From 6a0c43c0995ae4aa4596eb32ceed50c320f15f28 Mon Sep 17 00:00:00 2001 From: Amaris Sim Date: Mon, 20 Jan 2025 17:27:37 -0500 Subject: [PATCH 1/4] in progress --- nhsn/delphi_nhsn/run.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/nhsn/delphi_nhsn/run.py b/nhsn/delphi_nhsn/run.py index 15f5559c5..eb200b84a 100644 --- a/nhsn/delphi_nhsn/run.py +++ b/nhsn/delphi_nhsn/run.py @@ -79,8 +79,10 @@ def run_module(params, logger=None): df = geo_mapper.replace_geocode( df, from_col="state_code", from_code="state_code", new_col="geo_id", new_code="hhs" ) - else: + elif geo == "state": df = df[df_pull["geo_id"] != "us"] + df = df[df['geo_id'].str.len() == 2] # hhs region is a value in geo_id column + df["se"] = np.nan df["sample_size"] = np.nan dates = create_export_csv( From 4350c5a5f09ff6647623ad37b4864a1385320a96 Mon Sep 17 00:00:00 2001 From: Amaris Sim Date: Tue, 21 Jan 2025 14:39:11 -0500 Subject: [PATCH 2/4] filtering also on hhs and check in test --- nhsn/delphi_nhsn/run.py | 1 + nhsn/tests/test_data/page.json | 118 +++++++++++++++++++++++++++++++++ nhsn/tests/test_run.py | 3 + 3 files changed, 122 insertions(+) diff --git a/nhsn/delphi_nhsn/run.py b/nhsn/delphi_nhsn/run.py index eb200b84a..402287c2a 100644 --- a/nhsn/delphi_nhsn/run.py +++ b/nhsn/delphi_nhsn/run.py @@ -73,6 +73,7 @@ def run_module(params, logger=None): df = df[df["geo_id"] == "us"] elif geo == "hhs": df = df[df["geo_id"] != "us"] + df = df[df['geo_id'].str.len() == 2] df.rename(columns={"geo_id": "state_id"}, inplace=True) df = geo_mapper.add_geocode(df, "state_id", "state_code", from_col="state_id") df = geo_mapper.add_geocode(df, "state_code", "hhs", from_col="state_code", new_col="hhs") diff --git a/nhsn/tests/test_data/page.json b/nhsn/tests/test_data/page.json index 749147244..5d4eda759 100644 --- a/nhsn/tests/test_data/page.json +++ b/nhsn/tests/test_data/page.json @@ -2122,5 +2122,123 @@ "pctconfc19icubedsperchos": "-0.0002", "pctconffluicubedsperchos": "-0.012", "pctconfrsvicubedsperchos": "0.0" + }, + { + "weekendingdate": "2021-10-16T00:00:00.000", + "jurisdiction": "region 