From 97200558b68d104f1f2d476d74cdb56f115a1fa4 Mon Sep 17 00:00:00 2001 From: sagarpatil232 Date: Mon, 17 Dec 2018 12:14:03 +0000 Subject: [PATCH 1/3] Done --- __pycache__/__init__.cpython-36.pyc | Bin 159 -> 157 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 170 -> 177 bytes .../__pycache__/build.cpython-36.pyc | Bin 655 -> 766 bytes q01_outlier_removal/build.py | 50 +++++++++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 185 -> 183 bytes .../test_q01_outlier_removal.cpython-36.pyc | Bin 1835 -> 1837 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 179 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 1124 bytes q02_data_cleaning_all/build.py | 20 +++++++ .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 185 bytes .../test_q02_data_cleaning.cpython-36.pyc | Bin 0 -> 3407 bytes 11 files changed, 69 insertions(+), 1 deletion(-) create mode 100644 q02_data_cleaning_all/__pycache__/__init__.cpython-36.pyc create mode 100644 q02_data_cleaning_all/__pycache__/build.cpython-36.pyc create mode 100644 q02_data_cleaning_all/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q02_data_cleaning_all/tests/__pycache__/test_q02_data_cleaning.cpython-36.pyc diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index 2e5da7da778c48a9c58d7d055bbdb642fcb66418..9451c1a0537f7476483db04e8db6f095b8a8a906 100644 GIT binary patch delta 55 zcmbQwIG2&bn3tE!tz0~2B8R!MmwrZmZmNE9VtQgxL1IZ}j*+pEet3RSc5y*sa;koE KeoE@Z6l(yyml3G| delta 57 zcmbQsIG>Tjn3tDpxuj9lL=JORAN|nc)S_bj#H5VO;*8Yn;?ks|#N5QZ%)~tXywvje Mw9K5;;)zMt0Qi&>ga7~l diff --git a/q01_outlier_removal/__pycache__/__init__.cpython-36.pyc b/q01_outlier_removal/__pycache__/__init__.cpython-36.pyc index 2f9a42a105b2b26ec10c60ac4d11fa03f7624d22..4829d655e8c8c67c206015c973836fe149663fcf 100644 GIT binary patch delta 55 zcmZ3*xRH^=n3tE!tz0~2B8RzhoPI`rZmNE9VtQgxL1IZ}j*+pEet3RSc5y*sa;koE KeoE@ZXnz345)tPB delta 48 zcmdnUxQda(n3tF9Mtoz`L=JPAaQ%$@+*JLH|_5lDx3=34^ zVUEg}XORhmK&_ZvZ`BSru9mE(~4;YxMVy;xwMHBt*&^F`+K zbq7Z@f_oww>wMBk#y|Mja_1wdJ+aC-Pnc19k^9k5;85z4tSj0CtOpdph=CCUBdWj5 z!Ts;ZOrWa2UKQ^k%)-(oHJZYed;5FEOJz>2hER%HF%Ivygdm!_GJI*cwc!o5Q7x}s zvA%n+Qk@eGH{f2WGb)NVT_f18KKIlAJfrZKGXON&#-ZO1J(}S$o?$Zu9+ zY338zt@ODGI-eU(Sp`4FY=LQR1PGELk87|!Y<{>>tP}iE_|bL@kmEcWll`6t?3ecRlsEGM>c5b_@-O6#-SdR6-RJOj#l~&m2yDwre|8i^6pL1ZH;r z50h7>F8u*aJcofR5_aCFJb&+dFYh_e=kwVQ`K`Xo2>D5N7Q^?