{
 
 "cells": [
  {
   "cell_type": "markdown",
   "id": "134e7f9d",
   "metadata": {},
   "source": [
    "# Example 14: Knot supervised"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "0893a344",
   "metadata": {},
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[Errno 2] No such file or directory: './knot_data.csv'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m/var/folders/6j/b6y80djd4nb5hl73rv3sv8y80000gn/T/ipykernel_75986/3212158569.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     11\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     12\u001b[0m \u001b[0;31m# Download data: https://colab.research.google.com/github/deepmind/mathematics_conjectures/blob/main/knot_theory.ipynb#scrollTo=l10N2ZbHu6Ob\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 13\u001b[0;31m \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"./knot_data.csv\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     14\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/util/_decorators.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    309\u001b[0m                     \u001b[0mstacklevel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstacklevel\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    310\u001b[0m                 )\n\u001b[0;32m--> 311\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    312\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    313\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, error_bad_lines, warn_bad_lines, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options)\u001b[0m\n\u001b[1;32m    676\u001b[0m     \u001b[0mkwds\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkwds_defaults\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    677\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 678\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    679\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    680\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m    573\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    574\u001b[0m     \u001b[0;31m# Create the parser.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 575\u001b[0;31m     \u001b[0mparser\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mTextFileReader\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    576\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    577\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mchunksize\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0miterator\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m    930\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    931\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhandles\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mIOHandles\u001b[0m \u001b[0;34m|\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 932\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_engine\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mengine\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    933\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    934\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36m_make_engine\u001b[0;34m(self, f, engine)\u001b[0m\n\u001b[1;32m   1214\u001b[0m             \u001b[0;31m# \"Union[str, PathLike[str], ReadCsvBuffer[bytes], ReadCsvBuffer[str]]\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1215\u001b[0m             \u001b[0;31m# , \"str\", \"bool\", \"Any\", \"Any\", \"Any\", \"Any\", \"Any\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1216\u001b[0;31m             self.handles = get_handle(  # type: ignore[call-overload]\n\u001b[0m\u001b[1;32m   1217\u001b[0m                 \u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1218\u001b[0m                 \u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/lib/python3.9/site-packages/pandas/io/common.py\u001b[0m in \u001b[0;36mget_handle\u001b[0;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[1;32m    784\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencoding\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;34m\"b\"\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    785\u001b[0m             \u001b[0;31m# Encoding\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 786\u001b[0;31m             handle = open(\n\u001b[0m\u001b[1;32m    787\u001b[0m                 \u001b[0mhandle\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    788\u001b[0m                 \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: './knot_data.csv'"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import torch\n",
    "from kan import *\n",
    "import copy\n",
    "\n",
    "\n",
    "seed = 42\n",
    "torch.manual_seed(seed)\n",
    "np.random.seed(seed)\n",
    "\n",
    "# Download data: https://colab.research.google.com/github/deepmind/mathematics_conjectures/blob/main/knot_theory.ipynb#scrollTo=l10N2ZbHu6Ob\n",
    "df = pd.read_csv(\"./knot_data.csv\")\n",
    "df.keys()\n",
    "\n",
    "X = df[df.keys()[1:-1]].to_numpy()\n",
    "Y = df[['signature']].to_numpy()\n",
    "\n",
    "# normalize X\n",
    "X_mean = np.mean(X, axis=0)\n",
    "X_std = np.std(X, axis=0)\n",
    "X = (X - X_mean[np.newaxis,:])/X_std[np.newaxis,:]\n",
    "input_normalier = [X_mean, X_std]\n",
    "\n",
    "# normalize Y\n",
    "max_signature = np.max(Y)\n",
    "min_signature = np.min(Y)\n",
    "Y = ((Y-min_signature)/2).astype(int)\n",
    "n_class = int((max_signature-min_signature)/2+1)\n",
    "output_normalier = [min_signature, 2]\n",
    "\n",
    "dataset = {}\n",
    "num = X.shape[0]\n",
    "n_feature = X.shape[1]\n",
    "train_ratio = 0.8\n",
    "train_id_ = np.random.choice(num, int(num*train_ratio), replace=False)\n",
    "test_id_ = np.array(list(set(range(num))-set(train_id_)))\n",
    "\n",
    "dtype = torch.get_default_dtype()\n",
    "dataset['train_input'] = torch.from_numpy(X[train_id_]).type(dtype)\n",
    "dataset['train_label'] = torch.from_numpy(Y[train_id_][:,0]).type(torch.long)\n",
    "dataset['test_input'] = torch.from_numpy(X[test_id_]).type(dtype)\n",
    "dataset['test_label'] = torch.from_numpy(Y[test_id_][:,0]).type(torch.long)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e262aeca",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "def train_acc():\n",
    "    return torch.mean((torch.argmax(model(dataset['train_input']), dim=1) == dataset['train_label']).float())\n",
    "\n",
    "def test_acc():\n",
    "    return torch.mean((torch.argmax(model(dataset['test_input']), dim=1) == dataset['test_label']).float())\n",
    "\n",
    "model = KAN(width=[n_feature,1,n_class], grid=5, k=3, seed=seed)\n",
    "model.fit(dataset, lamb=0.005, batch=1024, loss_fn = nn.CrossEntropyLoss(), metrics=[train_acc, test_acc], display_metrics=['train_loss', 'reg', 'train_acc', 'test_acc']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2254d060",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.plot(scale=1.0, beta=0.2)\n",
    "\n",
    "n = 17\n",
    "for i in range(n):\n",
    "    plt.gcf().get_axes()[0].text(1/(2*n)+i/n-0.005,-0.02,df.keys()[1:-1][i], rotation=270, rotation_mode=\"anchor\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "54778a24",
   "metadata": {},
   "outputs": [],
   "source": [
    "scores = model.feature_score\n",
    "features = list(df.keys()[1:-1])\n",
    "\n",
    "y_pos = range(len(features))\n",
    "plt.bar(y_pos, scores)\n",
    "plt.xticks(y_pos, features, rotation=90);\n",
    "plt.ylabel('feature importance')"
   ]
  }
 ],
 "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}