Tab2df update and test fix (#78)

* wording update

* updated ksdistrib to correspond with scipy

* sanity check for scipy version within select.q added

* updated tab2df to account for list of char being passed

* updated percentage_recurring_all_val to account for pandas update

Author: Dianeod

fresh/tests/test.p

@@ -52,6 +52,7 @@ p)def< percentage_recurring_all_val(x):
         x = pd.Series(x)
         if len(x) == 0:
                 return np.nan
+        x = x.copy()
         value_counts = x.value_counts()
         return value_counts[value_counts > 1].sum() / len(x)
 

util/tests/utiltst.t

@@ -24,11 +24,13 @@ df :.ml.tab2df tt:([]fcol:12?1.;jcol:12?100;scol:12?`aaa`bbb`ccc)
 dfj:.ml.tab2df tj:select by jcol from tt
 dfs:.ml.tab2df ts:select by scol from tt
 dfsj:.ml.tab2df tx:select by scol,jcol from tt
+dfc:.ml.tab2df ([]s:`a`b`c;j:1 2 3;c:"ABC")
 (dfsx:.ml.tab2df tx)[`:index][:;`:names;(`scol;::)]
 (dfxj:.ml.tab2df tx)[`:index][:;`:names;(::;`jcol)]
 (dfxx:.ml.tab2df tx)[`:index][:;`:names;(::;::)]
 tt2:([]date:2005.07.14 2005.07.15;timesp:("N"$"12:10:30.000500000";"N"$"12:13:30.000200007");time:20:30:00.001 19:23:20.201;str:enlist each ("h";"i");ind:1.3 2.5;bool:10b)
 112 112 112 10 -9 -1h~type each first (.ml.tab2df tt2)[`:values]`
+(dfc[`:c.values]`)~enlist each "ABC"
 
 .ml.shape[1 2 3*/:til 10] ~ np[`:shape][1 2 3*/:til 10]`
 .ml.shape[enlist 1] ~ np[`:shape][enlist 1]`

util/util.q

@@ -20,7 +20,8 @@ traintestsplit:{[x;y;sz]`xtrain`ytrain`xtest`ytest!raze(x;y)@\:/:(0,floor n*1-sz
 i.q2npdt:{.p.import[`numpy;`:array;("p"$@[4#+["d"$0];-16+type x]x)-"p"$1970.01m;"datetime64[ns]"]`.}
 / q tab to pandas dataframe
 tab2df:{
- r:.p.import[`pandas;`:DataFrame;@[flip 0!x;i.fndcols[x]"pmdznuvt";i.q2npdt]][@;cols x];
+ updx:@[flip 0!x;i.fndcols[x;"c"];enlist each];
+ r:.p.import[`pandas;`:DataFrame;@[updx;i.fndcols[x]"pmdznuvt";i.q2npdt]][@;cols x];
  $[count k:keys x;r[`:set_index]k;r]}
 / pandas dataframe to q tab
 df2tab_tz:{