add sudoku reshape notebooks

3million_sudoku_reshape.ipynb

@@ -0,0 +1,230 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new_data = pd.read_csv(\"sudoku-3m.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>puzzle</th>\n",
+       "      <th>solution</th>\n",
+       "      <th>clues</th>\n",
+       "      <th>difficulty</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>1..5.37..6.3..8.9......98...1.......8761.........</td>\n",
+       "      <td>1985437266432785915276198439147352688761924352...</td>\n",
+       "      <td>27</td>\n",
+       "      <td>2.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>...81.....2........1.9..7...7..25.934.2..........</td>\n",
+       "      <td>9348172567286534196159427381764258934523981673...</td>\n",
+       "      <td>23</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>..5...74.3..6...19.....1..5...7...2.9....58..7...</td>\n",
+       "      <td>2159837463876542194692713855387169249413258677...</td>\n",
+       "      <td>25</td>\n",
+       "      <td>2.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>........5.2...9....9..2...373..481.....36....5...</td>\n",
+       "      <td>4738169256285397411954278637329481569413652785...</td>\n",
+       "      <td>26</td>\n",
+       "      <td>1.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>.4.1..............653.....1.8.9..74...24..91.....</td>\n",
+       "      <td>9471536821286493576532874913819267455724389164...</td>\n",
+       "      <td>25</td>\n",
+       "      <td>1.1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id                                             puzzle  \\\n",
+       "0   1  1..5.37..6.3..8.9......98...1.......8761.........   \n",
+       "1   2  ...81.....2........1.9..7...7..25.934.2..........   \n",
+       "2   3  ..5...74.3..6...19.....1..5...7...2.9....58..7...   \n",
+       "3   4  ........5.2...9....9..2...373..481.....36....5...   \n",
+       "4   5  .4.1..............653.....1.8.9..74...24..91.....   \n",
+       "\n",
+       "                                            solution  clues  difficulty  \n",
+       "0  1985437266432785915276198439147352688761924352...     27         2.2  \n",
+       "1  9348172567286534196159427381764258934523981673...     23         0.0  \n",
+       "2  2159837463876542194692713855387169249413258677...     25         2.6  \n",
+       "3  4738169256285397411954278637329481569413652785...     26         1.4  \n",
+       "4  9471536821286493576532874913819267455724389164...     25         1.1  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "new_data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new_data['puzzle'] = new_data['puzzle'].apply(lambda x: x.replace('.','0'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "quizzes = []\n",
+    "solutions = []\n",
+    "for idx, row in new_data.iterrows():\n",
+    "    quizz = row[\"puzzle\"]\n",
+    "    solution = row[\"solution\"]\n",
+    "    quizzes.append(np.array([int(x) for x in quizz],).reshape(9,9).astype(np.uint8))\n",
+    "    solutions.append(np.array([int(x) for x in solution]).reshape(9,9).astype(np.uint8))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((3000000, 9, 9), (3000000, 9, 9))"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "quizzes = np.stack(quizzes)\n",
+    "solutions = np.stack(solutions)\n",
+    "quizzes.shape, solutions.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sol = np.zeros((solutions.shape[0],2,9,9,9), dtype=np.uint8)\n",
+    "quizz = np.zeros((solutions.shape[0],2,9,9,9), dtype=np.uint8)\n",
+    "for i in range(9):\n",
+    "    sol[:,1,:,:,i] = (solutions==i+1).astype(np.uint8)\n",
+    "    sol[:,0,:,:,i] = ((solutions!=i+1) & (solutions!=0)).astype(np.uint8)\n",
+    "    quizz[:,1,:,:,i] = (quizzes==i+1).astype(np.uint8)\n",
+    "    quizz[:,0,:,:,i] = ((quizzes!=i+1) & (quizzes!=0)).astype(np.uint8)\n",
+    "    \n",
+    "np.savez(\"sudoku_reshaped_3_million.npz\",quizzes=quizz[:1000000],solutions=sol[:1000000])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.10.4"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}