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

Analysis.ipynb

@@ -6,12 +6,12 @@
    "metadata": {},
    "source": [
     "### Creates a correlation matrix\n",
-    "We should probably remove or combine some features"
+    "This used to see if we should remove or combine some features"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "557ed2b5",
    "metadata": {},
    "outputs": [
@@ -30,27 +30,25 @@
      "output_type": "stream",
      "text": [
       "<class 'pandas.core.frame.DataFrame'>\n",
-      "RangeIndex: 32561 entries, 0 to 32560\n",
-      "Data columns (total 15 columns):\n",
-      " #   Column          Non-Null Count  Dtype \n",
-      "---  ------          --------------  ----- \n",
-      " 0   age             32561 non-null  int64 \n",
-      " 1   workclass       32561 non-null  object\n",
-      " 2   fnlwgt          32561 non-null  int64 \n",
-      " 3   education       32561 non-null  object\n",
-      " 4   education.num   32561 non-null  int64 \n",
-      " 5   marital.status  32561 non-null  object\n",
-      " 6   occupation      32561 non-null  object\n",
-      " 7   relationship    32561 non-null  object\n",
-      " 8   race            32561 non-null  object\n",
-      " 9   sex             32561 non-null  object\n",
-      " 10  capital.gain    32561 non-null  int64 \n",
-      " 11  capital.loss    32561 non-null  int64 \n",
-      " 12  hours.per.week  32561 non-null  int64 \n",
-      " 13  native.country  32561 non-null  object\n",
-      " 14  income          32561 non-null  object\n",
-      "dtypes: int64(6), object(9)\n",
-      "memory usage: 3.7+ MB\n"
+      "Index: 30162 entries, 1 to 32560\n",
+      "Data columns (total 13 columns):\n",
+      " #   Column          Non-Null Count  Dtype\n",
+      "---  ------          --------------  -----\n",
+      " 0   age             30162 non-null  int64\n",
+      " 1   workclass       30162 non-null  int64\n",
+      " 2   education.num   30162 non-null  int64\n",
+      " 3   marital.status  30162 non-null  int64\n",
+      " 4   occupation      30162 non-null  int64\n",
+      " 5   relationship    30162 non-null  int64\n",
+      " 6   race            30162 non-null  int64\n",
+      " 7   sex             30162 non-null  int64\n",
+      " 8   capital.gain    30162 non-null  int64\n",
+      " 9   capital.loss    30162 non-null  int64\n",
+      " 10  hours.per.week  30162 non-null  int64\n",
+      " 11  native.country  30162 non-null  int64\n",
+      " 12  income          30162 non-null  int64\n",
+      "dtypes: int64(13)\n",
+      "memory usage: 3.2 MB\n"
      ]
     }
    ],
@@ -91,8 +89,8 @@
     "plt.show()\n",
     "\n",
     "#df_encoded.head(10)\n",
-    "df.info()\n",
-    "\n"
+    "df_encoded.info()\n",
+    "#df.head(20)\n"
    ]
   },
   {