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

adding HowBadIsMyBatchTest

Browse Source
This commit is contained in:
frankknoll
2022-01-25 21:07:35 +01:00
parent ce588d502a
commit cbd32489f3
2 changed files with 86 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

88
HowBadIsMyBatch.ipynb
View File

@@ -9,6 +9,7 @@
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"pd.set_option('display.max_rows', 100)\n",
"pd.set_option('display.max_columns', None)"
]
@@ -20,15 +21,15 @@
"metadata": {},
"outputs": [],
"source": [
"def createDataFrame(manufacturer):\n",
" def read_csv(file):\n",
" return pd.read_csv(file, index_col='VAERS_ID', encoding='latin1', low_memory=False)\n",
"def createDataFrame(baseDir, 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 = \"VAERS/\" + year + \"VAERSData/\"\n",
" folder = baseDir + \"/VAERS/\" + year + \"VAERSData/\"\n",
" return pd.merge(\n",
" read_csv(folder + year + \"VAERSDATA.csv\"),\n",
" read_csv(folder + year + \"VAERSVAX.csv\"),\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",
@@ -45,16 +46,15 @@
"source": [
"def createPivotTable(df):\n",
" def filter(df, col):\n",
" return df[df[col]=='Y'][['VAX_LOT']]\n",
" return df[df[col] == 'Y'][['VAX_LOT']]\n",
"\n",
" return pd.concat(\n",
" {\n",
" 'ADRs': df[['VAX_LOT']].value_counts(),\n",
" 'DEATHS': filter(df, 'DIED').value_counts(),\n",
" 'DISABILITIES': filter(df, 'DISABLE').value_counts(),\n",
" 'LIFE THREATENING ILLNESSES': filter(df, 'L_THREAT').value_counts()\n",
" },\n",
" axis=1)"
" pivotTableDict = {\n",
" 'ADRs': df[['VAX_LOT']].value_counts(),\n",
" 'DEATHS': filter(df, 'DIED').value_counts(),\n",
" 'DISABILITIES': filter(df, 'DISABLE').value_counts(),\n",
" 'LIFE THREATENING ILLNESSES': filter(df, 'L_THREAT').value_counts()\n",
" }\n",
" return pd.concat(pivotTableDict, axis=1).replace(to_replace=np.nan, value=0)\n"
]
},
{
@@ -64,7 +64,7 @@
"metadata": {},
"outputs": [],
"source": [
"df_moderna = createDataFrame(\"MODERNA\")"
"df_moderna = createDataFrame(\".\", \"MODERNA\")"
]
},
{
@@ -91,11 +91,65 @@
"cell_type": "code",
"execution_count": null,
"id": "bb7b2963",
"metadata": {},
"metadata": {
"scrolled": false
},
"outputs": [],
"source": [
"pivotTable"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9f506ac8",
"metadata": {},
"outputs": [],
"source": [
"import unittest"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e14465d7",
"metadata": {},
"outputs": [],
"source": [
"from pandas.testing import assert_frame_equal\n",
"\n",
"\n",
"class HowBadIsMyBatchTest(unittest.TestCase):\n",
"\n",
" def test_createPivotTable(self):\n",
" # Given\n",
" pivotTable = createPivotTable(createDataFrame(\"test\", \"MODERNA\"))\n",
"\n",
" # When\n",
" pivotTableExpected = pd.DataFrame(\n",
" {\n",
" 'ADRs': [2, 1],\n",
" 'DEATHS': [0, 1],\n",
" 'DISABILITIES': [2, 0],\n",
" 'LIFE THREATENING ILLNESSES': [0.0, 0.0]\n",
" },\n",
" index=pd.MultiIndex.from_arrays([['025L20A', '037K20A']], names=('VAX_LOT',)))\n",
" display(\"actual:\", pivotTable)\n",
" display(\"expected:\", pivotTableExpected)\n",
"\n",
" # Then\n",
" assert_frame_equal(pivotTable, pivotTableExpected, check_dtype=False)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ef8f99c4",
"metadata": {},
"outputs": [],
"source": [
"unittest.main(argv=[''], verbosity=2, exit=False)"
]
}
],
"metadata": {