From e57cacddeda7e0b3654424bba97964554a3bc75e Mon Sep 17 00:00:00 2001 From: nemkothari Date: Mon, 5 Nov 2018 06:56:13 +0000 Subject: [PATCH 1/5] Done --- __pycache__/__init__.cpython-36.pyc | Bin 0 -> 154 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 172 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 722 bytes q01_missing_value/build.py | 43 +++++++++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 178 bytes .../test_q01_imputation.cpython-36.pyc | Bin 0 -> 2327 bytes 6 files changed, 42 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..b183c176b7ea7ac0ea9cae6d30937a680f3ff059 GIT binary patch literal 154 zcmXr!<>d-_c|V!~2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CU+(%D`MIh3d8xVC z`6U^NMVb2H`9;~q1&PV2`pNkzsrqTDi6x~)sqv|K>6v+{sYRK2>G1_c`B|ySCHnF4 dnR%Hd@$q^EmA5!-a`RJ4b5iX<78C<90|07IDC7VD 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..5fb4b328b3cbf3818d9bd4dcd90b64e7efb74f3e GIT binary patch literal 172 zcmXr!<>d-_c|V!~2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CUy=G5`MIh3d8xVC z`6U^NMVb2H`9;~q1&PV2`pNkzsrqTDi6x~)sqv|K>6v+{sYRK2>G1_c`B|ySCHjR1 thVi+X#l;}8vc#OyRQ>q)%)HE!_;|g7%3B;Zx%nxjIjMFaD~o}c0RY4mFU$Y{ literal 0 HcmV?d00001 diff --git a/q01_missing_value/__pycache__/build.cpython-36.pyc b/q01_missing_value/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2608517f3ef3e29a605a0425fcd78471059e2b62 GIT binary patch literal 722 zcmZ8f&2AGh5FYPeHcQh(L4|PO#3h$*5!VWVK8PD^Mntc5pg}CDoJxbN?ag?v96bw zvM!Wykua*3()m=aoo}pm5wlnZJedk96?H*TGVUT;Ra`N&I8~$2?aj;D2sO*PQcvy` z!gN;WdlKZ-a_6hMaAf%d^dScE`!b!E1y2<(mZhCjEz+w}FHMC(r8z#3PC2!;<{4Kr zp*Yu_?@E_l8tKjPvuyW5wxY7;>2)n6JF3<$5k*y7YDK9A-S0d=0CGqIoC!G~PspD4 znCuh%2=_;kiz=!ZHO{M;i?JVAwrvo#&UOju`$*ifw}Ib*hj`%P6D&t9`3vk^FkQRG Je&QX3e*kRQ#ufko literal 0 HcmV?d00001 diff --git a/q01_missing_value/build.py b/q01_missing_value/build.py index 7dc4d18..ecc00b9 100644 --- a/q01_missing_value/build.py +++ b/q01_missing_value/build.py @@ -1,3 +1,4 @@ +# %load q01_missing_value/build.py # Default imports import pandas as pd @@ -6,5 +7,45 @@ # Selecting 4 most relevant variables along with target variable from the dataset fot the Cleaning and Preprocessing. housing_data = ny_housing[['MasVnrArea', 'GrLivArea', 'LotShape', 'GarageType', 'SalePrice']] - # Write your code here: +#MasVnrArea , GarageType + +def imputation(housing_data): + missinglist = list(housing_data.columns[housing_data.isnull().any()]) + cate=[] + num=[] + for k in missinglist : + if (str(housing_data[k].dtypes) == 