1", + "numinptbeds": "729772.05", + "numinptbedsadult": "660758.41", + "numinptbedsped": "53387.68", + "numinptbedsocc": "556817.29", + "numinptbedsoccadult": "510524.46", + "numinptbedsoccped": "35679.97", + "numicubeds": "114471.4", + "numicubedsadult": "86925.11", + "numicubedsped": "21902.45", + "numicubedsocc": "85344.84", + "numicubedsoccadult": "66877.69", + "numicubedsoccped": "14657.22", + "numconfc19hosppatsadult": "55448.05", + "numconfc19hosppatsped": "847.15", + "totalconfc19hosppats": "56295.2", + "totalconffluhosppats": "259.85", + "numconfc19icupatsadult": "18104.6", + "totalconfc19icupats": "18104.6", + "totalconffluicupats": "39.33", + "totalconfc19newadmped": "1301.0", + "numconfc19newadmadult18to49": "11532.0", + "totalconfc19newadmadult": "44677.0", + "numconfc19newadmunk": "1982.0", + "totalconfc19newadm": "45978.0", + "totalconfflunewadm": "266.0", + "pctinptbedsocc": "0.763", + "pctconfc19inptbeds": "0.0771", + "pctconffluinptbeds": "0.0004", + "pcticubedsocc": "0.7456", + "pctconfc19icubeds": "0.1582", + "pctconffluicubeds": "0.0003", + "pctconfc19newadmadult": "0.9717", + "pctconfc19newadmped": "0.0283", + "numinptbedshosprep": "5396", + "numinptbedsocchosprep": "5396", + "numicubedshosprep": "5396", + "numicubedsocchosprep": "5396", + "totalconfc19hosppatshosprep": "5396", + "totalconffluhosppatshosprep": "4317", + "totalconfrsvhosppatshosprep": "0", + "totalconfc19icupatshosprep": "5396", + "totalconffluicupatshosprep": "4306", + "totalconfrsvicupatshosprep": "0", + "totalconfc19newadmpedhosprep": "5278", + "totalconfc19newadmadulthosprep": "5394", + "totalconfc19newadmhosprep": "5394", + "totalconfflunewadmpedhosprep": "0", + "totalconfflunewadmadulthosprep": "0", + "totalconfflunewadmhosprep": "4307", + "totalconfrsvnewadmpedhosprep": "0", + "totalconfrsvnewadmadulthosprep": "0", + "totalconfrsvnewadmhosprep": "0", + "pctinptbedsocchosprep": "5396", + "pcticubedsocchosprep": "5396", + "pctconfc19inptbedshosprep": "5396", + "pctconffluinptbedshosprep": "4317", + "pctconfrsvinptbedshosprep": "0", + "pctconfc19icubedshosprep": "5396", + "pctconffluicubedshosprep": "4306", + "pctconfrsvicubedshosprep": "0", + "numinptbedsperchosprep": "0.9492", + "numinptbedsoccperchosprep": "0.9492", + "numicubedsperchosprep": "0.9492", + "numicubedsoccperchosprep": "0.9492", + "totalconfc19hosppatsperc": "0.9492", + "totalconffluhosppatsperc": "0.7594", + "totalconfrsvhosppatsperc": "0.0", + "totalconfc19icupatsperchosprep": "0.9492", + "totalconffluicupatsperchosprep": "0.7574", + "totalconfrsvicupatsperchosprep": "0.0", + "totalconfc19newadmpedper": "0.9284", + "totalconfc19newadmadultp": "0.9488", + "totalconfc19newadmperchosprep": "94.88", + "totalconfflunewadmpedper": "0.0", + "totalconfflunewadmadultp": "0.0", + "totalconfflunewadmperchosprep": "75.76", + "totalconfrsvnewadmpedper": "0.0", + "totalconfrsvnewadmadultp": "0.0", + "totalconfrsvnewadmperchosprep": "0.0", + "pctinptbedsoccperchosprep": "0.9492", + "pcticubedsoccperchosprep": "0.9492", + "pctconfc19inptbedsperchosprep": "0.9492", + "pctconffluinptbedsperchosprep": "0.7594", + "pctconfrsvinptbedsperchosprep": "0.0", + "pctconfc19icubedsperchosprep": "0.9492", + "pctconffluicubedsperchosprep": "0.7574", + "pctconfrsvicubedsperchosprep": "0.0", + "numinptbedsperchosprepabschg": "-0.07", + "numinptbedsoccperchospre": "-0.07", + "numicubedsperchosprepabschg": "-0.07", + "numicubedsoccperchosprepabschg": "-0.07", + "totalconfc19hosppatsperc_1": "-0.02", + "totalconffluhosppatsperc_1": "-1.23", + "totalconfrsvhosppatsperc_1": "0.0", + "totalconfc19icupatsperch": "-0.02", + "totalconffluicupatsperch": "-1.2", + "totalconfrsvicupatsperch": "0.0", + "totalconfc19newadmpedper_1": "-0.04", + "totalconfc19newadmadultp_1": "-0.04", + "totalconfc19newadmpercho": "-0.04", + "totalconfflunewadmpedper_1": "0.0", + "totalconfflunewadmadultp_1": "0.0", + "totalconfflunewadmpercho": "-1.27", + "totalconfrsvnewadmpedper_1": "0.0", + "totalconfrsvnewadmadultp_1": "0.0", + "totalconfrsvnewadmpercho": "0.0", + "pctinptbedsoccperchospre": "-0.0007", + "pcticubedsoccperchosprepabschg": "-0.0007", + "pctconfc19inptbedspercho": "-0.0002", + "pctconffluinptbedspercho": "-0.0123", + "pctconfrsvinptbedspercho": "0.0", + "pctconfc19icubedsperchos": "-0.0002", + "pctconffluicubedsperchos": "-0.012", + "pctconfrsvicubedsperchos": "0.0" } ] \ No newline at end of file diff --git a/nhsn/tests/test_run.py b/nhsn/tests/test_run.py index c96ec7953..ef99def7b 100644 --- a/nhsn/tests/test_run.py +++ b/nhsn/tests/test_run.py @@ -45,6 +45,9 @@ def test_output_files_exist(self, params, run_as_module): "geo_id", "val", "se", "sample_size", ] assert (df.columns.values == expected_columns).all() + if geo == "state": + states = list(df["geo_id"].values) + assert all(len(state) == 2 for state in states) for file