Add additional example for Lec3

lec3-3-results.ipynb

@@ -11,7 +11,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 2,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -65,7 +65,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 20,
+      "execution_count": 3,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/",
@@ -273,7 +273,7 @@
               "cardio         0.000000    1.000000    1.000000  "
             ]
           },
-          "execution_count": 20,
+          "execution_count": 3,
           "metadata": {},
           "output_type": "execute_result"
         }
@@ -293,7 +293,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 21,
+      "execution_count": 4,
       "metadata": {
         "id": "1BXW8--WKI3b"
       },
@@ -319,7 +319,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 22,
+      "execution_count": 5,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -348,7 +348,7 @@
               "  <td>Dependent Variable:</td>      <td>cardio</td>      <td>Pseudo R-squared:</td>    <td>0.194</td>  \n",
               "</tr>\n",
               "<tr>\n",
-              "         <td>Date:</td>        <td>2025-04-24 09:36</td>       <td>AIC:</td>        <td>66539.7930</td>\n",
+              "         <td>Date:</td>        <td>2025-04-24 12:35</td>       <td>AIC:</td>        <td>66539.7930</td>\n",
               "</tr>\n",
               "<tr>\n",
               "   <td>No. Observations:</td>        <td>59500</td>            <td>BIC:</td>        <td>66647.7178</td>\n",
@@ -417,7 +417,7 @@
               "\\hline\n",
               "Model:              & Logit            & Method:           & MLE         \\\\\n",
               "Dependent Variable: & cardio           & Pseudo R-squared: & 0.194       \\\\\n",
-              "Date:               & 2025-04-24 09:36 & AIC:              & 66539.7930  \\\\\n",
+              "Date:               & 2025-04-24 12:35 & AIC:              & 66539.7930  \\\\\n",
               "No. Observations:   & 59500            & BIC:              & 66647.7178  \\\\\n",
               "Df Model:           & 11               & Log-Likelihood:   & -33258.     \\\\\n",
               "Df Residuals:       & 59488            & LL-Null:          & -41242.     \\\\\n",
@@ -457,7 +457,7 @@
               "=================================================================\n",
               "Model:              Logit            Method:           MLE       \n",
               "Dependent Variable: cardio           Pseudo R-squared: 0.194     \n",
-              "Date:               2025-04-24 09:36 AIC:              66539.7930\n",
+              "Date:               2025-04-24 12:35 AIC:              66539.7930\n",
               "No. Observations:   59500            BIC:              66647.7178\n",
               "Df Model:           11               Log-Likelihood:   -33258.   \n",
               "Df Residuals:       59488            LL-Null:          -41242.   \n",
@@ -483,7 +483,7 @@
               "\"\"\""
             ]
           },
-          "execution_count": 22,
+          "execution_count": 5,
           "metadata": {},
           "output_type": "execute_result"
         }
@@ -507,7 +507,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 23,
+      "execution_count": 6,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -534,7 +534,7 @@
               "dtype: float64"
             ]
           },
-          "execution_count": 23,
+          "execution_count": 6,
           "metadata": {},
           "output_type": "execute_result"
         }
@@ -545,6 +545,87 @@
         "np.exp(log_result.params).sort_values(ascending=False)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Вычисление среднего квадратичного отклонения значений признаков"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "age             6.758844\n",
+              "gender          0.476715\n",
+              "height          7.821231\n",
+              "weight         13.472656\n",
+              "ap_hi          16.366878\n",
+              "ap_lo           9.071287\n",
+              "cholesterol     0.682134\n",
+              "gluc            0.571848\n",
+              "smoke           0.284051\n",
+              "alco            0.225918\n",
+              "active          0.397418\n",
+              "dtype: float64"
+            ]
+          },
+          "execution_count": 7,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "np.std(X_train, 0)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "#### Вычисление значимости признаков относительно текущей модели\n",
+        "\n",
+        "Признак const был добавлен искусственно и должен быть исключен из рассмотрения\n",
+        "\n",
+        "Признак gender имеет небольшую статистическую значимость (P>|z| = 0.6515, много больше 5 %) и поэтому исключается из рассмотрения"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 14,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "ap_hi          0.839295\n",
+              "age            0.348905\n",
+              "cholesterol    0.337191\n",
+              "ap_lo          0.189439\n",
+              "weight         0.171091\n",
+              "active         0.087144\n",
+              "gluc           0.070209\n",
+              "smoke          0.047513\n",
+              "alco           0.043046\n",
+              "height         0.034657\n",
+              "dtype: float64"
+            ]
+          },
+          "execution_count": 14,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "coefs = log_result.params.drop(labels=[\"const\",\"gender\"])\n",
+        "stdv = np.std(X_train, 0).drop(labels=\"gender\")\n",
+        "abs(coefs * stdv).sort_values(ascending=False)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -691,7 +772,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 40,
+      "execution_count": null,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/",
@@ -929,7 +1010,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 46,
+      "execution_count": null,
       "metadata": {},
       "outputs": [
         {