Small bug fixes

Analysis.ipynb

@@ -59,27 +59,22 @@
     "from sklearn.preprocessing import LabelEncoder\n",
     "import seaborn as sns\n",
     "\n",
-    "\n",
     "df = pd.read_csv('./Datasets/adult.csv', comment = '#')\n",
     "\n",
-    "\n",
     "# First, create a copy of the dataframe to avoid modifying the original\n",
     "df_encoded = df.copy()\n",
     "df_encoded.drop(['fnlwgt', 'education'], axis=1, inplace=True)\n",
     "\n",
-    "\n",
     "# drop all rows that contain '?'\n",
-    "for column in df_encoded.columns:\n",
-    "    df_encoded = df_encoded[df_encoded[column] != '?']\n",
+    "df_encoded = df_encoded[(df_encoded != '?').all(axis=1)]\n",
     "\n",
     "# Apply label encoding to categorical columns\n",
-    "label_encoder = LabelEncoder()\n",
     "categorical_columns = ['workclass', 'marital.status', 'occupation', \n",
     "                      'relationship', 'race', 'sex', 'native.country', 'income']\n",
     "\n",
     "for column in categorical_columns:\n",
-    "    df_encoded[column] = label_encoder.fit_transform(df_encoded[column])\n",
-    "\n",
+    "    le = LabelEncoder()\n",
+    "    df_encoded[column] = le.fit_transform(df_encoded[column])\n",
     "\n",
     "matrix = df_encoded.corr()\n",
     "\n",