in Path(export_dir).glob("*.csv"): os.remove(file) From 9f2d9ee41f47186d70bb29f6fa2620ed29a7f617 Mon Sep 17 00:00:00 2001 From: Amaris Sim Date: Tue, 21 Jan 2025 16:02:57 -0500 Subject: [PATCH 3/4] regenerated test data to update current behavior --- nhsn/tests/test_data/20241212.csv.gz | Bin 3446 -> 3467 bytes 1 file changed, 0 insertions(+), 0 deletions(-) diff --git a/nhsn/tests/test_data/20241212.csv.gz b/nhsn/tests/test_data/20241212.csv.gz index 61c85a5ba35e757dd53d819a9854aec78d534a17..26f91c200dfd1cae144458dfe91b0a6cf767d596 100644 GIT binary patch literal 3467 zcmV;64RrD!iwFop3y^05|1vN#H83$UF)m|sb^z>}$!_Jy5k>d@3V*;8kr6q2XZQoW zu)Q{_C3Sc8APH3}_wW1O$mIBvQfVOr1_Ve1+vm@Z50{5;zkhysdj8@5?(25{)7`h2FvyPcpn?8aZ!q2I&(AD`}i-=A!&vpJyl>cuc;B!p zc=$`JiigdslF!a_Q3yJmDS13%d^Y3x_8K0K7@z)lzP)zCKFVti4_Y@m z9<*+>d@}R3w5~LLGVfTF*T44Zhp)Fk|8%PGvA{QjM)#&SpNak7aw_+2(?Rgtri0{9 z#eORDQ-L3TWh=VuiTF5z}3`H{!wFVw)X&0T7H;qNp7+wd~nc&ogxYpH- zpTv=Re~G@P!Ny-gz;(N2KXPBQHEP>XhrPwMp0A9@F9(i0D@x)C=RB)tu1IOoQ<2sX zaSNvsS9RuT>9wfyt<$@FvXQXuA@!tx|Ci&5;I`*MvCg{G)V*}e0DfNMgcGl>h*1x6 z!9*FeQBMXx>MCVcOUXiNLEB0_`K%3psK#&B93~axA37(DiHalk1i~h1m#)xYD05+Y ztfZhLW{aZ&ZI7?dMLO=PUEFeOQK2?lhztLs!NrIC!N2$9Um5T(q~h#prW{KNBwLgW ziw5b$>;o@d`M&!Yx#zvZ_2YdLsZq-$V*K;0QUC|07ElA-U?bxtt0b6WN~u;q`2yLB zD|yn)s$`mT8j3evl`_G+W(8_vSa&cfbgscr2l1KQDyF9RB8@!`L##%?q@93vrv*CS zATW7~PPKF{Mq^+z<~VmUDh@UZZqY{feP2sspfyU{7z2IHD+6B{Z#+8L8qabLvJ$G* z_!WS;cl8E9zXhNV*8qIO>^Hm{FKxB#`}vb$^9itv?oR2(ZoiJp&Gbv1-$=RMxG>@& zTsZPjl5q?6j=;;39IF#74>1V?PB>Lxjeo(JA4j4QjxMuLg&x@$Lj$V~l*BGYgiSUj zxd$rt!e;Qryh19mni9>cbnQnP|Ek!1&+U;p^Ziohc!{aknVCv<%ka*8K=Hkxc&(%c z#ZcgN85Dz-#HR}oLO3|zn5DvI;uVVs9iRppQ?Ll$8<`0Ap6(q9n7E@ZVXDN3s2=*n zqcC4B6MzMF)>F9-HxoBOqMEwIg#;@eNn1LJ2y<#7eU}{|5qMP^YBDdCYEEIyWMQa| z(yLyBm{Yh%VsIM|FlX~P6mI1fiOnOywZGsNb`19YGq;fa$8O>E`0sQJR|qaO@;!c` z_uuCizA%4-+SP`Liffm{;cl}*<&|%!hvH^=B5qK%Xjn#}v2WC>LiY`BAr(U!LK>u@ zZxORc#6q@}++$;7Cd`=mj9yJgjC^pEt!s(qby~DrvY+e@aVB&6+SV#ed+_PZICJ03 zv}sX$Y}_75SqxFeSyQ2Tw$JuhVzC<%Vl^oegDp7rWg8s#=-AH| zxMQ$349W|hq31JO_EW=Pxbh71nP+%C{yRKF=MTPHs(JMc^NDAe_$0r>Gd!LBRnO2L zT*1w8ICTyE_q&Fh`3`lfjz_UF6~a|Mjh%*eKYVbENm6o=rH`q>P_&22(m>W|Xm&JG zr!eTs6&Y6JCBXfGj5(x2?R`;z@e)jHFDzCL21xS_{Q|@omut^G`Y&mzXntXh3n+4E zl8o{J!}o;YFjn>qG2jaThS_IuEs8{hsMyIF`?gf*9o>Ce#6aYPhC@h;%Ns7ke*@ao zRR^+>hrzR@@emM_;Kfb!UKkaVh5>R^+}K!P(z&98FuigWMj&P|b=gU|El+1UgNkTE z?4{3@SBC)99!PCrv!