minor updates on notebooks 05 and 06

notebooks/05_dataset_analysis_cleaning.ipynb

@@ -737,42 +737,6 @@
      "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "text/plain": [
-       "count    299.000000\n",
-       "mean      75.746154\n",
-       "std      254.425358\n",
-       "min        1.200000\n",
-       "25%        6.200000\n",
-       "50%        6.200000\n",
-       "75%        6.200000\n",
-       "max      999.900000\n",
-       "Name: VISIB, dtype: float64"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "text/plain": [
-       "count    278.000000\n",
-       "mean       5.935971\n",
-       "std        0.672031\n",
-       "min        1.200000\n",
-       "25%        6.100000\n",
-       "50%        6.200000\n",
-       "75%        6.200000\n",
-       "max        6.800000\n",
-       "Name: VISIB, dtype: float64"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -3011,6 +2975,7 @@
    ],
    "source": [
     "# Kolmogorov-Smirnov test\n",
+    "# null hypothesis: no difference between the two distributions\n",
     "ks_statistic, p_value = kstest(humans.Height, \"norm\")\n",
     "ks_statistic, p_value"
    ]
@@ -4515,7 +4480,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 65,
+   "execution_count": 98,
    "id": "708dbcd3-d704-4ea7-9db8-735aa15b4de8",
    "metadata": {},
    "outputs": [
@@ -4525,7 +4490,7 @@
        "768"
       ]
      },
-     "execution_count": 65,
+     "execution_count": 98,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -4535,7 +4500,7 @@
        "743"
       ]
      },
-     "execution_count": 65,
+     "execution_count": 98,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -4838,7 +4803,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 102,
    "id": "e8f8c6bd-9e38-4cb1-b2d9-2fe0739bfcc8",
    "metadata": {},
    "outputs": [
@@ -4981,7 +4946,7 @@
        "[6342 rows x 5 columns]"
       ]
      },
-     "execution_count": 70,
+     "execution_count": 102,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -6320,7 +6285,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 86,
+   "execution_count": 99,
    "id": "a37a9e62-31c8-49cb-9fd4-d352e9a62f51",
    "metadata": {},
    "outputs": [
@@ -6439,7 +6404,7 @@
        "[200 rows x 3 columns]"
       ]
      },
-     "execution_count": 86,
+     "execution_count": 99,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -6567,7 +6532,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 89,
+   "execution_count": 100,
    "id": "70500270-a048-48b5-8e36-27da5923e384",
    "metadata": {},
    "outputs": [
@@ -6585,7 +6550,7 @@
        "0.027756186064182953"
       ]
      },
-     "execution_count": 89,
+     "execution_count": 100,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -6645,17 +6610,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 92,
+   "execution_count": 101,
    "id": "accc963b-a11d-44b4-91ce-e7f0297ca7c0",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/eva/.local/share/virtualenvs/data-engineering-analytics-notebooks-Qx0adyYX/lib64/python3.9/site-packages/sklearn/base.py:441: UserWarning: X does not have valid feature names, but KNeighborsRegressor was fitted with feature names\n",
+      "  warnings.warn(\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
        "0.9743878175626131"
       ]
      },
-     "execution_count": 92,
+     "execution_count": 101,
      "metadata": {},
      "output_type": "execute_result"
     }