Merge branch 'main' of https://gitea.jany.se/Jany/MLPproject

info.ipynb

@@ -2,11 +2,138 @@
  "cells": [
   {
    "cell_type": "code",
+<<<<<<< HEAD
+   "execution_count": 10,
+=======
    "execution_count": 1,
+>>>>>>> caaa71666df3f35a02848991df9e15db55aef57c
    "id": "b6ea6c3b",
    "metadata": {},
    "outputs": [
     {
+<<<<<<< HEAD
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+<<<<<<< HEAD
+      "       age  workclass  education.num  marital.status  occupation  \\\n",
+      "0       90          0              9               6           0   \n",
+      "1       82          4              9               6           4   \n",
+      "2       66          0             10               6           0   \n",
+      "3       54          4              4               0           7   \n",
+      "4       41          4             10               5          10   \n",
+      "...    ...        ...            ...             ...         ...   \n",
+      "32556   22          4             10               4          11   \n",
+      "32557   27          4             12               2          13   \n",
+      "32558   40          4              9               2           7   \n",
+      "32559   58          4              9               6           1   \n",
+      "32560   22          4              9               4           1   \n",
+      "\n",
+      "       relationship  race  sex  capital.gain  capital.loss  hours.per.week  \n",
+      "0                 1     4    0             0          4356              40  \n",
+      "1                 1     4    0             0          4356              18  \n",
+      "2                 4     2    0             0          4356              40  \n",
+      "3                 4     4    0             0          3900              40  \n",
+      "4                 3     4    0             0          3900              40  \n",
+      "...             ...   ...  ...           ...           ...             ...  \n",
+      "32556             1     4    1             0             0              40  \n",
+      "32557             5     4    0             0             0              38  \n",
+      "32558             0     4    1             0             0              40  \n",
+      "32559             4     4    0             0             0              40  \n",
+      "32560             3     4    1             0             0              20  \n",
+      "\n",
+      "[32561 rows x 11 columns]\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAB1AAAAN8CAYAAADmrDj+AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjYsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvq6yFwwAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzs3XV0FNcXwPHvStyFCElwd3d3dyvSAoXS0gKlSIVfFdpSWlooBQpV3N3dAwRNgiXE3d2T3f39sWQhZDdGIAl9n3NyTrLz3szdie3OnXufRKVSqRAEQRAEQRAEQRAEQRAEQRAEQRAEQRCQl3UAgiAIgiAIgiAIgiAIr4vk5GQOHz7M2bNniY2NJT0traxDEgThP0Kup4elpSUNGzZk1KhR1KpVq6xDEgRBEIQKSyIqUAVBEARBEARBEARBEF5MTEwM786YwZGjR8jIyKRBVQccLI0x0pcjkZR1dIIg/Bdk5yhJSMvEMyCStIwsmjdrynffL6Vfv35lHZogCIIgVDgigSoIgiAIgiAIgiAIgvACYmJi6NG9GxEhgcwa1Joh7erhUsmirMMSBOE/Ki0zm9N3fPnr5B3cHoexZ89eBg0aVNZhCYIgCEKFIhKogiAIgiAIgiAIgiAIJaRQKGjZojlhQf7s/3wc9ZxtyzokQRAEALJyFExbeZBTd/04f/4C7du3L+uQBEEQBKHCkJZ1AIIgCIIgCIIgCIIgCBXVxYsXcffw5O85Q0TyVBCEckVfLuPPOUNwsTVn/fr1ZR2OIAiCIFQoIoEqCIIgCIIgCIIgCIJQQrt27cLFzor29V3KOhRBEIR89OUyhrWry/59e8nKyirrcARBEAShwhAJVEEQBEEQBEEQBEEQhBLav28vg1vXQiKRlHUogiAIWg1tV4+ExCQuXrxY1qEIgiAIQoUhEqiCIAiCIAiCIAiCIAglkJOTQ3hEJPVcROteQRDKrzpONgAEBweXcSSCIAiCUHGIBKogCIIgCIIgCIIgCEIJJCcnA2BmZFDGkQiCIOimJ5dhbKhPYmJiWYciCIIgCBWGSKAKgiAIgiAIgiAIgiCUgEqlAkAqfT3b924974HN2KU0+2DNf/L4peny/UBsxi7FZuzSMpkvCDKpVPM3SxAEQRCEwsnLOgBBEARBEARBEARBEAThvyMoKoFtFzwB+Hh05zKORvivSU7PZM1hNw5d9yYoKgGpVEpNRytGdKjP9P6t0JfLSrTfH3ZdYtnuK4WOu7FyBjUcrEp0DEEQBEEQXh2RQBUEQRAEQRAEQRAEQRBemaDoRE2iqaAEqrmxAbUqW+NobfaqQiu3jAz0qFXZuqzDqPCCoxMZ8vVWgqLVrWyNDfTIysnhrl8Ed/0i2H35Afs+fwNLU8MSH0NPJsXK1EjndvlrWrEuCIIgCK8bkUAVBEEQBEEQBEEQBEEQyp1BbeoyqE3dsg6jXGhZqzLXf3mnrMOo0HIUSsYv201QdCL2VqasmTmIbk2qoVSqOHDtER+uP4ZHQCTv/naI7Z+MLvFx2tR14uCXE0oxckEQBEEQyoJYA1UQBEEQBEEQBEEQBEEQhFL3KCSGG96hZR0GANsvePIgKBqADR8Np1uTaoB6DePhHerz8/R+AJy648sFz4AyilIQBEEQhPJCVKAKgiAIgiAIgiAIgiBUMEO+3sKVB8EsHNWRj4Z3YP2xm+xxfYh/RDxJaZkc+OINOjWsqhn/MCia9cdvcvl+EOFxyUglEqraW9K3ZS3eG9AaG3PjYh0/O0fB6bt+nLztg7t/JBFxycQlp2NhYkjjava80a0xIzrURyLJ26602QdrCI5O0nxtM3Zpnu3jujZi9cxBAGw978GstUdxqWTO3d9mao3DPyKe3w67cdEzgLDYZORyKTXsrRjQujYzBrTG3Ngg35zL9wMZ+s02AGJ3fIJfRDy/7HPlvGcAMYlp2Jgb06tZDRaO7kRlHe2DvUNjWXvEjSsPggiLTUapUmFjboyjlRmdG1VlbJdG1HGy0Xn+invM52N+1vPn6ZyHP2uP3OCubzipGdlUtbdkRIf6fDC4LYb6L/9SYHRiKnsuP2DnpXu4+0eycFRHWtdxeunHLcz2J+vudmpYRWs8IzrU59vtFwiMSmTHxXt0bVztFUcoCIIgCEJ5IhKogiAIgiAIgiAIgiAIFVRGtoIhX2/FzTsUuUyKqaE+z+Us+fXANRZvu4BSpQLU6z5mK5Q8CIrmQVA0W897sv3jUTSp7lDk4173CmHij3s0X5sZGWCgLycmKY1zHv6c8/DniJs3f84ZivSZNR9tzIxJTssiITUDADsLkzz71Zbw1GX/1YfMXH2YzGwFAKZG+mTnKPAIiMQjIJJNZz3Y9dkY6jrb6tzHpXuBTPhxD6kZWZga6aNUqQiPS2bTWXdO3fHl1Hdv5UtonvPwZ8Ky3Zrj6smkGBvqERabTFhsMrd8wtCXS3Wu71qSYxbVXydu8/E/J1GpwMLEgBylEq+QGL7feYkjbt4vvL6nLulZ2Ry78Zidl+5zzsOfHIUSAH25DCcb81I/XnGlZWZz3UtdCdurWU2tYyQSCT2a1uCfU3c47+H/KsMTBEEQBKEcEglUQRAEQRAEQRAEQRCECuqvE7cBWPXeAIZ3qI+Rvh5xyemaJOrms+58vfU8Job6fDisHRO6N8He0hSFUolnQBRfbTmnSehd/Xk6pob6RTqukYEek3s1Y3DberSo5ahJfManpLPz0n2+33GJA9ce0baeMzP6t9LMO/P95DzVlA/XzyrR83b3i+DdVYfIVihpW9eZn6b1oUEVO5RKFSfv+PDRHycIjU1iwrLdnF82VefzmvzzPjo3qsKX47tTx8mGrBwFR294M2fdMSLiU1i89TxrPxicZ86CP0+Qma2ge5PqLJ7Ug/pVKgGQkZVDQGQ8h6574WSrO2lYkmMWRWxSOos2nGZI23osntQDJ1tz0rOy2X7hHos2nMYjIJLZvx9l4/wRxd63NiqVisv3g9h56R4Hr3uRkp4FgEQC7es5M7pzI4a2q/dSErbF5R0aq7mBoL6L7oR6fRf19zIyIZX4lHSsTI2KfaxHwTF0nPcngVEJSCUSHKzN6FDfhal9mhfrJgVBEARBEMqWSKAKgiAIgiAIgiAIgiBUUKkZWWxZOJJ+LWtrHrM2Uyd9ktMz+WLzWQD+nTuMHs1qaMbIpFKa1XBg92dj6fO/jbj7RbD5jDvvDmxdpOO2rFWZlrUq53vcytSIGf1b4WhlypRf9vPHsZt5Eqil5dsdF8lWKKnhYMXuRWMxNtAD1OtZ9mtZm8rWZvRetBH/yAT+PXWHDwa31bqfRtXs2DRvpKZKVl8uY1j7+kQlpPLpv6c5dN2LVe8NRC6TAur2tP6RCQD8NnMgDlammn0Z6sup51KJek+ScLoU95hFlZaZTccGLnmqfo309ZjSuzl6Milz1h3jyA1vbvuE06KWY7H2/SyvkBh2XrrPrkv3CY192o65vkslRnVqwKhODXC2tShwH88m0Uti1XsDGN+tSZHHR8Qnaz53LKC619H66fczIi6lRAnU2OR04lMysDAxIDk9C9/wOHzD49h8zp25wzqwaFyXYu9TEARBEIRXTyRQBUEQBEEQBEEQBEEQKqh6zrZ5kqfPOnTdi8TUTJpUs8+TPH2WXCZlZIf6uPtFcNbDv8gJ1ML0bqFuk+ofmUBkQgr2lqaFzCi6xNQMzrr7AfDB4Laa5OmzmlR3YFCbOuy/+oi9Vx7oTKDOHdYhT4vhXANa1+bTf0+TnpWDb3icpg2wqZE+UokEpUpFZHxKngRqURX3mMXx0fCOWvc9vlsTfth9mbDYZPa5Pih2AjU6MZW9Vx6w49J93P0iNI9XtjFjZAd10rRRNfsi709fLsvXvrk4jPTzf88LklsdC+rqaZ37fWZbSkaWznHa1HCw5qsJ3enfqjZV7SzQk8vIylFw5X4Qi7dfwN0vgp/3uWJpYsD7On4eBUEQBEEoP0QCVRAEQRAEQRDKgFKp5OrVq+zatYuzZ88QGxtLWlp6WYclCILw0kkkEiwszHFxcWHo0GGMGjWKqlWrlnVYFVbbus46t7k9WfPROzSW+u+s0jkuPSsHgODoxGIdOzk9k39P3eXkbR+8Q2NJTM0g+8nal88Ki00u1QSqu38ET7qx0rVxNZ3jujWuzv6rj7gfFE12jgI9uSzfmJa1tScSHayeVikmpGRoPjfS16NL46qc9whgzPc7mdy7Gb2b16JJdXv0texfm+Ies6jkMint62v/eZBKJXRsUIVdl+5z95kEaFGExSXT/IO1mnVNLUwMGNymLqM6NaRTwypInl90twja1HUucfvm8mp054b5HtOXy+jetDrt67sw6Kst3PEN54fdV5jUsynmxmXf2vh1plAouHLlCrt27eL8k9fa6RnF/70SBEEobYYGBlhbW9Gxc1dGjx5N9+7dkctFqq48Et8VQRAEQRAEQXjFPDw8GDx4MEFBQTja2zGgVzccHewwNjIq0UVIQRCEikShUJCUnMIDbx8WLVrE/PnzGTp0CNu2bcfIqPjtMv/rbC2MdW6LiE8BICM7h4zEnEL3lZ6VXeTj+oTFMXzJNsJin7ZGNTbQw8LEEOmT/2VRiamAurVsaYpJTNN8/mzL1edVtlEnJHMUSuJTMrCzzF/xaGZkoHXus+1zsxWKPNtWzujPhGV7uBcYxU97XPlpjyv6chnNazrSv1VtJvZoUmDr15IcsyhszIww0NN9qS+3dW30M+evKHJyFJrkKUCvZjUZ3qEBHRuULHlaFkyNnq6Bm17Az+Oz24q6HnBRGOrL+d+4roz8djupGVlc8AxkcNu6pbZ/Ia+bN28ybOgQQsPCcbQyoVc9W+xcrDDSk1FBfmQFQXiNZWQriU7O4NT+7fzxxx/Y2lizfcdOevbsWdahCc8RCVRBEARBEARBeIU8PDzo0aMHVZwc+HflFjq0aYlUWrw1zgRBEF4XSckp7D18nDmLvmHLine truncated
+      "text/plain": [
+       "<Figure size 2000x1000 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Feature Importances:\n",
+      "           feature  importance\n",
+      "5     relationship    0.218174\n",
+      "0              age    0.174282\n",
+      "2    education.num    0.147966\n",
+      "8     capital.gain    0.129988\n",
+      "10  hours.per.week    0.105884\n",
+      "4       occupation    0.085228\n",
+      "1        workclass    0.052566\n",
+      "9     capital.loss    0.044720\n",
+      "6             race    0.023650\n",
+      "3   marital.status    0.011255\n",
+      "7              sex    0.006286\n"
+=======
+      "       age workclass  fnlwgt  education.num      marital.status  \\\n",
+      "0       90         ?   77053              9             Widowed   \n",
+      "1       82   Private  132870              9             Widowed   \n",
+      "2       66         ?  186061             10             Widowed   \n",
+      "3       54   Private  140359              4            Divorced   \n",
+      "4       41   Private  264663             10           Separated   \n",
+      "...    ...       ...     ...            ...                 ...   \n",
+      "32556   22   Private  310152             10       Never-married   \n",
+      "32557   27   Private  257302             12  Married-civ-spouse   \n",
+      "32558   40   Private  154374              9  Married-civ-spouse   \n",
+      "32559   58   Private  151910              9             Widowed   \n",
+      "32560   22   Private  201490              9       Never-married   \n",
+      "\n",
+      "              occupation   relationship   race     sex  capital.gain  \\\n",