~X#NQT5TJ_GRM0Mi zY)fkJXNo@C@iX-E9iIg{&>W9aM-{;~i z^?I~1y$&vQy2|79vPZ2{A{N$39byj7*jPvn;u`tAae8Tvk>Yb6Y5SeHIf{S1uRdbI ziYswlod|ysjIG`}(}^~C9Qs=NAlt@?wG-Z_!P`G%b@}vJWBQ<^a7b^=6<5`HFBKfx zo4ELg*-JNYfI#TMxcBL!ak~Yct;$$hu7UfQS%_07I5c>zF3H>^K?)l`cn2QfS)9Ju T80eLFiN783CBihD(f#~4xYMeW diff --git a/q01_outlier_removal/build.py b/q01_outlier_removal/build.py index ec278ba..24e028e 100644 --- a/q01_outlier_removal/build.py +++ b/q01_outlier_removal/build.py @@ -1,8 +1,56 @@ +# %load q01_outlier_removal/build.py # Default imports import pandas as pd +import numpy as np loan_data = pd.read_csv('data/loan_prediction_uncleaned.csv') loan_data = loan_data.drop('Loan_ID', 1) + +def outlier_removal(loan_data): +# col = loan_data[['ApplicantIncome','CoapplicantIncome','LoanAmount']] +# quantile_all = loan_data.quantile(0.95) + +# col_name = ['ApplicantIncome','CoapplicantIncome','LoanAmount'] +# for x in col: + +# loan_data = loan_data.drop(loan_data[loan_data[x]>quantile_all[x]].index) + #num_cols = ['ApplicantIncome','CoapplicantIncome','LoanAmount'] + q_ai = loan_data['ApplicantIncome'].quantile(0.95) + q_ci = loan_data['CoapplicantIncome'].quantile(0.95) + q_la = loan_data['LoanAmount'].quantile(0.95) + l_ai = list(loan_data.index[loan_data['ApplicantIncome'] > q_ai]) + l_ci = list(loan_data.index[loan_data['CoapplicantIncome'] > q_ci]) + l_la = list(loan_data.index[loan_data['LoanAmount'] > q_la]) + + l_95 = list(set(l_ai+l_ci+l_la)) + l_95 = np.sort(l_95) + loan_data.drop(loan_data.index[l_95], inplace=True) + return loan_data + +outlier_removal(loan_data) + + + + + + + + + + + + + + + + + + + + + + + + -# Write your Solution here: diff --git a/q01_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc b/q01_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc index 5a057ffb73694628cef3ed87e03ee3a17f7410bc..73f450950879831705d8a9ea84f9aea0abffa2e5 100644 GIT binary patch delta 55 zcmdnVxSf&1n3tE!y<9wIB8Rzhihf3ZZmNE9VtQgxL1IZ}j*+pEet3RSc5y*sa;koE KeoE@Zlu!W6vl0>j delta 57 zcmdnaxRa5?n3tDpxuj9lL=JP+H2u)x)S_bj#H5VO;*8Yn;?ks|#N5QZ%)~tXywvje Mw9K5;;)zM200=D;>;M1& diff --git a/q01_outlier_removal/tests/__pycache__/test_q01_outlier_removal.cpython-36.pyc b/q01_outlier_removal/tests/__pycache__/test_q01_outlier_removal.cpython-36.pyc index 4c0b6c7431c6a14108ba9d55dd44059612f144a5..d3392c391f02da8bba77665156d4aba0eb36dd4e 100644 GIT binary patch delta 71 zcmZ3@x0a97n3tE!y<9xzK7-bCl(bXmSpA_ b85`+`=NDxc7bGU9>L=%?q;6JV;${T^Of?s? delta 69 zcmZ3>x0;XBn3tE!Sjs4B??ld3EL`cSB^!6UFshd6hZd(673(J^Wn>m-q-GbFCKV;- ZCgx=(=IQ69mdB@M=A;&HR$}621pp0E7h3=T