update doc

aksnzhy · Oct 21, 2018 · 6ac5065 · 6ac5065
1 parent 81c3864
commit 6ac5065
Show file tree

Hide file tree

Showing 2 changed files with 28 additions and 0 deletions.
diff --git a/cli_api/index.rst b/cli_api/index.rst
@@ -177,6 +177,20 @@ For LR and FM, the input data format can be ``CSV`` or ``libsvm``. For FFM, the
 
      label field_1:index_1:value_1 field_2:index_2:value_2 ...
 
+xLearn can also use ``,`` as the splitor in file. For example: ::
+
+  libsvm format:
+
+     label,index_1:value_1,index_2:value_2 ... index_n:value_n
+
+  CSV format:
+
+     label,value_1,value_2 .. value_n
+
+  libffm format:
+
+     label,field_1:index_1:value_1,field_2:index_2:value_2 ...
+
 Note that, if the csv file doesn't contain the label ``y``, the user should add a 
 ``placeholder`` to the dataset by themselves (Also in test data). Otherwise, xLearn 
 will treat the first element as the label ``y``. 

diff --git a/python_api/index.rst b/python_api/index.rst
@@ -214,6 +214,20 @@ be the ``libffm`` format: ::
 
     label field_1:index_1:value_1 field_2:index_2:value_2 ...
 
+xLearn can also use ``,`` as the splitor in file. For example: ::
+
+  libsvm format:
+
+     label,index_1:value_1,index_2:value_2 ... index_n:value_n
+
+  CSV format:
+
+     label,value_1,value_2 .. value_n
+
+  libffm format:
+
+     label,field_1:index_1:value_1,field_2:index_2:value_2 ...
+
 Note that, if the csv file doesn’t contain the label ``y``, user should add a ``placeholder`` to the dataset 
 by themselves (Also in test data). Otherwise, xLearn will treat the first element as the label ``y``.