+      "0                      ?  Not-in-family  White  Female             0   \n",
+      "1        Exec-managerial  Not-in-family  White  Female             0   \n",
+      "2                      ?      Unmarried  Black  Female             0   \n",
+      "3      Machine-op-inspct      Unmarried  White  Female             0   \n",
+      "4         Prof-specialty      Own-child  White  Female             0   \n",
+      "...                  ...            ...    ...     ...           ...   \n",
+      "32556    Protective-serv  Not-in-family  White    Male             0   \n",
+      "32557       Tech-support           Wife  White  Female             0   \n",
+      "32558  Machine-op-inspct        Husband  White    Male             0   \n",
+      "32559       Adm-clerical      Unmarried  White  Female             0   \n",
+      "32560       Adm-clerical      Own-child  White    Male             0   \n",
+      "\n",
+      "       capital.loss  hours.per.week native.country income  \n",
+      "0              4356              40  United-States  <=50K  \n",
+      "1              4356              18  United-States  <=50K  \n",
+      "2              4356              40  United-States  <=50K  \n",
+      "3              3900              40  United-States  <=50K  \n",
+      "4              3900              40  United-States  <=50K  \n",
+      "...             ...             ...            ...    ...  \n",
+      "32556             0              40  United-States  <=50K  \n",
+      "32557             0              38  United-States  <=50K  \n",
+      "32558             0              40  United-States   >50K  \n",
+      "32559             0              40  United-States  <=50K  \n",
+      "32560             0              20  United-States  <=50K  \n",
+      "\n",
+      "[32561 rows x 14 columns]\n"
+     ]
+    },
+    {
+     "ename": "ValueError",
+     "evalue": "could not convert string to float: '?'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mValueError\u001b[39m                                Traceback (most recent call last)",
+      "\u001b[32m/tmp/ipykernel_3669/1374041598.py\u001b[39m in \u001b[36m?\u001b[39m\u001b[34m()\u001b[39m\n\u001b[32m     37\u001b[39m print(X)\n\u001b[32m     38\u001b[39m \n\u001b[32m     39\u001b[39m \u001b[38;5;66;03m# Create and train the decision tree classifier\u001b[39;00m\n\u001b[32m     40\u001b[39m clf = DecisionTreeClassifier(random_state=\u001b[32m42\u001b[39m)\n\u001b[32m---> \u001b[39m\u001b[32m41\u001b[39m clf.fit(X, y)\n\u001b[32m     42\u001b[39m \n\u001b[32m     43\u001b[39m \u001b[38;5;66;03m# Visualize the tree\u001b[39;00m\n\u001b[32m     44\u001b[39m plt.figure(figsize=(\u001b[32m20\u001b[39m,\u001b[32m10\u001b[39m))\n",
+      "\u001b[32m~/Documents/MLPproject/.venv/lib/python3.12/site-packages/sklearn/base.py\u001b[39m in \u001b[36m?\u001b[39m\u001b[34m(estimator, *args, **kwargs)\u001b[39m\n\u001b[32m   1361\u001b[39m                 skip_parameter_validation=(\n\u001b[32m   1362\u001b[39m                     prefer_skip_nested_validation \u001b[38;5;28;01mor\u001b[39;00m global_skip_validation\n\u001b[32m   1363\u001b[39m                 )\n\u001b[32m   1364\u001b[39m             ):\n\u001b[32m-> \u001b[39m\u001b[32m1365\u001b[39m                 \u001b[38;5;28;01mreturn\u001b[39;00m fit_method(estimator, *args, **kwargs)\n",