'object' ): + housing_data[k].fillna(housing_data[k].mode()[0], inplace =True) + cate.append(k) + else: + housing_data[k].fillna(housing_data[k].mean(), inplace =True) + num.append(k) + return housing_data[num] ,housing_data[cate] + + + + + + + + + + + + + + + + + + + + + + + + + + + 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..045666367c805e4e4d2c381835a2c703bef9e9f8 GIT binary patch literal 178 zcmXr!<>hL8c|V!~2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CU-9}G`MIh3d8xVC z`6U^NMVb2H`9;~q1&PV2`pNkzsrqTDi6x~)sqv|K>6v+{sYRK2>G1_c`B|ySCHjR1 zhVi+X#l;}8vc#OyRQ;0F;*w(h`1s7c%#!$cy@JYH95%W6DWy57b|8z3ftUdRApbI9 literal 0 HcmV?d00001 diff --git a/q01_missing_value/tests/__pycache__/test_q01_imputation.cpython-36.pyc b/q01_missing_value/tests/__pycache__/test_q01_imputation.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c4153e5d242547f8085d8ae84cadb098335ca86c GIT binary patch literal 2327 zcmcIlTW=gS6t?HGJ9`Tyl+ti1gGxk4s4&`96Q=__M*F`^)L?Pk(C>@&{S_ z!8f@NMRPEmaGH~X#*|{)$(`8cF86Y;@MFL3^Yd2Gj@y(7cN*~4g2o-u;cXu94)5~b z#NQ%uSNNg}BfWjX`+V?<@PVKUH|}%ikVG4&uoH=>4W0;X9xyFNr%uz;&5BuNn8`{B z;~NuU##Np(HPJJX&NnzSY-kkAr! z@9{p=0UsbNyMcHPmIzV`OX3gr2%tQGqW8cUV(5bYOka|zW89aN(=D=qJ%Q@A@3C`( zEL|M1~Yz=sh$1Zt{6NTb7TemC6Dj)jC)hc7CY zTQ?Una;&FCKDHhb`zuj>aQkyQJSqz@l%jZEnj@yN;SZ&Hu4gP2!?fgLI2O!QN+d!~ zGAV@0EHO;?S5dfhT8VHndT&hqBxN6z35oS7kHe-@A z9exE~j}$A!v%BF*S%Lh-nJ?UYxUHkMz1GO>Kp#kLm`sIr;qt9Bo@I|%%GRL2g=x&si>d zG!MU9*GXDR1F2buBQ`n)^Bo~(yW+-+9EL|tbL(8B!AWlFeg+P_DSdbm1z^)9$8ydw2JnzeKh_g1)fuMB)|8HHBbqx2_M}5vV+;+UW4%q+*Tv7KBU?{?K@p(lLpRT4m?%N literal 0 HcmV?d00001 From e6a3ab80d92b9d1244e288a446c7622ebe4ac6b8 Mon Sep 17 00:00:00 2001 From: nemkothari Date: Mon, 5 Nov 2018 09:24:29 +0000 Subject: [PATCH 2/5] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 174 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 591 bytes q02_outlier_removal/build.py | 11 ++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 180 bytes .../test_q02_outlier_removal.cpython-36.pyc | Bin 0 -> 1790 bytes 5 files changed, 10 insertions(+), 1 deletion(-) create mode 100644 q02_outlier_removal/__pycache__/__init__.cpython-36.pyc create mode 100644 q02_outlier_removal/__pycache__/build.cpython-36.pyc create mode 100644 q02_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q02_outlier_removal/tests/__pycache__/test_q02_outlier_removal.cpython-36.pyc diff --git a/q02_outlier_removal/__pycache__/__init__.cpython-36.pyc b/q02_outlier_removal/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..890901b809e236f44d96e5fb07372c2f15a07de7 GIT binary patch literal 174 zcmXr!