Add my new, shiny module.

README.md

@@ -69,19 +69,19 @@ The metric takes 3 inputs: sources (a list of source sentence strings), predicti
 
 ```python
 from evaluate import load
-sari = load("sari")
+sari = load("hxw15/sari_metric")
 sources=["About 95 species are currently accepted."]
 predictions=["About 95 you now get in."]
 references=[["About 95 species are currently known.","About 95 species are now accepted.","95 species are now accepted."]]
-sari_score = sari.compute(sources=sources, predictions=predictions, references=references)
+results = sari.compute(sources=sources, predictions=predictions, references=references)
 ```
 ## Output values
 
 This metric outputs a dictionary with the SARI score:
 
 ```
-print(sari_score)
-{'sari': 26.953601953601954}
+print(results)
+{'sari': 26.953601953601954, 'keep': 0.22527472527472525, 'del': 0.5, 'add': 0.08333333333333333}
 ```
 
 The range of values for the SARI score is between 0 and 100 -- the higher the value, the better the performance of the model being evaluated, with a SARI of 100 being a perfect score.
@@ -98,26 +98,26 @@ Perfect match between prediction and reference:
 
 ```python
 from evaluate import load
-sari = load("sari")
+sari = load("hxw15/sari_metric")
 sources=["About 95 species are currently accepted ."]
 predictions=["About 95 species are currently accepted ."]
 references=[["About 95 species are currently accepted ."]]
-sari_score = sari.compute(sources=sources, predictions=predictions, references=references)
-print(sari_score)
-{'sari': 100.0}
+results = sari.compute(sources=sources, predictions=predictions, references=references)
+print(results)
+{'sari': 100.0, 'keep': 1.0, 'del': 1.0, 'add': 1.0}
 ```
 
 Partial match between prediction and reference:
 
 ```python
 from evaluate import load
-sari = load("sari")
+sari = load("hxw15/sari_metric")
 sources=["About 95 species are currently accepted ."]
 predictions=["About 95 you now get in ."]
 references=[["About 95 species are currently known .","About 95 species are now accepted .","95 species are now accepted ."]]
-sari_score = sari.compute(sources=sources, predictions=predictions, references=references)
-print(sari_score)
-{'sari': 26.953601953601954}
+results = sari.compute(sources=sources, predictions=predictions, references=references)
+print(results)
+{'sari': 26.953601953601954, 'keep': 0.22527472527472525, 'del': 0.5, 'add': 0.08333333333333333}
 ```
 
 ## Limitations and bias

sari_metric.py

@@ -68,6 +68,9 @@ Args:
     references: list of lists of reference sentences where each sentence should be a string.
 Returns:
     sari: sari score
+    avgkeepscore: F1_keep score
+    avgdelscore: P_del score
+    avgaddscore: F1_add score
 Examples:
     >>> sources=["About 95 species are currently accepted ."]
     >>> predictions=["About 95 you now get in ."]
@@ -75,7 +78,7 @@ Examples:
     >>> sari = evaluate.load("sari")
     >>> results = sari.compute(sources=sources, predictions=predictions, references=references)
     >>> print(results)
-    {'sari': 26.953601953601954}
+    {'sari': 26.953601953601954, 'keep': 0.22527472527472525, 'del': 0.5, 'add': 0.08333333333333333}
 """