Return the path to the model with the best accuracy, given the path to\n",
    "    all the trained classifiers\n",
    "    Args:\n",
    "        classifier_path: path to all the trained classifiers\n",
    "        fmt: e.g. \"epoch_\\d+_[0-1].\\d+_(\\d+.\\d{4}).hdf5\"\n",
    "        'epoch_\\d+_valloss_(\\d+.\\d{4})_valacc_\\d+.\\d{4}.hdf5'\n",
    "        is_max: use max; otherwise, min\n",
    "        purge: True to purge models files except the best one\n",
    "    Return:\n",
    "        the path of the model with the best accuracy\n",
    "    \"\"\"\n",
    "    # list all files ending with .hdf5\n",
    "    day_list = sorted(glob.glob(os.path.join(classifier_path + '/', '*.hdf5')))\n",
    "\n",
    "    # re the last 4 digits for accuracy\n",
    "    hdf5_filename = []\n",
    "    hdf5_accu = np.zeros(len(day_list))\n",
    "    for dd in range(len(day_list)):\n",
    "        filename = os.path.basename(day_list[dd])\n",
    "        hdf5_filename.append(filename)\n",
    "        # m = re.search(\"_F1_(0.\\d{4}).hdf5\", filename)\n",
    "        # m = re.search(\"_([0-1].\\d{4}).hdf5\", filename)\n",
    "        # m = re.search(\"epoch_\\d+_[0-1].\\d+_(\\d+.\\d{4}).hdf5\", filename)\n",
    "        m = re.search(fmt, filename)\n",
    "        try:\n",
    "            hdf5_accu[dd] = float(m.groups()[0])\n",
    "        except:\n",
    "            continue\n",
    "\n",
    "    # select the laregest one and write to the variable classifier_file\n",
    "    if len(hdf5_accu) == 0:\n",
    "        best_model_path = ''\n",
    "        best_accu = 0\n",
    "    else:\n",
    "        if is_max is True:\n",
    "            ind_max = np.argmax(hdf5_accu)\n",
    "        else: # use min instead\n",
    "            ind_max = np.argmin(hdf5_accu)\n",
    "        best_model_path = day_list[int(ind_max)]\n",
    "        best_accu = hdf5_accu[ind_max]\n",
    "        # purge all model files except the best_model\n",
    "        if purge:\n",
    "            for ff in day_list:\n",
    "                if ff != best_model_path:\n",
    "                    os.remove(ff)\n",
    "    print('Best model:'+str(best_accu))\n",
    "    print(best_model_path)\n",
    "    return best_model_path, best_accu\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "amino-termination",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best model:0.3742\n",
      "/home/ys587/__Data/__whistle/__whislte_30_species/__fit_result_species/20210210_224527/epoch_80_valloss_0.3742_valacc_0.8743.hdf5\n"
     ]
    }
   ],
   "source": [
    "fit_result_path1 = '/home/ys587/__Data/__whistle/__whislte_30_species/__fit_result_species/20210210_224527'\n",
    "the_best_model, _ = find_best_model(fit_result_path1, purge=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "social-hawaii",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"model\"\n",
      "__________________________________________________________________________________________________\n",
      "Layer (type)                    Output Shape         Param #     Connected to                     \n",
      "==================================================================================================\n",
      "input (InputLayer)              [(None, 100, 128, 1) 0                                            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d (Conv2D)                 (None, 100, 128, 16) 160         input[0][0]                      \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization (BatchNorma (None, 100, 128, 16) 64          conv2d[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "activation (Activation)         (None, 100, 128, 16) 0           batch_normalization[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_1 (Conv2D)               (None, 100, 128, 16) 2320        activation[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_1 (BatchNor (None, 100, 128, 16) 64          conv2d_1[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_1 (Activation)       (None, 100, 128, 16) 0           batch_normalization_1[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d (MaxPooling2D)    (None, 50, 64, 16)   0           activation_1[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "dropout (Dropout)               (None, 50, 64, 16)   0           max_pooling2d[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_2 (Conv2D)               (None, 50, 64, 32)   4640        dropout[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_2 (BatchNor (None, 50, 64, 32)   128         conv2d_2[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_2 (Activation)       (None, 50, 64, 32)   0           batch_normalization_2[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_3 (Conv2D)               (None, 50, 64, 32)   9248        activation_2[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_3 (BatchNor (None, 50, 64, 32)   128         conv2d_3[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_3 (Activation)       (None, 50, 64, 32)   0           batch_normalization_3[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d_1 (MaxPooling2D)  (None, 25, 32, 32)   0           activation_3[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "dropout_1 (Dropout)             (None, 25, 32, 32)   0           max_pooling2d_1[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_4 (Conv2D)               (None, 25, 32, 64)   18496       dropout_1[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_4 (BatchNor (None, 25, 32, 64)   256         conv2d_4[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_4 (Activation)       (None, 25, 32, 64)   0           batch_normalization_4[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_5 (Conv2D)               (None, 25, 32, 64)   36928       