From 9bdea6e7242c6032439c944d0aea9683c7a0eaef Mon Sep 17 00:00:00 2001 From: Akashdesarda Date: Thu, 6 Dec 2018 06:12:59 +0000 Subject: [PATCH 1/3] Done --- __pycache__/__init__.cpython-36.pyc | Bin 0 -> 156 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 174 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 789 bytes q01_missing_value/build.py | 15 ++++++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 180 bytes .../test_q01_imputation.cpython-36.pyc | Bin 0 -> 2329 bytes 6 files changed, 14 insertions(+), 1 deletion(-) create mode 100644 __pycache__/__init__.cpython-36.pyc create mode 100644 q01_missing_value/__pycache__/__init__.cpython-36.pyc create mode 100644 q01_missing_value/__pycache__/build.cpython-36.pyc create mode 100644 q01_missing_value/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q01_missing_value/tests/__pycache__/test_q01_imputation.cpython-36.pyc diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4ee3283b78bae9ca195253c30d4ce8a57c71526e GIT binary patch literal 156 zcmXr!<>gwjmm`J&2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CU!M9I`MIh3j@gOD z87Zm7iA5=i`r-LS*~JBk$*KCu`6;RTX{m`NrA4Xnsd?#{d8w&InR)5)1x5K;smUe! f@$s2?nI-Y@dIgoYIBatBQ%ZAE?Lbx(12F>tN;D|K literal 0 HcmV?d00001 diff --git a/q01_missing_value/__pycache__/__init__.cpython-36.pyc b/q01_missing_value/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..37bcdbc5cf2b282cb5720d1a65af16f620354f7b GIT binary patch literal 174 zcmXr!<>gwjmm`J&2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CU(xy*`MIh3j@gOD z87Zm7iA5=i`r-LS*~JBk$*KCu`6;RTX{m`NrA4Xnsd?#{d8w&InR)5)1x5K;smUe! vg$9Q4xtYbqAhEKz0PP_sq#!FNMTmEJ=qxr_)*pK)3|5JzEov~8F$RI z=<+O}^Nf!EN^s3?xM79^-*6D%f&az35!YfRt~mq+pRf&g-YMJ0!rNGQ8ynrmMik=^ zP1wrYT7Sd9+p7h=M4LBok>)|<(h^=p)ka(bqoJ*Z2q z%cfXd$*M=4Mw&)tuvlAPek`?ea+U93?rRc*t( ztg1#*s}_*D>@C}V=;9v33dpTj*4;Oz4vFK>+hp0+n4Dcoy#&-!flS`C>QZ+y!z3e$ zBu8m_g$rzovO!et#+_vUPp;XODr;yrYILzpu;)s3@EQYVttQT8h>MoHCOoOBy ZxK9Ziozfus3ZJ-f>WCoXdm literal 0 HcmV?d00001 diff --git a/q01_missing_value/build.py b/q01_missing_value/build.py index 7dc4d18..0ed0682 100644 --- a/q01_missing_value/build.py +++ b/q01_missing_value/build.py @@ -1,6 +1,7 @@ +# %load q01_missing_value/build.py # Default imports import pandas as pd - +from sklearn.preprocessing import Imputer # Data loading ny_housing = pd.read_csv('data/train.csv') # Selecting 4 most relevant variables along with target variable from the dataset fot the Cleaning and Preprocessing. @@ -8,3 +9,15 @@ # Write your code here: +def imputation(housing_data): + df = housing_data + imp = Imputer(missing_values=float('NaN'),strategy='mean', axis=0) + df['MasVnrArea'] = imp.fit_transform(df[['MasVnrArea']]) + df['GrLivArea'] = imp.fit_transform(df[['GrLivArea']]) + df['SalePrice'] = imp.fit_transform(df[['SalePrice']]) + df['LotShape'] = df['LotShape'].fillna(df['LotShape'].mode()[0]) + df['GarageType'] = df['GarageType'].fillna(df['GarageType'].mode()[0]) + return df[['MasVnrArea', 'GrLivArea', 'SalePrice']],df[['LotShape', 'GarageType']] +#imputation(housing_data) + + diff --git a/q01_missing_value/tests/__pycache__/__init__.cpython-36.pyc b/q01_missing_value/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f4bac6d5fa7be6a783b6eea2741ee282233502cd GIT binary patch literal 180 zcmXr!<>flOmm`J&2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CUy1q|`MIh3j@gOD z87Zm7iA5=i`r-LS*~JBk$*KCu`6;RTX{m`NrA4Xnsd?#{d8w&InR)5)1x5K;smUe! zg$9Q4xtYbqAhEK@W1+F+}H?^H85NaKdRprZk}x+fLymE_bps6|P1{ME65&n)-dfP4BRagz1K!~w z?~eT~l7zw+A&hkQ3Gea#E5iGNF5INYokJ3DoWf2drZ#vgw0Xd^7@j&!Pnb_0? zC5&&3g&9>v!PHpKL^j{x%&>t`ESEc(K2E}~nf^|y`%18+v#%cK$8|G!T$;lpHWNv> z&lDSrrzggmRKNoO0(CX`n;xai6!K_7Nu3Erben zn|FB+>VWqVmfb)+2TKGQg(dNadjwD(K+$_(3^8;;f2J?V#4+wm%IOwaz@9+$+V{x0 zK^88O4y$`Zh0C3ynSc23C*Z>f9sxDgR7j(vZGI=(&yR(KR_rMs{FDdAcA3^fnTIbb zR#>+XGIp$|MKQ7-68j5LJ#hQ87#x*TF}VMn=_4*QQ=ARHFV%BBW0@FaB^QH{V5U+c z6>^+QAyh8M=}eUqILhF~XS?Y%*BbkdSy73B0Wx%LQyg5~?9S}OUdPe3z7&trhjVB= zGjRes|M)zcJD1HkM={Q{-QlSVUh^-OOmZ<|Rbis~@H*mUBuf)b znaPf#an0*_kJw#ttnhYYM}<(SE*hk?F$l`uym$q*NHG(_P2T~g*Ghto0eCy1(^|De4>yK~& z+gYwoU?-?*9!}Nb>){m3kA_RVV`W z7Mkm5-bQl+4MM#dD|_#O>(yD=Te5<=X&E@5z=we+V2e!X0&>&DU649Uc@RR7otEKq zmW>|GqbKV+$x3M;IqPW1hG&5k`!zh<%C&@4Zd*-!S(nL^^{`38W+hA>7o%sZR)Azp zV$td9az8@Ub;bZK%x_<&gv+M=d-SM>tD{%%g1f>iQtzW#OBYFZg?snP!1uOcnSTy^ zZy0xMkfsvCFHLQjrqhyF1-5%>iVs9HqBii9*U;QVvxVjZG?-e~PFaU4W;lfbiC-E` zKm#BCUeF4>dL-`Kppv=4i&QANq}Ak;TK3levC0eHJXdYd4?b>nc1;3!+j&|)_VOe> qDl2?olHOSZmB5 Date: Thu, 6 Dec 2018 06:35:46 +0000 Subject: [PATCH 2/3] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 176 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 635 bytes q02_outlier_removal/build.py | 11 +++++++++++ .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 182 bytes .../test_q02_outlier_removal.cpython-36.pyc | Bin 0 -> 1792 bytes 5 files changed, 11 insertions(+) create mode 100644 q02_outlier_removal/__pycache__/__init__.cpython-36.pyc create mode 100644 q02_outlier_removal/__pycache__/build.cpython-36.pyc create mode 100644 q02_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q02_outlier_removal/tests/__pycache__/test_q02_outlier_removal.cpython-36.pyc diff --git a/q02_outlier_removal/__pycache__/__init__.cpython-36.pyc b/q02_outlier_removal/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..bb5bb6ae04ddc996e499e7e89cd837862d41d14b GIT binary patch literal 176 zcmXr!<>gwjmm`J&2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CU$Ocb`MIh3j@gOD z87Zm7iA5=i`r-LS*~JBk$*KCu`6;RTX{m`NrA4Xnsd?