small changes

Analysis.ipynb

@@ -5,12 +5,13 @@
    "id": "8b66d061",
    "metadata": {},
    "source": [
-    "### Creates a correlation matrix"
+    "### Creates a correlation matrix\n",
+    "We should probably remove or combine some features"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": null,
    "id": "557ed2b5",
    "metadata": {},
    "outputs": [
@@ -263,7 +264,7 @@
        "12       1  "
       ]
      },
-     "execution_count": 28,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -304,8 +305,8 @@
     "plt.title(\"Correlation Heatmap\")\n",
     "plt.show()\n",
     "\n",
-    "df_encoded.head(10)\n",
+    "#df_encoded.head(10)\n",
-    "#df.head()\n"
+    "\n"
    ]
   },
   {
@@ -314,7 +315,7 @@
    "metadata": {},
    "source": [
     "### Creates a pairplot\n",
-    "This demonstrates that We need a model that is appropriate for discrete data (Decision Tree, Random Forest, Naive Bayes)"
+    "This demonstrates that we need a model that is appropriate for discrete data (Decision Tree, Random Forest, Naive Bayes)"
    ]
   },
   {

Decision_tree.ipynb

@@ -1,14 +1,20 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "946e852d",
+   "metadata": {},
+   "source": []
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 20,
    "id": "0952f099",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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 truncated
+      "image/png": "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 truncated
       "text/plain": [
        "<Figure size 1200x1200 with 1 Axes>"
       ]
@@ -16,11 +22,30 @@
      "metadata": {},
      "output_type": "display_data"
     },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAhkAAAHHCAYAAAASxkpJAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAUXtJREFUeJzt3XlYVNX/B/D3DDDDOsOibIqIoiiuaX2NzC0RRCxMSk1LcE1Dy90sF8SKwn1LK0vQNLNFU9AUxV0yJcmdFDFNRU2FEZT9/v7wx80RHJnLjAP4fvnc53HuPffcc3kQPn4+59wrEwRBABEREZGByU09ACIiIqqZGGQQERGRUTDIICIiIqNgkEFERERGwSCDiIiIjIJBBhERERkFgwwiIiIyCgYZREREZBQMMoiIiMgoGGQQPSFnz55FQEAA1Go1ZDIZNm7caND+L1y4AJlMhtjYWIP2W5117twZnTt3NvUwiJ5aDDLoqZKeno63334bDRo0gKWlJVQqFdq3b4+FCxfi3r17Rr12WFgYjh8/jo8//hirV6/Gs88+a9TrPUnh4eGQyWRQqVTlfh3Pnj0LmUwGmUyGOXPm6N3/lStXEBkZidTUVAOMloieFHNTD4DoSUlISMDrr78OpVKJgQMHonnz5igoKMD+/fsxceJEnDx5El9++aVRrn3v3j0kJyfjww8/xKhRo4xyDU9PT9y7dw8WFhZG6f9xzM3NcffuXWzevBl9+vTROrZmzRpYWloiLy9PUt9XrlzBzJkzUb9+fbRu3brC523fvl3S9YjIMBhk0FMhIyMD/fr1g6enJ5KSkuDm5iYei4iIwLlz55CQkGC069+4cQMAYG9vb7RryGQyWFpaGq3/x1EqlWjfvj2+++67MkHG2rVrERwcjJ9++umJjOXu3buwtraGQqF4ItcjovKxXEJPhZiYGOTk5ODrr7/WCjBKeXt747333hM/FxUVYdasWWjYsCGUSiXq16+PDz74APn5+Vrn1a9fHz179sT+/fvxv//9D5aWlmjQoAFWrVoltomMjISnpycAYOLEiZDJZKhfvz6A+2WG0r8/KDIyEjKZTGtfYmIiXnzxRdjb28PW1hY+Pj744IMPxOOPmpORlJSEDh06wMbGBvb29ggJCcHp06fLvd65c+cQHh4Oe3t7qNVqDBo0CHfv3n30F/Yh/fv3x9atW5GVlSXuO3z4MM6ePYv+/fuXaX/r1i1MmDABLVq0gK2tLVQqFYKCgvDnn3+KbXbv3o3nnnsOADBo0CCx7FJ6n507d0bz5s2RkpKCjh07wtraWvy6PDwnIywsDJaWlmXuPzAwEA4ODrhy5UqF75WIHo9BBj0VNm/ejAYNGuCFF16oUPuhQ4di+vTpaNOmDebPn49OnTohOjoa/fr1K9P23LlzeO2119CtWzfMnTsXDg4OCA8Px8mTJwEAvXv3xvz58wEAb7zxBlavXo0FCxboNf6TJ0+iZ8+eyM/PR1RUFObOnYtXXnkFBw4c0Hnejh07EBgYiOvXryMyMhLjxo3DwYMH0b59e1y4cKFM+z59+uDOnTuIjo5Gnz59EBsbi5kzZ1Z4nL1794ZMJsPPP/8s7lu7di2aNGmCNm3alGl//vx5bNy4ET179sS8efMwceJEHD9+HJ06dRJ/4Tdt2hRRUVEAgOHDh2P16tVYvXo1OnbsKPZz8+ZNBAUFoXXr1liwYAG6dOlS7vgWLlyI2rVrIywsDMXFxQCAL774Atu3b8fixYvh7u5e4XslogoQiGq47OxsAYAQEhJSofapqakCAGHo0KFa+ydMmCAAEJKSksR9np6eAgBh79694r7r168LSqVSGD9+vLgvIyNDACDMnj1bq8+wsDDB09OzzBhmzJghPPjPc/78+QIA4caNG48cd+k1Vq5cKe5r3bq14OzsLNy8eVPc9+effwpyuVwYOHBgmesNHjxYq89XX31VcHJyeuQ1H7wPGxsbQRAE4bXXXhO6du0qCIIgFBcXC66ursLMmTPL/Rrk5eUJxcXFZe5DqVQKUVFR4r7Dhw+XubdSnTp1EgAIy5cvL/dYp06dtPZt27ZNACB89NFHwvnz5wVbW1uhV69ej71HItIfMxlU42k0GgCAnZ1dhdpv2bIFADBu3Dit/ePHjweAMnM3fH190aFDB/Fz7dq14ePjg/Pnz0se88NK53L88ssvKCkpqdA5V69eRWpqKsLDw+Ho6Cjub9myJbp16ybe54NGjBih9blDhw64efOm+DWsiP79+2P37t3IzMxEUlISMjMzyy2VAPfnccjl938MFRcX4+bNm2Ip6I8//qjwNZVKJQYNGlShtgEBAXj77bcRFRWF3r17w9LSEl988UWFr0VEFccgg2o8lUoFALhz506F2v/999+Qy+Xw9vbW2u/q6gp7e3v8/fffWvvr1atXpg8HBwfcvn1b4ojL6tu3L9q3b4+hQ4fCxcUF/fr1w/r163UGHKXj9PHxKXOsadOm+Pfff5Gbm6u1/+F7cXBwAAC97qVHjx6ws7PD999/jzVr1uC5554r87UsVVJSgvnz56NRo0ZQKpWoVasWateujWPHjiE7O7vC16xTp45ekzznzJkDR0dHpKamYtGiRXB2dq7wuURUcQwyqMZTqVRwd3fHiRMn9Drv4YmXj2JmZlbufkEQJF+jdL5AKSsrK+zduxc7duzAW2+9hWPHjqFv377o1q1bmbaVUZl7KaVUKtG7d2/ExcVhw4YNj8xiAMAnn3yCcePGoWPHjvj222+xbds2JCYmolmzZhXO2AD3vz76OHr0KK5fvw4AOH78uF7nElHFMcigp0LPnj2Rnp6O5OTkx7b19PRESUkJzp49q7X/2rVryMrKEleKGIKDg4PWSoxSD2dLAEAul6Nr166YN28eTp06hY8//hhJSUnYtWtXuX2XjjMtLa3MsTNnzqBWrVqwsbGp3A08Qv/+/XH06FHcuXOn3MmypX788Ud06dIFX3/9Nfr164eAgAD4+/uX+ZpUNOCriNzcXAwaNAi+vr4YPnw4YmJicPjwYYP1T0T/YZBBT4VJkybBxsYGQ4cOxbVr18ocT09Px8KFCwHcT/cDKLMCZN68eQCA4OBgg42rYcOGyM7OxrFjx8R9V69exYYNG7Ta3bp1q8y5pQ+lenhZbSk3Nze0bt0acXFxWr+0T5w4ge3bt4v3aQxdunTBrFmzsGTJEri6uj6ynZmZWZksyQ8//IDLly9r7SsNhsoLyPQ1efJkXLx4EXFxcZg3bx7q16+PsLCwR34diUg6PoyLngoNGzbE2rVr0bdvXzRt2lTriZ8HDx7EDz/8gPDwcABAq1atEBYWhi+//BJZWVno1KkTfv/9d8TFxaFXr16PXB4pRb9+/TB58mS8+uqrePfdd3H37l0sW7YMjRs31pr4GBUVhb179yI4OBienp64fv06Pv/8c9StWxcvvvjiI/ufPXs2goKC4OfnhyFDhuDevXtYvHgx1Go1IiMjDXYfD5PL5Zg6depj2/Xs2RNRUVEYNGgQXnjhBRw/fhxr1qxBgwYNtNo1bNgQ9vb2WL58Oezs7GBjY4N27drBy8tLr3ElJSXh888/x4wZM8QltStXrkTnzp0xbdo0xMTE6NUfET2GiVe3ED1Rf/31lzBs2DChfv36gkKhEOzs7IT27dsLixcvFvLy8sR2hYWFwsyZMwUvLy/BwsJC8PDwEKZMmaLVRhDuL2ENDg4uc52Hl04+agmrIAjC9u3bhebNmwsKhULw8fERvv322zJLWHfu3CmEhIQI7u7ugkKhENzd3YU33nhD+Ouvv8pc4+Flnjt27BDat28vWFlZCSqVSnj55ZeFU6dOabUpvd7DS2RXrlwpABAyMjIe+TUVBO0lrI/yqCWs48ePF9zc3AQrKyuhffv2QnJycrlLT3/55RfB19dXMDc317rPTp06Cc2aNSv3mg/2o9FoBE9PT6FNmzZCYWGhVruxY8cKcrlcSE5O1nkPRKQfmSDoMaOLiIiIqII4J4OIiIiMgkEGERERGQWDDCIiIjIKBhlERERkFAwyiIiIyCgYZBAREZFR8GFc5SgpKcGVK1dgZ2dn0McZExHRkyEIAu7cuQN3d3fxTb+GlpeXh4KCAoP0pVAoYGlpaZC+qhIGGeW4cuUKPDw8TD0MIiKqpEuXLqFu3boG7zcvLw9Wdk5A0V2D9Ofq6oqMjIwaF2gwyCiHnZ0dAEDhGwaZWcVfH01UnVzcPcfUQyAymjsaDby9PMSf54ZWUFAAFN2F0jcMqOzvieICZJ6KQ0FBAYOMp0FpiURmpmCQQTWWSqUy9RCIjM7oJW9zy0r/nhBkNXd6JIMMIiIiqWQAKhvI1OCpfwwyiIiIpJLJ72+V7aOGqrl3RkRERCbFTAYREZFUMpkByiU1t17CIIOIiEgqlkt0qrl3RkRERCbFTAYREZFULJfoxCCDiIhIMgOUS2pwUaHm3hkRERGZFDMZREREUrFcohODDCIiIqm4ukSnmntnREREZFLMZBAREUnFcolODDKIiIikYrlEJwYZREREUjGToVPNDZ+IiIjIpJjJICIikorlEp0YZBAREUklkxkgyGC5hIiIiEgvzGQQERFJJZfd3yrbRw3FIIOIiEgqzsnQqebeGREREZkUMxlERERS8TkZOjHIICIikorlEp1q7p0RERGRSTGTQUREJBXLJToxyCAiIpKK5RKdGGQQERFJxUyGTjU3fCIiIiKTYiaDiIhIKpZLdGKQQUREJBXLJTrV3PCJiIiITIqZDCIiIskMUC6pwf/fZ5BBREQkFcslOtXc8ImIiIhMipkMIiIiqWQyA6wuqbmZDAYZREREUnEJq041986IiIjIpJjJICIikooTP3VikEFERCQVyyU6McggIiKSipkMnWpu+ERERFQDLVu2DC1btoRKpYJKpYKfnx+2bt0qHu/cuTNkMpnWNmLECK0+Ll68iODgYFhbW8PZ2RkTJ05EUVGRVpvdu3eLine truncated
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Mean Squared Error: 0.1921100613293552\n"
+      "Classification Report:\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "        Poor       0.87      0.87      0.87      4524\n",