activation_4[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_5 (BatchNor (None, 25, 32, 64)   256         conv2d_5[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_5 (Activation)       (None, 25, 32, 64)   0           batch_normalization_5[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d_2 (MaxPooling2D)  (None, 13, 16, 64)   0           activation_5[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "dropout_2 (Dropout)             (None, 13, 16, 64)   0           max_pooling2d_2[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_6 (Conv2D)               (None, 13, 16, 128)  73856       dropout_2[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_6 (BatchNor (None, 13, 16, 128)  512         conv2d_6[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_6 (Activation)       (None, 13, 16, 128)  0           batch_normalization_6[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_7 (Conv2D)               (None, 13, 16, 128)  147584      activation_6[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_7 (BatchNor (None, 13, 16, 128)  512         conv2d_7[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_7 (Activation)       (None, 13, 16, 128)  0           batch_normalization_7[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d_3 (MaxPooling2D)  (None, 7, 8, 128)    0           activation_7[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "dropout_3 (Dropout)             (None, 7, 8, 128)    0           max_pooling2d_3[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_8 (Conv2D)               (None, 7, 8, 256)    295168      dropout_3[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_8 (BatchNor (None, 7, 8, 256)    1024        conv2d_8[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_8 (Activation)       (None, 7, 8, 256)    0           batch_normalization_8[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_9 (Conv2D)               (None, 7, 8, 256)    590080      activation_8[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_9 (BatchNor (None, 7, 8, 256)    1024        conv2d_9[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "activation_9 (Activation)       (None, 7, 8, 256)    0           batch_normalization_9[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d_4 (MaxPooling2D)  (None, 7, 4, 256)    0           activation_9[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "dropout_4 (Dropout)             (None, 7, 4, 256)    0           max_pooling2d_4[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_10 (Conv2D)              (None, 7, 4, 512)    1180160     dropout_4[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_10 (BatchNo (None, 7, 4, 512)    2048        conv2d_10[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "activation_10 (Activation)      (None, 7, 4, 512)    0           batch_normalization_10[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "conv2d_11 (Conv2D)              (None, 7, 4, 512)    2359808     activation_10[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_11 (BatchNo (None, 7, 4, 512)    2048        conv2d_11[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "activation_11 (Activation)      (None, 7, 4, 512)    0           batch_normalization_11[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "max_pooling2d_5 (MaxPooling2D)  (None, 7, 2, 512)    0           activation_11[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "dropout_5 (Dropout)             (None, 7, 2, 512)    0           max_pooling2d_5[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "reshape (Reshape)               (None, 7, 1024)      0           dropout_5[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "dense (Dense)                   (None, 7, 512)       524800      reshape[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_12 (BatchNo (None, 7, 512)       2048        dense[0][0]                      \n",
      "__________________________________________________________________________________________________\n",
      "activation_12 (Activation)      (None, 7, 512)       0           batch_normalization_12[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "dropout_6 (Dropout)             (None, 7, 512)       0           activation_12[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "dense_1 (Dense)                 (None, 7, 512)       262656      dropout_6[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_13 (BatchNo (None, 7, 512)       2048        dense_1[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "activation_13 (Activation)      (None, 7, 512)       0           batch_normalization_13[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "dropout_7 (Dropout)             (None, 7, 512)       0           activation_13[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "dense_2 (Dense)                 (None, 7, 512)       262656      dropout_7[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_14 (BatchNo (None, 7, 512)       2048        dense_2[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "activation_14 (Activation)      (None, 7, 512)       0           batch_normalization_14[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "dropout_8 (Dropout)             (None, 7, 512)       0           activation_14[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "dense_3 (Dense)                 (None, 7, 512)       262656      dropout_8[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "dense_4 (Dense)                 (None, 7, 512)       262656      dropout_8[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "lambda (Lambda)                 (None, 512)          0           dense_3[0][0]                    \n",