diff --git a/q02_data_cleaning_all/__pycache__/__init__.cpython-36.pyc b/q02_data_cleaning_all/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..926d25d92a4ad863ad314371f1000fe8e6896d0a GIT binary patch literal 179 zcmYL?F$w}P5Jj_KA;Q+4!Ny3o6|u6kv9J-wAsOOmHi=0@Jd#(k^%hoU3-QBye17x0 zww-M5(}Spa5BjC4WnIamDkFAc)@+|54f9{0qdbM4WJZfAVqvE`CHEm+azss12Sd^Y z%ekP_7>1N3BaBUz&t))<7FSr&CzOj&K2^b6e^O|V~q=r5o+ z;#eXwpE1D#jl5AqV9@@3&Al0(e|WyPNrE~yBoWLF*~(%P*K599$l9chkqAZ|-kf2w zC>BRcJmBHX1G_C2osUPn^%;>a#|Nkv-#{*C-$s<4rBYDZ!?tS_OLJ<3HdL1~HQ-w+ z#zv+>Q6;kCiplGB&I}vKg5|VSf~Sc|i=2-0L<*J*-cR(E4d1)vcY8M&?ns<+qXiOx z?1Jd;pbQ!TYz{Cnsu1^9(5P`Y`!h7d&fW&7+~-XPhDXC-ia$N8@E$r@n|c+h?qce> zIghCz=5qTGP8Fz%g%s^^g5&a~e#;Y2>_BvkI!Pip~O{ zr?Y?K(zUTevXd3#+>qdn$hlA?{J@k-1t;;ID4i=ensg3?Jfp9(QWg_f>edX*1L;Sh zGP1bq*fR8Os!gFLWTD=1V3-+e&sHb7f^Wbwp?N3<@w4Zwi9 z+i>#70R}jJAhiOg+@1{1i%bkO8!}ZglgiDl&B0-zE_BHfF-YK2Xo?|#OB3jop%PlV z#wb-W5{VgHZfsJQ2Ce%f&4-jpIXE4slK0Dr?fkXYg&XxFPzbm2DvogE#dytYgY_7z zC*bcrunj%Y)+@C2A)j*_u+kO7hCEd{%Y+R|AdbP7lG|oJ&dQ03A(AZX3usl9_Z?A^ zY9S#%NVR6m?m*@fW{OOvr~Ur`>R)a=r~kZ-eho*#^G7yPf^q5|Lrc2H;P5Gjt4_b> g^qyL+L$)EKu@o;{+4MtDUHsI62NK#q0KoTu11vv9WdHyG literal 0 HcmV?d00001 diff --git a/q02_data_cleaning_all/build.py b/q02_data_cleaning_all/build.py index b56e2bc..685ecac 100644 --- a/q02_data_cleaning_all/build.py +++ b/q02_data_cleaning_all/build.py @@ -1,3 +1,4 @@ +# %load q02_data_cleaning_all/build.py # Default Imports import sys, os sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname('__file__')))) @@ -12,3 +13,22 @@ # Write your solution here : +def data_cleaning(data): + np.random.seed(9) + data['LoanAmount'] = data['LoanAmount'].fillna(data['LoanAmount'].mean()) + cat_cols = ['Gender', 'Married', 'Dependents', 'Self_Employed', + 'Loan_Amount_Term', 'Credit_History'] + + for col in cat_cols: + data[col] = data[col].fillna(data[col].mode()) + + X = data.drop('Loan_Status',1) + y = data['Loan_Status'] + X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.25, random_state=9) + return X,y,X_train, X_test, y_train, y_test + + + + + + diff --git a/q02_data_cleaning_all/tests/__pycache__/__init__.cpython-36.pyc b/q02_data_cleaning_all/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..0281b4dc2ed957a44bba1089d1823aa7e0a90d24 GIT binary patch literal 185 zcmYL?F$w}P5Jj_KA;Q+4!N!r@R>Tw7Sl9@|kR4+*o5V~kyoR^%O19oY8?%M@;XOXT z`E6ZKKKJQfmAnT1QkAkU$f&4OTQ#dT50!@bulE6tp=S^>lp{s E3-vBD)&Kwi literal 0 HcmV?d00001 diff --git a/q02_data_cleaning_all/tests/__pycache__/test_q02_data_cleaning.cpython-36.pyc b/q02_data_cleaning_all/tests/__pycache__/test_q02_data_cleaning.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..3915b2d00aa274b4be7f33496b581c70c5aa7b32 GIT binary patch literal 3407 zcmd6p&2HO95P-QPMN&VOf8yA2lQwKx2T+kpiF0TR6h(?84GaV>(6nek1YkDYl|q#w z<=v%G3F%3Bf*$(@eWktjryKQUO1 z)!!Pd&aH_RTw~;!(Q53&{*0X#(cX_-s)tl^XfI~DN@6ZT!3WtMP4-O~1pNz)DjG%! zr)iw_prhI2s+%VX6+JoR(fAe)=p-3U!=d0Tj#QkbVV)LKIBQ38FL0mY>+MJT1dK+w z{NaVGJb+t11;GnofyoFn-x`6%EM|iSRLlWgVJ`DPJFLoTpj}pH4bUE2U`^0fw#b%1 z*Vr<+xuTcRy+^a#k8pjwa9I!Thj7a+5Xw+wLVhD}jJ~O?H-wQ5V*=ZNEzCT3%{60E zd`Vcq-Vta{xFE(iAO8w46lXqg$p<`D(%)ov{3r1qPodSa1;&S{fY5a+B^T=PZcYWAxETLH{FY%+fE}I3e~!B)!@bx@*#0%?~5{nOXq;lzPCc?AZP00;p1{9FJI=N|cwVS~|7`0qml zq7LFunSHBo_bZGj2cvN&*36yp_fzK~qkbgaqT=0(RpnSnYN=$a9!!54P8Alr)^xi zMM{2i=r-ShuH0aVv%=E+2jH?q00wCilZ?MO7siuzE*ns>0xoG6oD?)p#VS0Bt0>k` ztfROF;y>8kKARny#q%-?@5}!K4-H*TdgS>tyER8_>*B;NDXYzT1lb!>+gX}O3I&m&| zXC;NwYI}~|#gjs5XQx%yUKpm3wZc%>!f=qWJi&G&46))W--t#0Xsahy|830{@I-1MQJjNd8UoFWbhSbpQYW literal 0 HcmV?d00001 From 32da4038480f3db38fb6b2a2a1d33680b0902848 Mon Sep 17 00:00:00 2001 From: sagarpatil232 Date: Mon, 17 Dec 2018 14:03:43 +0000 Subject: [PATCH 2/3] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 181 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 1641 bytes q02_data_cleaning_all_2/build.py | 46 ++++++++++++++++++ .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 187 bytes .../q02_test_data_cleaning_2.cpython-36.pyc | Bin 0 -> 4762 bytes 5 files changed, 46 insertions(+) create mode 100644 q02_data_cleaning_all_2/__pycache__/__init__.cpython-36.pyc create mode 100644 q02_data_cleaning_all_2/__pycache__/build.cpython-36.pyc create mode 100644 q02_data_cleaning_all_2/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q02_data_cleaning_all_2/tests/__pycache__/q02_test_data_cleaning_2.cpython-36.pyc diff --git a/q02_data_cleaning_all_2/__pycache__/__init__.cpython-36.pyc b/q02_data_cleaning_all_2/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..625298ffd458813f0b9f795da3ab7993c04e22b5 GIT binary patch literal 181 zcmYL?F$w}P5Jj_KA;Q+4!Ny3o6|u6kv9J+_F&Sbsn~6z8Jd#(k^%hoU3-QBye17x0 zww-M5(}Spa5BjC4WnIamDkFAc)@+|54f9{0qdaj>GNZ*5u{f_fCHI^zIie=1*^u;X zT`o>TBAX~@#{pvEGwC9)3k3!Xg7$>L1q*bD4GBch!h09q&KT@f6Uzt zB4K?}uYHgLJ@z^J0KE2;SLmt3m8Hr-T2umOhBM?hf6IB?>jl66cKG@aAE7_d*3Sj` z8(4(`!V$+35!