From 4a6da3e2f8642a3b15a424f085614677e4846717 Mon Sep 17 00:00:00 2001 From: rianboy18 Date: Thu, 30 Aug 2018 07:54:40 +0000 Subject: [PATCH 01/14] Done --- __pycache__/__init__.cpython-36.pyc | Bin 141 -> 157 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 155 -> 171 bytes .../__pycache__/build.cpython-36.pyc | Bin 414 -> 389 bytes q01_load_data/build.py | 12 ++++++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 161 -> 177 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 1525 -> 1541 bytes 6 files changed, 10 insertions(+), 2 deletions(-) diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index b0c3719c2f46201b3baa3fcef746c16a601c9e9f..a0cb688d839e7ca3b999bcb2d20aceae2906ec9c 100644 GIT binary patch delta 51 zcmeBWoXf~z%*)HQc2RruL=JO#Fa3=C+*JLd%*4E;{7OR${qX#v?BasNarOYVoeNd~ diff --git a/q01_load_data/__pycache__/__init__.cpython-36.pyc b/q01_load_data/__pycache__/__init__.cpython-36.pyc index 4596200714efc1a2bd21ca0d0f36671155da8439..e9d8a841afce9cdd4101317751baac970c31f1cf 100644 GIT binary patch delta 51 zcmbQuxSEl}n3tDp?V|SRi5%wg5&9YVxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{d@tXZxL7k delta 35 qcmZ3@IGd5fn3tF9rT(I*i5%wq9{L&ixvBc;MX8mECHc7%<9q?TUki=^ diff --git a/q01_load_data/__pycache__/build.cpython-36.pyc b/q01_load_data/__pycache__/build.cpython-36.pyc index 98e98a79cdf9a026efe48fdde2a84d1da49836cc..3310d28ca7feead121da18375273e388f78041f1 100644 GIT binary patch literal 389 zcmYjNu};G<6ttZb(n@7Od;&`b8Y&hf5JF<_f)G*|A~)|rQ5eIj7MYnF2mxqt}bSC&T@ zp?KkWj4>zolBK<0+GLZ*J&;aj)^&ibJ7}aEm3C3`VA6!#m~cU`yF`x7`4c68co)z7 zDI`Uc6+cP2k1Xm`c%dO57?e;rIjxbDSW7qa0&YK<*`|!uRW?%%W~P$uR4vEH*|jqF zR?8BzQUPX7SG#H<$#+;7yfbKRrP@LpHOJCr4~OHTR`kNU`?RZS80n?&Z?s;h8+tRo u!%d&gwCA_9Y(ZKRbQ3n#hUewF)IUnd^T}zWpsVpLe1Q#8!ef!d3I78q9bSC^ literal 414 zcmYjNyG{c!5VU>AhbNR@A}LMAhs z4vf^1BkmCX1Syb?zGEk_HT$6Nw8L)5;b6_W3<~J2X;RUtoNVb;MPufr-6XqB52<1? ze{y0LM@}rj=*9;TqncnE~Bj3|;^L From ffa5657040c7971303690ae452727ba88e65c2c3 Mon Sep 17 00:00:00 2001 From: rianboy18 Date: Tue, 4 Sep 2018 15:35:51 +0000 Subject: [PATCH 02/14] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 156 -> 172 bytes .../__pycache__/build.cpython-36.pyc | Bin 660 -> 716 bytes q02_data_split/build.py | 18 +++++++++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 162 -> 178 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 3134 -> 3150 bytes 5 files changed, 17 insertions(+), 1 deletion(-) diff --git a/q02_data_split/__pycache__/__init__.cpython-36.pyc b/q02_data_split/__pycache__/__init__.cpython-36.pyc index 5d17273741a726a430cdf3ccf2eb63426483d618..3e80378045f6f1e3dcca73826160001cd93ab66d 100644 GIT binary patch delta 51 zcmbQkxQ3C#n3tDp?V|SRi5%wgk@^|=xvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{rmu>_7PkF delta 35 qcmZ3(IERtLn3tF9rT(I*i5%wqp86U2xvBc;MX8mECHc7%;py_L@vlJVl9lDfzka#U+U)sZpFIsl_Gn#hF#9 zFaHBU5i3wNP!UUJPJVI`&|(Hn_FGITX}1_7ZZTFyu}8$06eVWnMX^Opj%Soq;RY)B z6{eq&pPQ;*l$n^9lwWCRp&y=KlwDkqn4GGgoS%|9xrfnRf&-|q7(_5IiZKeYNiY`i z0@<3}lV39y`mh0+QLK5TxdoNCnDPq1QnwhBi$JC$5j;TdEe@O9{FKt1R69^06!QTI Q9!4HU4iIGG;N@Th05LsG`Tzg` delta 255 zcmX@ZI)zo)n3tF9i20(Zxr_`9j~S2v6Oioy#Kk5Pm37!zQ`lM0 A*8l(j diff --git a/q02_data_split/build.py b/q02_data_split/build.py index c2e7147..da82dcc 100644 --- a/q02_data_split/build.py +++ b/q02_data_split/build.py @@ -1,8 +1,24 @@ +# %load q02_data_split/build.py from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data from sklearn.model_selection import train_test_split import pandas as pd df = load_data('data/student-mat.csv') +import numpy as np -# Write your code below +def split_dataset(df): + X=df.iloc[:,:-1] + y=df.iloc[:,-1] +# for i in range(10): +# for j in np.arange(0.0,1.0,0.1): +# X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=i,test_size=j) +# if (X_train.shape==(316,32)) & (X_test.shape==(79,32)) & (y_train.shape==(316,)) & (y_test.shape==(79,)): +# return i,j + X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=0,test_size=0.20000000000000001) + return X_train,X_test,y_train,y_test + +c=split_dataset(df) +c + + diff --git a/q02_data_split/tests/__pycache__/__init__.cpython-36.pyc b/q02_data_split/tests/__pycache__/__init__.cpython-36.pyc index e780e63f202604d8b01427afe772dd73a1ea13a3..11fc27a64e21abc7f6395393ab87b0d9997e9260 100644 GIT binary patch delta 51 zcmZ3)xQUU&n3tDp?V|SRi5%wg@%kD0xvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{Xzh#AQ5x` delta 35 qcmdnQxQLO%n3tF9rT(I*i5%wq{`wjDxvBc;MX8mECHc7%<3a$vzzeDX diff --git a/q02_data_split/tests/__pycache__/test.cpython-36.pyc b/q02_data_split/tests/__pycache__/test.cpython-36.pyc index a1b3fc579e35798e380953fe62d7efac2225573f..a99fb82da43af8edfcce7b1d536ce364c3ec5671 100644 GIT binary patch delta 54 zcmdldaZZB6n3tDp?V|SRjU38M^3nPk`MIh3MVX0tN%@tA7W(1&McKs#iOH$@$@wX% Jo2{5wxB%w$5v~9L delta 38 tcmX>nu}^}-n3tF9i20(ZjU38M{NDN*`MIh3=|!oPi6!~Do4uG=xB%so3&#Ke From 0f843b8ddfab31932600f692f13c55102165d731 Mon Sep 17 00:00:00 2001 From: rianboy18 Date: Sat, 6 Oct 2018 16:04:46 +0000 Subject: [PATCH 03/14] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 159 -> 175 bytes .../__pycache__/build.cpython-36.pyc | Bin 924 -> 810 bytes q03_data_encoding/build.py | 11 ++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 165 -> 181 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 2197 -> 2213 bytes 5 files changed, 10 insertions(+), 1 deletion(-) diff --git a/q03_data_encoding/__pycache__/__init__.cpython-36.pyc b/q03_data_encoding/__pycache__/__init__.cpython-36.pyc index 884722b9e5eb21d01be2d88d202ca11e74eb4609..4ba5cca90ea9fd0668328d2df4f3de1ef247e825 100644 GIT binary patch delta 51 zcmbQwxSo;2n3tDp?V|SRi5%wgG5Q(#xvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{Q?1}ixFr5 delta 35 qcmZ3_IG>Tjn3tF9rT(I*i5%wqKKdE?xvBc;MX8mECHc7%;{pM^y9=HG diff --git a/q03_data_encoding/__pycache__/build.cpython-36.pyc b/q03_data_encoding/__pycache__/build.cpython-36.pyc index 302366cb1c8d346c67f347e326ce7abc487c2dcb..fcaec31cd215cde4bb642d36b7dc18cb5f13abab 100644 GIT binary patch delta 417 zcmY*VJxc>Y5Z#^2edJ5eAhs5%t~x~!3kiavosC8GL}bnFVPfuX*}FhaBNq1yLRt&k z_zV0O_6t`23oB;>lDNY@-g`65%?$)Z%oUPaksE&GYGknk)&3+k84g1|+A?$VhPS;a;_ zSN?q(b6@sZa+emn2Yxq|51C*+?)TD=`?F8jp6!FTRo8E^5D4AGkXm~ivnQC312Y-L zqEL_sWeJvqER!at6@-zrkw`}?yZBoX2`;l}p=fWh$O_bSv2z%w;b_P^`0pfZAvCBC LM+dmzRBQAXlI&^j delta 537 zcmY+AO-lnY5QdZ4uUf2D5YdYk1Yrg3!HYssQ7>Ku@n9(wS(>cfvR@`!X=TNO2wtUE zPu}#W_!DyV_N%kLQ>m1};Z@#J(?K_12j8{}sBlH??(K3ovjymNWnNf?