Merge branch 'main' of ssh://gitea.cs.ru.is:2222/isakg22/Data-Mining-Mushrooms

notebooks/mushroom_analysis.ipynb

@@ -2,19 +2,246 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 1,
    "id": "45bdce35",
    "metadata": {},
    "outputs": [
     {
-     "ename": "ModuleNotFoundError",
+     "name": "stdout",
-     "evalue": "No module named 'sklearn'",
+     "output_type": "stream",
-     "output_type": "error",
+     "text": [
-     "traceback": [
+      "Feature data: (8124, 22)\n",
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "Target data: (8124,)\n"
-      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+     ]
-      "Cell \u001b[0;32mIn[5], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdatasets\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m fetch_openml\n\u001b[1;32m      3\u001b[0m mushroom \u001b[38;5;241m=\u001b[39m fetch_openml(data_id\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m43922\u001b[39m, as_frame\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m      5\u001b[0m X \u001b[38;5;241m=\u001b[39m mushroom\u001b[38;5;241m.\u001b[39mdata\n",
+    },
-      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'sklearn'"
+    {
+     "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>cap_shape</th>\n",
+       "      <th>cap_surface</th>\n",
+       "      <th>cap_color</th>\n",
+       "      <th>bruises</th>\n",
+       "      <th>odor</th>\n",
+       "      <th>gill_attachment</th>\n",
+       "      <th>gill_spacing</th>\n",
+       "      <th>gill_size</th>\n",
+       "      <th>gill_color</th>\n",
+       "      <th>stalk_shape</th>\n",
+       "      <th>...</th>\n",
+       "      <th>stalk_surface_below_ring</th>\n",
+       "      <th>stalk_color_above_ring</th>\n",
+       "      <th>stalk_color_below_ring</th>\n",
+       "      <th>veil_type</th>\n",
+       "      <th>veil_color</th>\n",
+       "      <th>ring_number</th>\n",
+       "      <th>ring_type</th>\n",
+       "      <th>spore-print-color</th>\n",
+       "      <th>population</th>\n",
+       "      <th>habitat</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>x</td>\n",
+       "      <td>s</td>\n",
+       "      <td>n</td>\n",
+       "      <td>t</td>\n",
+       "      <td>p</td>\n",
+       "      <td>f</td>\n",
+       "      <td>c</td>\n",
+       "      <td>n</td>\n",
+       "      <td>k</td>\n",
+       "      <td>e</td>\n",
+       "      <td>...</td>\n",
+       "      <td>s</td>\n",
+       "      <td>w</td>\n",
+       "      <td>w</td>\n",
+       "      <td>p</td>\n",
+       "      <td>w</td>\n",
+       "      <td>o</td>\n",
+       "      <td>p</td>\n",
+       "      <td>k</td>\n",
+       "      <td>s</td>\n",
+       "      <td>u</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>x</td>\n",
+       "      <td>s</td>\n",
+       "      <td>y</td>\n",
+       "      <td>t</td>\n",
+       "      <td>a</td>\n",
+       "      <td>f</td>\n",
+       "      <td>c</td>\n",
+       "      <td>b</td>\n",
+       "      <td>k</td>\n",
+       "      <td>e</td>\n",
+       "      <td>...</td>\n",
+       "      <td>s</td>\n",
+       "      <td>w</td>\n",
+       "      <td>w</td>\n",
+       "      <td>p</td>\n",
+       "      <td>w</td>\n",
+       "      <td>o</td>\n",
+       "      <td>p</td>\n",
+       "      <td>n</td>\n",
+       "      <td>n</td>\n",
+       "      <td>g</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>b</td>\n",
+       "      <td>s</td>\n",
+       "      <td>w</td>\n",
+       "      <td>t</td>\n",
+       "      <td>l</td>\n",
+       "      <td>f</td>\n",
+       "      <td>c</td>\n",
+       "      <td>b</td>\n",
+       "      <td>n</td>\n",
+       "      <td>e</td>\n",
+       "      <td>...</td>\n",
+       "      <td>s</td>\n",
+       "      <td>w</td>\n",
+       "      <td>w</td>\n",
+       "      <td>p</td>\n",
+       "      <td>w</td>\n",
+       "      <td>o</td>\n",
+       "      <td>p</td>\n",
+       "      <td>n</td>\n",
+       "      <td>n</td>\n",
+       "      <td>m</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>x</td>\n",
+       "      <td>y</td>\n",
+       "      <td>w</td>\n",
+       "      <td>t</td>\n",
+       "      <td>p</td>\n",
+       "      <td>f</td>\n",
+       "      <td>c</td>\n",
+       "      <td>n</td>\n",
+       "      <td>n</td>\n",
+       "      <td>e</td>\n",
+       "      <td>...</td>\n",
+       "      <td>s</td>\n",
+       "      <td>w</td>\n",
+       "      <td>w</td>\n",
+       "      <td>p</td>\n",
+       "      <td>w</td>\n",
+       "      <td>o</td>\n",
+       "      <td>p</td>\n",
+       "      <td>k</td>\n",
+       "      <td>s</td>\n",
+       "      <td>u</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>x</td>\n",
+       "      <td>s</td>\n",
+       "      <td>g</td>\n",
+       "      <td>f</td>\n",
+       "      <td>n</td>\n",
+       "      <td>f</td>\n",
+       "      <td>w</td>\n",
+       "      <td>b</td>\n",
+       "      <td>k</td>\n",
+       "      <td>t</td>\n",
+       "      <td>...</td>\n",