+      "\u001b[32m~/Documents/MLPproject/.venv/lib/python3.12/site-packages/sklearn/tree/_classes.py\u001b[39m in \u001b[36m?\u001b[39m\u001b[34m(self, X, y, sample_weight, check_input)\u001b[39m\n\u001b[32m   1020\u001b[39m         self : DecisionTreeClassifier\n\u001b[32m   1021\u001b[39m             Fitted estimator.\n\u001b[32m   1022\u001b[39m         \"\"\"\n\u001b[32m   1023\u001b[39m \n\u001b[32m-> \u001b[39m\u001b[32m1024\u001b[39m         super()._fit(\n\u001b[32m   1025\u001b[39m             X,\n\u001b[32m   1026\u001b[39m             y,\n\u001b[32m   1027\u001b[39m             sample_weight=sample_weight,\n",
+      "\u001b[32m~/Documents/MLPproject/.venv/lib/python3.12/site-packages/sklearn/tree/_classes.py\u001b[39m in \u001b[36m?\u001b[39m\u001b[34m(self, X, y, sample_weight, check_input, missing_values_in_feature_mask)\u001b[39m\n\u001b[32m    248\u001b[39m             check_X_params = dict(\n\u001b[32m    249\u001b[39m                 dtype=DTYPE, accept_sparse=\u001b[33m\"csc\"\u001b[39m, ensure_all_finite=\u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[32m    250\u001b[39m             )\n\u001b[32m    251\u001b[39m             check_y_params = dict(ensure_2d=\u001b[38;5;28;01mFalse\u001b[39;00m, dtype=\u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[32m--> \u001b[39m\u001b[32m252\u001b[39m             X, y = validate_data(\n\u001b[32m    253\u001b[39m                 self, X, y, validate_separately=(check_X_params, check_y_params)\n\u001b[32m    254\u001b[39m             )\n\u001b[32m    255\u001b[39m \n",
+      "\u001b[32m~/Documents/MLPproject/.venv/lib/python3.12/site-packages/sklearn/utils/validation.py\u001b[39m in \u001b[36m?\u001b[39m\u001b[34m(_estimator, X, y, reset, validate_separately, skip_check_array, **check_params)\u001b[39m\n\u001b[32m   2962\u001b[39m             \u001b[38;5;66;03m# :(\u001b[39;00m\n\u001b[32m   2963\u001b[39m             check_X_params, check_y_params = validate_separately\n\u001b[32m   2964\u001b[39m             \u001b[38;5;28;01mif\u001b[39;00m \u001b[33m\"estimator\"\u001b[39m \u001b[38;5;28;01mnot\u001b[39;00m \u001b[38;5;28;01min\u001b[39;00m check_X_params:\n\u001b[32m   2965\u001b[39m                 check_X_params = {**default_check_params, **check_X_params}\n\u001b[32m-> \u001b[39m\u001b[32m2966\u001b[39m             X = check_array(X, input_name=\u001b[33m\"X\"\u001b[39m, **check_X_params)\n\u001b[32m   2967\u001b[39m             \u001b[38;5;28;01mif\u001b[39;00m \u001b[33m\"estimator\"\u001b[39m \u001b[38;5;28;01mnot\u001b[39;00m \u001b[38;5;28;01min\u001b[39;00m check_y_params:\n\u001b[32m   2968\u001b[39m                 check_y_params = {**default_check_params, **check_y_params}\n\u001b[32m   2969\u001b[39m             y = check_array(y, input_name=\u001b[33m\"y\"\u001b[39m, **check_y_params)\n",