=E_lkslbQeoY}&|8?C`zlp32wb2`_taR2b|iT=hzW4~LGc!r)_d zp~VdxFcNtgO68YDdq*j8>E@mP#N}ybtg8B;vHoW zQ(6`z#cYW=pE6Bs0@Yd)FLdzP+eLtH7YHpFmX?rPyucQ{6$4csYyv$uZSV>U$cRsi zZf(=yS62AFGTxZu&kK7U^7?+v6=kL064jD^X-mH{px+y2f7uV@UEPPd^_2y}WyEVv zpyftn*TsrWx>ss zlzyq1RBRbz7*)m-Ox#uYg_f1(+9EwRJgtx!QUinhaDj&`XD7ZNVJ!On{poPK9>TL#{4S{RQDz${N z_u&J9?}@-VK%i%2%SF7DxV&#>4UsKY zlabX1xRx+(lLa&Uy)X`1qS)IcVxh22q+T}5flYWd$2C)&gC)46x)p`BeLmc!NMmndXBZR}Fy$;$|MYm+(rxebrzd zp+u8g2#GH|WNNv%5Ub_>n6F+x9dtR%7KFAiBRvz>+{1$>IL;IYFB?zJrL#prmq$tB z;rQ2*#LY8{_2{d`99~}+G`IZaB=KwW-`Gmucne6$ygs-dA5tXqb|Ionng`KwK9r4s tqSq;swt#V}eSUoSvwX<;L(cz4a{ey>009600|55l2_^kH004`mwp#!I literal 3446 zcmV-+4T}$#Uh!5k>dZ*hsUR%@9(~E_dnhJ`0})^c)Y*c9)7*OJse(*K;1m(_Qx`R z+g&@i<9)|@^5y8*eVzLD>%%X%Qh)pU{qgbB(>m{=p1q&GK7IOfs9!68`SN3_T*u@0 z)@ipB^oHH|t2*?1xc~Fh-5>jtZFM%Ml&7zu4n`a=q}Bd-_t^IQ~y4rfXpj~JiLc)q=c$0Nq4Kb~)|-tmZUw`1)dTZWJFTEm0ZjgAMc z8!eyAd@ZdjO`ps=7UlJ?efs(P?Qg%HDts*P&7je}>CI~C_;UHi#RPhWw}&W-K6!BgIeKSn1a6~AN=Gl8ZtXcNd-sZ zed3`{R)|JFNx0M`))+ZK#B`k2Cc*Ea-EktXtmy@7d|-9u&?1~&xfi*0_MeI89->!s@MFQe;Px?YPxt;Sv4NngyW)xS{WlIwg9*EO!n+)#C@zSr}o zr=^$MkAK7b|F{2B1^w$Ef4$`BB;xeyCFL4}o1$DIBoZg5mzdQD>_HHk@N_207q3O! z`FJU{KvY^F#8~6xp|T*NoU&?$WHn$o1}Eq)IQ)JoP?16# z5NqPymURbb5K%ALB$$1|89@so3 zQtvO(*EHDpO9;4bx9msmYqmyh8|tvPxYqN9@%ZJyac4zIJmH*Y^~@D1EqW@_8X|7t zRN|`6JT1Kzb-s0amrphlwmqbt^zZ+2JQ3XXJSf&#mzuhlZW+MOYn*W6)fF-7K`xjm zV>ar^;747h%xWoFNG)hvsVASc;SbgL&6>lcV*EqrgfUTZ#GXLdB<<1_8VqGFOplcm zbi{0NRG{tg^|?sLUA2o_ZY?U*W(#rQUo^P*kU#kMp8P8V{)JSWJ2*l3~#x zotS;#r7PceA0zj?cesAMZz45nnM90#o>dCqz|;b2pc`ytykwOGQ%ot<>L*_yTX7{% znpu@hb529?rmIpWnAfa8Z4B!UCWX#580sKClUv2q6knvV$6<)o2$-}J(C)NA=Nkkj zPtmEC&c$d9Y{netPDaJSM!_xG=)Ui3X$-VRX&YmpuX$zQ3*(JPCtKrL&Ouf}wHm(y zF!!$B0O+>>^x+zSZZ|cDIP>F3G{Vtk_NmY#8)Il-wSkh@rHHV}rX=@3 z#a`G9zL-}?C00|Sd6lmHNaJ4>yYIO@GH1SD${a5-^*S?C$!;0mnGYzw7Zk6R)Sws& zye@-c(31Fc0YV4|=Nq$B*i5`)5upRrKw}CP!FwYU;oj4|BLNe4)Fn)n_z=}YpLi7J zt7QVPz|MLq*WqU3CP-9Mm$;B%#Up7;ClO&zEu`1$i7FzvyoGvmyCGt;I; z?XhutAZ0N`8D~v}=Gi{mV~NFXNRST_z9$J~6dnhqfwb^gJ^U~84gnoF^)Z!#SQKue zYNT_BhYt{S-%#P4DP2PcLeewLkRyyUKojWG;gu=~jX^;WwkgVqfVJQd?5=jtFax>; zfOU0(O7L={FR423;CDS2cv4&EvDmoa%q%tz77dpoW{K6LNDQ{%*q3c^+@oVZTi}kt z+At{3c!r+OY}ro@gW<|E%x9kA_4rqKhRz>+w^Z}$8RiquF!4#g!ZSRb{YB5vA6&uB zaX57i{p(%B&3uQtRmY=PnF`@5pT9{rcJR5ZV^#sw5PG)YGJ zfZ=<>a2P9lh8XY#0K@DvxE4hsLR9SJjD1@w^p5U6En*;YLc<}X#pMl`;lBZG>Z$|T z$iv{-(s&36N$}z(dM}KMNy7j+DsF5nFzH;;L6}~-3L_9Rn7Ztw+?J;^ok2x3A@FY7eBguvt@EpUHT)ZK<&CVCXGO&V7|Cner?eA*jk=69KQ3X1rlv8VId1v`qtH z(iMa+j5jdFX9{Ce*`W;AyKx3XgIF;VmMsbMz!