refactoring

HowBadIsMyBatch.ipynb

@@ -21,16 +21,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def createDataFrameFromDescr(vaersDescr, manufacturer, dose):\n",
-    "    def filter(df):\n",
+    "def filter(df, manufacturer, dose):\n",
     "    return df[\n",
     "        (df[\"VAX_TYPE\"] == \"COVID19\") &\n",
     "        (df[\"VAX_MANU\"] == manufacturer) &\n",
     "        (df[\"VAX_DOSE_SERIES\"].str.contains(dose))]\n",
     "\n",
+    "def createDataFrameFromDescr(vaersDescr, manufacturer, dose):\n",
     "    return pd.merge(\n",
     "        vaersDescr['VAERSDATA'],\n",
-    "        filter(vaersDescr['VAERSVAX']),\n",
+    "        filter(vaersDescr['VAERSVAX'], manufacturer, dose),\n",
     "        left_index = True,\n",
     "        right_index = True)\n",
     "\n",
@@ -47,8 +47,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def createDataFrameFromFiles(dataDir, manufacturer, dose):\n",
-    "    def readVaersDescr(year):\n",
     "def read_csv(file, usecols, dtype = {}):\n",
     "    return pd.read_csv(\n",
     "        file,\n",
@@ -58,6 +56,7 @@
     "        usecols = usecols,\n",
     "        dtype = dtype)\n",
     "\n",
+    "def readVaersDescr(dataDir, year):\n",
     "    folder = dataDir + \"/\" + year + \"VAERSData/\"\n",
     "    return {\n",
     "        'VAERSDATA':\n",
@@ -71,8 +70,9 @@
     "                    dtype = {\"VAX_DOSE_SERIES\": \"string\"})\n",
     "        }\n",
     "\n",
+    "def createDataFrameFromFiles(dataDir, manufacturer, dose):\n",
     "    return createDataFrameFromDescrs(\n",
-    "        [readVaersDescr(\"2021\"), readVaersDescr(\"2022\")],\n",
+    "        [readVaersDescr(dataDir, \"2021\"), readVaersDescr(dataDir, \"2022\")],\n",
     "        manufacturer,\n",
     "        dose)"
    ]
@@ -110,6 +110,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "e59a1825",
    "metadata": {},
    "outputs": [],
    "source": [