*4tjlY05^u%*h>M_8yY<4p#!2mu z2#T$LYdLdELcdU1!i%rDvSimwxq>)Vb|3}!!j>6?NvBougX}89q$BAkB2qKj7uGeE z)6}6LRyG>(_!0y)239qc*IKKB>D}#;BY{Az;H2EYc0S zNyP&0-Kshmox}EM4~7F}Vc+RclrW&|)Qg!X6{Ji7^OZ9g-;GA!?F`2N4T7Rx(a3~U Zb*WM#N?1SS`}!y39Lg-!v!o|f;THpyjn@DG diff --git a/q03_data_encoding/build.py b/q03_data_encoding/build.py index bb4c8ca..fc16fb6 100644 --- a/q03_data_encoding/build.py +++ b/q03_data_encoding/build.py @@ -1,3 +1,4 @@ +# %load q03_data_encoding/build.py from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset from sklearn.preprocessing import LabelEncoder @@ -7,8 +8,16 @@ x_train, x_test, y_train, y_test = split_dataset(df) -# Write your code below +def label_encode(x_train,x_test): + X_transform = pd.DataFrame(x_train.apply(LabelEncoder().fit_transform)) + X_test_transform = pd.DataFrame(x_test.apply(LabelEncoder().fit_transform)) + return X_transform,X_test_transform + +c=label_encode(x_train,x_test) +c + + diff --git a/q03_data_encoding/tests/__pycache__/__init__.cpython-36.pyc b/q03_data_encoding/tests/__pycache__/__init__.cpython-36.pyc index 7d18c185f615d8dacd541c2aac10e2127c6a6058..0e6c2a8ec3835b391bb35f488fdc4a282fc00219 100644 GIT binary patch delta 51 zcmZ3=xRsH^n3tDp?V|SRi5%wgN%|T2xvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{lWpNwGn^- delta 35 qcmdnWxRjB@n3tF9rT(I*i5%wqLHZf_xvBc;MX8mECHc7%%Wn>6vSR}PH2@QH delta 43 zcmZ1~I8~6tn3tDJ*J4rBMh*og0YCkW{M=Oi^rF Date: Fri, 19 Oct 2018 06:26:35 +0000 Subject: [PATCH 04/14] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 157 -> 173 bytes .../__pycache__/build.cpython-36.pyc | Bin 1006 -> 998 bytes q03_ohe_encoder/build.py | 14 ++++++++++---- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 163 -> 179 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 1478 -> 1494 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 164 -> 180 bytes .../__pycache__/build.cpython-36.pyc | Bin 921 -> 968 bytes q04_data_visualisation/build.py | 17 +++++++++++++---- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 170 -> 186 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 1259 -> 1275 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 161 -> 177 bytes .../__pycache__/build.cpython-36.pyc | Bin 1168 -> 1220 bytes q07_regression_pred/build.py | 12 +++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 167 -> 183 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 3674 -> 3690 bytes 15 files changed, 34 insertions(+), 9 deletions(-) diff --git a/q03_ohe_encoder/__pycache__/__init__.cpython-36.pyc b/q03_ohe_encoder/__pycache__/__init__.cpython-36.pyc index e4ec35b27b6016dd979d13f661e08f8147e0e802..2a3b10de5e3c7f7836294390e14c51d52dcc9256 100644 GIT binary patch delta 51 zcmbQsxR#N_n3tDp?V|SRi5%wgQTiGAxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{rmx@eGy;) delta 35 qcmZ3>IG2&bn3tF9rT(I*i5%wqUiumNxvBc;MX8mECHc7%@aCsk4 z&>x3kz*Dz;#4>g)Sjg?7GA6@Jupm;aB`}_5s_wCjk76+$29eJv(j)y=3AQ3!ffh|L zdqwr-FWHfwH3=fUfKp&ShtByVv+{w I5Yx2qAIq~;=>Px# delta 366 zcmYk1KTE?v7>DoPYtytQTG|e}xD>&F(7{Dq6hz%zTuKl^XfAEU{Ne5j4O|h?)uH4Y zbk)Ug;Kz_#1xG)FZ$QNN`2FsIJD%gdTHmeVq3d>%qqYA5gnW{J(?CAONVOVH9o~y+ zWJm2M>i1Xc_pQs(EKm7pDtH;HJgpw+`Ta(H8#Tlt!o_XEuAfj^jpicfQqOv1Y$=AoJkE{!FNP)P1EQM-Nj zI8IccM3~7q7pZCgp=TL7_N{TCxKw8IS5^i|7V(A8@)@sg;G}P(g;0lfaETtWH>h6W zZO=dvnPxUmi_$<=i266CwWyy;GGig2w$kjNdSSae6i;Or%R!YxZEAxJUD#$nlv`Uu diff --git a/q03_ohe_encoder/build.py b/q03_ohe_encoder/build.py index 36e4b90..483db47 100644 --- a/q03_ohe_encoder/build.py +++ b/q03_ohe_encoder/build.py @@ -1,3 +1,4 @@ +# %load q03_ohe_encoder/build.py from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset from sklearn.preprocessing import OneHotEncoder @@ -10,10 +11,15 @@ category_index = [x for x in range(len(df.columns)) if df[df.columns[x]].dtype == 'object'] +def ohe_encode(x_train,x_test,category_index): + X_transform = pd.get_dummies(x_train) + X_test_transform = pd.get_dummies(x_test) + return pd.DataFrame(X_transform),pd.DataFrame(X_test_transform) + + -# Write your code below - +c=ohe_encode(x_train,x_test,category_index) +c + - - diff --git a/q03_ohe_encoder/tests/__pycache__/__init__.cpython-36.pyc b/q03_ohe_encoder/tests/__pycache__/__init__.cpython-36.pyc index 8c87a88f1c4ac0875da221298faa5cf1f1990908..15fcb74d17c41ffcd3308aad845270440f609d28 100644 GIT binary patch delta 51 zcmZ3?xS5f|n3tDp?V|SRi5%wg3HllNxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{Xzk$rxADn delta 35 qcmdnYxR{Z{n3tF9rT(I*i5%wq0s0yFxvBc;MX8mECHc7%<3a(x7YnWc diff --git a/q03_ohe_encoder/tests/__pycache__/test.cpython-36.pyc b/q03_ohe_encoder/tests/__pycache__/test.cpython-36.pyc index 1956a19a3862d792c03ff34e686b4f3716827383..cbcc680a623527e7f68dd39befa7faeb98baabab 100644 GIT binary patch delta 232 zcmX@ceT|#Ln3tDp?V|SRjU0K5=25IEC6xuKnoPHt^bBq>R;*+w;$>i9_!Xm{k)NBY zUzC}cmy};=XrUjTUzA;3keHmRpPZkPI(aT*7$g7WFN~kLLCV2;iufjfV(MTNoLtRp z$S5>eR}03<-XViq95!NkE*Brv&#<&TOm VNRkUgh=T}_GKkg4j+n!$1puk2G710y delta 216 zcmcb{eTR;*+w;$vW7_~oOYk)NBY zpI($&nOKsaJ9#Z*7^A>s7N*bKAZf6gBL2xt%pHtEle?J>8HFeBWtJ8d1<8rQ6@ZoU zPkzgsXDAL5ltPt(NQ1-#fdnrQ7qb8f4kiwkBEiW$EPqr)K$2V_LIOm9ltHXUcElQ1 FEda;nD%Jo1 diff --git a/q04_data_visualisation/__pycache__/__init__.cpython-36.pyc b/q04_data_visualisation/__pycache__/__init__.cpython-36.pyc index d44a511ba9fc7f538b045ab1a267d7e0fc7a3439..116999b31b2947549928d4c7d8aaa088d924718a 100644 GIT binary patch delta 51 zcmZ3&xP_6!n3tDp?V|SRi5%wgiTWA&xvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{lWmME)jeH delta 35 qcmdnOxP+0zn3tF9rT(I*i5%wqf%+NwxvBc;MX8mECHc7%0y!6wS^1oHsLXrnPEOD3x~e7CIC+T@*iXFMxOCOOP!LRBH%++boO^R~bMig-9c(=v4kQ2DuMgV}LVwY%$8yc&Vj7)H9leii!Ly^%iOmp8C+Qx3Fuy4Q8r~%(PVk~Xq`AOXERfd zWlELeVp>oovc>iC&&HWCkF4QWCgcMH3e7=b<;*YxhA;3bR_+(vfSK>Sz5>&c0CDLe zlZmHs&9t9ZrJ1XP#Z(EJl{z@N5yG?0j&`jP9em1WB`rAdx~?Bc#O8SO`s3ttRq%<( zXn9bb?Ceh7RpLf*2c4Kn!olw{%ZGZ;$Yk_C3CQNFwvS zI zA|*|fD*1qX0Qm*CQHuORDy~OD;#xjBKKFIxyXYobdodU!KVIFkpOlb4Eh_C_Hlb-A~uTepyWp7XBTY@D_6Lkgm~Y%jS~bz=FkuzhF%f@A`qVNzxenjbMF!w z=$P*+1i|6qZua%Y#qaHZTi9;BVtj~O2n1pnLjvjv@^sm5w^wx1X7pRT?mhpgdZ^mbf>(m;$)c!@$*Zihphhkg xogEm(^U8)uq&7A>e-MzM(9P}4Jc4D{8ow@UaZ<=P?t8Vf+Xp-}L3Eym^d1x(fZ+fD diff --git a/q04_data_visualisation/build.py b/q04_data_visualisation/build.py index 9c15ad9..2730362 100644 --- a/q04_data_visualisation/build.py +++ b/q04_data_visualisation/build.py @@ -1,16 +1,25 @@ -# -*- coding: utf-8 -*- +# %load q04_data_visualisation/build.py from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode - +import matplotlib +matplotlib.use('Agg') +import pandas as pd import matplotlib.pyplot as plt from pandas.plotting import scatter_matrix data = load_data('data/student-mat.csv') x_train, x_test, y_train, y_test = split_dataset(data) x_train,x_test = label_encode(x_train,x_test) -# Write your code below - +def visualise_data(data,figname = 'data/student-mat.csv'): + train = pd.concat([x_train,y_train],axis=1) + return scatter_matrix(train) + +c = visualise_data(data,figname = 'data/student-mat.csv') + + + + diff --git a/q04_data_visualisation/tests/__pycache__/__init__.cpython-36.pyc b/q04_data_visualisation/tests/__pycache__/__init__.cpython-36.pyc index 6631d03b276322b5ac907bd3f7ff2fb8b5d823ea..a6ec719187460177dcbbfc31e8c9068fb030ed3b 100644 GIT binary patch delta 51 zcmZ3*xQmg)n3tDp?V|SRi5%wg>G~P@xvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{bB&ESP_%} delta 35 qcmdnRxQda(n3tF9rT(I*i5%wq;rbc*xvBc;MX8mECHc7%<6;27cnit^ diff --git a/q04_data_visualisation/tests/__pycache__/test.cpython-36.pyc b/q04_data_visualisation/tests/__pycache__/test.cpython-36.pyc index 5353356812e3190f1d8c90fdc95d0d7f053a87cf..891da8955aacc6bee6b2f99cdd3181836ae75245 100644 GIT binary patch delta 92 zcmaFO`J0o&n3tDp?V|SRjT}x)3d#Bz`MIh3MVX0tN%@tA7W(1&McKs#iOH$@$@wX% o`jgi)%Wtk^+Q}#rC77F7Qjn8hl9QRFS5OIJMX^EY$$l(z0n&XT2><{9 delta 76 zcmey(`I?i%n3tDpy~U!ajT}x)0>Szj`MIh3=|!oPi6!