Analyzer - Fix bugs in data diagnosis (#355)

**Description**
Fix bugs in data diagnosis.

**Major Revision**
- add support to get baseline of the metric which uses custom benchmark naming with ':' like 'nccl-bw:default/allreduce_8_bw:0'
- save raw data of all metrics rather than metrics defined in diagnosis_rules.yaml when output_all is True
- fix bug of using wrong column index when applying format(red color and percentile) in the excel

superbench/analyzer/data_diagnosis.py

@@ -63,8 +63,8 @@ def _get_baseline_of_metric(self, baseline, metric):
         if metric in baseline:
             return baseline[metric]
         else:
-            # exclude rank info
-            short = metric.split(':')[0]
+            # exclude rank info, for example, '.*:\d+'->'.*'
+            short = metric.strip(metric.split(':')[-1]).strip(':')
             if short in baseline:
                 return baseline[short]
             # baseline not defined
@@ -221,7 +221,7 @@ def output_all_nodes_results(self, raw_data_df, data_not_accept_df):
             DataFrame: all nodes' detailed information inluding ['Accept','#Issues','Category','Issue_Details']
         """
         append_columns = ['Accept', '#Issues', 'Category', 'Issue_Details']
-        all_data_df = (raw_data_df[self._enable_metrics]).astype('float64')
+        all_data_df = (raw_data_df).astype('float64')
 
         if data_not_accept_df.shape[0] == 0:
             all_data_df['Accept'] = [True for i in range(len(all_data_df))]

superbench/analyzer/file_handler.py

@@ -120,7 +120,8 @@ def output_excel_data_not_accept(writer, data_not_accept_df, rules):
 
             for rule in rules:
                 for metric in rules[rule]['metrics']:
-                    col_index = columns.index(metric)
+                    # The column index of the metrics should start from 1
+                    col_index = columns.index(metric) + 1
                     # Apply percent format for the columns whose rules are variance type.
                     if rules[rule]['function'] == 'variance':
                         worksheet.conditional_format(