<>d-_c|V!~2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CU(xy*`MIh3d8xVC z`6U^NMVb2H`9;~q1&PV2`pNkzsrqTDi6x~)sqv|K>6v+{sYRK2>G1_c`B|ySCHjR1 xM)CQjB{`X?Me#+cx%p*@Ir{POnR%Hd@$q^EmA5!-a`RJ4b5iX2PH_xAOMF=_d;9r}A|6RW1cm*~BA;A$+P0=b zKLB#IkBtSqnJGVBxvnv`%)Y$079nnVSng^ zZ?mBv*4lz@ysE(`{27qa`VE8% Bn(6=m literal 0 HcmV?d00001 diff --git a/q02_outlier_removal/build.py b/q02_outlier_removal/build.py index 74df5f2..defa455 100644 --- a/q02_outlier_removal/build.py +++ b/q02_outlier_removal/build.py @@ -1,3 +1,4 @@ +# %load q02_outlier_removal/build.py # Default imports import pandas as pd @@ -6,5 +7,13 @@ # Selecting 4 most relevant variables from the dataset fot the Cleaning and Preprocessing. housing_data = ny_housing[['MasVnrArea', 'GrLivArea', 'LotShape', 'GarageType', 'SalePrice']] +def outlier_removal(housing_data): + df= housing_data.quantile(.95) + housing_data = housing_data.drop(housing_data [housing_data['GrLivArea'] > df['GrLivArea']].index) + housing_data = housing_data.drop(housing_data [housing_data['MasVnrArea'] > df['MasVnrArea']].index) + housing_data = housing_data.drop(housing_data [housing_data['SalePrice'] > df['SalePrice']].index) + return housing_data + + + -# Write your code here: diff --git a/q02_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc b/q02_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ea33e160c7cca5d917f559bf9d165a4c546d0d69 GIT binary patch literal 180 zcmYL?F$%&!5Jfj&AwmvfIBY7no3oEZ+<)#onyvOG^ zf0^f#{rh<|DX&4lWT|Wtagtms2PY}pAthE&f2bLywwje0DBsh`P zUI-~vE)a7?l1ZMjjE9_)Z>3gfOItdrlewW=zjM=8)(+d8fj#$RYsJG3bYxq4vLk)jow~a$ z^uYxmzjTk7?8*LnCi}owcG#2FF&hrnI1?N4$~ysVo(c`)wbi`&q$o|AfQl4k#hFMk zXfOpcDbrM_sa`<597tir$S9HI2eCd2{hx&XHCIm*h_G{{UL%Az<@k}fr^pAuR zQ#d(CzjG{7_*o?}#8kt_i)Md}x86qsEaZ}fmgLfU&zk=6=}1?$@aa;o_-x4z_TpFf zsfm|Y%Z@pYLl+I~;r$eE{RoX=hOhXa{2iNH#(u{o-(@SD2qAC%pIAF=WfN|k!Wk=g2$RXG~c zN#zjD4@~ti?BCPTtjJ)LL-wXHGog~vZ-siJ7b1pHTu2yAK$ucN1o@-G={R?!q zu{Y33-5bRAcx_|U^4kqv2@_GKCO{3ApaWS1d0~P~n0OXUYt~mIhV~_QMJqnEl#dV9 zB|}X$rjK6r@Wu`<2E2`#RPKZZ3Ok!ID~IME@&@EJhJ%_RodtE; z4mPN%UB(C8;>)jY<+e$=LTaOyPdB9ImUN`O(TF=<@8H&2)Am{({;~~3(>a40L7`l# z1U_!mT0$s?