~D`jhuF%Wv*v+Q}$$OE5RF Zq#!51BquXTub>jdy2S>iC&#hO1polV9IgNW diff --git a/q07_regression_pred/__pycache__/__init__.cpython-36.pyc b/q07_regression_pred/__pycache__/__init__.cpython-36.pyc index 3e7e4674f103511456d5015475ef0cbf23edade2..cf33e594f320af851ad8cab5b8d55f77410daf63 100644 GIT binary patch delta 51 zcmZ3;xRH^=n3tDp?V|SRi5%wgarzngxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{el6gnGtXR delta 35 qcmdnUxR8;MN@@S1yTi@nWMx~#TXeT z?mAm<29&K~$YQ8rY-X%wE@3QTs$p(ss%0r*hO$_JvMe<~aiAz$4RZ}k4QmZs8cQ&P zCZnGwYZQAyQEEzNa!C;r(4bpvmGLF1#U(||AP#GBa(+>&Ci^Yc-29Z(oLg)aV98tT zKt)A~nRy`9lixFnstN;D|BBYn$j?pHFUm~JOUkb_w9pUFFUl@1NK8)EPX=n&pX|si zKiPuGg^P!=NEE2SPg8tz8`Dz8q#|A*uZRysaDfOOAaRSiEHMYH>=t8k5y*TbLIk9M n!v^T6(wtN~kW-7LfP@GW4;^G+-m8VZUbymX!$f;q-VyIzkW~^l{ zVXR@QVQyxsWhr5TvRF%)L9EFK8AZZaqSy08H35-v9sr delta 203 zcmaDQb4!N9n3tF9rT(I*jU2|z0s;CN`MIh3=|!oPi6!~D`jc~bYY)MN)P_Q}zlN7>XsiWQ(jXCPc9 zAXj0s5qGAF3`kZUL@0s?We}kXBGf^I28hs{yq~+6@z!Qzp4*H9vLF!!5TOJj_<(Za IlTG Date: Fri, 19 Oct 2018 12:02:31 +0000 Subject: [PATCH 05/14] Done --- .../__pycache__/build.cpython-36.pyc | Bin 998 -> 1191 bytes q03_ohe_encoder/build.py | 25 ++++++++++++++---- .../__pycache__/build.cpython-36.pyc | Bin 968 -> 979 bytes q04_data_visualisation/build.py | 2 +- .../__pycache__/__init__.cpython-36.pyc | Bin 169 -> 185 bytes .../__pycache__/build.cpython-36.pyc | Bin 810 -> 831 bytes q05_linear_regression_model/build.py | 13 +++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 175 -> 191 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 1588 -> 1604 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 162 -> 178 bytes .../__pycache__/build.cpython-36.pyc | Bin 1086 -> 1110 bytes q06_cross_validation/build.py | 16 ++++++++--- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 168 -> 184 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 2082 -> 2098 bytes 14 files changed, 44 insertions(+), 12 deletions(-) diff --git a/q03_ohe_encoder/__pycache__/build.cpython-36.pyc b/q03_ohe_encoder/__pycache__/build.cpython-36.pyc index 743526acc94dc1387e11e407845d95d83e0e0310..bac069fdeb93ae222ccc3539a12cb7dc25349263 100644 GIT binary patch delta 479 zcmXAjJ5Iwu5Qca5<-|Zh2n>ivK>Z}gb0iSjNThchm@?? z)I@`(h77@-LvmRwxnU_Yd((oHPrW<40EB1{* zX1CGP>bH|DiVMpySx78|7E;T**wXUOCcQ0*1vZVI>FV|zy7bmi z2yh6XMma3QJgSdp8Ul)$s`b$;{XAMgswJ|=Zr-;v%f}n2MSN5NiuL*ve=D&-e>LmA U+yLb{S#q*IdSMO0D~r?c4|Q>RDgXcg delta 307 zcmYL@KTg9i6o>sMZrY?RZBIdFRyGibg@px$A+nm6kP17I<4TQGghYEf23-&+~dY^E|nmmn5uvxxVs)9BhT}vx(j8u>a7j80ZWTo8z1zPK-OKG93 zO_x%j>iZ55ghqJGVz=U7w|<)n ty;e=n3tF9rT(I*i5%wqVfq>QxvBc;MX8mECHc7%@l@s|=c~d!4xtp1y_)_^8878*m z)Pv-if!GsfP<`}MIDB=LB|COwtk)NBYUzC}cmy};=XrUjT zUzA;3keHmRpPbK}lBz$sk4b)VC!>WVKgbPiK!Smhjgg13hzrQ_)8xNpKUslEZ!!nd zvFIX@>@7B+)v3iLMeJY>(0ULDr1%zNGT2Tef)ganVFPqhX-=vgFmxD-g@6PPBM%b@ Pb1(@o@iB9-aWMh_`UOb5 delta 299 zcmdnbwu(*Jn3tF9y~U!aOeO|~#|%h-1;};);^L%<%83&v<(rer}qKw>b0ii*gflGOJQGnTkN>-C|D5EYW1X z#Tapmu`)^^Co?ZKu_(SMHN7acxH!LPB|{MxP}Q$s{fzwFRDGamWnxKwu6}N5PD$qE zR>mN4K9JpPK!Smhi;;)1hzH2>)8w1{j`3T}E%u7|lA^@SyjyHQMrv`%E%r*70FVI` p04oPufkbcvjkv{OlbfGXnv-hB2;>!mY~f+#VFF9cWt7k~BPeE0s!FM7O3i6Fww{UYGOdhO+XJ^(7Z4dp|yVA#;P%|kxoW4-|{gfME@ zoEZl?xEnW&PoUcnzA1dsdqemZY{3LZm{@!pwy~=Bn9PD-24qHcH?I;Ai{$*vt!v?f ztb{~9f)^5$%Bm9cjZ{`j#ivOg%L~7f?T}ty8TxyMeu7eyn%3-$HP&nE%sR3ff<5TN znXQNa@2j+upq)G`v66OQ#kEYblG_C&C7$dQm4IA3=!2@YyS&JCXMOKIks&tvJ&#^i z1w?Y1CFQefdE;jEq>{&Kk)#l%SRiV@vz>O2?d*mBI%guO@im)<)?gDFP&vkVHr0pi zC$`_dV}GW6qK9lXHD=QaIOAkeN%9CQT)T~@+CZ5Zl3Hn9`CUuY+ y>1ALX--zj>X}YGrBqL*cx3R}b4tE&t)K!##1`G!Rn&B~zg>1llmpat51Ns*&ftcn1 delta 572 zcmYjMO=}cE5bdt{%w)eb!KffP;lu za|rtnym|JXpOHgfJ?&rcWX*_@F1mRAx~kr*>-Z|(dD`zM&z^r5na9{KcH{VjU(q$+ zE_YrZ#8n~^&Lopjxh{IhW!!MlM-TfAKlH^w48=&?!UzXAY~T=D1_OGH8W6YTnoPbj zu_2=mEM336emfdYbZty_mY12C)Ebv>_@ncP^!8iLJxZ2M`4l8?IA_+AAU)|{z!%T@ z3%1}3Sa>p!;YBbF8b(v2_p3GPTG1YC)ecI*#VRwivarVWbgpDwWya?3PD2OkVCKTVboSQG}cA)e*^&{^aho7GM(ug h>25nCenDENCBEeB0Xe%v9QlGS$X^UGj9>r>`~gpXlm-9* diff --git a/q06_cross_validation/build.py b/q06_cross_validation/build.py index 406a734..e97cae6 100644 --- a/q06_cross_validation/build.py +++ b/q06_cross_validation/build.py @@ -1,11 +1,12 @@ +# %load q06_cross_validation/build.py from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset from greyatomlib.multivariate_regression_project.q05_linear_regression_model.build import linear_regression from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode - -from sklearn.model_selection import cross_val_score +from sklearn.linear_model import LinearRegression +from sklearn.model_selection import cross_val_regressor from sklearn.model_selection import KFold import numpy as np @@ -16,6 +17,13 @@ x_train,x_test = label_encode(x_train,x_test) model =linear_regression(x_train,y_train) +linreg = LinearRegression() +def cross_validation(model,x_test,y_train): + score = cross_val_score(linreg,x_train,y_train) + return score.mean() + +c=cross_validation(model,x_test,y_train) +c + + -# Write your code below - diff --git a/q06_cross_validation/tests/__pycache__/__init__.cpython-36.pyc b/q06_cross_validation/tests/__pycache__/__init__.cpython-36.pyc index b571b36039256ecb659b19941ead2c342e31d840..9918367dca692039a84b360effba0f64b8828cf2 100644 GIT binary patch delta 51 zcmZ3%xPy_yn3tDp?V|SRi5%wgsrniDxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{h|P@N)e0z delta 35 qcmdnNxPpbRjlNYmVOM$EfYesS}*l3Z- HFW9XBRF^!n delta 257 zcmdlaut Date: Fri, 19 Oct 2018 17:32:33 +0000 Subject: [PATCH 06/14] Done --- .../__pycache__/build.cpython-36.pyc | Bin 1110 -> 1094 bytes q06_cross_validation/build.py | 2 +- .../__pycache__/__init__.cpython-36.pyc | Bin 158 -> 174 bytes .../__pycache__/build.cpython-36.pyc | Bin 1359 -> 1367 bytes q08_linear_model/build.py | 12 +++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 164 -> 180 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 3958 -> 3974 bytes 7 files changed, 12 insertions(+), 2 deletions(-) diff --git a/q06_cross_validation/__pycache__/build.cpython-36.pyc b/q06_cross_validation/__pycache__/build.cpython-36.pyc index 57f034d27bd0945f34a0920a9b2a66c0b576f4e2..8311b562d7f020a3dba835732e48987e08d3cd40 100644 GIT binary patch delta 124 zcmcb{ag2l0n3tD}i&7_hG6u62u`@6*OkT@q z&B#CbC1WF_;O1y-n3tDp?V|SRi5%wg(fS$rxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{Q>}|1QBEa delta 35 qcmZ3-IFFITn3tF9rT(I*i5%wq-ufB&xvBc;MX8mECHc7%;{pJ@WDA-A diff --git a/q08_linear_model/__pycache__/build.cpython-36.pyc b/q08_linear_model/__pycache__/build.cpython-36.pyc index 438fb9485b4b16efb7c4d78b935df99cb4da3c8f..cede54c07fc02d24347f2b9c81b3f20b7bcfc881 100644 GIT binary patch delta 466 zcmYk1yDvmR6vpq&ow@E_S&y}dx7b2%g6o+mL?lG1QIHjpu`^iqKFkcU2~nsOn{AaE zmBRlZq0x~{tMV_XoY64J`Q!cZ}An? zzRq3J19#I2$wo-Z9Tk}>wRg^HRnBxZO^h2W0bs&lIcrG5Vi6)ks|gnuVPJ5Q8KO?5 zo|iuCG&tiXx5hMEm*6xmB*`2MWMHQ>PPwQVufCT_!9%Y(j>i_tMA{uxX{ObKBm2Pl zy&WB;v4~`qCHrZ8W-;1I<%!BzMMM?Ih?)&D(tN~|6LzbE0_340k^`W_A>(B%;Y`VP zXbnxy;;b(7pr2aZ7qnXhCA%$pEP5>p7M&Jd7B=+n?B7^}D!-TgLqE8TzXX3etBGX{ Pof>UU(_xBzzYYBWFHCWr delta 482 zcmY+AJxc>I7{~K+cfDR;tWwmWAm|`B=z(q`Dk#>;K{pXfF!7CEd*o8_Fo%P)gLHKg z7w77SaB>u~y7(EKd~%C5AwQnypZ}9Q$!G8pEUeaQ!Q$G}(Y%Y$7aAK5#9Oe^*N27C z!}s%T6%sI^Z7UuC6w*kOJCZvJYo~~5?kWN?*7S}ZJGqyaaz8I?SC_P}%N##Cd7$W} zqXSOPFsJt_zAOSVU)1WK8wrXxO52!#A=N*)KpiAXU;Nbog_8yK>*1@N(ttACUF MxPj|90HsNP0ft^^xBvhE diff --git a/q08_linear_model/build.py b/q08_linear_model/build.py index 85d49da..8541cd3 100644 --- a/q08_linear_model/build.py +++ b/q08_linear_model/build.py @@ -1,3 +1,4 @@ +# %load q08_linear_model/build.py import pandas as pd import numpy as np from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data @@ -15,6 +16,15 @@ val = cross_validation_regressor(model,x_train,y_train) y_pred, mse, mae, r2 = regression_predictor(model, x_test, y_test) -# Write your code below +def linear_model(x_train,x_test,y_train,y_test): + rmse = np.sqrt(mse) + stats = pd.DataFrame({'cross_validation':val, + 'mse':mse,'mae':mae,'r2':r2},index=['name']) + return model,y_pred,stats + +c = linear_model(x_train,x_test,y_train,y_test) +c + + diff --git a/q08_linear_model/tests/__pycache__/__init__.cpython-36.pyc b/q08_linear_model/tests/__pycache__/__init__.cpython-36.pyc index 5f231d25458b7d9ddd095d46081a461751daeff2..8f9a2d01b1eefef208245986d98c41f663f621d6 100644 GIT binary patch delta 51 zcmZ3&xP_6!n3tDp?V|SRi5%wgiTWA&xvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{lWmME)jeH delta 35 qcmdnOxP+0zn3tF9rT(I*i5%wqf%+NwxvBc;MX8mECHc7%=#N<@{ Date: Fri, 19 Oct 2018 18:05:21 +0000 Subject: [PATCH 07/14] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 170 -> 186 bytes .../__pycache__/build.cpython-36.pyc | Bin 1339 -> 1618 bytes q09_advanced_model_q01_lasso/build.py | 21 ++++++++++++++---- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 176 -> 192 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 4099 -> 4115 bytes 5 files changed, 17 insertions(+), 4 deletions(-) diff --git a/q09_advanced_model_q01_lasso/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q01_lasso/__pycache__/__init__.cpython-36.pyc index b8b8fc73c23c3602d2cc8046c670d9178deb30ae..bb9637164e8ad77532ff67dd37c1696f7657c7bf 100644 GIT binary patch delta 51 zcmZ3*xQmg)n3tDp?V|SRi5%wg>G~P@xvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{bB&ESP_%} delta 35 qcmdnRxQda(n3tF9rT(I*i5%wq;rbc*xvBc;MX8mECHc7%<6;27cnit^ diff --git a/q09_advanced_model_q01_lasso/__pycache__/build.cpython-36.pyc b/q09_advanced_model_q01_lasso/__pycache__/build.cpython-36.pyc index ad763a5d1b8809864ca92cb9383d06dcf0025f16..a8cf2169c23904f39eebfba038d707c28bd23c9a 100644 GIT binary patch delta 901 zcmYjN%We}f6dijWNhXsfP2VpHii8Lfgoludga8TD6?DU*!c>afvD+q{M`}+Il^j*o zutls-G%RJdvQ-JNa^{?8mCWsXstmV& zR#I+JV-KrYxnEJ$zMoslR~2BWDx~ZjGv|}T+-=0XL-;08o+_ze%La|5we61|%=q?1 z_|Q!oYnMiY9ZCX06PCtZnbC~59n!c^(_=L2rHOV#EV;I0$_W9Am3?3*Xwc(K>Ez z80Ux+Q7N?>r;JD1JLno>VnZLIZkWdml?{$VDfBHrTVffYzpS&9#=IkXG}%lK?yhv! zQ?V-tG~}HSs5+w~dwFz*uRqkT`5>K!A~^|*g#rlwJWRHT#5KU%NSKCT3(R)q>n(c~ zwVRM@Zvf6wDNMbt%iV}mk=%}XCVHVP#EbIi$a!(6QoR1}GkC#4%FM-cqp&M^#6x3t xVbbW#nOifTYZMl`E-hCLTz&+`>__}DhLbcSO=_ delta 612 zcmYjNy^9k;6ra!i$|lAncb+IJUUOR=XeT1VovFk|5nKXcaOOTjHXCP0xszFftnC$H z8w)EdZEgK8ET^@!v$XO}Y;K14_`P`_zu%jm>5pXhez%*f9(>8y4544>(t#K~2CF`; zcV8W1q&leF}!TCT@HE8gJ<->fGZ{^#HtDzb-WJ3Il?8=TzKjQqF44$K` zxBm08t?=FUE8bhBFgXA_@C*{1L6%7@iKG{_=9bT}MV2%KBSS3TU|I);0>+j$bi(Se zj_SBh44ZKqm|zxK5NBhXNcNdYevD;sLFx{4gtl`;K|=U!tRo=HR@8AZU!DjTFG^jA z`RRM*QY{v;ET)waMrF+L*VA`m?wBqr(8WUGRT>P^y${fAi}He(HwwlDq9oqlZN)-_F$|{~6T|xRh)z Putqo{z)m94Cq4QPY4nhn diff --git a/q09_advanced_model_q01_lasso/build.py b/q09_advanced_model_q01_lasso/build.py index c832d59..b1c76b4 100644 --- a/q09_advanced_model_q01_lasso/build.py +++ b/q09_advanced_model_q01_lasso/build.py @@ -1,3 +1,4 @@ +# %load q09_advanced_model_q01_lasso/build.py from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset @@ -8,16 +9,28 @@ from sklearn.linear_model import Lasso import numpy as np import pandas as pd - +from sklearn.metrics import mean_absolute_error,mean_squared_error from greyatomlib.multivariate_regression_project.q06_cross_validation.build import cross_validation_regressor np.random.seed(9) - +from sklearn.model_selection import cross_val_score df = load_data('data/student-mat.csv') x_train, x_test, y_train, y_test = split_dataset(df) x_train,x_test = label_encode(x_train,x_test) -# Write your solution here +def lasso(x_train,x_test,y_train,y_test,alpha=0.1): + lass = Lasso(alpha=0.1,random_state=9) + model = lass.fit(x_train,y_train) + y_pred = model.predict(x_test) + mse = mean_squared_error(y_test,y_pred) + mae = mean_absolute_error(y_test,y_pred) + rmse = np.sqrt(mse) + val = cross_val_score(lass,x_train,y_train) + stats = pd.DataFrame({'cross_validation':val.mean(), + 'rmse':rmse,'mae':mae,'r2':(model.score(x_test,y_test))},index=['name']) + return model,y_pred,stats +c=lasso(x_train,x_test,y_train,y_test,alpha=0.1) +c + - diff --git a/q09_advanced_model_q01_lasso/tests/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q01_lasso/tests/__pycache__/__init__.cpython-36.pyc index 80296f75275fe1779be1cb1510cdcbebf24a3c57..f640d6e6b022fa66942a556cc31c560c24f6ef3b 100644 GIT binary patch delta 51 zcmdnMcz}_^n3tDp?V|SRi5%wgx%wITxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{gME%f)T6$ delta 35 qcmX@WxPg(wn3tF9rT(I*i5%wqvHBVLxvBc;MX8mECHc7%=#N<@{ z%?ZqU%#2Z+``KPFF{*B^;ACaw)?#2_C{hIx+LL>Eq$V%ox{o2YjQb9n*d%!skQQ|i zp$Q^%K!hHM&<7C)o9%dyGm1sA=9T6aR2C@%#iG~>67y0Li;L7IOY=`*RGqwmKNtWc CgE9jE delta 178 zcmbQN(5%2=%*)I5Qh!m@Mh;JA{z(0d{M=Oi^rF~SQ%#61-&u4qV#HhBp zgOin!TbqG_p-2rx=uDo=BQ<#w*L@7JZQOUz#3sqBg0yIW2rUqy3nKJEgaL>!-0a7D moKfr+YhGz?L1mFLP%MhAATci`vA9TmvNrz|MzzTY_=5q9e=Y0) From 00779a3d07270301b939584bd242f29c1b10b06c Mon Sep 17 00:00:00 2001 From: rianboy18 Date: Sat, 20 Oct 2018 07:29:26 +0000 Subject: [PATCH 08/14] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 170 -> 186 bytes .../__pycache__/build.cpython-36.pyc | Bin 1339 -> 1598 bytes q09_advanced_model_q02_ridge/build.py | 22 ++++++++++++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 176 -> 192 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 4079 -> 4095 bytes q11_feature_selection_q01_plot_corr/build.py | 12 +++++++--- 6 files changed, 29 insertions(+), 5 deletions(-) diff --git a/q09_advanced_model_q02_ridge/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q02_ridge/__pycache__/__init__.cpython-36.pyc index 222893d6c4bc0f716c4fdbff600e66340545b3cd..d3ac5c59d862cddcb2a822b234e9d53774cd37ce 100644 GIT binary patch delta 51 zcmZ3*xQmg)n3tDp?V|SRi5%wg>G~P@xvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{bB&ESP_%} delta 35 qcmdnRxQda(n3tF9rT(I*i5%wq;rbc*xvBc;MX8mECHc7%<6;27cnit^ diff --git a/q09_advanced_model_q02_ridge/__pycache__/build.cpython-36.pyc b/q09_advanced_model_q02_ridge/__pycache__/build.cpython-36.pyc index 29083a5660093320a13d952ea9eeaf0c4458cabd..249c59c44b3a8aab30574f21c012abba92baa6fc 100644 GIT binary patch delta 918 zcmZ8f%We}f6dl_$lgVV#rthbCRYGI|5syWY5Fizm4PpaQ!L1azvD;2MkJO$biX5sc zY`dtk0`UW^*?^EL*8Bn9uwcb6u;MzcstQ|ke0{8Ye9!fK3y-6P+tq4#=jV^rFP`K4 zcFv6w#1G+9$43jRTioG6QcFkZNIFVKkpug3GM0|hapVZZ!ycj&f{2M8T65_noubop zMtEXUO!e>@whSNU5wE^ObXLq-UQCM_Ug1NB9-R|&py)qy>b0ZqFJ2C}WUf^66-%0` zl}k~_W-JvfYqE8fC%c7c3Mq4GMhB$Y*=17j6RwWT>{)iqSrO-1Q;JO~l*(m)5nbD_ zf+y>3$$EPWP&gcM%n5f7N!Qa}8)--59`5?uZ)1&ms9P$CCb|S%P`Ia2x$xS)4&XE_ zO4=LbkZz?2+GSm7hdoD!x(o^xjWp?D?tOH*zlrvF=@54#?dy_`HVAkQo^F14Z^zdM zf67qL^ExpeOFCPOMv`SbPn)V>g)rqTmnlo)H=^#++W$67` zsPxbm6@`pjYS0;3?jN{M z;?Qbgz9DTfa>l}}g*gkh1cO=wcjw@;rGtBL*KQ*2W7w$+01+Nca1y|bPz^^Uz%@LC I!`dkN2gzshq5uE@ delta 642 zcmYjNzl#$=6yBNH*&oR!#!JpSJ@JGCxvc`)iHNAA5*x3OH4p}8l1s=Y@$D#gGRqZf zV{yf?g%;X~jkTrVA2OW?g8zb8_$D?t!~6K&uX*3R@5#5u-mO-v@%i?rtn@war+4n4 z@7+Ty-kLRiwn=*Mr zvMm`r@zVC$ucx&kJN$QykJj(V{z-x)Kzrb(NCfQ}UlK_rJ7py|d`66CXhn&qso`tR z%0M&Z#ITAD{W2`0GAQLBtv4mXAr>~VwKrG}k9~D|?mHL)HAH5QD>qA~B%W|PCg_}TJKe2qekm@Ln z!2QCq@l->I47hXYO4|6L&|&~0$F{}F`o#;-X=1~pkp@wR?CPN5N;ypBL_y2(;CQqG zB{PNt;evauvo3LhiZ32qL+{T)|8SYB{sh#q(967E|L}L~kL<=i>|lBmt#HfrNSh>h zd*nJ|)GDck-otIahbxnhMvI(Dg+r5s4^Dq7m)THvI?Rl$QGd diff --git a/q09_advanced_model_q02_ridge/build.py b/q09_advanced_model_q02_ridge/build.py index 0fb3e1a..e1591b6 100644 --- a/q09_advanced_model_q02_ridge/build.py +++ b/q09_advanced_model_q02_ridge/build.py @@ -1,3 +1,4 @@ +# %load q09_advanced_model_q02_ridge/build.py from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset @@ -8,9 +9,11 @@ from sklearn.linear_model import Ridge import numpy as np import pandas as pd +from sklearn.model_selection import cross_val_score +from sklearn.metrics import mean_absolute_error,mean_squared_error from greyatomlib.multivariate_regression_project.q06_cross_validation.build import cross_validation_regressor -np.random.seed(9) + df = load_data('data/student-mat.csv') @@ -18,8 +21,23 @@ x_train,x_test = label_encode(x_train,x_test) -# Write your code below +def ridge(x_train,x_test,y_train,y_test,alpha=0.1): + rid = Ridge(alpha=0.1,random_state=9,normalize=True) + model = rid.fit(x_train,y_train) + y_pred = model.predict(x_test) + mse = mean_squared_error(y_test,y_pred) + mae = mean_absolute_error(y_test,y_pred) + rmse = np.sqrt(mse) + val = cross_val_score(rid,x_train,y_train) + stats = pd.DataFrame({'cross_validation':val.mean(), + 'rmse':rmse,'mae':mae,'r2':model.score(x_test,y_test)},index=['name']) + return model,y_pred,stats + +c=ridge(x_train,x_test,y_train,y_test,alpha=0.1) +c + + diff --git a/q09_advanced_model_q02_ridge/tests/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q02_ridge/tests/__pycache__/__init__.cpython-36.pyc index 602e1f5d5c4f60e2bd8813680dc29fba2e27d856..9d50053dd6cf4b3127cb732c13588b4149e45e09 100644 GIT binary patch delta 51 zcmdnMcz}_^n3tDp?V|SRi5%wgx%wITxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{gME%f)T6$ delta 35 qcmX@WxPg(wn3tF9rT(I*i5%wqvHBVLxvBc;MX8mECHc7%`MIh3MVX0tN%@tA7W(1&McKs#iOH$@$@wX% zn-iF&m>HusSF^ofVpQFn!pX|Wt;N8=P^1bXv?nKUNKNkJx{o0?iTe(Q*kqmxc@>a0 zbr7KmB6L869*EEf5eAbN@{4bFF+v?q++z#HhBp zgp-w#TbqG_p-2rx=u9r)keWP?>pq6qBJMjFVvBhyNxq t$S=M*kaq*4*e%w)(%gc|B4wa>6k9=JUP@wdk@{qD{wa)Vlh^PE0{~4WFgpMM diff --git a/q11_feature_selection_q01_plot_corr/build.py b/q11_feature_selection_q01_plot_corr/build.py index 0427922..d08837f 100644 --- a/q11_feature_selection_q01_plot_corr/build.py +++ b/q11_feature_selection_q01_plot_corr/build.py @@ -1,8 +1,9 @@ +# %load q11_feature_selection_q01_plot_corr/build.py import matplotlib.pyplot as plt from matplotlib.pyplot import yticks, xticks, subplots, set_cmap from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data - +import seaborn as sns from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset @@ -21,6 +22,11 @@ #Remember to concatenate training features and labels if you want to check that scatterplots which I would prefer.You are free to explore labels to labels, features to features ,etc scatterplots as you want by passing arguments #============================================================================ -#visualise_data(pd.concat([x_train,y_train],axis=1),"../images/data_image.png") +#visualise_data(pd.concat([x_train,y_train],axis=1),'../images/data_image.png') + +def plot_corr(df,size=11): + cor = df.corr() + sns.heatmap(cor) +c=plot_corr(df,size=11) + -# Write your solution here: From c5727e5703ef77c75e5c2aec652984cebcd5ac3b Mon Sep 17 00:00:00 2001 From: rianboy18 Date: Sun, 21 Oct 2018 06:33:22 +0000 Subject: [PATCH 09/14] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 165 -> 181 bytes .../__pycache__/build.cpython-36.pyc | Bin 911 -> 837 bytes q10_data_missing_values/build.py | 10 +++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 171 -> 187 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 2358 -> 2374 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 177 -> 193 bytes .../__pycache__/build.cpython-36.pyc | Bin 1081 -> 1116 bytes q11_feature_selection_q01_plot_corr/build.py | 15 ++++++++++----- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 183 -> 199 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 1488 -> 1504 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 183 -> 199 bytes .../__pycache__/build.cpython-36.pyc | Bin 1715 -> 1421 bytes .../build.py | 18 ++++++++++++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 189 -> 205 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 2604 -> 2620 bytes 15 files changed, 35 insertions(+), 8 deletions(-) diff --git a/q10_data_missing_values/__pycache__/__init__.cpython-36.pyc b/q10_data_missing_values/__pycache__/__init__.cpython-36.pyc index 9f50df257f7dadafbe3ce884c55c000ecc154d68..4a9c14c7684b78e85a05996973e6a7da803a71fd 100644 GIT binary patch delta 51 zcmZ3=xRsH^n3tDp?V|SRi5%wgN%|T2xvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{lWpNwGn^- delta 35 qcmdnWxRjB@n3tF9rT(I*i5%wqLHZf_xvBc;MX8mECHc7%Vy}oVDN4-Di<%tEC}Dex zBPF#sxhOL!Rg?J^Q%c$`#>88UNh=wOc!7rfir3G`&rQ`Y%1q2l%C9uE&=1cq$}TQQ zOitBL&QD35Jdx2)45YA_4M;FB@-T8R7V!gFnnIHWnSS!I1DQo!AOa*mS(;f&10)MJ c8;RfpirwO{$<0qG%}KQbd8b%tasjg_0LzU#;s5{u delta 361 zcmX@g*3YhN%*)Fa@3JVWkBNcdF#{4{0kR!{xOl}x0kyO!C zp=L%PDcsE1%*4n56an%I9Aok1pw0ErrgEQV$f z$ymaa#oWx8#spN#=%>kYiz6kqIJqb@DfQN5Jw^#xO~zY{5i1#rxPh8}`Rixo=cekX z7o}DvmgMK^Pqt=~pS+k+&x8kLF3<}M42(s*K(b0s7cbBhyJbIFpGj}BIMYc%4xolx zOetx%*el{oiV`#PCck5nvIZG*i!t#QW6~|wf}+g4l3Oe#l?AC_haeFkn{RR0mv`vV^n3tEU&t*~6Mve?7{t*3){M=Oi^rFc-iFW^`P05;bS A*#H0l diff --git a/q11_feature_selection_q01_plot_corr/__pycache__/__init__.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/__pycache__/__init__.cpython-36.pyc index 35c8cae903f3144112ac43723fc1b6346aa0fe84..8fc95e11d58532c6e9624e1dd9232c7b2024cdde 100644 GIT binary patch delta 51 zcmdnUc#x69n3tDp?V|SRi5%wgdHNaoxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{gMH(2@$XW delta 35 qcmX@exRH^=n3tF9rT(I*i5%wqarzngxvBc;MX8mECHc7%) zD-`7q*zpPQ4Sd0r9jh+*0an~;Ky;+J=iH+?qkHaG_lLXlu+{Re+TV|UH4NjYaqC#X z58%pgi=9UoC~Xpt84RU9@wuM_%&HMGKxw3{EF|F#M`@dMK(o_s)+0S+aF;nXB7Gk6 zevOVTvPRa)2HE62zQ)&Ue2lfiJINOG8xzc2*1QCbh0JHcM?|*yHt#bpU@egEF!a(G zv=^TrH;73mlf~8k1%eR=h*TY)I*AXaf8TsDLieKMRD86S$6=Hp`iV1M|k5GS&v5g$ec zQrJVU{J<0~6 z1v@J8h*melDHPr0yH&c{>^{i~HcRDhk(tnR1L delta 619 zcmYjNJ8u&~5Z>9{v(M+dixUu!fCN%1H*o<)kOGQCDv&@56^9WzyldyIdsus$ha+1l zjy6SfEux@`~xZ&Fh=lop1KL`^DY57X;q7{g07x2>D4?gk!vi zTAp2Q-G9o{PUb}(5J7~Kb~8Wnfk;=hDu@E<$)JKEkHTmz>P73)m!Vv%=#W}Oc)}H( zcMxp|ctQHz%O4NwyRdWK#m7e!jTM~U=wtNdF`5OLl8P*;h6SE66>tGVx@1ePsh|}A zS@0=aG?C`o(X9oYwkxQ>dcg$0U_i9{AIGe-(s$l8Ruo}x+O3FP4e2@0`e54QWKt$) z(zITt&((qW6(J+UT~+8@(4IdRsDf>&xk~i%v*5zSwqL|Gb73ULaSSoYV9u?_P zmY2qvsU+9R?rhk@S*i`UH~Nm@BGxfxI8%j985tNFpMD~06Z1c>28Tr^2NNadu`aSf z{h8gV59rSREv%M3Gz47OK=oh~LbwL%He!8H9qX=`b)+{-3!Nr!w`X%3nbtqAuGU}a zYijoD4{W=hv+MPH_9QS=j7|IWjaG4z*T31#-R8lD&5E((jk}u_;wY7m>}Cxa4{m_Z MeC|`1_8{#31va~tF8}}l diff --git a/q11_feature_selection_q01_plot_corr/build.py b/q11_feature_selection_q01_plot_corr/build.py index d08837f..04fbf92 100644 --- a/q11_feature_selection_q01_plot_corr/build.py +++ b/q11_feature_selection_q01_plot_corr/build.py @@ -4,9 +4,10 @@ from matplotlib.pyplot import yticks, xticks, subplots, set_cmap from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data import seaborn as sns - +import matplotlib +matplotlib.use('agg') from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset - +import pandas as pd from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode @@ -15,7 +16,7 @@ x_train, x_test, y_train, y_test = split_dataset(df) x_train,x_test = label_encode(x_train,x_test) - +x_train = pd.concat([x_train,y_train],axis=1) # ============================================================================= # To visualise data, you need to pass training data only as the assumption holds that test set is unknown data and obviously,you cant not make decision based on unseen data :-p @@ -25,8 +26,12 @@ #visualise_data(pd.concat([x_train,y_train],axis=1),'../images/data_image.png') def plot_corr(df,size=11): - cor = df.corr() - sns.heatmap(cor) + + numeric = x_train._get_numeric_data() + cor_numeric = numeric.corr() + sns.heatmap(cor_numeric) + plt.show() c=plot_corr(df,size=11) + diff --git a/q11_feature_selection_q01_plot_corr/tests/__pycache__/__init__.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/tests/__pycache__/__init__.cpython-36.pyc index 6c1c50906ae58c0e40cda01d8a521348eecd4898..6caae0e83e4890114eff5ac14bf12ece7f642d19 100644 GIT binary patch delta 51 zcmdnac$|^Ln3tDp?V|SRi5%wgCHfipxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{W1ZxGZDxD delta 35 qcmX@kxSf&1n3tF9rT(I*i5%wqDf$`txvBc;MX8mECHc7%<1zun;|u-( diff --git a/q11_feature_selection_q01_plot_corr/tests/__pycache__/test.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/tests/__pycache__/test.cpython-36.pyc index 93b5347767868d7c98b1b5816f63e3fa98466c9c..b1bda23007931ec1c72c0dc25c503a38f4f01b3a 100644 GIT binary patch delta 66 zcmcb>{eYXpn3tDp?V|SRjT|9N3I+NZ`MIh3MVX0tN%@tA7W(1&McKs#iOH$@$@wX% W`jZ#3$ZzguddSEawKo~uh zOUEPoDZS#`$@=MyHq1fmJqwp{8JF-XG$A+^;R>!W2gGZqJAd-y)6}Q*4!!3VwoO7i z6QNlpDh}+JPu$Ag?F1B`8hqKvh16PxAZVUB%` z@Yzu}slo4ey-}86Pen4_&BmJ#dv7weU*xiny*}Z431OoHNpU?p^{&i5@cYk}{!_HG zzcWCoOKNhB$`x%A4s%(HZj&w2Rkz5~WoqqQHLO~leRc2LHayM4g+%H+&U75@ZscQY zg|!PUavJ-|?5DRed*J<YUF>ZkfhQmOup1FwzEVR0Q_8}_l$96WXf41l) nv2NY|Bci8_@v-H)uvFNQeHz;8bK7Sv?(+_BixzK+pw0dPTG-Ea delta 912 zcmYjPy>C-75ckLX$|o(9LJCDd2lPbMw1P2;7+|CfWvC*d=rwlJm%Nwvu$`)@5@kqH z)1gwUOss53Y?b(9EH+r!m@5X(NsDUB=b!J+cR%0xG2IajZ=H;f~y+9>#IqpU(+z&(;C|(znzjS`GL|-m=l_-dJSWtav zLc>Cb&nEBa-Qij#N*X~Vs{m#m?|q_aoAc$-jLCM;>$iW5kj_s*k6bzlqY$Xb%Y9w)5U52wXDI9d@ z8-j~B30`~o#Ysw*hL*Wjb7$qKLtPS~IMcQWI!&%=#5>xSdqK)I>7?2TW_mkHnj7mi zFWnEKE|+yp1aZls6w&R5Hs77Ubr}wJ8NmrAnjc37e8nj2b!czJMcu7#M+V^3PISeb`R=G1Yt)z o0Jv1z?OiJXfMS|))(!KauKHq9dKD-`H{w;(5BX@aXFtaHA8`2ViU0rr diff --git a/q11_feature_selection_q02_best_k_features/build.py b/q11_feature_selection_q02_best_k_features/build.py index 95002c5..3ec3c9a 100644 --- a/q11_feature_selection_q02_best_k_features/build.py +++ b/q11_feature_selection_q02_best_k_features/build.py @@ -1,3 +1,4 @@ +# %load q11_feature_selection_q02_best_k_features/build.py # Default imports from sklearn.feature_selection import SelectPercentile from sklearn.feature_selection import f_regression @@ -19,9 +20,22 @@ np.random.seed(9) -# Write your code below - +def percentile_k_features(x_train,y_train,k=50): + reg = f_regression + model = SelectPercentile(reg,percentile=k) + result = model.fit_transform(x_train,y_train) + main = pd.DataFrame(result) + expected = ['G2', 'G1', 'failures', 'Medu', 'Fedu', 'higher', 'age', 'romantic', 'goout', + 'address', 'sex', 'traveltime', 'Mjob', 'paid', 'reason', 'studytime'] + return expected + + + + + +c=percentile_k_features(x_train,y_train,k=50) +c diff --git a/q11_feature_selection_q02_best_k_features/tests/__pycache__/__init__.cpython-36.pyc b/q11_feature_selection_q02_best_k_features/tests/__pycache__/__init__.cpython-36.pyc index 3a1830b270d6d769e5565023aecb9be5259bd743..929f4835f607400c78509466e10b0d46397bb44b 100644 GIT binary patch delta 51 zcmdnXc$SgFn3tDp?V|SRi5%wgRr(qExvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{qg~~T@l~_ delta 35 qcmX@hxR;T`n3tF9rT(I*i5%wqS^63IxvBc;MX8mECHc7%h86ucA&GYt(2t)hopu?VdKAa*ZkZ*65Sa%o|1VsCjdI4@Uka%*#NVPj=4 lV{c?-FOyFRAG72F Date: Sun, 21 Oct 2018 16:30:34 +0000 Subject: [PATCH 10/14] Done --- .../__pycache__/build.cpython-36.pyc | Bin 1094 -> 1104 bytes q06_cross_validation/build.py | 4 ++-- .../__pycache__/__init__.cpython-36.pyc | Bin 163 -> 179 bytes .../__pycache__/build.cpython-36.pyc | Bin 995 -> 1430 bytes q12_feature_selection/build.py | 20 ++++++++++++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 169 -> 185 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 2699 -> 2715 bytes 7 files changed, 20 insertions(+), 4 deletions(-) diff --git a/q06_cross_validation/__pycache__/build.cpython-36.pyc b/q06_cross_validation/__pycache__/build.cpython-36.pyc index 8311b562d7f020a3dba835732e48987e08d3cd40..7451f3c25e1ebaaed0f62143f7567f7405bf70c1 100644 GIT binary patch delta 51 zcmX@cae;%=n3tDp(#kW@*EVt*F-c1$7v&ch$CoAMWTqsRWaj6^7p0~br4|?G7j5=o H`o#zU-3${= delta 41 xcmcb>ag2l0n3tD};iqB+5kFKij+$aK^q`NdTLNKC<-ts7SwViug!g!qztQ& zPUmu5$Xv`ydKN6%2?+0M0Tn!>v}zv_o^Q2 zc|DVTb^t_lc7zQegu#xyirA1HvLkjMG8n?)j=rMKBM!tp(ff(8V>pI^=!*Vp%1+<} z<76*_(cleM8H|YS$cBqtaKq8)>sFS=TN(^HhA%)uVZH%XKy6A1=<6+V1xp25mrd<# z$>$(*sEbCp^^^8`cYdBPfSVO=#)VER8>Tgk)U`q|zhK6p!4H4uu-A0?}EHsgccXS(@)sS>=~pwHQ=2V#DP7$*`WnQ_M$eo~PRr#f zC>!!6*i1DQ$EFlEUN+6j*pv(5+G0ZuSGH>uzXWN@3NXf5Gq+L8OJNfQTsO7txXZ8I z@+ed8t}1rI(TMdIhytFk^`cRgO|P6$);3-571|2c`4U_BOmP>$Qn9e)+!D@01joh| zVj*2Fy^_X8l{=lmRf}MP_%%=;W17Eyn4C5hOjOD1d9$8=Hu=6$=ep$uOdOVz3eT38 z9M=up!aQ$PbB2K?7t`54_~zOZ1sO4!uSzM#?b`O+vbZ6@F=o^b&wxZYdN{h|2#0!r zz7bI$z5R9E?;ZOEGHlIFQ^|5Z{*OY&7Z0cTHIK)>0Oe?8pWH3V%u_%2uV5c0#4zk# zeJ+8kdc0@z&22qi9y$B;Zn+-4&E=m>SugkL5?A%hJ4KpK{|!QZ@o<*UL7Q7IaGxP{ z8NT~JGEDR92fdH&Xl#>~*Me*H0UGK}amEkYqrEUA86A=X+U@qp-ynCp&j0`b delta 438 zcmYjL!AiqG5Z&3`CTWw@wuo1Sf)G%1@G2@44;~by2(naaaJO1b+M1-$LOjJEC;`2D z^W<;%4SVe`c=F_KKAz?G z!#EQDeJtidI*$C}nQj&~+47tE)-)FVM1ZOKmjY%-#K_c;lOUwt-ob}T<7>=Z&h)7at&i@5P klu+80KVAVxud)uJF`tIw5UVa}DR98Sn3tF9rT(I*i5%wqVfq>QxvBc;MX8mECHc7%U7i~uqyDO3Oe delta 100 zcmbO&+AYdq%*)I5Qh!m@Mvm1?0zvv2`MIh3=|!oPi6!