+      "\u001b[32m~/Documents/MLPproject/.venv/lib/python3.12/site-packages/sklearn/utils/validation.py\u001b[39m in \u001b[36m?\u001b[39m\u001b[34m(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_writeable, force_all_finite, ensure_all_finite, ensure_non_negative, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator, input_name)\u001b[39m\n\u001b[32m   1050\u001b[39m                         )\n\u001b[32m   1051\u001b[39m                     array = xp.astype(array, dtype, copy=\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[32m   1052\u001b[39m                 \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m   1053\u001b[39m                     array = _asarray_with_order(array, order=order, dtype=dtype, xp=xp)\n\u001b[32m-> \u001b[39m\u001b[32m1054\u001b[39m             \u001b[38;5;28;01mexcept\u001b[39;00m ComplexWarning \u001b[38;5;28;01mas\u001b[39;00m complex_warning:\n\u001b[32m   1055\u001b[39m                 raise ValueError(\n\u001b[32m   1056\u001b[39m                     \u001b[33m\"Complex data not supported\\n{}\\n\"\u001b[39m.format(array)\n\u001b[32m   1057\u001b[39m                 ) \u001b[38;5;28;01mfrom\u001b[39;00m complex_warning\n",
+      "\u001b[32m~/Documents/MLPproject/.venv/lib/python3.12/site-packages/sklearn/utils/_array_api.py\u001b[39m in \u001b[36m?\u001b[39m\u001b[34m(array, dtype, order, copy, xp, device)\u001b[39m\n\u001b[32m    753\u001b[39m         \u001b[38;5;66;03m# Use NumPy API to support order\u001b[39;00m\n\u001b[32m    754\u001b[39m         \u001b[38;5;28;01mif\u001b[39;00m copy \u001b[38;5;28;01mis\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[32m    755\u001b[39m             array = numpy.array(array, order=order, dtype=dtype)\n\u001b[32m    756\u001b[39m         \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m757\u001b[39m             array = numpy.asarray(array, order=order, dtype=dtype)\n\u001b[32m    758\u001b[39m \n\u001b[32m    759\u001b[39m         \u001b[38;5;66;03m# At this point array is a NumPy ndarray. We convert it to an array\u001b[39;00m\n\u001b[32m    760\u001b[39m         \u001b[38;5;66;03m# container that is consistent with the input's namespace.\u001b[39;00m\n",
+      "\u001b[32m~/Documents/MLPproject/.venv/lib/python3.12/site-packages/pandas/core/generic.py\u001b[39m in \u001b[36m?\u001b[39m\u001b[34m(self, dtype, copy)\u001b[39m\n\u001b[32m   2167\u001b[39m             )\n\u001b[32m   2168\u001b[39m         values = self._values\n\u001b[32m   2169\u001b[39m         \u001b[38;5;28;01mif\u001b[39;00m copy \u001b[38;5;28;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[32m   2170\u001b[39m             \u001b[38;5;66;03m# Note: branch avoids `copy=None` for NumPy 1.x support\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m2171\u001b[39m             arr = np.asarray(values, dtype=dtype)\n\u001b[32m   2172\u001b[39m         \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m   2173\u001b[39m             arr = np.array(values, dtype=dtype, copy=copy)\n\u001b[32m   2174\u001b[39m \n",
+      "\u001b[31mValueError\u001b[39m: could not convert string to float: '?'"
