more updates to app

app.py

@@ -1,36 +1,40 @@
 from fixed_f1 import FixedF1
 from fixed_precision import FixedPrecision
 from fixed_recall import FixedRecall
-
+import evaluate
 import gradio as gr
 
 title = "'Combine' multiple metrics with this 🤗 Evaluate 🪲 Fix!"
 
 description = """<p style='text-align: center'>
-As I introduce myself to the entirety of the 🤗 ecosystem, I've put together this space to show off a workaround for a current 🪲 in the 🤗 Evaluate library. \n
+As I introduce myself to the entirety of the 🤗 ecosystem, I've put together this space to show off a temporary fix for a current 🪲 in the 🤗 Evaluate library. \n
 
-Check out the original, longstanding issue [here](https://github.com/huggingface/evaluate/issues/234). This details how it is currently impossible to \
+    Check out the original, longstanding issue [here](https://github.com/huggingface/evaluate/issues/234). This details how it is currently impossible to \
 'evaluate.combine()' multiple metrics related to multilabel text classification. Particularly, one cannot 'combine()' the f1, precision, and recall scores for \
 evaluation. I encountered this issue specifically while training [RoBERTa-base-DReiFT](https://huggingface.co/MarioBarbeque/RoBERTa-base-DReiFT) for multilabel \
-text classification of 805 labeled medical conditions based on drug reviews for treatment received for the same underlying conditio. Use the space below for \
-a preview of the workaround! \n
+text classification of 805 labeled medical conditions based on drug reviews. \n
 
 Try to use \t to write some code? \t or how does that work? </p>
 
 
 """
 
-article = "<p style='text-align: center'>Check out the [original repo](https://github.com/johngrahamreynolds/FixedMetricsForHF) housing this code, and a quickly \
-trained [multilabel text classicifcation model](https://github.com/johngrahamreynolds/RoBERTa-base-DReiFT/tree/main) that makes use of it during evaluation.</p>"
+article = "<p style='text-align: center'> Check out the [original repo](https://github.com/johngrahamreynolds/FixedMetricsForHF) housing this code, and a quickly \
+trained [multilabel text classification model](https://github.com/johngrahamreynolds/RoBERTa-base-DReiFT/tree/main) that makes use of it during evaluation.</p>"
+
+def show_off(predictions, references, weighting_map): 
+
+    f1 = FixedF1(average=weighting_map["f1"])
+    precision = FixedPrecision(average=weighting_map["precision"])
+    recall = FixedRecall(average=weighting_map["recall"])
 
-def show_off(input):
-    f1 = FixedF1()
-    precision = FixedPrecision()
-    recall = FixedRecall()
+    combined = evaluate.combine([f1, recall, precision])
 
+    combined.add_batch(prediction=predictions, reference=references)
+    outputs =  combined.compute()
 
 
-    return "Checking this out! Here's what you put in: " + f"""{input} """
+    return "Your metrics are as follows: \n" + outputs
 
 
 gr.Interface(
@@ -40,5 +44,5 @@ gr.Interface(
     title=title,
     description=description,
     article=article,
-    examples=[["What are you doing?"], ["Where should we time travel to?"]],
+    examples=[[[1, 0, 2, 0, 1], [1,0,0,0,1], {"f1":"weighted", "precision": "micro", "recall": "weighted"}]],
 ).launch()