From 96acc86ec38ed1aea6148a4830fd1bf474d4dd6d Mon Sep 17 00:00:00 2001 From: rohanhg91 Date: Tue, 1 May 2018 07:28:32 +0000 Subject: [PATCH 1/2] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 196 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 822 bytes q01_load_data_and_add_column_names/build.py | 17 ++++++++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 202 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 0 -> 1188 bytes 5 files changed, 16 insertions(+), 1 deletion(-) create mode 100644 q01_load_data_and_add_column_names/__pycache__/__init__.cpython-36.pyc create mode 100644 q01_load_data_and_add_column_names/__pycache__/build.cpython-36.pyc create mode 100644 q01_load_data_and_add_column_names/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q01_load_data_and_add_column_names/tests/__pycache__/test.cpython-36.pyc diff --git a/q01_load_data_and_add_column_names/__pycache__/__init__.cpython-36.pyc b/q01_load_data_and_add_column_names/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e7e5716f2b3285d1dd77bce5e3706da36909c92f GIT binary patch literal 196 zcmYL@u?oU47=%-B5TUE@;80_65<~>~Hc1B`$yai9@fn;<2l3!O zj)Q|+=J~`=-)E8Z8t_w=!ZtaK5=c~HmK`6$5A`3PPS$L-^jxE>FRN0X*xy2nN=wD0 zWfd_Rz7z-TEjrkFO-+P7Ml7K9eAOz-Zc&0^B%o9SIszmD#iq9o99kVDK;zO5=I#AC OUR$Q#=*@5?B#SQybvHr) literal 0 HcmV?d00001 diff --git a/q01_load_data_and_add_column_names/__pycache__/build.cpython-36.pyc b/q01_load_data_and_add_column_names/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..dda174036b925f3497daf9e51cbca3e7671c5e57 GIT binary patch literal 822 zcmah{y>1jS5cclv)bHtdl)I}u3O-taYDRKO;()-jWpqQ7a7PAx*nk0~ zun9xhf+sM7F>J#QJcVa4fnAsuQ+WP8{u13pFx_X%7-q2dH4fSd`)k{W**_b#c5ueW zGS5w`y>MRo)^+{bXkYSiZV@Uk%F20TSKXj#ZDSnr(St+QA!|K#@~YB>6Av`m!f0@O zh;^gPsz&YkPNj)ksh|ieJ+3DWT4%IW4@EPF*L+yC(n?L$9N)I+DnOm1a1~*fHr7y* zU-6zSkk5=S(Tc~!jgs2&L1|jbDENVH>jj0F3xU^k2eOI#&K*ydX5sjTs^mf;-}I=k zDUC)xzAzT6LW|GFenPuW3u7Q#NSH@mU&|WZZJ3u0a2qBz?{#qlU20K+pmBBsi_}Pt z^SDbI>B}w&L;u0-h@yY%tTZ)d)|670#hc^oBh_&Y#b>zz%+6^9$`pt9e?*+#k0AV& zLqQL)#N20>FOP*XR4xz;sX<7f+D5gt7I!^ni?&j5)U3J}{|_EeUoItJ(d%fJw%w-l nJn1$X;+D<^pWO-&9C!D41Y@#w=}B#%RroeMiAxC5UK0NS4(#|_ literal 0 HcmV?d00001 diff --git a/q01_load_data_and_add_column_names/build.py b/q01_load_data_and_add_column_names/build.py index 3c7624e..d52d0e9 100644 --- a/q01_load_data_and_add_column_names/build.py +++ b/q01_load_data_and_add_column_names/build.py @@ -1,6 +1,21 @@ +# %load q01_load_data_and_add_column_names/build.py import pandas as pd path = 'data/GermanData.csv' -def q01_load_data_and_add_column_names(): +def q01_load_data_and_add_column_names(path): + data = pd.read_csv(path,names=['account_status','month','credit_history','purpose','credit_amount','savings_account/bonds','employment','installment_rate','personal_status/sex','guarantors','residence_since','property','age','other_installment_plans','housing','number_of_existing_credits','jobs','liable','telephone','foreign_worker','good/bad']) + data['good/bad'] = data['good/bad'].replace(1,0) + data['good/bad'] = data['good/bad'].replace(2,1) + return data + + + + + + + + + + diff --git a/q01_load_data_and_add_column_names/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data_and_add_column_names/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..849da34aee8027edfd1d3c45621f8cad03148818 GIT binary patch literal 202 zcmYL@u?oUK5JWFvAwpXJ!6Kf)N)Qng>}*m9Hp`M-Of+{J?=Fa+ zx(FB=Ib}O`1}$tHQypN70W)ZwoVg78I?JIEB%oLWS^^}3Qku?KuxQxpz&>~lP}{hM SX?uSTmqw^-c-0^B(dr9y4mqj- literal 0 HcmV?d00001 diff --git a/q01_load_data_and_add_column_names/tests/__pycache__/test.cpython-36.pyc b/q01_load_data_and_add_column_names/tests/__pycache__/test.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..9939db37700cc90b4f360f6c642425be3d10a100 GIT binary patch literal 1188 zcmah|OK%e~5VrS`Y|4I+5x(Pa%Q+y~!IcY0v$8E4(;iVf{C+^hee%j4?aS!Z9?8%Pw z<}}_sC88;UTOtD4p1W~h&@&RX7EqrIBWi=u#%Lhv+;wl`7-;doT|YeU)I1`-Rz$K=e~kvhEr> zroy=;v5S4c?g<~THS80_^g#jy$g+fC3MNJgg;-petO;@qqW3@ZRGG}pu8zVNVlO!;rXrR;pqOum=CXhk*f}bgd7{YumzChA0t(M$m+|>1^jO zbRMkySHvPO7*`Yf2n?VTsGT~(6Yh#Yf4I1F30XV_huNF+u?$yCDrqW}hvvGJp(w(< zFk!|`G7i5?%s4dQy5VVW- z2Q={NlV~e$l4fIlI#!P{j+@9;)7vK-JpeMUR@I35k$-_Bb)qW}N^ literal 0 HcmV?d00001 From 5e0274edab27244a14e8cdc82c83b51ba6ec10ae Mon Sep 17 00:00:00 2001 From: rohanhg91 Date: Wed, 2 May 2018 11:34:29 +0000 Subject: [PATCH 2/2] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 182 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 799 bytes q04_correlation_plot/build.py | 26 ++++++++++++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 188 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 0 -> 896 bytes q05_split/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 171 bytes q05_split/__pycache__/build.cpython-36.pyc | Bin 0 -> 763 bytes q05_split/build.py | 15 ++++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 177 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 0 -> 2190 bytes 10 files changed, 36 insertions(+), 5 deletions(-) create mode 100644 q04_correlation_plot/__pycache__/__init__.cpython-36.pyc create mode 100644 q04_correlation_plot/__pycache__/build.cpython-36.pyc create mode 100644 q04_correlation_plot/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q04_correlation_plot/tests/__pycache__/test.cpython-36.pyc create mode 100644 q05_split/__pycache__/__init__.cpython-36.pyc