&oEK#qCu^YLexDpm0Ks@(&XK`$p(H@2R_6cO{WUu%e`BB+|C%|8hBBZ zBiksd{3yx_S*GOoqKHn0=8GEOnCcFh2V_1cbIH8+NW6+5lc+WI;Bn8zU#osQ>{niy zCx(hvRAbm`WTNilpUQn*CaG*rrgoCkVQ%V86MA@d%cwrg^YaL$p;0|y@4|^_#cEjf dEH@QZdEYf%eNWSBYNdy}r^kDi&+l>1`VTO9-|GMX literal 0 HcmV?d00001 From a3509911d0ddc345ae78d19d969a14d140b2c71d Mon Sep 17 00:00:00 2001 From: nemkothari Date: Mon, 5 Nov 2018 09:43:42 +0000 Subject: [PATCH 3/5] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 171 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 494 bytes q03_skewness_log/build.py | 8 +++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 177 bytes .../test_q03_skewness_log.cpython-36.pyc | Bin 0 -> 2202 bytes 5 files changed, 7 insertions(+), 1 deletion(-) 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..f1880406856c5fbc77e2dd70e6c508b3e22e4ada GIT binary patch literal 171 zcmXr!<>d-_c|V!~2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CUlIBl`MIh3d8xVC z`6U^NMVb2H`9;~q1&PV2`pNkzsrqTDi6x~)sqv|K>6v+{sYRK2>G1_c`B|ySCHjR1 u#_`43spWa8#l`VC`RV%c@tJv}(RA`}tU!xA^scH7q`YZ=}dS5cPh^y@(h!;@rr7utTMZo zUFd_T7M8#F@w_S_mQXIMX3kX}KU8X|Yo0-zRRZEE@MfhT1v$$lfXd}8tyQ&vtcjmb zhp81QLF*J5;-^(!h(WzEy?r>e3N0I<$9R>kqmDVySzd1jy5Ws>yO~zarQq7IT9`nt q%6g+b>@^{35-EP33b1tZZu>pgc73C=5~~8vtx|1idNiaV>#{$3WqB?D literal 0 HcmV?d00001 diff --git a/q03_skewness_log/build.py b/q03_skewness_log/build.py index f008d0f..9ca97d0 100644 --- a/q03_skewness_log/build.py +++ b/q03_skewness_log/build.py @@ -1,8 +1,14 @@ +# %load q03_skewness_log/build.py from scipy.stats import skew import pandas as pd import numpy as np data = pd.read_csv('data/train.csv') +def skewness_log(data): + data['GrLivArea'] = np.log(data['GrLivArea']) + data['SalePrice'] = np.log(data['SalePrice']) + return skew(data['GrLivArea']) , skew(data['SalePrice']) + + -# Write code here: diff --git a/q03_skewness_log/tests/__pycache__/__init__.cpython-36.pyc b/q03_skewness_log/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f4aa1b61a060b840ad34ea209753912a189ae1ac GIT binary patch literal 177 zcmYL?F$%&!6ht>*Awmvf;}_D3cmf**3&BrF#<(WgANOw%kK~nXEUdhOm778wc#mP4 z$C0dv=d)zmlvQyO3)E` z=sg&&vJUXpRor?Z=DXzWLK7 z}(U!6y9?pJW1zv*cH|e30e!VO#)hakEJ#bxR!&3Re$N~iTo~;TC*e{!HKnz zG{YiExEkrHjAm0vT8kdMmYe@{|Ipe6*skNI5cl|6F zfKi414lICLKr#blHa3!Ng-X_7_Q`R?P#nJ5pGtq2D_==SaaM=#$J&4TX_9mE^oGBm z7r-@ncmPuGU)6zAuGidpq#tG4@GO#L2WcP$0|alD?hw^W2ki&6Mh3~Y0*YUO5{+dv zVfF3X>a%$7zLK0(+8c0QV`v1hvFPmP+35U-h1U#{!tAc%a!Xx=FX|GAbAz(O6ZyG{ zBUyuj8Gc1jPFXks3O0+1Ip|Z(9N}O)nmdQ>#~qB;8!vu%9e*X23uU|A@-c@hIJ+Bfibbw7zQOMi#gtg4e6;L=|SWA^b&?