#{d8w&InR)5)1x5K;smUe! zg$73P`K2W}nW;tbMX9;@Wr;cZ@$s2?nI-Y@dIgoYIBatBQ%ZAE?LgKR12F>t4dyVA literal 0 HcmV?d00001 diff --git a/q02_outlier_removal/__pycache__/build.cpython-36.pyc b/q02_outlier_removal/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c9f40672b2ae037b6fe2f8ca24378227390811b4 GIT binary patch literal 635 zcmZ8f&2G~`5Z+zeiQ_a-dW*z?1D8msu7HA&5Kw{COQ?{7sAPex#WQi7*lTy!jvC~g z%9RJXH76*c=f61D>;p zBVP&-S3Gji0S8?0pa=cb8?(p-9|m7p4#VmF9!e zCmN+4oa$+|-l_hytY-^Zp$$%@mMOm9kUp5n9N+0I!Gw3^h`eilP0~yWTDGL#K%@ek zZ+y#JzU1Iu@vXRg(DFCz)BUZ}iq;vktxK_@rHsyM-IY6LONS!a#l3U#QrF&@?a%X4 z)=wT=FH`Bk|DycvkD=M%)%?sk)0M#a5l#QV??cTK#cSGK#?XGYG?ocV~KQBsX Ra(v;CWx9XmJApWG{{m6Ww3+|_ literal 0 HcmV?d00001 diff --git a/q02_outlier_removal/build.py b/q02_outlier_removal/build.py index 74df5f2..a45721d 100644 --- a/q02_outlier_removal/build.py +++ b/q02_outlier_removal/build.py @@ -1,3 +1,4 @@ +# %load q02_outlier_removal/build.py # Default imports import pandas as pd @@ -8,3 +9,13 @@ # Write your code here: +def outlier_removal(df): + + num_columns =df.select_dtypes(include=['float64','int64']) + quantile_95= num_columns.quantile(0.95) + for colname in num_columns: + quantile = quantile_95[colname] + df=df.drop(df[df[colname]>quantile].index) + return df + + diff --git a/q02_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc b/q02_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..680d671fd47d78fa25f7fe409bbe0af705ed223a GIT binary patch literal 182 zcmYL?F$%&!5Jfj&5riDX#u05r%mr*LY=mLi9g{W5Zk*W&-bfGOMQpu=m77BR@E)Jv z{8dp*@6Y_GQr@F}$x_)SWRhgnUd^)IL-9EO^)XO~j-YI`)RsiE)o=*hNUsfn36|hQ zIu1-ozH*+3ov*Oxa3&MsvRGmmV(W;JsS8)#LL`X-h|ar+IPY(-eBA{*w6qz|C854h C+cNk7 literal 0 HcmV?d00001 diff --git a/q02_outlier_removal/tests/__pycache__/test_q02_outlier_removal.cpython-36.pyc b/q02_outlier_removal/tests/__pycache__/test_q02_outlier_removal.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d69e1bb371e6ef55e97911207a03629e39bdfbbd GIT binary patch literal 1792 zcma)+&2HO95XX1blM7Rc6$#~tX%whUxPhH_`( z@3A-pA42@HbIfE{_TDqu1HN+Ou5?b=pufhM*nr#MC1~?RXc(=X=FLZCW%3MEqF`R0 ziX4Ob6ENc{&xM-k1*FTq6h;h<5?OJW>eD#B|;Aed-mTE!n|d zLVK5*cyYPxl;b#b(ZB)TPw>|F(HLg?N?aPDcI6H*`y@98Ej8nME%}p2n!b ze~!*J_y#-adjr`WtzC>-KHTt?FcwvAB2-}oI+A5nlqQ-BlTM>aP5W}hz`Y=^Xw3(X z3h|+K$WT*_>7i%uUE9I=fVVNC0l*Q!(f zNQ_%jb4JS-7XWadMFw|GG%i)700mGqG@?vLuNI<^LPy_X)OSkE;nhKOR#qrWIFCh* zMEiQswznD?KGV+%ZA6iR-T5^$Q`8KtzjYSUdTFV^`ePa>?rg@i9?d`C4ah4D`!z#4 z4eGRAY*16XjQ6?2mtWqYshgwBTMi|XT;>K2(#$b3fTf_d$ccojh=QETcU;DL|7R{eI+ zvq4p4hKg2HW87+FqVD1!