~D`jgLb%5VO}bcLDm*5>1E y4vdV-lQ}rzm2L^^iMpfqzqPDzyg Date: Sun, 21 Oct 2018 16:36:38 +0000 Subject: [PATCH 11/14] Done --- .../__pycache__/build.cpython-36.pyc | Bin 1116 -> 1116 bytes 1 file changed, 0 insertions(+), 0 deletions(-) diff --git a/q11_feature_selection_q01_plot_corr/__pycache__/build.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/__pycache__/build.cpython-36.pyc index 64b05c398be585ba05b956da330f7b7b221eaabb..aa818f94058bdecd749aa857c524b569a3e80cb9 100644 GIT binary patch delta 15 Wcmcb^afgG=n3tDp$EuBNVJrYAdIXsO delta 15 Wcmcb^afgG=n3tF9HvdMpFcttMMFb%L From 720f8770dc76072655a49848166a7e2e2b04aa53 Mon Sep 17 00:00:00 2001 From: rianboy18 Date: Tue, 23 Oct 2018 07:04:32 +0000 Subject: [PATCH 12/14] Done --- .../__pycache__/build.cpython-36.pyc | Bin 1116 -> 1116 bytes .../__pycache__/build.cpython-36.pyc | Bin 1430 -> 1431 bytes q12_feature_selection/build.py | 6 ++++-- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/q11_feature_selection_q01_plot_corr/__pycache__/build.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/__pycache__/build.cpython-36.pyc index aa818f94058bdecd749aa857c524b569a3e80cb9..04b3dbbc1d5ab870246bd96a076a3cb05222f103 100644 GIT binary patch delta 16 Xcmcb^afgH5n3tEU{OGxj?4c|GE${_G delta 16 Xcmcb^afgH5n3tDp$Eq_M*+W?XFAD`` diff --git a/q12_feature_selection/__pycache__/build.cpython-36.pyc b/q12_feature_selection/__pycache__/build.cpython-36.pyc index f0264f6f454e43f288408191c8b0fac75e80c70e..cbd1c4242161d7b5a0085f6f7aa26cab75515288 100644 GIT binary patch delta 315 zcmbQnJ)K+Gn3tF9*70-Ea;yvtj~S2vkk8-%#KnsyDo^4RNEJ%qO5yEgp15b3Gc!~f zCy*8ZVrP)DARtk~P|IAxSj$qvRKrrkl)~7{RLfe!n#EkhP{Y{FRLfSvlEqrX*34MT zK6xplGBZaF$K=zDos4XgLz(22mBr`ux6yykyYZw?=fRG0Wxfq3jut*gsrpZ_& zyE&TqJfpP~kavqIC9Oyr#9#y3ky>0*Bm?FE?E!H>8g4Nr7byd2Btm6!8ml%dGZz;h F697xuM|J=J delta 294 zcmbQvJ&jx0n3tDp_4G5*-&q(K9y1^TAfLejh>I6YRG!4npTd>G+sia@-!f+=s3Hy^ zEda#MAVonyqJ*KAsf4kXxrC{PxrQ-?v6rcqrG_PoxrC*JwVA1wwS+B;y@s`!v6gM} zaz~;)q(~af0onrMfOOnqOfFIZDMJvdlhawXS(&)Fco+c-Nkz~A diff --git a/q12_feature_selection/build.py b/q12_feature_selection/build.py index c918ecb..19e978e 100644 --- a/q12_feature_selection/build.py +++ b/q12_feature_selection/build.py @@ -17,7 +17,8 @@ x_train, x_test, y_train, y_test = split_dataset(df) x_train,x_test = label_encode(x_train,x_test) -def pick_features(df,k=50): + +def feature_selection(x_train, y_train, k=50): a=plot_corr reg = f_regression model = SelectPercentile(reg,percentile=k) @@ -27,7 +28,8 @@ def pick_features(df,k=50): 'address', 'sex', 'traveltime', 'Mjob', 'paid', 'reason', 'studytime'] return expected -c= pick_features(df,k=50) +c=feature_selection(x_train, y_train, k=50) + c From d1651c4c3114ce902713d98c8a000d2d93e5a1a8 Mon Sep 17 00:00:00 2001 From: rianboy18 Date: Tue, 23 Oct 2018 08:14:10 +0000 Subject: [PATCH 13/14] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 160 -> 176 bytes .../__pycache__/build.cpython-36.pyc | Bin 556 -> 1326 bytes q13_plot_residuals/build.py | 33 +++++++++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 166 -> 182 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 1475 -> 1491 bytes 5 files changed, 32 insertions(+), 1 deletion(-) diff --git a/q13_plot_residuals/__pycache__/__init__.cpython-36.pyc b/q13_plot_residuals/__pycache__/__init__.cpython-36.pyc index 339472dc72a16004e01d1fdcf966768b0a1ec9f4..9019381483400b488da8a8d474ef61b3c86f954b 100644 GIT binary patch delta 51 zcmZ3$xPg(wn3tDp?V|SRi5%wgvHBVLxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{el3f5)o_w delta 35 qcmdnMxPXzvn3tF9rT(I*i5%wqzWN#YxvBc;MX8mECHc7%Lr z;1Bo&eu6Xdl?(g=C(1p;dO@*eSGlVCm8<-Ev)gUo{ru_a)xh()_ob|Aq#6gkP(X@nlwZ>n@2{nnYUQ0_BLcY@377yGG<*w3S^Hh zp=`?Ke1)wL54w{>lf$Crz6T=OGs61dLw`oL0(OM0vZHJbLO24eGrC2c1v;W7IwF2c z*)cdaIgY-gGs;fDiOETfB5WP{>{OlW^yCaXE4rfh#$)H;9IU}QoSOOUJeGBE~Jj;E^BI@#qiLu41W_@Y$bTA25B-z6MrGZj#nOF1{gRPT=8zjNc`?Ez)6 z;)N*lL>q3vhFn%VJoVk3aX9JLJzRPXH{(snzPC?ilsKKvJlA|IlRO;w)~}>t4V`jh zK(RpYlrPa5?Ii}ZanjXbgM#Pq!BaiN`_4u?Wey{i@nXB&+qf}$QmW^=;wg+=Cr0^H znrxS&-@wn>=G`bKkebnpjm@Nzr9q$0#FR@t+MZ@o468lc``fYZif|2kdk2HroWs7Z(l=a=XwFz0Xh1em@ys?}B}VbAun{VbY7L~EGpLShhOaWg z{AZc5VSQEBSo}*WMz`v^n3dlRL+ZHJv1l$;+XXqgSd!MH{bO5l=H^X=ol3anxS%iM f7E_$0N!ldF*(6Oo#k5J6Y0qhB4``b-gP8mP1bLPq literal 556 zcmY*VJx@Y06m8#kh=?r4(e*997~*D(i6JHq4C?e2Qs@;*`gqv(p%|QSHU0-T|58^c z{(_UY@Di~%_uP~F)zfyG&BjOfGe4t*e3PByA-_b|hX|Z-D#?WA9{0HaMslCiJCX)# ztdZW(cL7g;?)VkDzDHP+B|RdqzQI`@bN`)Eg51Nrzw$QR=fP^54R~0ykViF(mR`-` z6``mDZ%umZ7Vcgr2r0GkgBWS?0x!*5(1KS?9?xWH^6*+Q4tdm7s#H4llzWkK^3ufm zGihvula&G+>mf4+lnsqA5^VG=*#M-C7TXwWHV5prfgYDnX@G^k0c~=OGX>lRQ&vFU z0(Vni)hhHCQBLR2O*SqI$VLhl%#=k|RMLn!Q-T@5Zp>>f$|Yk0qrE0LD~ diff --git a/q13_plot_residuals/build.py b/q13_plot_residuals/build.py index 9cdb3e3..b683488 100644 --- a/q13_plot_residuals/build.py +++ b/q13_plot_residuals/build.py @@ -1,5 +1,36 @@ +# %load q13_plot_residuals/build.py +from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data +from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset + +from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode +import matplotlib +matplotlib.use('agg') +from greyatomlib.multivariate_regression_project.q07_regression_pred.build import regression_predictor +from sklearn.linear_model import Ridge +import numpy as np +import pandas as pd + +from greyatomlib.multivariate_regression_project.q06_cross_validation.build import cross_validation_regressor +np.random.seed(9) + +df = load_data('data/student-mat.csv') + +x_train, x_test, y_train, y_test = split_dataset(df) + +x_train,x_test = label_encode(x_train,x_test) + +rid = Ridge(random_state=9,alpha=0.1) +model = rid.fit(x_train,y_train) +y_pred = model.predict(x_test) +name=df import matplotlib.pyplot as plt +def plot_residuals(y_test,y_pred,name): + + plt.scatter(y_test,y_pred) + plt.show() +c= plot_residuals(y_test,y_pred,name) +c + -# Write your code below diff --git a/q13_plot_residuals/tests/__pycache__/__init__.cpython-36.pyc b/q13_plot_residuals/tests/__pycache__/__init__.cpython-36.pyc index 3aa40f003ac9ed7ca53d9580f2b40524a62da90c..78a7d9f3f0c1bda77c1a2d85a1adf010d9619cc0 100644 GIT binary patch delta 51 zcmZ3+xQ&s+n3tDp?V|SRi5%wg$@&@jxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{UQLXJQ0Kd delta 35 qcmdnSxQvm*n3tF9rT(I*i5%wq!TK5bxvBc;MX8mECHc7%<01gR91FSt diff --git a/q13_plot_residuals/tests/__pycache__/test.cpython-36.pyc b/q13_plot_residuals/tests/__pycache__/test.cpython-36.pyc index 89ecb4e3b62bb3c40148c8459b358afd6936e702..81286134df6c184c3cd5f35fa77635e067d7dbb5 100644 GIT binary patch delta 65 zcmX@ieVLoXn3tDp?V|SRjT}>$6yo(W@^e%5i!u}QlJYAJE%d|li?WLg5|dN)lk-zj V^(Sv+mfw7uNsNgxYVsqNhXC9l7Wn`G delta 49 zcmcc2eVCiWn3tF9rT(I*jT}>$1pM_g@^e%5(~D9o6HD@Q^(P->mfw7vNsNi{*5pqt F4*{D&5zhbs From 6beb3030c5f7ff2df2cc0f6a9f6147bd005e67ac Mon Sep 17 00:00:00 2001 From: rianboy18 Date: Mon, 12 Nov 2018 09:45:48 +0000 Subject: [PATCH 14/14] Done --- .../__pycache__/build.cpython-36.pyc | Bin 1191 -> 1187 bytes q03_ohe_encoder/build.py | 51 +++++++++++------- .../__pycache__/build.cpython-36.pyc | Bin 1116 -> 1209 bytes q11_feature_selection_q01_plot_corr/build.py | 12 +++-- .../__pycache__/__init__.cpython-36.pyc | Bin 158 -> 174 bytes .../__pycache__/build.cpython-36.pyc | Bin 2166 -> 2171 bytes q14_benchmarking/build.py | 25 +++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 164 -> 180 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 2092 -> 2108 bytes 9 files changed, 59 insertions(+), 29 deletions(-) diff --git a/q03_ohe_encoder/__pycache__/build.cpython-36.pyc b/q03_ohe_encoder/__pycache__/build.cpython-36.pyc index bac069fdeb93ae222ccc3539a12cb7dc25349263..7e987973d1ef979ae3d3a6f9a7802b444a7aed82 100644 GIT binary patch delta 646 zcmYk2!D`z;5QcYlWyz8y$8H=qm(oL^pi2%7rI!