+>>>>>>> 2ff73d660ba62540b0a320049b9314f62843e037
+=======
      "ename": "InvalidIndexError",
      "evalue": "(slice(None, None, None), 0)",
      "output_type": "error",
@@ -25,6 +152,7 @@
       "\u001b[36mFile \u001b[39m\u001b[32m~/Documents/MLP/Projects/MLPproject/.venv/lib/python3.12/site-packages/pandas/core/frame.py:4113\u001b[39m, in \u001b[36mDataFrame.__getitem__\u001b[39m\u001b[34m(self, key)\u001b[39m\n\u001b[32m   4111\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m.columns.nlevels > \u001b[32m1\u001b[39m:\n\u001b[32m   4112\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m._getitem_multilevel(key)\n\u001b[32m-> \u001b[39m\u001b[32m4113\u001b[39m indexer = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m   4114\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m is_integer(indexer):\n\u001b[32m   4115\u001b[39m     indexer = [indexer]\n",
       "\u001b[36mFile \u001b[39m\u001b[32m~/Documents/MLP/Projects/MLPproject/.venv/lib/python3.12/site-packages/pandas/core/indexes/base.py:3818\u001b[39m, in \u001b[36mIndex.get_loc\u001b[39m\u001b[34m(self, key)\u001b[39m\n\u001b[32m   3813\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[32m   3814\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(casted_key, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m (\n\u001b[32m   3815\u001b[39m         \u001b[38;5;28misinstance\u001b[39m(casted_key, abc.Iterable)\n\u001b[32m   3816\u001b[39m         \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28many\u001b[39m(\u001b[38;5;28misinstance\u001b[39m(x, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m casted_key)\n\u001b[32m   3817\u001b[39m     ):\n\u001b[32m-> \u001b[39m\u001b[32m3818\u001b[39m         \u001b[38;5;28;01mraise\u001b[39;00m InvalidIndexError(key)\n\u001b[32m   3819\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01merr\u001b[39;00m\n\u001b[32m   3820\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m:\n\u001b[32m   3821\u001b[39m     \u001b[38;5;66;03m# If we have a listlike key, _check_indexing_error will raise\u001b[39;00m\n\u001b[32m   3822\u001b[39m     \u001b[38;5;66;03m#  InvalidIndexError. Otherwise we fall through and re-raise\u001b[39;00m\n\u001b[32m   3823\u001b[39m     \u001b[38;5;66;03m#  the TypeError.\u001b[39;00m\n",
       "\u001b[31mInvalidIndexError\u001b[39m: (slice(None, None, None), 0)"
+>>>>>>> caaa71666df3f35a02848991df9e15db55aef57c
      ]
     },
     {
@@ -61,7 +189,11 @@
     "    df_encoded[column] = label_encoder.fit_transform(df_encoded[column])\n",
     "\n",
     "# Now properly separate features and target\n",
+<<<<<<< HEAD
+    "X = df_encoded.drop(columns=['income', 'native.country', 'education','fnlwgt'])\n",
+=======
     "X = df_encoded.drop(columns=['income', 'native.country', 'education'])\n",
+>>>>>>> 2ff73d660ba62540b0a320049b9314f62843e037
     "y = df_encoded['income']\n",
     "\n",
     "# Split the data\n",
@@ -87,8 +219,28 @@
     "        if(j==0):\n",
     "            ax.set_ylabel(f'$x_{{{i}}}$', fontsize=22)\n",
     "\n",
+<<<<<<< HEAD
+    "# Print feature importances\n",
+    "importances = pd.DataFrame({\n",
+    "    'feature': X.columns,\n",
+    "    'importance': clf.feature_importances_\n",
+    "})\n",
+    "print(\"\\nFeature Importances:\")\n",
+    "print(importances.sort_values('importance', ascending=False))\n",
+<<<<<<< HEAD
+    "\n"
+=======
+    "\n",
+    "# Example prediction\n",
+    "print(\"\\nPrediction for a new sample:\")\n",
+    "new_sample = pd.DataFrame([[350, 0, 0, 0.09]], columns=X.columns)  # Force=300, Coating=Yes, Defects=No, Moisture=0.05\n",
+    "prediction = clf.predict(new_sample)\n",
+    "print(f\"Will the rod break? {'Yes' if prediction[0] == 1 else 'No'}\")"
+>>>>>>> 2ff73d660ba62540b0a320049b9314f62843e037
+=======
     "        ax.grid(True)\n",
     "        plt_num +=1\n"
+>>>>>>> caaa71666df3f35a02848991df9e15db55aef57c
    ]
   }
  ],

test.ipynb

@@ -0,0 +1,35 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e144ae0f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  }
+ ],
+ "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": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}