>%XqDTsCJ@J1gioH}$5813bNDQXl8VS%T8gsGhic?j*Eg gHLQA;>x#0$*G*U7(6pLb>EiC`@~#u|J3Mgy11E>y$p8QV literal 0 HcmV?d00001 From c51277719606dc2a607d87542d45260ccd373259 Mon Sep 17 00:00:00 2001 From: Akashdesarda Date: Thu, 6 Dec 2018 07:39:20 +0000 Subject: [PATCH 3/3] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 173 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 562 bytes q03_skewness_log/build.py | 11 +++++++++++ .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 179 bytes .../test_q03_skewness_log.cpython-36.pyc | Bin 0 -> 2204 bytes 5 files changed, 11 insertions(+) create mode 100644 q03_skewness_log/__pycache__/__init__.cpython-36.pyc create mode 100644 q03_skewness_log/__pycache__/build.cpython-36.pyc create mode 100644 q03_skewness_log/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q03_skewness_log/tests/__pycache__/test_q03_skewness_log.cpython-36.pyc diff --git a/q03_skewness_log/__pycache__/__init__.cpython-36.pyc b/q03_skewness_log/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..805dcd1b81d12bea6e8ca6c56df22535a03c70a8 GIT binary patch literal 173 zcmXr!<>gwjmm`J&2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CUs3uQ`MIh3j@gOD z87Zm7iA5=i`r-LS*~JBk$*KCu`6;RTX{m`NrA4Xnsd?#{d8w&InR)5)1x5K;smUe! wg$Bm)#o4Lld8x(4@j3bF`tk9Zd6^~g@p=W7w>WHa^HWN5Qtd!?76UN@0B=aZ~rt)VP`74ZG znfMD#_^eW4>E7M*`TWl3ey7ts{tWLwC?Q|u-(ogCx28`mNFr%QmXuS9G0PbDocDPE z-n=HgE#-CT%ixXhP_i4+t$o`%(xt}N3wR#C97s`#s8S-$dx?HZte#t*MYIcR`qDy0 z=5%BAj>r~08<2{jNB&B8S#Ov1cUj+M*@kY|1l5BvZ(ONS`ZQD^cxxYyZh7NIWN@w0 z1bAy7j&8f2VR>o1te7f%yX8K%%-h&M$asp^?U}25C#q(T{@g{gVhPc3A@odw7D|ff zu22hIiUgvhkPuBkR4WBB*5riDX#xJB5(F@pE*a+VxJ0>y7Zrr~?ypbNli`aS#D>sEW@E*f7 zlV{oV{!9-l<~{0{B$jnVCQ(N1)GXOPlpp86K1Zrt2ii1RDg)8pXxcm9NUsY};SA^m z9R?4EEo%$-+LqjVcSaHDvdCE)TrEVnbtMHz5Mr)v9hm3+?UgP&XNDH5@mV733#w}| Au>b%7 literal 0 HcmV?d00001 diff --git a/q03_skewness_log/tests/__pycache__/test_q03_skewness_log.cpython-36.pyc b/q03_skewness_log/tests/__pycache__/test_q03_skewness_log.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..6c631a07681a61fcf4ae362c7c90b8be89d9238b GIT binary patch literal 2204 zcmc&#OK%)S5bmDG?(EArKnw;6MnVBi6nRN5P_0?B3w+DmnPrrJP{%{HT zjWiwy*7soOFF*()XhKpNQi^LUu|iwe!bzOe4c+RSo3zq)*rr6@4Ub zE9{279U|JodrE{S>B0{C!rCQ4X9>1RKuhm)sm*<^KgO#Lxx(o*t1s%h*R$&`q*{ zTLGxX``Fqb3mYK=`_4$Axh0DE+Yi2l$cz*|1X-jqGupopr$TD31Rs8xt9?D=ksL<3 zki)U$rcjc}Y!YWusyLglnacOTmEn{3Z?k41h6d2km1O7lwq}Rr2JWBHVCYQ`T+!$@ zu{}C}?>wYi7i*nC8nr8=--1OG=^AGw8ydne@lG@|A=XXLa~~to_FyCpkBdZ}^9K z0c?}U2O#zSH61wRdd;qf`eCLG&mvj&kOopPK=5Yij#0gI(0)K`WRPwRQ2Yv%Xey(9 zR^Ps(K8X*umE^3_-hlHOLnDBVMdvp!M(1BF{LdgM%x)8xTj~|~qFx1YX;5}~B0p7e zBx_JG!!HQRISXe%!FEwG2YsrUBOGi<3+K22xueN?>)CfN{cv=5i6u6_{#lbMB8O@@ zEfsmvpsG4L(R>cA=SoeO?Ig{0-IUbJVD2AqxLT2;E=IQEg%1iEyDFjccQ0ncd6oZ+ zwrantXr0mI$6tQ`>RJ2wUG+NL^CHng2iOD^g}l8?SgX9e0}7W5Yo#&@I;F>0##6~y z*<~!vMUmjT&lq<6dPl9HL+dE6qIeAjQb@gt;G<1@R e02N%7?Tg$gy*qVeAL3<|PkrbHecHFWF#ZBpW=Wd> literal 0 HcmV?d00001