Corrected HDBSCAN cache and uniform weights init

examples/CIDIE COVID features.ipynb

@@ -1,15 +1,5 @@
 {
  "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import sys\n",
-    "sys.path.insert(0, '../')"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -19,6 +9,8 @@
     "import json\n",
     "import pandas as pd\n",
     "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib.image as mpimg\n",
     "from sklearn.preprocessing import MinMaxScaler\n",
     "from scipy.spatial.distance import cdist\n",
     "from neural_map import NeuralMap, _plot"
@@ -30,6 +22,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# cargar los conjuntos de datos\n",
     "train_features = np.load('datasets/train_features.npy')\n",
     "train_labels = np.load('datasets/train_labels.npy')\n",
     "test_features = np.load('datasets/test_features.npy')\n",
@@ -38,12 +31,43 @@
     "train_features.shape, train_labels.shape, test_features.shape, test_labels.shape"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "#     '01a4059c-22f7-4f51-8a27-50aff0b3aeb3.jpg': 5931,\n",
+    "#     '01cc7c75-4498-43ab-b650-5553d0507f76.jpg': 5936,\n",
+    "#     '042bde1a-88c1-4ae5-af0c-1a409e1e09ee.jpg': 5952,\n",
+    "#     'lancet-case2.png': 41,\n",
+    "#     'streptococcus-pneumoniae-pneumonia-1.jpeg': 10\n",
+    "\n",
+    "images_indices = {\n",
+    "    'auntminnie-a-2020_01_28_23_51_6665_2020_01_28_Vietnam_coronavirus.jpeg': 35,\n",
+    "    'nejmoa2001191_f3-PA.jpeg': 46,\n",
+    "    'SARS-10.1148rg.242035193-g04mr34g0-Fig8a-day0.jpeg': 0,\n",
+    "    'SARS-10.1148rg.242035193-g04mr34g0-Fig8b-day5.jpeg': 1,\n",
+    "}\n",
+    "\n",
+    "for image_name, index in images_indices.items():\n",
+    "    img = mpimg.imread('datasets/train_images/' + image_name)\n",
+    "    imgplot = plt.imshow(img, cmap='Greys_r')\n",
+    "    plt.show()\n",
+    "    print(train_features[index])\n",
+    "    print('\\n')\n"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
+    "# escalar los valores al rango [0, 1]\n",
+    "\n",
     "scaler = MinMaxScaler()\n",
     "\n",
     "s_train_features = scaler.fit_transform(train_features)\n",
@@ -58,12 +82,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# cargar la instancia de NeuralMap cargada\n",
     "dictionary = {}\n",
     "\n",
     "with open('datasets/features_training_correlation_10.json') as json_file: \n",
     "    dictionary = json.load(json_file)\n",
     "    dictionary['relative_positions'] = np.array(dictionary['relative_positions'])\n",
     "    dictionary['weights'] = np.array(dictionary['weights'])\n",
+    "    del dictionary['seed']\n",
     "    \n",
     "nm = NeuralMap(**dictionary)"
    ]
@@ -74,25 +100,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "nm.plot_unified_distance_matrix(detailed=True, borders=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "nm.plot_analysis(data=s_train_features)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "nm.plot_analysis(data=s_test_features)"
+    "nm.plot_unified_distance_matrix(detailed=True, borders=True, size=13)"
    ]
   },
   {
@@ -101,7 +109,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "nm.plot_labels(data=s_train_features, labels=train_labels)"
+    "nm.plot_analysis(data=s_train_features, attached_values=train_labels, size=13, title='Distribución de las clases de radiografías (conjunto de datos de entrenamiento)')"
    ]
   },
   {
@@ -110,7 +118,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "nm.plot_labels(data=s_test_features, labels=test_labels)"
+    "nm.plot_analysis(data=s_test_features, attached_values=test_labels, size=13, title='Distribución de las clases de radiografías (conjunto de datos de prueba)')"
    ]
   },
   {
@@ -138,7 +146,7 @@
     "# 3) mostramos una imagen y la otra al lado.\n",
     "# Un ejemplo simple es, hacer esos pasos con una imagen de entrenamiento y recuerar la clase de la misma.\n",
     "\n",
-    "selected_feature_index = 412\n",
+    "selected_feature_index = 413\n",
     "\n",
     "if not ('mapped_train_features_indices' in vars() or 'mapped_train_features_indices' in globals()):\n",
     "    mapped_train_features_indices = nm.map_attachments(s_train_features, np.array(range(s_train_features.shape[0])))\n",
@@ -178,4 +186,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}