`T#w18XEP8{N3V{1t_@rc*Rw)B%WX=5btEa1)(laA=jy4>a7(gN8N zokr&v{@NuyvP1f0Kz7NH`@H=#B6}RaK%?LT_(kU^s}mzu~1Zr zBzwmssJhSDrI2T7m~o*NUz!^enX#1SO7J)=<1D3B+F%Gi4vTl%dv46nPCsC96WYcZ z`~p~QSSPTGmtf+MvqU#`4H@$mx1-h(x^ZCVn2b!sJm4MPjeO9%HQqYq!R}M1{P$nf z&MEro;HF*MGh91$`v@%?{sdi<3j}s=%kJIUfrEWaROyRYP7lgS&dh6jcQz5b?eH8-hO_rOw~#MIL~Dqvb1~#ol6ASJ;~Tds=)N= zILWHCB<@p@LVt<(JyR+coCK#LH>$KONc)UeAv2vOy%$1W(X%9%*&I#{npUqc=u4pz zvU6fSi;{j97iFgAr1yi$a-qsOJywE|?mw{fA?dBW(r-n=q#(nMANo`=Ua?Y;!5xS6 zJR`wvh(_MKgHC^}6qCxlFZgh6_C78ay|hXwzoMmLar$7Pn+JOuCT-(L9Dz%k!-H8MMR!I_zLfagY)lRPBwA4=VhUG%LVU_~!D9{GR zM4{akp7!Qz1qk3kTWL-G5Y=uiYThZ!Pn8{y}I)K#wqLVk!@kzlVrgCVT zoIajTE;9AD$XO^R<{`rij-Wwt2oF6{qA1KO&Q&%OVL7>eIHh+617%Xu>EyDCB_Bif z{kzubz&z=%fFSH+7giT{tu+tufwfuz@BxNpfxY<;@vxEAeYiW?*KW>I&I)B_g@Un( z)IJb>0wK;>nI$s59REk;<4;CDZsJy!K|22bNRQ}8v+x$D1vunh@fL=rO2;q+p=_b4 zU>Yei>$DHwIj3e2wwpO=ilw^7f?sJoSEgEO*N~whdxn_&o91niL(pmeNs{qOim#2^ S!d&oI^@R!tP(vT@+kXREt=K65 literal 0 HcmV?d00001 diff --git a/q02_data_cleaning_all_2/build.py b/q02_data_cleaning_all_2/build.py index e20ff7b..9fd796c 100644 --- a/q02_data_cleaning_all_2/build.py +++ b/q02_data_cleaning_all_2/build.py @@ -1,8 +1,10 @@ +# %load q02_data_cleaning_all_2/build.py # Default Imports import pandas as pd import numpy as np from greyatomlib.logistic_regression_project.q02_data_cleaning_all.build import data_cleaning from greyatomlib.logistic_regression_project.q01_outlier_removal.build import outlier_removal +from sklearn.preprocessing import LabelEncoder loan_data = pd.read_csv('data/loan_prediction_uncleaned.csv') loan_data = loan_data.drop('Loan_ID', 1) @@ -11,3 +13,47 @@ # Write your solution here : +def data_cleaning_2(X_train, X_test, y_train, y_test): + import numpy as np + num_df_train = X_train[['ApplicantIncome','CoapplicantIncome', + 'LoanAmount',]] + cat_df_train = X_train[['Gender', 'Married', 'Dependents','Education', 'Self_Employed', + 'Loan_Amount_Term', 'Credit_History','Property_Area']] + + num_df_test= X_test[['ApplicantIncome','CoapplicantIncome', + 'LoanAmount']] + cat_df_test = X_test[['Gender', 'Married', 'Dependents','Education', 'Self_Employed', + 'Loan_Amount_Term', 'Credit_History','Property_Area']] + + for col in num_df_train: + num_df_train[col] = np.sqrt(num_df_train[col]) + + for col in num_df_test: + num_df_test[col] = np.sqrt(num_df_test[col]) + + cat_df_train = pd.get_dummies(cat_df_train) + cat_df_test = pd.get_dummies(cat_df_test) + + cat_df_train = cat_df_train.drop(['Dependents_0','Gender_Female','Education_Graduate', + 'Self_Employed_No','Married_No','Property_Area_Rural'],axis=1) + cat_df_test = cat_df_test.drop(['Dependents_0','Gender_Female','Education_Graduate', + 'Self_Employed_No','Married_No','Property_Area_Rural'],axis=1) + + print('num_df_train ',num_df_train.shape) + print('cat_df_train ',cat_df_train.shape) + print('num_df_test ',num_df_test.shape) + print('cat_df_test ',cat_df_test.shape) + X_train = pd.concat([num_df_train,cat_df_train],axis=1) + X_test = pd.concat([num_df_test,cat_df_test],axis=1) + + print('X_train ',X_train.shape) + print('X_test ',X_test.shape) + return X_train, X_test, y_train, y_test + + + + + + + + diff --git a/q02_data_cleaning_all_2/tests/__pycache__/__init__.cpython-36.pyc b/q02_data_cleaning_all_2/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fb238f97b1d00d4c694ed81f118e46ae768e254b GIT binary patch literal 187 zcmYL@F$w}P5Jj_KA;Q+4!N!qnD`I77V__o~MaEyNG+@%h#7 z+IF_P&rhP}J?fXHmTiS6RYn}dqS-%19_PP4J@j!PU}aTKsyHt@3CEZ(oRlWe(Gd7( z9T%rDlg-5JV!)K+nRJ2cN}^Fkq4uPL3l^34D4`G+21FNJL0qQCYq}nyxp~@*54a+} D$i_37 literal 0 HcmV?d00001 diff --git a/q02_data_cleaning_all_2/tests/__pycache__/q02_test_data_cleaning_2.cpython-36.pyc b/q02_data_cleaning_all_2/tests/__pycache__/q02_test_data_cleaning_2.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5f256b4a345447895a61c21f21dd0ff2a534844c GIT binary patch literal 4762 zcmd5=OS9896!t5L^SbW`7fNwyfu=(f68fMNIxxJ3nNHd%?Z9}LF(%RtP8~Z)4ka17 z3Y-3euDb8P=~~;a@)x@5IdYQg+~%e?fd%pS=tP!3OP|g|(&b_?clVdw$A1(ReN zOM`v`ZvGbtq7cuL*cqv(eY2glvr^Caxpv;p zs|rnfd+b(7G+%q%g1SZ)n2pL?G1a=-l8eGPB-W#-5MB=jY;h~ z$?qwx?SW$N&~;K6>AQ4eqMrbL+-C2dLW*SNwL(^?KG5xxM17!?R);VurCw5n`6K1g zEtk`w1~pKzO5DhG8a{OcFK9Y7s47lXVVkfU`5t8sqwVm8>qFH_lScbp-*;J)cW9%3 z7T>A(p&K|IMv2#myfAROfdr@c1`&6v_U892>`)f< zoSTfg&QI*A8#J)f;~#eS2He~SLFMGw8c~V%TCsJU94HNvB55d7BtuLn(?~m%8ImUj zD9xA}J4;r{8vM_Zb+Q3vo@|mWC<|np>_Ay0yW|9vD`XGIJ1I7iwA<4>HEV?{W^b-Fe=1eWCj_C~3mr)ZZ5dPR*YRTZLx- zysSJ6+qA;nrpr2Rv`?VQFm*)da%>x3-d3Ya` zrB|5R_}jzKmi!J74q*BAh|4W>g}cmc(MC>Gp zBN+VnI1D22M}U!}@Y=EzBG^01Vec@9A`OAmqgzScazC9^bY(w zVT|a3%tA5882{g$W8Cr~2A6Z^7;B2aNv^<7j-w>xX~@(~$kmfPVbr~c5LJgap;`aR z56O_&2)me^NeJ2EAXU(D`j&abiW@<$zziV_A9Ae7O8<4_Qfl#FCvju*{S4W`6^OD# zpiAH^%gi=1Gl0*(F*EEOporXrnCdb?EHR?