-H~GM-At z$~I$ZE{X)#UBD{R#`xq~)eCk3s=+ds$hVeI`;7Ppz literal 0 HcmV?d00001 From cc230041502f8e123e9bc26cb38208d5b97ac95c Mon Sep 17 00:00:00 2001 From: nemkothari Date: Mon, 5 Nov 2018 09:54:04 +0000 Subject: [PATCH 4/5] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 172 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 503 bytes q03_skewness_sqrt/build.py | 7 ++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 178 bytes .../test-q03_skewness_sqrt.cpython-36.pyc | Bin 0 -> 2073 bytes 5 files changed, 6 insertions(+), 1 deletion(-) create mode 100644 q03_skewness_sqrt/__pycache__/__init__.cpython-36.pyc create mode 100644 q03_skewness_sqrt/__pycache__/build.cpython-36.pyc create mode 100644 q03_skewness_sqrt/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q03_skewness_sqrt/tests/__pycache__/test-q03_skewness_sqrt.cpython-36.pyc diff --git a/q03_skewness_sqrt/__pycache__/__init__.cpython-36.pyc b/q03_skewness_sqrt/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..154aa8f3fcb046646433e940853866e0a4b3b59f GIT binary patch literal 172 zcmXr!<>d-_c|V!~2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CUy=G5`MIh3d8xVC z`6U^NMVb2H`9;~q1&PV2`pNkzsrqTDi6x~)sqv|K>6v+{sYRK2>G1_c`B|ySCHjR1 v#_`43spWa8#l`W(g+(R$@$s2?nI-Y@dIgoYIBatBQ%ZAE?Lbx*12F>t$(=9s literal 0 HcmV?d00001 diff --git a/q03_skewness_sqrt/__pycache__/build.cpython-36.pyc b/q03_skewness_sqrt/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..528cfd62c2488bafc4dce3a38d18efb1c4559f03 GIT binary patch literal 503 zcmY*Vy-ve05VoD9O$%j!iAU(tRCKKnh=B!FNR>beLuBG>n>KM$+bJqyE3d#q@JgAG zn0N&y&K5}Jto!@)oxVGddcE%OG|$M)6DzQoTu0&za3W`W3n!V=!b% zUr_Iq>|7rIA?z1nh%jWh-c^n}v#Q=C?o4?Ow<=2^?p&*zY;&oA_q~S63U^s6qwHz8 zSXXY7MOo`i&fke@A^3e4Ey@BS3B{^33$C*0zEmq+@f4!86cEjTn_58va-K;5g|kVe z$|a;GS`SBwy;XwNi4}?->ns<8YTNYw;h{a%>JfU3PuafTX%2LnRoj6!+-SFB)2g@> xTsN!|O(5%{+A0sZO^6qX1bhBRbd`UB1%eKi08 literal 0 HcmV?d00001 diff --git a/q03_skewness_sqrt/build.py b/q03_skewness_sqrt/build.py index 4bdb0e4..670b99e 100644 --- a/q03_skewness_sqrt/build.py +++ b/q03_skewness_sqrt/build.py @@ -1,10 +1,15 @@ +# %load q03_skewness_sqrt/build.py # Default imports from scipy.stats import skew import pandas as pd import numpy as np ny_housing = pd.read_csv('data/train.csv') +def skewness_sqrt(ny_housing): + ny_housing['SalePrice'] = np.sqrt(ny_housing['SalePrice']) + ny_housing['GrLivArea'] = np.sqrt(ny_housing['GrLivArea']) + return skew(ny_housing['GrLivArea'] ) , skew(ny_housing['SalePrice'] ) + -# Write your Solution Here: diff --git a/q03_skewness_sqrt/tests/__pycache__/__init__.cpython-36.pyc b/q03_skewness_sqrt/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..923294567efb5521f0e4ede51ead2fd526fd7d75 GIT binary patch literal 178 zcmYL?F$%&!6ht>*Awmvf;}_D3cmf**3yV)k#$=7zP4@pF9?2`&SXg-lD>sEW@E*f7 zlcniw|9&1#%xlyyNi3U)OrlD&GxKD7H({Lr`Y_eL1v#{h*E$cD4n8!