def diagnosticEngineering(df,pullDown,path):
phcVals = pullDown[phcCol].dropna().values
ageVals = pullDown[ageCol].dropna().values
sexVals = pullDown[sexCol].dropna().values
dfM = df.copy()
dfM["count"] = 1
dfM = dataCleaning(dfM)
regTable = _utils.basicTable(dfM, phcCol,phcVals)
ageTable = _utils.basicTable(dfM,ageCol,ageVals)
sexTable = _utils.basicTable(dfM,sexCol,sexVals)
dateTable = dateTabling(dfM,testDateCol)
regDateTable = regDateCrossTab(dfM,col1=testDateCol,col2=phcCol)
regDateCumTable = regDateTable.cumsum()
dir_ = _utils.getOutputDir()
path2Save1 = dir_ + path.split("/")[-1][:-5] + f"_陽性者集計1.xlsx"
path2Save2 = dir_ + path.split("/")[-1][:-5] + f"_陽性者集計2.xlsx"
with pd.ExcelWriter(path2Save1, engine="openpyxl", mode="wa") as writer:
#dfError = _utils.createErrorCheckDF(path)
#dfError.to_excel(writer, sheet_name="エラー確認")
regTable.to_excel(writer ,sheet_name="保健所")
ageTable.to_excel(writer, sheet_name="年齢")
sexTable.to_excel(writer, sheet_name="性別")
dateTable.to_excel(writer, sheet_name="日付")
regDateTable.to_excel(writer, sheet_name="日付-地域")
regDateCumTable.to_excel(writer, sheet_name="日付-地域-累積")
regDateAgeCrossTab(dfM,path2Save2,path,phcVals,ageVals,testDateCol,ageCol)
def crossTabulation(df, path):
hc_occur = _utils.basicTable(df, '保健所', '発生状況（公表）')
age_hcSex = _utils.basicTable(df, '年代', ['保健所', '性別'])
hosp_bedUnhosp = _utils.basicTable(df, '入院医療機関（現在）', ['入院病床（現在）', '退院の有無'])
age_sexResult = _utils.basicTable(df, '年代', ['性別', '身体状況（現在の症状）'])
dir_ = _utils.getOutputDir()
pathOutput = dir_ + path.split("/")[-1][:-5] + f"_層別集計.xlsx"
with pd.ExcelWriter(pathOutput, engine='openpyxl', mode='w') as writer:
hc_occur.to_excel(writer, sheet_name="保健所×発生状況"),
age_hcSex.to_excel(writer, sheet_name="年代×保健所性別"),
hosp_bedUnhosp.to_excel(writer, sheet_name="入院医療機関×病床退院"),
age_sexResult.to_excel(writer, sheet_name="年代×性別現在の状況"),
def getHospitalTable(df_):
df_[inHosp] = df_[inHosp].dt.date
cond = df_[inHosp].apply(type) == type(datetime.date(2020, 1, 1))
df_[inOrNot] = "空白"
df_.loc[cond, inOrNot] = "有"
tableIn = _utils.basicTable(df_, phc, inOrNot)
tableIn = tableIn.add_prefix(inOrNot + "_")
tableOut = _utils.basicTable(df_, phc, outOrNot)
tableOut = tableOut.add_prefix(outOrNot + "_")
tableHosp = pd.concat((tableIn, tableOut), axis=1)
# tableHosp["現在入院患者数"] =\
# tableHosp[inOrNot +"_有"] - tableHosp[outOrNot + "_01_有"]
return (tableHosp)
def getStatusTable(df_, col):
table = _utils.basicTable(df_, phc, col)
perLis = ["01_孤発", "02_初発", "03_後発"]
for c in perLis:
if c not in table.columns:
table[c] = 0
tablePer = table[perLis]
tablePer = tablePer.divide(tablePer.sum(axis=1), axis=0)
tablePer["合計"] = tablePer.sum(axis=1)
tablePer = np.round(tablePer * 100, 2)
table = table.add_suffix("_(N)")
tablePer = tablePer.add_suffix("_(%)")
ret = pd.concat((table, tablePer), axis=1)
return (ret)
def tableProcessing(df, path):
df = df.dropna(axis=0, how="all")
for c in [phc, statusPub, outOrNot, physicalStatus]:
df[c] = df[c].replace(np.nan, '空白')
df["count"] = 1
tablePub = getStatusTable(df, statusPub)
tablePhysical = _utils.basicTable(df, phc, physicalStatus)
tableHosp = getHospitalTable(df)
dir_ = _utils.getOutputDir()
pathOutput = dir_ + path.split("/")[-1][:-5] + f"_発生状況.xlsx"
with pd.ExcelWriter(pathOutput, engine="openpyxl", mode="wa") as writer:
tablePub.to_excel(writer, sheet_name="公表")
tablePhysical.to_excel(writer, sheet_name="身体状況")
tableHosp.to_excel(writer, sheet_name="入院状況")