refactoring

HowBadIsMyBatch.ipynb

@@ -17,34 +17,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "233bc590",
+   "id": "7b5d6df0",
    "metadata": {},
    "outputs": [],
    "source": [
-    "def createDataFrame(dataDir, manufacturer):\n",
+    "def _createDataFrame(vaersDescrs, manufacturer):\n",
-    "    def read_csv(file, usecols):\n",
-    "        return pd.read_csv(file, index_col = 'VAERS_ID', encoding = 'latin1', low_memory = False, usecols = usecols)\n",
-    "\n",
-    "    def createDataFrameForYear(year):\n",
-    "        folder = dataDir + \"/\" + year + \"VAERSData/\"\n",
-    "        return pd.merge(\n",
-    "            read_csv(folder + year + \"VAERSDATA.csv\", ['VAERS_ID', 'DIED', 'L_THREAT', 'DISABLE']),\n",
-    "            read_csv(folder + year + \"VAERSVAX.csv\", ['VAERS_ID', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT']),\n",
-    "            left_index = True,\n",
-    "            right_index = True)\n",
-    "\n",
-    "    df = pd.concat([createDataFrameForYear(\"2021\"), createDataFrameForYear(\"2022\")])\n",
-    "    return df[(df[\"VAX_TYPE\"] == \"COVID19\") & (df[\"VAX_MANU\"] == manufacturer)]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "dea776cd",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def createDataFrame2(vaersDescrs, manufacturer):\n",
     "    def vaersDescr2Vaers(vaersDescr):\n",
     "        return pd.merge(vaersDescr['VAERSDATA'], vaersDescr['VAERSVAX'], left_index = True, right_index = True)\n",
     "\n",
@@ -55,6 +32,29 @@
     "    return df[(df[\"VAX_TYPE\"] == \"COVID19\") & (df[\"VAX_MANU\"] == manufacturer)]"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "233bc590",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def read_csv(file, usecols):\n",
+    "    return pd.read_csv(file, index_col = 'VAERS_ID', encoding = 'latin1', low_memory = False, usecols = usecols)\n",
+    "\n",
+    "def readVaersDescr(dataDir, year):\n",
+    "    folder = dataDir + \"/\" + year + \"VAERSData/\"\n",
+    "    return {\n",
+    "        'VAERSDATA': read_csv(folder + year + \"VAERSDATA.csv\", ['VAERS_ID', 'DIED', 'L_THREAT', 'DISABLE']),\n",
+    "        'VAERSVAX': read_csv(folder + year + \"VAERSVAX.csv\", ['VAERS_ID', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT'])\n",
+    "        }\n",
+    "\n",
+    "def createDataFrame(dataDir, manufacturer):\n",
+    "    return _createDataFrame(\n",
+    "        [readVaersDescr(dataDir, \"2021\"), readVaersDescr(dataDir, \"2022\")],\n",
+    "        manufacturer)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -97,7 +97,6 @@
     "class BatchCodeTableTest(unittest.TestCase):\n",
     "\n",
     "    def test_createBatchCodeTable2(self):\n",
-    "        # Given\n",
     "        vaersData2021 = pd.DataFrame(columns = ['DIED', 'L_THREAT', 'DISABLE'], index = ['0916600', '0916601'])\n",
     "        vaersData2021.loc['0916600'] = pd.Series({'DIED': 'Y',    'L_THREAT': np.NaN, 'DISABLE': np.NaN})\n",
     "        vaersData2021.loc['0916601'] = pd.Series({'DIED': np.NaN, 'L_THREAT': np.NaN, 'DISABLE': 'Y'})\n",
@@ -114,28 +113,21 @@
     "        vaersVax2022.loc['1996873'] = pd.Series({'VAX_TYPE': 'HPV9',    'VAX_MANU': 'MERCK & CO. INC.', 'VAX_LOT': 'R017624'})\n",
     "        vaersVax2022.loc['1996874'] = pd.Series({'VAX_TYPE': 'COVID19', 'VAX_MANU': 'MODERNA', 'VAX_LOT': '025L20A'})\n",
     "        \n",
-    "        dataFrame = createDataFrame2(\n",
+    "        dataFrame = _createDataFrame(\n",
     "            [\n",
     "                {'VAERSDATA': vaersData2021, 'VAERSVAX': vaersVax2021},\n",
     "                {'VAERSDATA': vaersData2022, 'VAERSVAX': vaersVax2022}\n",
     "            ],\n",
     "            \"MODERNA\")\n",
-    "        display(\"dataFrame:\", dataFrame)\n",
     "\n",
-    "        # When\n",
     "        self._test_createBatchCodeTable(dataFrame);\n",
     "    \n",
     "    def test_createBatchCodeTable(self):\n",
-    "        # Given\n",
+    "        self._test_createBatchCodeTable(createDataFrame(\"test/VAERS\", \"MODERNA\"));\n",
-    "        dataFrame = createDataFrame(\"test/VAERS\", \"MODERNA\")\n",
-    "        display(\"dataFrame:\", dataFrame)\n",
-    "        self._test_createBatchCodeTable(dataFrame);\n",
-    "\n",
     "\n",
     "    def _test_createBatchCodeTable(self, dataFrame):\n",
     "        # When\n",
     "        batchCodeTable = createBatchCodeTable(dataFrame)\n",
-    "        display(\"batchCodeTable:\", batchCodeTable)\n",
     "\n",
     "        # Then\n",
     "        batchCodeTableExpected = pd.DataFrame(\n",
@@ -146,7 +138,6 @@
     "                'LIFE THREATENING ILLNESSES': [0, 0]\n",
     "            },\n",
     "            index = pd.MultiIndex.from_arrays([['025L20A', '037K20A']], names = ('VAX_LOT',)))\n",
-    "        display(\"batchCodeTableExpected:\", batchCodeTableExpected)\n",
     "        assert_frame_equal(batchCodeTable, batchCodeTableExpected, check_dtype = False)\n",
     "\n",
     "        "
@@ -186,16 +177,6 @@
     "saveBatchCodeTable(\"PFIZER\\BIONTECH\", \"results/pfizer.xlsx\")\n",
     "saveBatchCodeTable(\"JANSSEN\", \"results/janssen.xlsx\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "ef8f99c4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "unittest.main(argv = [''], verbosity = 2, exit = False)"
-   ]
   }
  ],
  "metadata": {