refactoring

HowBadIsMyBatch.ipynb

@@ -128,11 +128,7 @@
     "    \n",
     "    def __init__(self, dataFrame : pd.DataFrame):\n",
     "        self.dataFrame = dataFrame        \n",
-    "        self._convertColumnOfDataFrameToNumeric('DIED')\n",
-    "        self._convertColumnOfDataFrameToNumeric('L_THREAT')\n",
-    "        self._convertColumnOfDataFrameToNumeric('DISABLE')\n",
-    "        self._convertColumnOfDataFrameToNumeric('HOSPITAL')\n",
-    "        self._convertColumnOfDataFrameToNumeric('ER_VISIT')\n",
+    "        self._convertColumnsOfDataFrameToNumerics(['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT'])\n",
     "\n",
     "    def createBatchCodeTable(self):\n",
     "        batchCodeTable = self.dataFrame.groupby('VAX_LOT').agg(\n",
@@ -193,6 +189,10 @@
     "        manufacturerByBatchCodeTable = manufacturerByBatchCodeTable.drop_duplicates(subset = ['VAX_LOT'])\n",
     "        return manufacturerByBatchCodeTable.set_index('VAX_LOT')\n",
     "\n",
+    "    def _convertColumnsOfDataFrameToNumerics(self, columns):\n",
+    "        for column in columns:\n",
+    "            self._convertColumnOfDataFrameToNumeric(column)\n",
+    "\n",
     "    def _convertColumnOfDataFrameToNumeric(self, column):\n",
     "        self.dataFrame[column] = np.where(self.dataFrame[column] == 'Y', 1, 0)\n",
     "\n",

help.txt

@@ -1,5 +1,8 @@
 jupyter notebook
 
+get VAERS data:
+- download data (e.g. 2022VAERSData.zip) from https://vaers.hhs.gov/data/datasets.html and save and unzip in VAERS folder
+
 FK-TODO:
 - https://www.howbadismybatch.com/firstsecond.html nachprogrammieren
 - VAX_LOT-Spalte normalisieren, d.h. mindestens toUpperCase() darauf anwenden