From 8740b1bb3a93b6d24b358bf196ffd3b0a89e9332 Mon Sep 17 00:00:00 2001 From: dharmil25 Date: Fri, 24 Aug 2018 09:17:54 +0000 Subject: [PATCH 1/5] Done --- __pycache__/__init__.cpython-36.pyc | Bin 148 -> 142 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 162 -> 156 bytes .../__pycache__/build.cpython-36.pyc | Bin 397 -> 530 bytes q01_load_data/build.py | 11 ++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 168 -> 162 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 1529 -> 1529 bytes 6 files changed, 10 insertions(+), 1 deletion(-) diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index 91557cd05bf4f07dc1526cbb9ff684bfca7460c3..9224d25b2e49caafa01071b270c3dc52ae813ba4 100644 GIT binary patch delta 51 zcmbQj*vH6W%*)GVcD6oxB8R!WwSGo^ZmNDtMq*KJW{#1met3RSc5y*sa;koEeoE@Z G6axT?-Vmn% delta 57 zcmeBUoWjUq%*)I5)-ob$B8R!Eqkd>{YEiL%Vp2wCaYkx(acNRfVs2tyW@4UxUTS%K MT4qja@x(X-01EgM+yDRo diff --git a/q01_load_data/__pycache__/__init__.cpython-36.pyc b/q01_load_data/__pycache__/__init__.cpython-36.pyc index 5e9e2e2740ce75441ea56a2372f1c0fc7b50e02f..a05783c63954ea572e682a922438c1cd219ffe9f 100644 GIT binary patch delta 51 zcmZ3)IERtLn3tE!>}-AXL=JO#PyLMi+*JLPjKrec%p45)BOnk}0BF+m!U>@i`=Cg2zX@+F^x zg9%62W^;~#qiM(-puo;Erwkl-Fb*7Cu_Ro*>?{mWK>|K3ltg8odbyr8Q}ejj$Xb1^ zmzRm~yu~asbTQ8DeJ09E=f0ckYF0Nk3A||KwD25nv$#k`#ddltx_zc zsmp3`lwNCdXIq)8G}j!}>hmP&(xL4UnAn0CBIrQ~W|Mr<^aky)IPnq6F)RFs&Tn3tKDr=OQv9-o$(lUh7EoY7o{ z4P+z`GZcYXn(VjO3KH{D5{qv!6{Jkw&ZuPw5=NK|VX*?mZgJS;=BJeAq}qX8Rt!?c K!N|eL!wdix#w%0+ diff --git a/q01_load_data/build.py b/q01_load_data/build.py index 1a26cc1..728458f 100644 --- a/q01_load_data/build.py +++ b/q01_load_data/build.py @@ -1,10 +1,19 @@ +# %load q01_load_data/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split def q01_load_data(path): - "write your solution here" + 'write your solution here' # use .read_csv function to read the # data and header=0 to skip the first row + df = pd.read_csv(path, header=0) + new_header = df.iloc[0] # grab the first row for the header + new_header[0] = 'country name' + df = df[1:] # take the data less the header row + df.columns = new_header # set the header row as the df header + return df + + diff --git a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc index 46496ca72cf628223c8e5f0e036e3f379bb90b43..7ae5cf7340e132a36ba701d3400c6b03c3496b5c 100644 GIT binary patch delta 51 zcmZ3%xQLO%n3tE!@@#$dL=JO#fBlU7+*JLPjKrec%p4`9DM1iC26HOIU6s^GRk}FXXNLm>ZfER7UgE<7@6va z=NDxc7bGU9>L=%?q)rxQ@?jL%oWP{a$RonQz);KrBp4XEHuo|sFfvL^UdJ+npC2U7 d1|&EbIaoMYCWo?4m-q-GbFCKV;- zCgx=(=IQ69mdB@M=A;%+7G&~a Date: Fri, 24 Aug 2018 09:36:23 +0000 Subject: [PATCH 2/5] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 167 -> 161 bytes .../__pycache__/build.cpython-36.pyc | Bin 509 -> 641 bytes q02_rename_columns/build.py | 9 +++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 173 -> 167 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 1628 -> 1626 bytes 5 files changed, 7 insertions(+), 2 deletions(-) diff --git a/q02_rename_columns/__pycache__/__init__.cpython-36.pyc b/q02_rename_columns/__pycache__/__init__.cpython-36.pyc index 687491c04ee351a2a8984006b2759809a18bb255..b9a7413b697e07c1ece4734b1bf6e240147e22fb 100644 GIT binary patch delta 51 zcmZ3^xR8;}-AXL=JO#KmCmS+*JLPjKrec%p4{&_Z+H^~w<6+U9`C(*Gt7K7o?Gpa?