}6bN(xaSX6vjnFS^@fx@vtnT(BOGC1Sn^;WAtR literal 0 HcmV?d00001 diff --git a/q03_skewness_sqrt/tests/__pycache__/test-q03_skewness_sqrt.cpython-36.pyc b/q03_skewness_sqrt/tests/__pycache__/test-q03_skewness_sqrt.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b8ed3b9d81bc6f7da6dba1ad5ce81db3a36abefa GIT binary patch literal 2073 zcmc&#-EJF26rR~1d*j$q!cR-8s;rO#+A74*T!AXms+6b_vMN#)X+hdfJ;%-_`{T^a z24a;f_hk^Tz?19+NO0vF9)KG-XV-OXl1j}LYt7l&ojGT}^UZgTcRQWdlj-l@ebiv= zPquJ5IKPKOKSd*%MkJqFyqHC0hvz@*^?Ng*z7sa@TL*GRMEaZ}fmgLfU$!gqqccd#Dcz0`D zVMDIWo?C1V4*Z zEj$mbYiwc@Y4`!BrzqT%%=rC>KVoVIq>ot^DP%_bTXNgqk53`PS>Pxa_bED?a#d&z z$~-(NL{i!bWPw#W8j?Zj5Jx{V)y8dqr`^Lmg>DAvac&NUio4(D>R69NAG-ZqLU#bd z6bd59hH(a<;%pd=RDOg&x+kCPMoS0LHOPjp?8g@tcSdLBb=t7(6A>K3q6s&%Jw6UD zkh=34za_HCzask6P zF}%DZu+Q06bk2dLT6j~dWGJE9bZ}PQxCH+!+*`O_r_M3;?Ket&<~q-wF-<*xWALPncfJdFx4EVA3pM90&!aUpd&+-B_2eS<* z0e?#ePPtxd?2&$yX(O^el(57}8_$@y;6&GDN-8<`~oX?)Z6%4y@TcolpKfz9;>(yH_`9vl+4|iD4~W? z)eM2DRYRRn+7oBqf`*^p+I_tF&mVhJs<83xZx&@Db1atgN`Y4`swyMwIUBV`?k8!k z>u#h-@t5bV-o>R4aA<0tj9(qJFT6J69bG_L_iQryBZ1J?_h zr58n+NFj>KRurYVEE1ZxqlnsWy`t7A>^d3BPEnMF_E6OV^$0~Gr`}ODLyvn6&&6NE zv#XV$Q+h=f8>$sW?1YVx$fVGvHIk+KyoeK7cm8Ia(O;mc+EeIZ4ao@q0>f5z79Hk= i#`3L>ph~rheHon6yIbe;1%0f-)W!;I^S0IEZTnxT))(^t literal 0 HcmV?d00001 From 265f4753e1be49232c738d0fc83176d4d566ba55 Mon Sep 17 00:00:00 2001 From: nemkothari Date: Mon, 5 Nov 2018 11:56:09 +0000 Subject: [PATCH 5/5] Done --- q04_encoding/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 167 bytes q04_encoding/__pycache__/build.cpython-36.pyc | Bin 0 -> 673 bytes q04_encoding/build.py | 9 ++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 173 bytes .../__pycache__/test_q04_encoding.cpython-36.pyc | Bin 0 -> 1731 bytes 5 files changed, 8 insertions(+), 1 deletion(-) create mode 100644 q04_encoding/__pycache__/__init__.cpython-36.pyc create mode 100644 q04_encoding/__pycache__/build.cpython-36.pyc create mode 100644 q04_encoding/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q04_encoding/tests/__pycache__/test_q04_encoding.cpython-36.pyc diff --git a/q04_encoding/__pycache__/__init__.cpython-36.pyc b/q04_encoding/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d5b165f48e9c5d6fbed2dc11484cf723e499a48a GIT binary patch literal 167 zcmXr!<>d-_c|V!~2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CUm^M#`MIh3d8xVC z`6U^NMVb2H`9;~q1&PV2`pNkzsrqTDi6x~)sqv|K>6v+{sYRK2>G1_c`B|ySCHjR1 nCO~nZGN7P-e0*kJW=VX!UP0w84x8Nkl+v73JCJR~K+FIDzg8`q literal 0 HcmV?d00001 diff --git a/q04_encoding/__pycache__/build.cpython-36.pyc b/q04_encoding/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..f5a034ff40231e18cafa71e6dbaac321108f00f8 GIT binary patch literal 673 zcmYjO%Zd|06s@X$Os6La8gMb6kWE_9We`PVK;oc86nYj-rR%2CNx!