3rd meeting

P4. Appendix - embeddings in high demensional spaces.ipynb

@@ -9,12 +9,12 @@
      "data": {
       "text/plain": [
        "['dimensions: 1, cases when observation is the nearest: 0.0%',\n",
-       " 'dimensions: 2, cases when observation is the nearest: 0.0%',\n",
-       " 'dimensions: 3, cases when observation is the nearest: 0.0%',\n",
-       " 'dimensions: 10, cases when observation is the nearest: 13.0%',\n",
-       " 'dimensions: 20, cases when observation is the nearest: 61.0%',\n",
-       " 'dimensions: 30, cases when observation is the nearest: 96.0%',\n",
-       " 'dimensions: 40, cases when observation is the nearest: 98.0%',\n",
+       " 'dimensions: 2, cases when observation is the nearest: 1.0%',\n",
+       " 'dimensions: 3, cases when observation is the nearest: 1.0%',\n",
+       " 'dimensions: 10, cases when observation is the nearest: 8.0%',\n",
+       " 'dimensions: 20, cases when observation is the nearest: 68.0%',\n",
+       " 'dimensions: 30, cases when observation is the nearest: 93.0%',\n",
+       " 'dimensions: 40, cases when observation is the nearest: 100.0%',\n",
        " 'dimensions: 50, cases when observation is the nearest: 100.0%',\n",
        " 'dimensions: 60, cases when observation is the nearest: 100.0%',\n",
        " 'dimensions: 70, cases when observation is the nearest: 100.0%',\n",
@@ -46,15 +46,15 @@
     "        i1, i2 = random.sample(range(nb_vectors), 2)\n",
     "        target = (vectors[i1] + vectors[i2]) / 2\n",
     "\n",
-    "        distances = pd.DataFrame(\n",
+    "        similarities = pd.DataFrame(\n",
     "            enumerate(\n",
     "                np.dot(target, vectors.transpose())\n",
     "                / norm(target)\n",
     "                / norm(vectors.transpose(), axis=0)\n",
     "            )\n",
     "        )\n",
-    "        distances = distances.sort_values(by=[1], ascending=False)\n",
-    "        if (i1 in (list(distances[0][:k]))) | (i2 in (list(distances[0][:k]))):\n",
+    "        similarities = similarities.sort_values(by=[1], ascending=False)\n",
+    "        if (i1 in (list(similarities[0][:k]))) | (i2 in (list(similarities[0][:k]))):\n",
     "            successes += 1\n",
     "    result.append(successes / trials)\n",
     "\n",
@@ -63,13 +63,6 @@
     "    for i, j in zip(dimensions, result)\n",
     "]"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {