Prefer nunique over len after unique

samedii · Jim-Holmstroem · samedii · commit d775f84e23a9 · 2020-06-29T20:57:52.000+02:00
Co-authored-by: Jim Holmström &lt;jim.holmstroem@gmail.com&gt;
diff --git a/datastream/tools/split_dataframes.py b/datastream/tools/split_dataframes.py
@@ -42,7 +42,7 @@ def split_dataframes(
             for split_name in proportions.keys()
         }
 
-    if len(dataframe[key_column].unique()) != len(dataframe):
+    if dataframe[key_column].nunique() != len(dataframe):
         raise ValueError(f'key_column {key_column} contains duplicate values')
 
     if frozen:

Original file line number	Diff line number	Diff line change
`@@ -42,7 +42,7 @@ def split_dataframes(`
`42`	`42`	`for split_name in proportions.keys()`
`43`	`43`	`}`
`44`	`44`
`45`		`- if len(dataframe[key_column].unique()) != len(dataframe):`
	`45`	`+ if dataframe[key_column].nunique() != len(dataframe):`
`46`	`46`	`raise ValueError(f'key_column {key_column} contains duplicate values')`
`47`	`47`
`48`	`48`	`if frozen:`