`kYJbV&;pQhR=0 z^n-lwNWPx7p*I4TTw6s~%u!G}Y~RblY4y3pbV z6-PXwMg+lbf)1UMck~0nI|wNNbledx|G~#Au@v(H;SJJEYp4u+!@3ijM)8g^h$$@# zl47>RoKKl1Hi2p_i5EKf?Cm1Jw+n<83`p0Gn>Kib1!TmhMYp!; z@GC3)UKnr8@#lrT4tae)=8Ce?Z;5J2zqF-a8PM+yvp??#@~-Z~-1@=-;WFYSC(v>u zvg=~SCS4-##_0%y@Yle*D%E(G8pARJ6L?uEDpO=&Rc_&}Ye{4JfL!5m(jsEOuG*4K zwFsrTm4!%!wvC)zMW1~@F}nA{tZ-dXsM0UCX176M3rk9vZ++J01ZGKlOXVV8qYo6m z4+;k|YAAFPO0%Oi06feS!!p}ya!ipz@ysEY5Q05?4-bb~VZhKylS^fWjDm61drH65 zOe(gFF^nqX2`26;{6fo0b8V3x8=h9k45@)Zez?HIFy(_6b=irw=A42pKS%JES&|ft zdtMWZ2zgt`9Q~XxwvQ6}i`0y7PA$n!ub4|Y%zh)254i7U$1hVkOy@n3JPCT`sn6{YJ9xpRvWN9%DR~HGI z_F;^WtCb&+57N; z!1qL89U#y%vgIOPN?hJIvxdl)zFCab$70KbnwZ}O{{qY%lN*wNNBcgeB<9J$F2@gL z$iEDyZ{oKGDK^>x5-`{NhKn9#;$k2IW(3M96p2Ko8E(BWwsyAYIPXNW^H8d9OWLOT z=zO*?gv51R#SF&7&^4E|Yi{?&jJ^J{PmNd#8G#pmDBzA9H$)ehl`qRa%{Ta0wi%GV zCRk_wy*S>OQ=ch(<5AxGbMWB8%D*zBivZLu0o}kKeB=D*sSzo=)QG;68c}&=YGj>w z%^k;`ekF}K*pLQK&;kQk#Kytc{KDFjyV^dGDU41ir_j>JoqN7zcOe)S*}`H*$7E!+ z0j?#C+hoBEe=m%KmMHc%iC8FX6RDTYa$pl)&2h~X=U@pgscuDKZJ!UikIx6+6NN`9 z844ASo2?2bI7>iS;F>?)US@n_OhxQ_0ytraj_KC Date: Tue, 21 Jan 2025 16:06:19 -0500 Subject: [PATCH 4/4] lint --- nhsn/delphi_nhsn/run.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/nhsn/delphi_nhsn/run.py b/nhsn/delphi_nhsn/run.py index 402287c2a..92e24bbda 100644 --- a/nhsn/delphi_nhsn/run.py +++ b/nhsn/delphi_nhsn/run.py @@ -73,7 +73,7 @@ def run_module(params, logger=None): df = df[df["geo_id"] == "us"] elif geo == "hhs": df = df[df["geo_id"] != "us"] - df = df[df['geo_id'].str.len() == 2] + df = df[df["geo_id"].str.len() == 2] df.rename(columns={"geo_id": "state_id"}, inplace=True) df = geo_mapper.add_geocode(df, "state_id", "state_code", from_col="state_id") df = geo_mapper.add_geocode(df, "state_code", "hhs", from_col="state_code", new_col="hhs") @@ -82,7 +82,7 @@ def run_module(params, logger=None): ) elif geo == "state": df = df[df_pull["geo_id"] != "us"] - df = df[df['geo_id'].str.len() == 2] # hhs region is a value in geo_id column + df = df[df["geo_id"].str.len() == 2] # hhs region is a value in geo_id column df["se"] = np.nan df["sample_size"] = np.nan