update some comments

nl2bash_m.py

@@ -11,7 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Exact Match metric."""
+"""nl2bash metric."""
 import re
 import string
 
@@ -28,50 +28,23 @@ returns a score that indicates how close the bash command generated is to the ac
 _KWARGS_DESCRIPTION = """
 Args:
     predictions: List of predicted texts.
-    references: List of reference texts.
-    regexes_to_ignore: List, defaults to None. Regex expressions of characters to
-        ignore when calculating the exact matches. Note: these regexes are removed
-        from the input data before the changes based on the options below (e.g. ignore_case,
-        ignore_punctuation, ignore_numbers) are applied.
-    ignore_case: Boolean, defaults to False. If true, turns everything
-        to lowercase so that capitalization differences are ignored.
-    ignore_punctuation: Boolean, defaults to False. If true, removes all punctuation before
-        comparing predictions and references.
-    ignore_numbers: Boolean, defaults to False. If true, removes all punctuation before
-        comparing predictions and references.
+    references: List of reference texts. 
+    cmd_weight: The weight you want to put on getting the command correct
+    opt_weight: The weight you want to put on getting the option correct  
+    arg_weight: The weight you want to put on getting the arg correct
+    ignore_case=False,
+    ignore_numbers=False,
 Returns:
-    exact_match: Dictionary containing exact_match rate. Possible values are between 0.0 and 1.0, inclusive.
+    nl2bash metric: Dictionary containing nl2bash score. Possible values are between 0.0 and 1.0, inclusive.
 Examples:
-    >>> exact_match = evaluate.load("exact_match")
-    >>> refs = ["the cat", "theater", "YELLING", "agent007"]
-    >>> preds = ["cat?", "theater", "yelling", "agent"]
+
+
+    >>> metric = evaluate.load("Josh98/nl2bash_m")
+    >>> preds = ["ls -l /home/userr", "ls -l /home/josh", "lss /home/josh some argument"]
+    >>> refs = [["ls -l /home/user"], ["ls -l --v /home/josh"], ["ls /home/josh"]]
     >>> results = exact_match.compute(references=refs, predictions=preds)
-    >>> print(round(results["exact_match"], 2))
+    >>> print(round(results["nl2bash"], 2))
     0.25
-    >>> exact_match = evaluate.load("exact_match")
-    >>> refs = ["the cat", "theater", "YELLING", "agent007"]
-    >>> preds = ["cat?", "theater", "yelling", "agent"]
-    >>> results = exact_match.compute(references=refs, predictions=preds, regexes_to_ignore=["the ", "yell"], ignore_case=True, ignore_punctuation=True)
-    >>> print(round(results["exact_match"], 2))
-    0.5
-    >>> exact_match = evaluate.load("exact_match")
-    >>> refs = ["the cat", "theater", "YELLING", "agent007"]
-    >>> preds = ["cat?", "theater", "yelling", "agent"]
-    >>> results = exact_match.compute(references=refs, predictions=preds, regexes_to_ignore=["the ", "yell", "YELL"], ignore_case=True, ignore_punctuation=True)
-    >>> print(round(results["exact_match"], 2))
-    0.75
-    >>> exact_match = evaluate.load("exact_match")
-    >>> refs = ["the cat", "theater", "YELLING", "agent007"]
-    >>> preds = ["cat?", "theater", "yelling", "agent"]
-    >>> results = exact_match.compute(references=refs, predictions=preds, regexes_to_ignore=["the ", "yell", "YELL"], ignore_case=True, ignore_punctuation=True, ignore_numbers=True)
-    >>> print(round(results["exact_match"], 2))
-    1.0
-    >>> exact_match = evaluate.load("exact_match")
-    >>> refs = ["The cat sat on the mat.", "Theaters are great.", "It's like comparing oranges and apples."]
-    >>> preds = ["The cat sat on the mat?", "Theaters are great.", "It's like comparing apples and oranges."]
-    >>> results = exact_match.compute(references=refs, predictions=preds)
-    >>> print(round(results["exact_match"], 2))
-    0.33
 """
 
 _CITATION = """
@@ -138,7 +111,6 @@ class nl2bash_m(evaluate.Metric):
         final_score = 0
 
         for pred, ref in zip(predictions, references):
-            print(pred, ref)
             pred_words, ref_words = pred.split(), ref[0].split()
             # Get the cmd of predicted and ref 
             cmd_corr = 1 if pred_words.pop(0)==ref_words.pop(0) else 0
@@ -158,7 +130,6 @@ class nl2bash_m(evaluate.Metric):
 
             score = cmd_score + opt_score + arg_score
             final_score += score
-            print(score)
 
         final_score = final_score/len(predictions)
         print("f_s: ", final_score)