{`-3%d3xddo}J7LMFEIp@o9fs1wt7dfc7^R(1XiO3Fjl< cx<9M_foDC#j)cN81?ejWIfQ|! zh-2~{Mj6IilYcUX8gl?ez=k3b>_D+w95%W6DWy57c8ow?F-RE)BL^c7BM%b*7?e3` diff --git a/q02_rename_columns/build.py b/q02_rename_columns/build.py index 20dd8e9..dab10c7 100644 --- a/q02_rename_columns/build.py +++ b/q02_rename_columns/build.py @@ -1,9 +1,14 @@ +# %load q02_rename_columns/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from greyatomlib.olympics_project.q01_load_data.build import q01_load_data def q02_rename_columns(path): - "write your solution here" + 'write your solution here' df = q01_load_data(path) - \ No newline at end of file + df.columns = ['country name', '# Summer', 'Gold', 'Silver', 'Bronze', 'Total', '# Winter', 'Gold', 'Silver', 'Bronze','Total', '# Games', 'Gold', 'Silver', 'Bronze', 'Combined total'] + return df + + + diff --git a/q02_rename_columns/tests/__pycache__/__init__.cpython-36.pyc b/q02_rename_columns/tests/__pycache__/__init__.cpython-36.pyc index 198a8989427b98b820ac8af30a735121ced2b430..16de172f4d6c9a043a361814ace9ca7917a090b2 100644 GIT binary patch delta 51 zcmZ3>xSWy0n3tE!>}-AXL=JQL5dDn&+*JLPjKrec%p4}-9s=0;9lMh?F8)RMH)oSe;4jNOd#0s0yFxvBao8Hq)?nK?$L z`r-LS*~JBk$*KCu`6;QJPcbnuGDdAa%UsLICc?nLP$V%qfVGb?YVv(nHDNKJz%912 V#GKO9;v#X7EIUwEe6l{9E&$S4BSioJ delta 114 zcmcb`bBBl1n3tF9L_|cC;zmwhMi#F0)RN6|jNOc?VfvxPsYS*5iAfom#TlvD#idC_ ziMfe+nTdJ&d8y^`X_+~x#hXtsF)=dU+I*V1mXS@Afq|h&ahuABqj^8c>(}0z9cvR From 635c660bba8f915b3270c6684e773abc69961771 Mon Sep 17 00:00:00 2001 From: dharmil25 Date: Fri, 24 Aug 2018 11:53:41 +0000 Subject: [PATCH 3/5] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 166 -> 160 bytes .../__pycache__/build.cpython-36.pyc | Bin 522 -> 791 bytes q03_split_country/build.py | 21 ++++++++++++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 172 -> 166 bytes .../tests/__pycache__/test.cpython-36.pyc | Bin 1424 -> 1422 bytes 5 files changed, 19 insertions(+), 2 deletions(-) diff --git a/q03_split_country/__pycache__/__init__.cpython-36.pyc b/q03_split_country/__pycache__/__init__.cpython-36.pyc index e71d6ad8447b136dd4ced8957fb372b04928ae9b..1296dd730678601cb75d3105a83c28716d80f40d 100644 GIT binary patch delta 51 zcmZ3+xPXzvn3tE!>}-AXL=JO#U;T{y+*JLPjKrec%p4CToCU7 delta 57 zcmZ3$xQvm*n3tDJ-6|q#B8RzZuzqN9YEiL%Vp2wCaYkx(acNRfVs2tyW@4UxUTS%K MT4qja@x(YM0PwmKUjP6A diff --git a/q03_split_country/__pycache__/build.cpython-36.pyc b/q03_split_country/__pycache__/build.cpython-36.pyc index 5935601a743a778838cf0355c720e3720a4bcae6..faf8a3b1eb920c03f27f100bc48bab38a0d03059 100644 GIT binary patch delta 527 zcmYjO!HN_y5KX0%OiwclvY@VbnWKGba1lI+2;TPUg3um@wv%_PV6H~0sBOYjFgdfk(iQNcsKq~3d}N0CqLtH@4|jJ}cI=MaS2m}-y~aEG4}ZXqwlx%O4(a$2%#)3|ch45q7Um8UjAOGx(4+rXXa z8Xs8KIA6}4@~dW$YEv?4wF&&t1QxUMG%!>7b)fPhKo#I^fI5H-paNWcBld0#J}cI` zSA|?xwr{$}Pm0&tzIO(5i&{%n=x*Dargkf1Zyv(a7x53=2?C)hq;Ll-;sP>y499r4 z_fgB|LBtI!7pRdXAI9En1076xvxD+9S`P95!9C?#gvk^lA(wVDD*2pKeRZts8~NSDI>EuBQ?9YG^r>tH!&|W zF;71)wLCs8GbgopG8>bN7CXoWkW~y!MI1mRF!C@10J9G>ssI20 diff --git a/q03_split_country/build.py b/q03_split_country/build.py index 6c075fb..043c09c 100644 --- a/q03_split_country/build.py +++ b/q03_split_country/build.py @@ -1,3 +1,4 @@ +# %load q03_split_country/build.py import pandas as pd import numpy as np from sklearn.model_selection import train_test_split @@ -5,6 +6,22 @@ def q03_summer_gold_medals(path): - "write your solution here" + 'write your solution here' df = q02_rename_columns(path) - \ No newline