+       "      <td>s</td>\n",
+       "      <td>w</td>\n",
+       "      <td>w</td>\n",
+       "      <td>p</td>\n",
+       "      <td>w</td>\n",
+       "      <td>o</td>\n",
+       "      <td>e</td>\n",
+       "      <td>n</td>\n",
+       "      <td>a</td>\n",
+       "      <td>g</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 22 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  cap_shape cap_surface cap_color bruises odor gill_attachment gill_spacing  \\\n",
+       "0         x           s         n       t    p               f            c   \n",
+       "1         x           s         y       t    a               f            c   \n",
+       "2         b           s         w       t    l               f            c   \n",
+       "3         x           y         w       t    p               f            c   \n",
+       "4         x           s         g       f    n               f            w   \n",
+       "\n",
+       "  gill_size gill_color stalk_shape  ... stalk_surface_below_ring  \\\n",
+       "0         n          k           e  ...                        s   \n",
+       "1         b          k           e  ...                        s   \n",
+       "2         b          n           e  ...                        s   \n",
+       "3         n          n           e  ...                        s   \n",
+       "4         b          k           t  ...                        s   \n",
+       "\n",
+       "  stalk_color_above_ring stalk_color_below_ring veil_type veil_color  \\\n",
+       "0                      w                      w         p          w   \n",
+       "1                      w                      w         p          w   \n",
+       "2                      w                      w         p          w   \n",
+       "3                      w                      w         p          w   \n",
+       "4                      w                      w         p          w   \n",
+       "\n",
+       "  ring_number ring_type spore-print-color population habitat  \n",
+       "0           o         p                 k          s       u  \n",
+       "1           o         p                 n          n       g  \n",
+       "2           o         p                 n          n       m  \n",
+       "3           o         p                 k          s       u  \n",
+       "4           o         e                 n          a       g  \n",
+       "\n",
+       "[5 rows x 22 columns]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "0    p\n",
+       "1    e\n",
+       "2    e\n",
+       "3    p\n",
+       "4    e\n",
+       "Name: class, dtype: category\n",
+       "Categories (2, str): ['e', 'p']"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "class\n",
+      "e    4208\n",
+      "p    3916\n",
+      "Name: count, dtype: int64\n"
      ]
     }
    ],
@@ -35,19 +262,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "69e1a254",
    "metadata": {},
    "outputs": [
     {
-     "ename": "NameError",
+     "name": "stdout",
-     "evalue": "name 'X' is not defined",
+     "output_type": "stream",
-     "output_type": "error",
+     "text": [
-     "traceback": [
+      "Missing cells: 0\n",
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "Rows with missing cells: 0\n",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "stalk_root\n",
-      "Cell \u001b[0;32mIn[3], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMissing cells:\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[43mX\u001b[49m\u001b[38;5;241m.\u001b[39misna()\u001b[38;5;241m.\u001b[39msum()\u001b[38;5;241m.\u001b[39msum())\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRows with missing cells:\u001b[39m\u001b[38;5;124m\"\u001b[39m, X\u001b[38;5;241m.\u001b[39misna()\u001b[38;5;241m.\u001b[39many(axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\u001b[38;5;241m.\u001b[39msum())\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28mprint\u001b[39m(X[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstalk_root\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39mvalue_counts(dropna\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m))\n",
+      "b    3776\n",
-      "\u001b[0;31mNameError\u001b[0m: name 'X' is not defined"
+      "?    2480\n",
+      "e    1120\n",
+      "c     556\n",
+      "r     192\n",
+      "Name: count, dtype: int64\n"
      ]
     }
    ],
@@ -56,30 +287,11 @@
     "print(\"Rows with missing cells:\", X.isna().any(axis=1).sum())\n",
     "print(X[\"stalk_root\"].value_counts(dropna=False))"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "a3459b1e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "hello\n"
-     ]
-    }
-   ],
-   "source": [
-    "a = \"hello\"\n",
-    "print(a)"
-   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv (3.9.6)",
+   "display_name": ".venv (3.12.10)",
    "language": "python",
    "name": "python3"
   },
@@ -93,7 +305,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.6"
+   "version": "3.12.10"
   }
  },
  "nbformat": 4,