$mw-2>X5j#q1X_}t;X~-a5Eq1Ri5pXf zZ|K<(%$%PW-bVuhN4=Whhl)=mmGza6UUQh6{aF9vh z%q9jCcN}C|8Zi>#B~>5(j!uMY#{Q+L@WP+Dun?OYU0}s|8D3-<2Sy==y$8BT$(N6? zl+rv)kuTy}3X}H@z#2Qz^+kW-1sq5& ztw%9;;lPpvs+U%U={Nx_f*nWX9H$+Uu8(@bad1NyKVj?GbKEGgQz%ZO_yEO+C@!G* z1O=u_h5?6tf#M2^gGIE|a4W*HAU5FUxN0<2GYwZtUTISwU$Rx{l%0;({4%`@vm1C3 z8V|$qi`3Ju=M%XRwQs?mvFAo%+xMQ9=WHd*Gq;lE7%2s)_RZrXRh>g86C)g4{)>zk z;L$`RH)*yB#|p&3V~DIgrNG@R92mfv2WL lK1ESQfn3faS(w-2+585aTj2<4s)g~T Date: Mon, 17 Dec 2018 17:28:42 +0000 Subject: [PATCH 3/3] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 0 -> 181 bytes .../__pycache__/build.cpython-36.pyc | Bin 0 -> 1380 bytes q03_logistic_regression/build.py | 28 ++++++++++++++++++ .../tests/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 187 bytes ...est_q03_logistic_regression.cpython-36.pyc | Bin 0 -> 2301 bytes 5 files changed, 28 insertions(+) create mode 100644 q03_logistic_regression/__pycache__/__init__.cpython-36.pyc create mode 100644 q03_logistic_regression/__pycache__/build.cpython-36.pyc create mode 100644 q03_logistic_regression/tests/__pycache__/__init__.cpython-36.pyc create mode 100644 q03_logistic_regression/tests/__pycache__/test_q03_logistic_regression.cpython-36.pyc diff --git a/q03_logistic_regression/__pycache__/__init__.cpython-36.pyc b/q03_logistic_regression/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e6ea1744e2158113bf53a91d2ccfd19af11a4989 GIT binary patch literal 181 zcmXr!<>hiK7mr~8g2x~N1{i@12OutH0TL+;!3>&=ek&P@K*9*(SCW24er~FMabkL6 zQ9)u!W{#1uk$!l7QFd`bVsff}a(+sxeolURW^qYoa(q#0dQoa|ab|vAd_hruR%&vI nexZSJJQjKV`1s7c%#!$cy@JYH95%W6DWy57b|AZpftUdRnCLOh literal 0 HcmV?d00001 diff --git a/q03_logistic_regression/__pycache__/build.cpython-36.pyc b/q03_logistic_regression/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b5e829283b94495173e40d1d360f5167415aa367 GIT binary patch literal 1380 zcmbtUJC7ST5GJ{A>15fyX96Sv(p@9jy4DDCIJ+=lxX2YThyxZh$x~J)muqrmSi!1N z@=wyFN#UPEyK{AaAytN(Q(!x1AV7A(+2J>{A2|>5WHcJQd3Sj6HbLk;`rt`H{~m_> z4TL}fD?~ATi6T0p5e`_SVx7>W*JG9HjAp%_s9YDc==D?$^pFmFJySb+L`N7&ytpOu z4W?r`UfdRi7;FgWg&g~Ed7tQO3QbIz2sfZTmz=9OzJ{)3!b>0D)MKyPzXUoOL>)U37DYrw{4 z*{Vv~(n@V!F$K^_u$GlvNmf_&JotPBl(V0|4Zu_xR+o*HqT+4fT-N=m8?jG&*vaDRXhkYt6{u^=K6@jO~5UA({xB9aZpsEsygop$LW?$9EE z5};p6mt2xBP_P1?eg^-Xf861J^RyYPl66^Fr6U^x%-JIE@CL8*w&R@*38vg;JvkT>ASo|WKH)jkD9y4Gi_EdWXYNZrt(3%wvpZj_^G zKe3)D>(f9$<&+yCq1b;n6!giq zqkzXOByXoL@12x4*r(5zl@b$(clQSCF0Aan1c7jl2Y3gk_y`{n7)c7V0lfAbupS@z zv}?vVPZ;MGld(-Kl)!xpB=V$mPfu&|GXHI2v5JYLy-@UjO%90qX|L`Zqx6(5MN0rU9-Nas????O|$;G094 O{&`6#VUG9kLHrk@K$I{5 literal 0 HcmV?d00001 diff --git a/q03_logistic_regression/build.py b/q03_logistic_regression/build.py index cdbd506..690a99d 100644 --- a/q03_logistic_regression/build.py +++ b/q03_logistic_regression/build.py @@ -1,3 +1,4 @@ +# %load q03_logistic_regression/build.py # Default Imports import pandas as pd from sklearn.preprocessing import StandardScaler @@ -15,4 +16,31 @@ # Write your solution code here: +def logistic_regression(X_train,X_test,y_train,y_test): + import numpy as np + scaled_cols = ['ApplicantIncome','CoapplicantIncome','LoanAmount'] + np.random.seed(9) + scaler = StandardScaler() + scaler.fit(X_train.loc[:,scaled_cols]) + scaler.transform(X_train.loc[:,scaled_cols]) + + scaler.fit(X_train.loc[:,scaled_cols]) + scaler.fit(X_test.loc[:,scaled_cols]) + +# for col in scaled_cols: +# X_train[col] = scaled_train[col] +# X_test[col] = scaled_test[col] + lr = LogisticRegression() + lr.fit(X_train,y_train) + y_pred = lr.predict(X_test) + cm = confusion_matrix(y_test,y_pred) + return cm + + + + + + + + diff --git a/q03_logistic_regression/tests/__pycache__/__init__.cpython-36.pyc b/q03_logistic_regression/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e997bc11ae422ebd80cdb660cd0ca2ceeece9bea GIT binary patch literal 187 zcmXr!<>hiK7mr~8g2x~N1{i@12OutH0TL+;!3>&=ek&P@K*9*(SB8E@er~FMabkL6 zQ9)u!W{#1uk$!l7QFd`bVsff}a(+sxeolURW^qYoa(q#0dQoa|ab|vAd_hruR%&vI texZSJJQjKVlGNgoV*U8|%)HE!_;|g7%3B;Zx%nxjIjMFa7Zd|A0|4V`G&KMK literal 0 HcmV?d00001 diff --git a/q03_logistic_regression/tests/__pycache__/test_q03_logistic_regression.cpython-36.pyc b/q03_logistic_regression/tests/__pycache__/test_q03_logistic_regression.cpython-36.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ddd1eba2a1f074ffcdaddd5912e564750ce0f27f GIT binary patch literal 2301 zcmbtVQE%He5EdobRvg<&+ca5*VbcQSK|o-)&QptSXpv<_fFLg$u!0DtvLfTkqa=r< zvf9X=+&{CwvDf_rz3wT0VNbi0630#xbloKIcsf!?-gh65yX|)K`(HPX|EycqU)J0M z-_~W zY4>D1>Cg_b1R1XIr75ASVs&_rH~I3^2E8d(OIscL<2t=hAJ8@Wkgn4W;fXczP^^oM zseA0stgUM+{p_X1TfF_=;%(th9lFWM4_45*fHCcvWAefVM__*-vq7v)9Kpaq39aKS1#@R0%t(+699HLguV1mAMJ*>jQ0$Hqe~gyF{L{i7h5>(w*SLfg!f^W8pF37k4&E4 z0ebi2ju!HQ4$HiJ3Cet4s;uA%oaMkdx^Q6D2i3jSqCqh4y*or(L zpiIW%jKH~0jB0_ez*ZgT)CvmBLnZEkR(ySDD3?z42286UAppsfPln{m&kPZy7*?bb zkuN|2h5}cOJ#;uRF0yuxllIZ%@EQs@e!dxxgnyDLUkQ_|w8F)Ywf{QJlhL@Fa;6j; zzuxi3Sq|hCmlL5V_}e!|3Gk48{fEcm||GMpayz z9|I;Ke-t_|oP@o*1CH&F!BJ9o3%qD7Qx=(g^Iu^oJsky&!VANcB_a%qW*8Ay7>asAw!`9`S1M)=O*fIjxTvP(l~>h$}n`g_ozX z!H5+GL-*jm7&DV4GJey&r8r#`ukPuie#MKcD=K7CcHiW&Jj5Gssk{)8@^F2rY*dg}1sT)EtI#MG wr?d_Vz(pJ5D+4HqAM&b%`L?VS-m@yL-y+N!lLx6Gt+}@ex<}T?I_cQ|0MQngTL1t6 literal 0 HcmV?d00001