+      "        Rich       0.62      0.62      0.62      1509\n",
+      "\n",
+      "    accuracy                           0.81      6033\n",
+      "   macro avg       0.74      0.75      0.74      6033\n",
+      "weighted avg       0.81      0.81      0.81      6033\n",
+      "\n"
      ]
     }
    ],
@@ -33,7 +58,9 @@
     "from sklearn.tree import DecisionTreeClassifier, plot_tree\n",
     "from sklearn.preprocessing import LabelEncoder\n",
     "from sklearn.metrics import mean_squared_error, mean_absolute_error , r2_score\n",
+    "from sklearn.metrics import classification_report, confusion_matrix, ConfusionMatrixDisplay\n",
     "\n",
+    "# Load dataset\n",
     "df = pd.read_csv('./Datasets/adult.csv', comment = '#')\n",
     "\n",
     "# First, create a copy of the dataframe to avoid modifying the original\n",
@@ -74,20 +101,29 @@
     "plt.figure(figsize=(12, 12))\n",
     "plot_tree(\n",
     "    model.named_steps['full_dt_classifier'],\n",
-    "    feature_names=df.columns[:-1],\n",
+    "    feature_names=X.columns,\n",
     "    class_names=[\"Poor\", \"Rich\"],\n",
     "    filled=True,\n",
     "    rounded=True,\n",
-    "    max_depth=10,       # Keep tree shallow for readability\n",
+    "    max_depth=5,       # Keep tree shallow for readability\n",
-    "    fontsize=1,\n",
+    "    fontsize=3,\n",
     "    precision=2        # Limit decimals\n",
     ")\n",
     "\n",
-    "#plt.savefig('decision_tree.pdf', format='pdf', dpi=300)\n",
+    "plt.savefig('decision_tree.pdf', format='pdf', dpi=300)\n",
     "plt.show()\n",
     "\n",
-    "mse = mean_squared_error(y_val, y_pred)\n",
+    "#mse = mean_squared_error(y_val, y_pred)\n",
-    "print(f'Mean Squared Error: {mse}')"
+    "#print(f'Mean Squared Error: {mse}')\n",
+    "\n",
+    "CM = confusion_matrix(y_val, y_pred)\n",
+    "disp = ConfusionMatrixDisplay(confusion_matrix=CM, display_labels=[\"Poor\", \"Rich\"])\n",
+    "disp.plot(cmap=\"Blues\")\n",
+    "plt.title(\"Confusion Matrix\")\n",
+    "plt.show()  \n",
+    "\n",
+    "print(\"Classification Report:\")\n",
+    "print(classification_report(y_val, y_pred, target_names=[\"Poor\", \"Rich\"]))"
    ]
   },
   {