embedding-clustering/extract/test.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a314a8ac",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.        , 0.        ],\n",
       "       [0.26726124, 0.56694671]])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics.pairwise import cosine_similarity\n",
    "import numpy as np\n",
    "X = [[0, 0, 0], [1, 2, 3]]\n",
    "Y = [[1, 0, 0], [1, 1, 0]]\n",
    "cosine_similarity(X, Y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "4b560c4f",
   "metadata": {},
   "outputs": [],
   "source": [
    "sims = cosine_similarity(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d8d5d17a",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "a1098a5a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(3, 3)\n",
      "(array([0, 0, 1]), array([1, 2, 2]))\n",
      "(3,)\n",
      "mean sim: -0.3333333333333334 std: 0.47140452079103173\n"
     ]
    }
   ],
   "source": [
    "# X = np.array([\n",
    "#     [0, 0, 0], \n",
    "#     [-1, 100, -1000],\n",
    "#     [-1, -2, -4]\n",
    "#     ]\n",
    "#              )\n",
    "\n",
    "X = np.array([\n",
    "    [0, 0, 0], \n",
    "    [1,1,1],\n",
    "    [-1, -1, -1]\n",
    "    ]\n",
    "             )\n",
    "print(X.shape)\n",
    "sims = cosine_similarity(X)\n",
    "\n",
    "triu_idxs = np.triu_indices_from(sims, k=1)\n",
    "print(triu_idxs)\n",
    "dist_vals = sims[triu_idxs]\n",
    "print(dist_vals.shape)\n",
    "print(\"mean sim:\", dist_vals.mean(), \"std:\", dist_vals.std())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "2dacad18",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.])"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dist_vals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "76d25e07",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}