at end of file + a = df['country name'] + b = a.str.split('(',expand=True) + c = b[0] + d = b[1] + e = d.str.split(')', expand=True) + f = list(e[0]) + df = df.set_index(c) +# df['country code'] = f + df.drop(['Totals'], axis = 0, inplace = True) + df.drop(['country name'], axis = 1, inplace = True) + df.index.name = 'country name' + return df + +# path = 'data/olympics.csv' +# q03_summer_gold_medals(path) + + diff --git a/q03_split_country/tests/__pycache__/__init__.cpython-36.pyc b/q03_split_country/tests/__pycache__/__init__.cpython-36.pyc index 6015fed2dbea86e31eda4681fd1f53f29b2ef18c..2f24b31d3cb8d779bdc13e8da46d8854276cfd82 100644 GIT binary patch delta 51 zcmZ3(xQvm*n3tE!>}-AXL=JQLVEv5z+*JLPjKrec%p4tdh9J2rb delta 97 zcmeC Date: Fri, 24 Aug 2018 12:13:02 +0000 Subject: [PATCH 4/5] Done --- .../__pycache__/build.cpython-36.pyc | Bin 791 -> 822 bytes q03_split_country/build.py | 4 ++-- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/q03_split_country/__pycache__/build.cpython-36.pyc b/q03_split_country/__pycache__/build.cpython-36.pyc index faf8a3b1eb920c03f27f100bc48bab38a0d03059..1452f6da73a7ec66ac4804e4e8146ff4b5b57195 100644 GIT binary patch delta 129 zcmbQvwvCO`n3tE!=39OA<%yg#8T%$Kj;6_WE)QYRNOO0q|>hUAwd=1lHl UJjy6FIeLmB6%3Om?pO{Z2|x+L?5{T diff --git a/q03_split_country/build.py b/q03_split_country/build.py index 043c09c..432349d 100644 --- a/q03_split_country/build.py +++ b/q03_split_country/build.py @@ -15,9 +15,9 @@ def q03_summer_gold_medals(path): e = d.str.split(')', expand=True) f = list(e[0]) df = df.set_index(c) -# df['country code'] = f + df['country code'] = f df.drop(['Totals'], axis = 0, inplace = True) - df.drop(['country name'], axis = 1, inplace = True) + df.drop(['Total'], axis = 1, inplace = True) df.index.name = 'country name' return df From 4fe21860d3cd39bf980a95a103513c1c999c033e Mon Sep 17 00:00:00 2001 From: dharmil25 Date: Fri, 24 Aug 2018 12:17:24 +0000 Subject: [PATCH 5/5] Done --- .../__pycache__/build.cpython-36.pyc | Bin 822 -> 731 bytes q03_split_country/build.py | 10 +++++----- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/q03_split_country/__pycache__/build.cpython-36.pyc b/q03_split_country/__pycache__/build.cpython-36.pyc index 1452f6da73a7ec66ac4804e4e8146ff4b5b57195..b35626d40a6e78e7c4bd5c4f1e27e0e80ddb32cc 100644 GIT binary patch delta 235 zcmdnScAJ&cn3tE!<9mJdqluh7e5?!%3?S?b#KlPy7wcFvW--^WG&9yR)-YzVq_Cwk zrm&_kr?B@jGctfh7=a=jFp(6HD%N(NGt<3V(E4EHd@6(Vm5asgiA>F@Ph;kTTeLh6Ra$3 z?feyX>o4#RSXlW~EaWlshIuo*H~uV~y}`g8f83nBE}gqoNeJPH14MJbeAt;atoc^Le5%-3R=`kjtM$kIa5#^^X|feUuOj!@#iSOlsLu4 z5edECh5f^Kz_*_eUVBM7pXvH4NJ^DP;<(gt(S$T&@nzOTb~dYuI7uV^a|mT^Vb55N zt_^RhBGZNyS<}xU*p`M>u|79cO$@{a&I}|5l!4U1@|DQJc7rONYITBC6 diff --git a/q03_split_country/build.py b/q03_split_country/build.py index 432349d..63bdc4b 100644 --- a/q03_split_country/build.py +++ b/q03_split_country/build.py @@ -11,13 +11,13 @@ def q03_summer_gold_medals(path): a = df['country name'] b = a.str.split('(',expand=True) c = b[0] - d = b[1] - e = d.str.split(')', expand=True) - f = list(e[0]) +# d = b[1] +# e = d.str.split(')', expand=True) +# f = list(e[0]) df = df.set_index(c) - df['country code'] = f +# df['country code'] = f df.drop(['Totals'], axis = 0, inplace = True) - df.drop(['Total'], axis = 1, inplace = True) + df.drop(['country name'], axis = 1, inplace = True) df.index.name = 'country name' return df