create mode 100644 q05_split/__pycache__/build.cpython-36.pyc create mode 100644 q05_split/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q05_split/tests/__pycache__/test.cpython-36.pyc diff --git a/q04_correlation_plot/__pycache__/__init__.cpython-36.pyc b/q04_correlation_plot/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a3d139fdeb6fdfece6f01167b6549f2c552dc9ac GIT binary patch literal 182 zcmXr!<>e|8dlAI|1dl-k3@`#24nSPY0whuxf*CX!{Z=v*frJsnuVnp<{M=OiqWp}+ zyo_{9L;djlqU_>=#N<@{UH8QVNPAwW?Ie0RJP?;h{&JkKXT`v+1)2>nKn7M#(0*!D93M;uGEz$6;9 zm?R)0dC;XK#XIkaj0WGBj6ufou$z#{;7jCDmyrzg1CsNUkG>;v%<(mvjvpX4x|(92 z_eS(aSHjv>)nGVT&CaP%mF9xp3g*^ESTMg{&CaOQj8o1WqfBwiIH#4C>rPR{I$^(^ z1XuY{n2xCrpca+=TH%lhR=nSrAnhvvhqmY*-{CD@;CplzZKFlRF^_)WKpsfOS3YT4 z>mYlwY!#ozCV_iCskAXZ>7{nl7$kFz#|)})3v`V6h0GEB_UB94=uVVIH%vA4+q3dU zo2BhpCCc!)^4c*cb$zk6z{@(*kgbRR4a>~;|wr~{sQV5>c{{9 literal 0 HcmV?d00001 diff --git a/q04_correlation_plot/build.py b/q04_correlation_plot/build.py index 5e0d2ae..96d9e2f 100644 --- a/q04_correlation_plot/build.py +++ b/q04_correlation_plot/build.py @@ -1,9 +1,29 @@ import matplotlib.pyplot as plt import seaborn as sns -plt.switch_backend('agg') +from sklearn import preprocessing +#plt.switch_backend('agg') import sys, os from greyatomlib.statlog_german_credit_data_project.q03_encode_features.build import q03_encode_features +from greyatomlib.statlog_german_credit_data_project.q01_load_data_and_add_column_names.build import q01_load_data_and_add_column_names + path = 'data/GermanData.csv' -def q04_correlation_plot(): - +def q04_correlation_plot(path): + a = q01_load_data_and_add_column_names(path) + df_corr = a.corr() + df_corr.plot(kind='hist') + + + + + + + + + + + + + + + diff --git a/q04_correlation_plot/tests/__pycache__/__init__.cpython-36.pyc b/q04_correlation_plot/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a85ef4fef46b2251da2c1a66e7aa5fb6a233f58b GIT binary patch literal 188 zcmXr!<>e|8dlAI|1dl-k3@`#24nSPY0whuxf*CX!{Z=v*frJsnuT1@n{M=OiqWp}+ zyo_{9L;djlqU_>=#N<@{UH8Yx15VhBvWSb^w5mk>>IUo_KbU|=ILa0)ydh4Y~NPDr&dXjALe$@6>G%Ba` z&+w0suUzO~;Ka;EpdRYgynUW^X5KvK&3HVt`@gfFoUvc*!HSWeV7L{6W||w8@$MaE zQTG;^fM^*ndms?|9S#taHK&KuuOhQm4znS0p<}aMjaEOcYr!aA)Rk;Z?J+-@ zgP*m=C_8rz2dC^bE^7pQN0rkw}$}ToH!%b(H+Z#7N{Z)d(>S* zmDd{N43uvzxEx*U7F8HvoMN~m1kXHru#CR*TecKFzQr9?)O^Ed(LP%X@&c=ii+d`x zdUo~=^?J~UD7`JA@-N)<@VP!ZJTI=HLN@K$9-g#xJ0Ye4!?tn`tUtSIl?lQ?HH|{- zz|4Zc??0FwW%A0!ra^sRbwV(?x$*q^N zvGo#VrH|R2dbGuLc--8CE!s-bMO_`qWPHe12amaT{QvL;8k|U3sS>0NLn+Hzw}$vg zN*ZkQ#qMCaZk`7)p|I8XbhYK~lRAH_9(UUo{O>I>gJm zsKP)OmU@JK-df}#X{*AMK1&rt?