^RJs3$=aqEZp zDgHvO1XuG5uDso&I0g4v)Tw*UeKHz_Kcb)4*MhNM?B4Mye@>?73%P>gRh8BX@XJ_9 zBO`+{uV$&fvEdu3KUDYvLE6D3F7lf`4HmUoZe#;Cyp$+2c)zE7u#^S7#XNquoFA-1K;uk&40m8T@-U>#MYtA={iS2m3v?Zk%^AQH*sVKw)K?rzakF) z6?%jikN*vm^i;4@>9!ky*tzm^uBSedk}MvrbCVFaO0R1yt!R`z&%h+AEz2CV_0zga zrLnHUx|uq5xT#y6S6R}D5|0bHDxgT zH=IyC4XoeDN=c0&mGL9JD?nm3YY+%L1>FtbQ?~&vP$m6Ft9|m97mn#!57pDS=N{69 W4d!L7+5(<+OVk0mfDc8;C*lv!O18WJ literal 0 HcmV?d00001 diff --git a/q04_encoding/build.py b/q04_encoding/build.py index a52c57f..10e967b 100644 --- a/q04_encoding/build.py +++ b/q04_encoding/build.py @@ -1,3 +1,4 @@ +# %load q04_encoding/build.py # Default imports import pandas as pd from sklearn.preprocessing import LabelEncoder @@ -5,6 +6,12 @@ ny_housing = pd.read_csv('data/train.csv') housing_data = ny_housing[['MasVnrArea', 'GrLivArea', 'LotShape', 'GarageType', 'SalePrice']] +def encoding(housing_data): + lablel_encoder = LabelEncoder() + housing_data['LotShape_Label'] = lablel_encoder.fit_transform(housing_data['LotShape']) + df = pd.get_dummies(housing_data['GarageType']) + housing_data = pd.concat([housing_data,df] , axis=1) + housing_data= housing_data.drop('GarageType', axis=1) + return housing_data -# Write your code here: diff --git a/q04_encoding/tests/__pycache__/__init__.cpython-36.pyc b/q04_encoding/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..bff2f500038a7d2e800367f934d0dbcae2b0cd80 GIT binary patch literal 173 zcmXr!<>d-_c|V!~2p)q77+?f49Dul(1xTbY1T$zd`mJOr0tq9CUs3uQ`MIh3d8xVC z`6U^NMVb2H`9;~q1&PV2`pNkzsrqTDi6x~)sqv|K>6v+{sYRK2>G1_c`B|ySCHjR1 tCO~nZGN7P-NosLPv3`7fW?p7Ve7s&kO>f&q5Z&d6MA4FvIEh=MMMAX5L4aWeO)mw4AVumL0aCT7jTT@J%$7Tns8FP` zyEI}UJt=>t_x_PydFi1i{e_-7v$SP7X-a{^(eCW*yf<(6VXqgSuK)VwPmi&`+1ArS z{|UZYqLEDUoXvU6Ir&cR#IAIumwR(R_U)LTx907*%^A3}K(?3 zy+-r~WQ0Uib100C?#qMdI6H#^y@98Ej8oWGR__R{L7AghmB?#1hhpH=o`!r}dqm^! zOm#8rpL94a=P)c_{<1Vvp|au6rFy9sB84IH55qACQz=NGm}CWj!j2>hRnD-G;j0H< z;&{`hp+OF`waNDQ;o`jBrMXRHLi^L^nhIr3z?b*72|Rp1`WmOS%5r)aoo!AVMoFw2 z{@l^p#i-?18|oyCMU|WAOym{lNS0AinrJReI*lfl$mXJDcRSM}-V{L*F~h-LcFy1=>t@ z^&SG&1fTIfclh$N_o;h#$u;ISQn|fhZstf&x*LJ`qxBznXx7xt<%1u$3DR_Rpg>S1 zR}z8CBWU%5TKE_js(myl6q1M9MN|8B@dvQp+{S7HKgBhg?hD43cRz^HhK{fqL6Q{6 zZIaYslFUn4<>YshgbsT%qxzUk-5~Q3nNP@Eac(`5tRi*^yr$v<9{Bic+0j9-4yqzE zRIQ@o;#Q*D!vb+3OQFZXB WLG_rn)dZ!BC#TE1PRMt8;QR}CQ^mOe literal 0 HcmV?d00001