fix key error by adding metric map

app.py

@@ -20,36 +20,44 @@ This Space shows how one can instantiate these custom `evaluate.Metric`s, each w
 HF `evaluate.CombinedEvaluations` object. From here, we can easily compute each of the metrics simultaneously using `compute`.</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 evaluation(predictions, metrics) -> str:
+def populate_map(metric_df: pd.DataFrame, metric_set: set) -> dict:
+    
+    metric_map = dict()
+
+    for key in metric_set:
+        for val in metric_df.loc[metric_df["metric"] == key]["average"]:
+            metric_map[key] = val
+    
+    return metric_map
+
+
+def evaluation(predictions_df: pd.DataFrame, metrics_df: pd.DataFrame) -> str:
 
-    metric_set = set(metrics["Metric"].to_list())
+    metric_set = set(metrics_df["Metric"].to_list())
+    metric_map = populate_map(metrics_df, metric_set)
     combined_list = []
 
     if "f1" in metric_set:
-        f1 = FixedF1(average=metrics.loc[metrics["Metric"] == "f1"]["Averaging Type"][0])
+        f1 = FixedF1(average=metric_map["f1"])
         combined_list.append(f1)
     if "precision" in metric_set:
-        precision = FixedPrecision(average=metrics.loc[metrics["Metric"] == "precision"]["Averaging Type"][0])
+        precision = FixedPrecision(average=metric_map["f1"])
         combined_list.append(precision)
     if "recall" in metric_set:
-        recall = FixedRecall(average=metrics.loc[metrics["Metric"] == "recall"]["Averaging Type"][0])
+        recall = FixedRecall(average=metric_map["f1"])
         combined_list.append(recall)
     
     combined = evaluate.combine(combined_list)
 
-    predicted = [int(num) for num in predictions["Predicted Class Label"].to_list()]
-    references = [int(num) for num in predictions["Actual Class Label"].to_list()]
+    predicted = [int(num) for num in predictions_df["Predicted Class Label"].to_list()]
+    references = [int(num) for num in predictions_df["Actual Class Label"].to_list()]
 
     combined.add_batch(predictions=predicted, references=references)
     outputs = combined.compute()
 
     return f"Your metrics are as follows: \n {outputs}"
 
-def filter_records(records, gender):
-    return records[records["gender"] == gender]
 
 space = gr.Interface(
     fn=evaluation,
@@ -72,7 +80,6 @@ space = gr.Interface(
     outputs="text",
     title=title,
     description=description,
-    article=article,
     examples=[
         [
             pd.DataFrame(columns=["Predicted Class Label", "Actual Class Label"], data=[[0,1],[1,1],[2,2],[1,0],[0,0]]),