From 660860540b82c052c35a7f19b11b06ff9212e5d5 Mon Sep 17 00:00:00 2001 From: Rohan2015 Date: Tue, 27 Jun 2017 02:33:18 +0000 Subject: [PATCH] Done --- build.py | 50 +++++++++++++++++++---- build.pyc | Bin 0 -> 2773 bytes tests/__init__.pyc | Bin 0 -> 167 bytes tests/test_get_categorical_variables.pyc | Bin 0 -> 2730 bytes 4 files changed, 42 insertions(+), 8 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..df70ec2 100644 --- a/build.py +++ b/build.py @@ -1,26 +1,60 @@ +import pandas as pd + def get_categorical_variables(df): - return [] + #returning for now based on visual analysis + return df[['country','new_user','source','converted']] def get_numerical_variables(df): - return [] + return pd.DataFrame._get_numeric_data(df) def get_numerical_variables_percentile(df): - pass + df = pd.DataFrame._get_numeric_data(df) + df = df.groupby('converted').describe() + return df def get_categorical_variables_modes(df): - pass - + dfn = df[['country','new_user','source','converted']] + df_mode = dfn.mode() + return df_mode def get_missing_values_count(df): - pass + ndf = df.isnull().sum() + ndf = pd.DataFrame(ndf) + ndf2 = ndf.reset_index() + ndf2 = ndf2.rename(columns={'index':'var_name',0:'missing_value_count'}) + return ndf2 def plot_histogram_with_numerical_values(df): - pass + age = df['age'].tolist() + new_user = df['new_user'].tolist() + total_pages_visited = df['total_pages_visited'].tolist() + converted = df['converted'].tolist() + + fig, axes = plt.subplots(2, 2) + + axes[0,0].hist(age) + axes[0,0].set_title('age') + + axes[0,1].hist(new_user) + axes[0,1].set_title('new_user') + + axes[1,0].hist(total_pages_visited) + axes[1,0].set_title('total_pages_visited') + + axes[1,1].hist(converted) + axes[1,1].set_title('converted') + + plt.tight_layout() + plt.show() def plot_facet_box(df): - pass + list_of_columns = df.columns.values + for col in list_of_columns: + plt.boxplot(df[col]) + plt.title(col) + plt.show() diff --git a/build.pyc b/build.pyc new file mode 100644 index 0000000000000000000000000000000000000000..61289ebc4dcecf90e1495e5c353b30e4494e1f78 GIT binary patch literal 2773 zcmcImO>ZMb5bc>bj-7Qjn_WH<@hOB@OUP?jiEu#(X;&aFMmssIK%mjs-L^YBo-xxs z`H+%R_-FhP{sR|o@LshYXG3z^*zR_9O}VP8>h)`{{k^sM*Pkzb9;wAE#`kv^?k7wd zpGf6O{Sql1t3M#bO0S8qrgTGuhSKXItSj9Vp{ewS2pdYbL}<~^LAMQ`_FudPqX;6$ zI>s{$_ZFrziHAstp&M$_PsXr}erk|A4ta$pxmtXZ?menga&qk&{Dz)hwo%P0L)eHWd zEsI{2dDGLG&z$l7VQq8$WPa-R;A>)hI>OUQS=mvRr$5{- z1ihLfn-Nls{-5IKcz7+vb7}J-8XPg>!-l$0Dku-Stj!={_R{u*%}v<)gkb~(ld7!e z!vF$p+^DicbLaVgg6Oy8pUw@iS9qJ74y+uvtfGg}+o2rH2V=N(&JQ~LKPtKMj`(Zyxt0V3G5!i zWKoKDqRtJacmV^HA|#C?z|_p3fQ&^|0zRZFhhUgUS@X=hkgvA|kiZh>t@nc%+Dz zXBh4uOaYa93k(8}z*4N1YoRA_@^Xz9;W^lOVc$?*NDSS;=OR|W#_D`soj27P?t&KV zmQ9VQXhVV4NtZ>j87yM9T@?3%#Y)i$7HgLlTft(bxF0M4mxYh*U=bADA9jX1P-=># z70ww+cpx3lCPt2$V8fRlBsYi7rAO9TTqtt-06stnLs_0fA*`^Z?)K$15M65`Rv7Lx{c4FKe;rUa<;{H=^y`13IOOLIeE-yT}dvIVKS;&2e zNktFBJKl|VqMg^q=8Aflm*D+J2*59}3*G_Coa~cvp8xiQm`B}7uf6O_Ei=`p7srq!NB gdZU+53;w^s=s`S%kgPOlvn9IgG3RP*+Dc*mz(?(%qaNWzozI)qdJ7jScOHB|2ow=8dV8Z{1LYSM lPLyr&f;M{bi~@oz49=yT#JPHS%UnmBp5pU?yYZUU<_mp9Coup3 literal 0 HcmV?d00001 diff --git a/tests/test_get_categorical_variables.pyc b/tests/test_get_categorical_variables.pyc new file mode 100644 index 0000000000000000000000000000000000000000..49d806fd97a67200bb726c0d4e0bd43693e12f0f GIT binary patch literal 2730 zcmc&$$!^p@5G{L_WLQMl7qJM0#9WdAByI>0K_D(UI7o=OSdHD2IC$)lyB!oMIl&+E z0q|ZqOok+bIG|*bE_b!d?SAi7b-VTB{F#?4Yo8L?|Fv*^h31AZDgFb=MaF>)0}1Gd zl7}*EN!pTOTWm|VI%3=M4G~>+7sPheU6d37fs6u4JMvxRo5-hOk5jDoyO=)viC;fJ z&o9D!u+Fa0g_NVZ9?KmhwEmiE75wtgC`TtLuS}k(Oe0G3CM=B zvj=u|;kU$xz!~g?vMaKM$=k9U$`@rM*dOW~9qJw(T9_G11(cDawHeNC!rz!j0hWOk zj{E{HNm&=Z+EJ1V`!%ketvm&AWnCrK_cVq)dz<##@H|m}uCqLiI8Q{}{tS$9eD*_C z+rEx5*x7ufVV*;kb$wh!jT@mi*eu6(5S5#zc>4Isv%$x*`r;-gu@E=41Dl%VQCTe? zD7{=k)Md);tRHx!g;N{PMY}TD@pthm#?Fr-PInGQf~DX>a9RJ3YWp4m|3zC>jXck) zb{#%(6!q91O528Jl4uZd8CPF=P7#D5#$8qxQBPmt>$=)eZd{p;u;<~&?34-mo*Yyftg8ujXOQsA7V9A+K)Y*8h9*{ zljZyd-bl{JnL`e5;JD0d>??XY944Ew|3bFLogUfz5}1;G9IpF+vaF@8=U^NcsMa{v znvN++ox_cIJVZ-0S7}%o5f9pfom6`#c(6tM_~35oxVLwM-eRxY>-0K(x{9SPGEWvF z42T}=6H}zdX?b9S6d7S})6mMAH0C!HM|r|(^)yQJJ*Nj#m-oEU;RTnXaF>E}VHaoh Gh42?s6N?=H literal 0 HcmV?d00001