      "                                                                 dense_4[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "batch_normalization_15 (BatchNo (None, 512)          2048        lambda[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "activation_15 (Activation)      (None, 512)          0           batch_normalization_15[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "dropout_9 (Dropout)             (None, 512)          0           activation_15[0][0]              \n",
      "__________________________________________________________________________________________________\n",
      "dense_5 (Dense)                 (None, 21)           10773       dropout_9[0][0]                  \n",
      "==================================================================================================\n",
      "Total params: 6,320,901\n",
      "Trainable params: 6,312,773\n",
      "Non-trainable params: 8,128\n",
      "__________________________________________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model = load_model(the_best_model)\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "plastic-machinery",
   "metadata": {},
   "outputs": [],
   "source": [
    "label_pred = model.predict(fea_test)\n",
    "# label_pred = model.predict(test_generator)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "centered-australian",
   "metadata": {},
   "outputs": [],
   "source": [
    "np.set_printoptions(linewidth=200, precision=3, suppress=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "falling-coffee",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Confusion matrix:\n",
      "['BD', 'MH', 'CD', 'STR', 'SPT', 'SPIN', 'PLT', 'RD', 'RT', 'WSD', 'FKW', 'BEL', 'KW', 'WBD', 'DUSK', 'FRA', 'PKW', 'LPLT', 'CLY', 'SPE', 'ASP']\n",
      "\n",
      "[[  9   0   0   7   1   1   0   0   1   4   2   0   0   0   1   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [ 77  28 182  52  26  19   4   1  40  31  10   0   0   3   1  42   0   0   3   1   0]\n",
      " [ 97   0  73 261  19  79  22   4  55  73  52   0   2   1   1 171   1   0  14  10   0]\n",
      " [ 10   0   0   8  49  37   2   2   0   3   2   0   0   0   1   1   0   0   1   4   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  3   1   7   7   7  17  19   1   2   2  75   0   0   0   1   1   0   3   1   1   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [119  11  36   3  50  33 114   9 110  53  78  42 618   2   3   3   0  30   2  34   1]\n",
      " [ 38   5  65   7   1   6   6   1  72  20  17   0   1  16   7   1   0   0   2   2   1]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]\n",
      " [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]]\n",
      "\n",
      "[[0.346 0.    0.    0.269 0.038 0.038 0.    0.    0.038 0.154 0.077 0.    0.    0.    0.038 0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.148 0.054 0.35  0.1   0.05  0.037 0.008 0.002 0.077 0.06  0.019 0.    0.    0.006 0.002 0.081 0.    0.    0.006 0.002 0.   ]\n",
      " [0.104 0.    0.078 0.279 0.02  0.084 0.024 0.004 0.059 0.078 0.056 0.    0.002 0.001 0.001 0.183 0.001 0.    0.015 0.011 0.   ]\n",
      " [0.083 0.    0.    0.067 0.408 0.308 0.017 0.017 0.    0.025 0.017 0.    0.    0.    0.008 0.008 0.    0.    0.008 0.033 0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.02  0.007 0.047 0.047 0.047 0.115 0.128 0.007 0.014 0.014 0.507 0.    0.    0.    0.007 0.007 0.    0.02  0.007 0.007 0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.088 0.008 0.027 0.002 0.037 0.024 0.084 0.007 0.081 0.039 0.058 0.031 0.457 0.001 0.002 0.002 0.    0.022 0.001 0.025 0.001]\n",
      " [0.142 0.019 0.243 0.026 0.004 0.022 0.022 0.004 0.269 0.075 0.063 0.    0.004 0.06  0.026 0.004 0.    0.    0.007 0.007 0.004]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]\n",
      " [0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.    0.   ]]\n"
     ]
    }
   ],
   "source": [
    "print(\"Confusion matrix:\")\n",
    "# cm = confusion_matrix(label_test, np.argmax(label_pred, axis=1), )\n",
    "cm = confusion_matrix(label_test, np.argmax(label_pred, axis=1), labels=species_id)\n",
    "\n",
    "print(species_list)\n",
    "print('')\n",
    "print(cm)\n",
    "print('')\n",
    "\n",
    "cm2 = cm*1.0\n",
    "for ii in range(cm.shape[0]):\n",
    "    cm_row = cm[ii, :]*1.0\n",
    "\n",
    "    cm_row_sum = cm_row.sum()\n",
    "    if cm_row_sum != 0:\n",
    "        cm2[ii, :] = cm_row / cm_row_sum\n",
    "    else:\n",
    "        cm2[ii, :] = np.zeros(cm.shape[1])\n",
    "\n",
    "print(cm2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "elegant-course",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import plot_confusion_matrix\n",
    "from sklearn.metrics._plot.confusion_matrix import ConfusionMatrixDisplay\n",
    "disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=species_list)\n",
    "disp2 = ConfusionMatrixDisplay(confusion_matrix=cm2, display_labels=species_list)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "british-processor",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7f483cc293d0>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x1080 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=[15, 15])\n",
    "disp.plot(include_values=True,\n",
    "                     cmap='viridis', ax=ax, xticks_rotation='horizontal',\n",
    "                     values_format=None, colorbar=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "effective-retailer",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7f483cc297c0>"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x1080 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=[15, 15])\n",
    "disp2.plot(include_values=True,\n",
    "                     cmap='viridis', ax=ax, xticks_rotation='horizontal',\n",
    "                     values_format='.2f', colorbar=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "settled-laugh",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}