From ba11f96912304e82b0fe88706bcac38217f0ebdb Mon Sep 17 00:00:00 2001 From: nikhilakki Date: Sun, 9 Jul 2017 12:35:50 +0000 Subject: [PATCH] Done --- build.py | 29 ++++++++++++++++------- build.pyc | Bin 0 -> 2237 bytes tests/__init__.pyc | Bin 0 -> 168 bytes tests/test_get_categorical_variables.pyc | Bin 0 -> 2737 bytes 4 files changed, 20 insertions(+), 9 deletions(-) create mode 100644 build.pyc create mode 100644 tests/__init__.pyc create mode 100644 tests/test_get_categorical_variables.pyc diff --git a/build.py b/build.py index 35cdd2a..ea928f8 100644 --- a/build.py +++ b/build.py @@ -1,26 +1,37 @@ -def get_categorical_variables(df): - return [] +import pandas as pd +df = pd.read_csv('data/conversion_data.csv') +def get_categorical_variables(df): + df['converted'] = df['converted'].astype('category') + df['new_user'] = df['new_user'].astype('category') + return df.select_dtypes(include=['category','object']).columns def get_numerical_variables(df): - return [] - + df['converted'] = df['converted'].astype('category') + df['new_user'] = df['new_user'].astype('category') + return df.select_dtypes(exclude=['category','object']).columns def get_numerical_variables_percentile(df): - pass + df['converted'] = df['converted'].astype('category') + df['new_user'] = df['new_user'].astype('category') + var = df.select_dtypes(exclude=['category','object']) + return var.describe() def get_categorical_variables_modes(df): - pass + df['converted'] = df['converted'].astype('category') + df['new_user'] = df['new_user'].astype('category') + var = df.select_dtypes(include=['category','object']) + return var.mode() def get_missing_values_count(df): - pass + return df.isnull() def plot_histogram_with_numerical_values(df): - pass + return df.plot.hist() def plot_facet_box(df): - pass + return df.plot.box() diff --git a/build.pyc b/build.pyc new file mode 100644 index 0000000000000000000000000000000000000000..84ddb43ec505d17abec12ff6c78511c5e254aa10 GIT binary patch literal 2237 zcmc&#OK;RL5O(&_eLw+$P+O@I2sq@j-9Jzvq#oc@A@_jj0V^9%cfIRPqS)ECQaP1> z%nyM1oGnXBdqG`DVrRzBZ$8hAo8LG4yRS!|Q?Yy+{C~&Aec?*;7YQrGaU>`b(}vIu zaT$r@rqE6CjoVv7w}Q|Xx*dcKp*Moi5xNtEuF%~e^n~sOp^s&c;y!O-e(-bXwy|5{ zlVO@?3o4z-GX;Gwb&E9OPLvjx11|18R~G@>&Xj)vQ?2jg*A&;An*z<#2v~VA10C}e z5wSf-@dmGT=zCn(TYJ*J3oY?9&dc+lWOS-3N2Tv@kI7P7Y4VtvkEWFRxXEJB6X(wh z@|&zXvfQOK8eEu|=C+z=E`}{0MC+57YY{5iBqb(B z(~xvBILXVwilsrxI0vB0ksppKWA$Ef?ss^xF?qGL!la2+i=;Hk$dUt(4(LU+#qU4h zS7I{>yCv)nY|vStQ36dMP`1$zToN<~nk0^5T_kPs+8`;b=2Tv%2>x)BA|U_ef*)DA z2N(PriHi_em*UD7Z*V0MCAX0j98;4^OEaPv-~w45zQ{+tF4A7{@^_G?3Mx~|ys`9% zM>(8b?PA-tll>OeGX?WR=EW*1AGu%!{>zj zn*|u}aUg}weGn$b`Sly}X1S%pcKNtW=IYe=$+e^a(_ZqpzcNZbydq)0N&mlaqq>I<)=L@T~-Ll%)pfD)r67L-p=Jw*i%mB^f{ iC<)U2-d{)^`y3IKrMGY$2LKPF$BkZ_-wwa6Uh5})FX=)6 literal 0 HcmV?d00001 diff --git a/tests/__init__.pyc b/tests/__init__.pyc new file mode 100644 index 0000000000000000000000000000000000000000..4240eb61beced9b2893cd2176b3fa4e37852f018 GIT binary patch literal 168 zcmZ9FK?*`K3`8rs5W#!=P0a;FJb@xE#8oM6}YUnSa)+ z<2ziF`)OvmH_O71ojZ3^bLb524|1{&dcGr6Dm@Lc6oL!4B4bPli8BJ`=x^M7;`+oU k#MQT`=yTL4sGuk+5CT=w5H{mWm$tgSbAAlCo4&>DzG12)E)pUeYp^G+8^?}3<07Q8f)C*z z`2aZQx}>3P5DV0#o$I;d>+zg(?wxV#$N4jFzsDaEIrz13eTL?SFe&~6$welC3&NbcG`r*kq+0*PFJF>eg{t`oQKS?ZKAmn1{07C zW#?QG>KfGg`NvA(A<GzaT!-%dL;G~u8a3Fm;DwfVlqVMX&4?6nJN-drRK(2j-f3< ziraYWOo|hLUc`Mz2)~7xiNJ)~WBy-5(Z5)|-jjcsbh@)&X_Fvf6xFxd9&w&}+CjqkJL4n#k&@q3%fY6 HFND7UnMjpT literal 0 HcmV?d00001