From 6e46087bc1598e59f49102f01ed9376cc20b4f55 Mon Sep 17 00:00:00 2001
From: frankknoll <Knoll_Frank@web.de>
Date: Sun, 6 Feb 2022 12:46:54 +0100
Subject: [PATCH] refactoring

---
 HowBadIsMyBatch.ipynb | 50 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 49 insertions(+), 1 deletion(-)

diff --git a/HowBadIsMyBatch.ipynb b/HowBadIsMyBatch.ipynb
index 47f8c2a3978..a942762e787 100644
--- a/HowBadIsMyBatch.ipynb
+++ b/HowBadIsMyBatch.ipynb
@@ -24,6 +24,10 @@
     "class DataFrameNormalizer:\n",
     "    \n",
     "    @staticmethod\n",
+    "    def convertVAX_LOTColumnToUpperCase(dataFrame):\n",
+    "        dataFrame['VAX_LOT'] = dataFrame['VAX_LOT'].str.upper()\n",
+    "\n",
+    "    @staticmethod\n",
     "    def convertColumnsOfDataFrameToNumerics(dataFrame, columns):\n",
     "        for column in columns:\n",
     "            DataFrameNormalizer._convertColumnOfDataFrameToNumeric(dataFrame, column)\n",
@@ -73,10 +77,12 @@
     "        return VAERSDATA\n",
     "\n",
     "    def _readVAERSVAX(self, file):\n",
-    "        return self._read_csv(\n",
+    "        VAERSVAX = self._read_csv(\n",
     "            file = file,\n",
     "            usecols = ['VAERS_ID', 'VAX_DOSE_SERIES', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT'],\n",
     "            dtype = {\"VAX_DOSE_SERIES\": \"string\"})\n",
+    "        DataFrameNormalizer.convertVAX_LOTColumnToUpperCase(VAERSVAX)\n",
+    "        return VAERSVAX\n",
     "\n",
     "    def _read_csv(self, file, **kwargs):\n",
     "        return pd.read_csv(\n",
@@ -306,6 +312,48 @@
     "import unittest"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ccb9838d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pandas.testing import assert_frame_equal\n",
+    "\n",
+    "class DataFrameNormalizerTest(unittest.TestCase):\n",
+    "\n",
+    "    def test_convertVAX_LOTColumnToUpperCase(self):\n",
+    "        # Given\n",
+    "        dataFrame = self.createDataFrame(\n",
+    "            columns = ['VAX_LOT'],\n",
+    "            data = [  ['037K20A'],\n",
+    "                      ['025l20A'],\n",
+    "                      ['025L20A']],\n",
+    "            index = [\n",
+    "                \"0916600\",\n",
+    "                \"0916601\",\n",
+    "                \"1996874\"])\n",
+    "            \n",
+    "        # When\n",
+    "        DataFrameNormalizer.convertVAX_LOTColumnToUpperCase(dataFrame)\n",
+    "        \n",
+    "        # Then\n",
+    "        dataFrameExpected = self.createDataFrame(\n",
+    "            columns = ['VAX_LOT'],\n",
+    "            data = [  ['037K20A'],\n",
+    "                      ['025L20A'],\n",
+    "                      ['025L20A']],\n",
+    "            index = [\n",
+    "                \"0916600\",\n",
+    "                \"0916601\",\n",
+    "                \"1996874\"])\n",
+    "        assert_frame_equal(dataFrame, dataFrameExpected, check_dtype = False)\n",
+    "\n",
+    "    def createDataFrame(self, index, columns, data, dtypes = {}):\n",
+    "        return pd.DataFrame(index = index, columns = columns, data = data).astype(dtypes)\n"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,