@L=4y|H~zRP?v<-A#l@&$@086w&CGWQFAYW{?kb Sy>1sF;k*2RkLZbFo`}D&@$8xa literal 0 HcmV?d00001 diff --git a/q05_split/__pycache__/__init__.cpython-36.pyc b/q05_split/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8505c5be7a34f456b51d99f2a1cf2462e72b8709 GIT binary patch literal 171 zcmXr!<>e|8dlAI|1dl-k3@`#24nSPY0whuxf*CX!{Z=v*frJsnuL%8&{M=OiqWp}+ zyo_{9L;djlqU_>=#N<@{UH80I5iD>ZL-IsKWBb-rclGytTbZyGl;5 zM;-u<+;|jT!B-AwUx5pZvrzTGNHhLC{+Vw+`)GH!fB1EiJs=4EKsU?-{2W|AhQJZW zCCauV&M?eLNh&Y%u*-R+UjQBxzdp?Y2x z26B5>2S-%Yx#WUQ1TzaI^lFbY!_t>RRjhsiaFpx!Kfio-_Wju=hU;?2&e;xl5BwNh zzk^^+hd6657-&%Z@g=e&rEb9RP)v|E;F984&-;f%@`CqTo znXE*r7&E+jZ~L<&T^4DWz$ojQ_AW7R#JMb1TPGA((co_k{2R3>D9r*?W?5Y zMN#t6d}-tBoTIAy5D*^V2;af?u(}PigeV^d6*wGOPcOA4QfGJdWht1dM-`MWsTL)a zC}iCUkiD8Jv1CS8WicK(sel`ucF#@oEw@gJztl$m`6Hu_WGAh1f1qR2iE$&`f(08r U0S=2&JayV@C-)F~7+|0L0S4^T5dZ)H literal 0 HcmV?d00001 diff --git a/q05_split/build.py b/q05_split/build.py index f2a25f3..ea20f09 100644 --- a/q05_split/build.py +++ b/q05_split/build.py @@ -1,7 +1,18 @@ +# %load q05_split/build.py import sys, os from sklearn.model_selection import train_test_split from greyatomlib.statlog_german_credit_data_project.q03_encode_features.build import q03_encode_features path = 'data/GermanData.csv' -def q05_split(): - +def q05_split(path,test_size = 0.2,random_state=9): + data,data_dict = q03_encode_features(path) + Y = data['good/bad'] + X = data.iloc[:,:-1] + X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=test_size, random_state=random_state) + return X_train[1:], X_test, y_train[1:], y_test + + + + + + diff --git a/q05_split/tests/__pycache__/__init__.cpython-36.pyc b/q05_split/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..53f5b88ca49eb579d6aa50e5049b4f12cc4f599b GIT binary patch literal 177 zcmXr!<>e|8dlAI|1dl-k3@`#24nSPY0whuxf*CX!{Z=v*frJsnuQ>gT{M=OiqWp}+ zyo_{9L;djlqU_>=#N<@{UH8Q)Z&t2{rLFIJfNa@y@JYH95%W6DWy57b|8C;ftUdR>)9`^ literal 0 HcmV?d00001 diff --git a/q05_split/tests/__pycache__/test.cpython-36.pyc b/q05_split/tests/__pycache__/test.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cc6dc2f81ac863c5ba9c4390ccd7785bc6b5684a GIT binary patch literal 2190 zcmb`I&5qne5P;pb$K(0UCYvlQKUs4?!cwvWigE~wAkq@8a+%9U0{LP!(>*hu_%Ge< zg&l3ANSiAU0B^vXfW#B@l>^KxaH6WcGnv`2fRfm9b=fXg*H=~DzSHZq#m=A6Z?0wi zZmk^+&>z4hpMzi)BdHY;Gun}DMkjK(J#%Lb?tt`+Y=ZR92%ZGLveQ=9j@qC*%uPF4 zH|m<_jkK5bqdw?ff#SSE8Gbp_2?k;PI`#YZ^j^1#_1z$Nd4;3gN42g2+ZR^%WZj4o?155@-4 z!053SYs1)N9oB`>XFXu)>kcy1G0PDFe|X>oO}Gx=lD9x8OFLq$55U z6^sv#AZKYYxm{;FJ`kKGD#onej!RL@AgsZvRs+nrG;+T@(RB$hm>x_eF*b{|$^6Dz zruI#l&}JiNXlrtI6O=kn!o0LwabwS{xZi~v=n&`@u_4%+(Kfgc=m&5SQrm2-8*)lZ9+H|Dn`I64xoMbkexs&# z1x8s{^aIpB1aS%EW?3O_C>8EI|6SJFb{Mv_AICY(cpU3?9A^cqQq;R~jN5PhMr>gm z*HFBJ;yn~NkJv-;a)lWUcNBrY4%}`e3ZM8coDQDmO?Wl(O8B)=DG*UR@