francois/HowBadIsMyBatch
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

adding SevereEffectsBatchCodeTableTest

Browse Source
This commit is contained in:
frankknoll
2022-01-31 09:30:07 +01:00
parent 38170520a1
commit 22d54d6eb9
1 changed files with 81 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

86
HowBadIsMyBatch.ipynb
View File

@@ -97,16 +97,37 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"def createBatchCodeTable(df : pd.DataFrame):\n", "def createBatchCodeTable(df : pd.DataFrame):\n",
" def filter(df, col):\n", " def filterDataFrame(df, col):\n",
" return df[df[col] == 'Y'][['VAX_LOT']]\n", " return df[df[col] == 'Y'][['VAX_LOT']]\n",
"\n", "\n",
" batchCodeTableDict = {\n", " batchCodeTableDict = {\n",
" 'ADRs': df[['VAX_LOT']].value_counts(),\n", " 'ADRs': df[['VAX_LOT']].value_counts(),\n",
" 'DEATHS': filter(df, 'DIED').value_counts(),\n", " 'DEATHS': filterDataFrame(df, 'DIED').value_counts(),\n",
" 'DISABILITIES': filter(df, 'DISABLE').value_counts(),\n", " 'DISABILITIES': filterDataFrame(df, 'DISABLE').value_counts(),\n",
" 'LIFE THREATENING ILLNESSES': filter(df, 'L_THREAT').value_counts()\n", " 'LIFE THREATENING ILLNESSES': filterDataFrame(df, 'L_THREAT').value_counts()\n",
" }\n", " }\n",
" return pd.concat(batchCodeTableDict, axis = 'columns').replace(to_replace = np.nan, value = 0)\n" " return pd.concat(batchCodeTableDict, axis = 'columns').replace(to_replace = np.nan, value = 0)\n",
"\n",
"def getManufacturerOfBatchCode(df, batchCode):\n",
" return df[df['VAX_LOT'] == batchCode].iloc[0]['VAX_MANU']\n",
"\n",
"def createSevereEffectsBatchCodeTable(df):\n",
" def filterDataFrame(df, col):\n",
" return df[df[col] == 'Y'][['VAX_LOT']]\n",
"\n",
" batchCodeTableDict = {\n",
" 'ADRs': df[['VAX_LOT']].value_counts(),\n",
" 'DEATHS': filterDataFrame(df, 'DIED').value_counts(),\n",
" 'DISABILITIES': filterDataFrame(df, 'DISABLE').value_counts(),\n",
" 'LIFE THREATENING ILLNESSES': filterDataFrame(df, 'L_THREAT').value_counts(),\n",
" 'HOSPITALISATIONS': filterDataFrame(df, 'HOSPITAL').value_counts(),\n",
" 'EMERGENCY ROOM OR DOCTOR VISITS': filterDataFrame(df, 'ER_VISIT').value_counts()\n",
" }\n",
" batchCodeTable = pd.concat(batchCodeTableDict, axis = 'columns')\n",
" batchCodeTable['COMPANY'] = batchCodeTable.apply(\n",
" lambda row: getManufacturerOfBatchCode(df, row.name[0]),\n",
" axis = 'columns')\n",
" return batchCodeTable.replace(to_replace = np.nan, value = 0)\n"
] ]
}, },
{ {
@@ -365,6 +386,61 @@
" return pd.DataFrame(index = index, columns = columns, data = data).astype(dtypes)\n" " return pd.DataFrame(index = index, columns = columns, data = data).astype(dtypes)\n"
] ]
}, },
{
"cell_type": "code",
"execution_count": null,
"id": "ded70c87",
"metadata": {},
"outputs": [],
"source": [
"from pandas.testing import assert_frame_equal\n",
"\n",
"class SevereEffectsBatchCodeTableTest(unittest.TestCase):\n",
"\n",
" def test_createSevereEffectsBatchCodeTable(self):\n",
" dataFrame = createDataFrameSevereEffectsFromDescrs(\n",
" [\n",
" {\n",
" 'VAERSDATA': self.createDataFrame(\n",
" columns = ['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT'],\n",
" data = [ ['Y', 'Y', np.NaN, 'Y', 'Y'],\n",
" [np.NaN, np.NaN, 'Y', np.NaN, 'Y']],\n",
" index = [\n",
" \"0916600\",\n",
" \"0916601\"]),\n",
" 'VAERSVAX': self.createDataFrame(\n",
" columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n",
" data = [ ['COVID19', 'MODERNA', '037K20A', '1'],\n",
" ['COVID19', 'PFIZER\\BIONTECH', '025L20A', '1']],\n",
" index = [\n",
" \"0916600\",\n",
" \"0916601\"],\n",
" dtypes = {'VAX_DOSE_SERIES': \"string\"})\n",
" }\n",
" ],\n",
" '1')\n",
"\n",
" # When\n",
" batchCodeTable = createSevereEffectsBatchCodeTable(dataFrame)\n",
"\n",
" # Then\n",
" batchCodeTableExpected = pd.DataFrame(\n",
" data = {\n",
" 'ADRs': [1, 1],\n",
" 'DEATHS': [0, 1],\n",
" 'DISABILITIES': [1, 0],\n",
" 'LIFE THREATENING ILLNESSES': [0, 1],\n",
" 'HOSPITALISATIONS': [0, 1],\n",
" 'EMERGENCY ROOM OR DOCTOR VISITS': [1, 1],\n",
" 'COMPANY': ['PFIZER\\BIONTECH', 'MODERNA']\n",
" },\n",
" index = pd.MultiIndex.from_arrays([['025L20A', '037K20A']], names = ('VAX_LOT',)))\n",
" assert_frame_equal(batchCodeTable, batchCodeTableExpected, 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", "cell_type": "code",
"execution_count": null, "execution_count": null,