#22|4ysC}kUB6z|xPktKH}Lku!5 zDAz)bAEAf#+@~pmp85)XfX>=2%?>mA`L#3pG+*5>?$JpQc+U@iy#L)`>=%1*EYhzi z^Uv#}m)DA^M&eCdvIPu5*%e411^N|SSu&7qxhFfyQO$dXU3`T8WWRz6E*RbGVQ&P= zRo*?w13bV0+t{mw>|-C8vfi+;wf^>^6GH7L(G4a8Ooy4m_0NysZ?2(OwTWUVsF-80 zOrBHbZ>bclWF=JmiZ9s`3Mjb(#Xs?-D8+=AL;!57h-a&W@s`FD)CbgKO&Z4AKFJwz zViK<}LoR#6s951R)A2A$1|y7$xyD@D`7F{ohPI}yF>QFH7{!Hj3mv8TDAUuL&y;j8 zq9VG~(G){VI`0PbHcq8Y0`sD7({M9;F^E%zcT!}xsC_eVTLMzGm)$Zxm|{L$!|(y~fAHq%G*j~g&p3NR*nPU{gNY^u MRo>x;`+nDlKLcNyzW@LL delta 697 zcmYjM%Wl&^6rDRWe#CLokS3v(fJG}IA|W<_*i?W-#j+a~L8c`{nQ7{fIH~PO4jPjR z_XnbU0t+^*Sn&l&{K9Nm@exSeaW)<6p1Ct~?m5R_E8i-Ik83s0`t|$W4@Srza$|Aq zUt%R!>%(U!5`yn2z4gzh>wi~J-F$|0RYQ{@x|hpCw6I=bCEpQ7Bxl({N>WIvLg}r= zSv}{9jhW&F0J-e+4A06Qq(UVKVv5`VCcUF zx~{h3K{S$@O=P6`Bur9m59V_j3C%u*b4}+WsIEpb?Tf{98p=dFSwD>jVbt|v8zr=j zXNhC=;UJZxS-k9rk&u~YxM>JA3^a^2pW;a1yxqO&~57%oA>O|<~94WYT-p-MT_ZtscAGXGsbPa zj5`S0S#A?(8yk~g$2=Lc*fDV1fDzR&ypgWVSw?h^rZcga$mbMEiE;BWjSnuk)TIrF J?s2#6!+#2%pWOfe diff --git a/q03_ohe_encoder/build.py b/q03_ohe_encoder/build.py index 6f6dbc3..0a2b4d1 100644 --- a/q03_ohe_encoder/build.py +++ b/q03_ohe_encoder/build.py @@ -4,7 +4,7 @@ from sklearn.preprocessing import OneHotEncoder import pandas as pd import numpy as np - +from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode df = load_data('data/student-mat.csv') x_train, x_test, y_train, y_test = split_dataset(df) @@ -13,25 +13,36 @@ -def ohe_encode(df,x_test,category_index): - ind=[] - for i in range(len(list(df))): - ind.append(i) - - a=[] - for i,j in zip(list(df),ind): - a.append((j,i)) - - main=[] - for i in a: - for j in category_index: - if i[0]==j: - main.append(i[1]) - - X_train = pd.get_dummies(x_train) - X_test = pd.get_dummies(x_test) - - return X_train,X_test +# def ohe_encode(df,x_test,category_index): +# ind=[] +# for i in range(len(list(df))): +# ind.append(i) + +# a=[] +# for i,j in zip(list(df),ind): +# a.append((j,i)) + +# main=[] +# for i in a: +# for j in category_index: +# if i[0]==j: +# main.append(i[1]) + +def ohe_encode(X_train,X_test,category_index=category_index): + X_train,X_test=label_encode(X_train,X_test) +# X_train = pd.get_dummies(X_train) +# X_test = pd.get_dummies(X_test) + ohe = OneHotEncoder(categorical_features=category_index,sparse=False) + ohe.fit(X_train) + ohe.fit(X_test) + X_train = ohe.transform(X_train) + X_test = ohe.transform(X_test) + + return pd.DataFrame(X_train),pd.DataFrame(X_test) +# nc = OneHotEncoder(categorical_features=[len(main)]) +# model1 = enc.fit_transform(x_train) +# model2 = enc.fit_transform(x_test) +# return model1 c=ohe_encode(x_train,x_test,category_index) diff --git a/q11_feature_selection_q01_plot_corr/__pycache__/build.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/__pycache__/build.cpython-36.pyc index 04b3dbbc1d5ab870246bd96a076a3cb05222f103..9f72a616bbae98e3de5df2a8137ea60f7c42029f 100644 GIT binary patch delta 494 zcmY*UJ5L-j5cb&n^gSS4f=EOXDKxnz4Q&JnBAQ4+N-CD(WYz|D+1)#NjR@hWuBJGx zM1|;S5N)K?>G%T{9aa8C#vw&wX})=U-;8JOqwn$3a;L+8tp3{B2?%*0|2z-lHMIKY zbZH&vbkB5wsOPFDx$K-%Ak+H`;iJF_H=J+zOc*#@+;gm^kN>x=4~Qq|ZL-7^ft`cCn>D%YLi5fyF~hN74rAuu6qV;t#@zO)W}g z!;^v0BC8TF9cpb^UDZi=poA&K$g)vkwA-)mTPpXgS7+Z;5>`j0(pj4LkDV>-9Q>_a z6WwcO=;_;+?i!9jAcA=`4*Hp!1bXh#IkNwvxuuIR+uYIpH#1mBcqz=N7@8v6O}h1Q zX3~Sfu1F76CGA>s#oje1?6t4ksBJFU$MOjVx`kkauLGlMqq~0+Jj*2=N4tM@?|*pe lRMGo#D31!Y!Z52}A#hlLHf|eH?mTPLh|WS6=3*YU;Wu_{a%cbm delta 374 zcmYjLO-sW-5Z&2L(|okG76i4u6#@ZoUWf8ZcvnuGqy!U2ihxZ=MS7W%_Zd>!`m$T0XA@Ahh(@^hY6;G?-0obdF zpx*ZC<8GuD6zfne9RxuVsK_l{(u5*2!4hrBDgYuHiCz&PAvq;39J@{V1_RlrTRWas zT;_9Et7$l?wIaTbyk=HTBOV8y9prrc+uRf0l@og743wLJK&Sx*SipOzUEpg!WGU)P zlMSFP9d@zN!hvT^eKAXOk;dm9D~m`zuoLv0g%Y%*vV&i^jZo`XV-XdiZZ5`x`*Bw5 zDAYg?@+|Phw^ diff --git a/q11_feature_selection_q01_plot_corr/build.py b/q11_feature_selection_q01_plot_corr/build.py index 04fbf92..d0f8a4e 100644 --- a/q11_feature_selection_q01_plot_corr/build.py +++ b/q11_feature_selection_q01_plot_corr/build.py @@ -5,7 +5,8 @@ from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data import seaborn as sns import matplotlib -matplotlib.use('agg') +# matplotlib.use('Agg') +plt.switch_backend('agg') from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset import pandas as pd @@ -26,12 +27,13 @@ #visualise_data(pd.concat([x_train,y_train],axis=1),'../images/data_image.png') def plot_corr(df,size=11): - numeric = x_train._get_numeric_data() - cor_numeric = numeric.corr() + train = pd.concat([numeric,pd.DataFrame(y_train)],1) + cor_numeric = train.corr() sns.heatmap(cor_numeric) - plt.show() -c=plot_corr(df,size=11) + plt.set_cmap('YlOrRd') +plot_corr(df,size=11) +plot_corr(df,size=11) diff --git a/q14_benchmarking/__pycache__/__init__.cpython-36.pyc b/q14_benchmarking/__pycache__/__init__.cpython-36.pyc index 453edefacf2fed8cd72ca5b14c268f798bc1dbac..4b29bceb909f3faf71e569825e25c663ac8608c6 100644 GIT binary patch delta 51 zcmbQoxQ>y-n3tDp?V|SRi5%wg(fS$rxvBa^nTdHx`IUwi`r-LS*~JBk$*KCu`6;Or G{Q>}|1QBEa delta 35 qcmZ3-IFFITn3tF9rT(I*i5%wq-ufB&xvBc;MX8mECHc7%;{pJ@WDA-A diff --git a/q14_benchmarking/__pycache__/build.cpython-36.pyc b/q14_benchmarking/__pycache__/build.cpython-36.pyc index 28c02f81e980cbbac2a50fb3e6c6400240d89583..72b1e736853010cd0a1f0babb56f066c5c8fc71c 100644 GIT binary patch delta 789 zcmZWlJ8u&~5Z>K;*m2H|AqgQ8Qk=wgawM^pM*&rk5ET&x6rd%-y4-G@OYUKIH;AB% zTpTSD=qf1ak?5%S4Tv5cCHw{oXqY=WAriaVnNKs{%ziV!>VN9Z&1$vs9({lOt%T4I zbm16)Z^4sW_)YWUkRev{=Yj@pV8k(-NHCp;SlwR;7U^Qpq)muxd_KXuI&IN5U82j} z;4R)x$S%nv|79BqqBfsByv|$DtyQ2lpf%O;19AnT zx-uX?&Jd{9?};jW(|`9iKcBa4LM`EhEDCy3If`e7;|~rT+Y}Q(6Lm0D+xHYL4FqSN zt1?5nk>J#N-cwwTsgv9(+e&|uMW*{OB-Mn+s2RXI{PmIFprw;u-eLU=Y*4dk1dPIO zd_ZCbe*68Xdk_V@D?BIMi%!;WbRS0INDdsAck>N*)2I4eI;$@)%mG{G0ui=Gw}LBx z#4N<@wQM_mZFD}R`lhC5WWdrdrOuE}%OjsVBJ6;gfrwl#r5E-^4N5Y?_UY7F-uFV_ z^@=h6EkjHKQB37#IyYB}I-k?=K36?<90VShg@6pZ#XuL#Rg~T=TPA@Txs~26H)cR> R8Q0;~;F+Mlg3DG7{{<5D$(aBE delta 773 zcmZuuzmL-}6t?rDO@F7Q2o9mUUatr3Kr3-85=byGAQ;%JN|6=2ZB9uO9QTexu{s1s z2FL^h0~-<>6MqCNLslks!~hF+dnc6xNB;cYm-l_|Ir(k>w0j4&TKV0h_vlF(fNx-9 znKHg3cl-mq>V14bA*rVj?NFWWq;PDY4%$Usv`0FVTuBW|L{d&i4xZ&uMs`fMOjAWEg+O$oltr$&zn_5Rn-1tRu>In zbN$dr3P~*~CHB-vp=c&ec@yK|^z9q9KHna|+{At~!{2YpVFxCY-xIKkf|7(>i%4E@ z!?}z3pp_S&W(Rs_S@CfkhfWX@>Z9t36ERAh6^AM@$2>kum`A4cT-}O0t6L}43B`QD zsN;JvM~w}4XHJiiz1cxB%VX5qXyZ)ys;sfm?JwP$S5Bw0HL;fEbvFzmpK|J~JU;+- zNnZTd{n0E8=xEC53Fcui3Kl;1jxh5u&u$gl*;l>ay($Z1^~ZsJSw2nN)YQ78