fixups: base64 query components and quoting agg in code sample

app.py

@@ -1,3 +1,4 @@
+import base64
 import re
 import json
 import pandas as pd
@@ -23,7 +24,13 @@ def generate_vis(df, mode='Document'):
  max_score = max(max(t.values()) for t in df['toks'])
  for row in df.itertuples(index=False):
  if mode == 'Query':
- tok_scores = {m.group(2): float(m.group(1)) for m in re.finditer(r'combine:0=([0-9.]+)\(([^)]+)\)', row.query)}
+ tok_scores = {m.group(2): float(m.group(1)) for m in re.finditer(r'#combine:0=([0-9.]+)\((#base64\([^)]+\)|[^)]+)\)', row.query)}
+ for key, value in list(tok_scores.items()):
+ if key.startswith('#base64('):
+ b64 = re.search('#base64\(([^)]+)\)', key).group(1)
+ del tok_scores[key]
+ key = base64.b64decode(b64).decode()
+ tok_scores[key] = value
  max_score = max(tok_scores.values())
  orig_tokens = factory_max.tokenizer.tokenize(row.query_0)
  id = row.qid
@@ -51,7 +58,7 @@ def predict_query(input, agg):
 import pyterrier as pt ; pt.init()
 import pyt_splade
 
-factory = pyt_splade.SpladeFactory(agg={agg})
+factory = pyt_splade.SpladeFactory(agg={repr(agg)})
 
 query_pipeline = factory.query()
 
@@ -70,7 +77,7 @@ def predict_doc(input, agg):
 import pyterrier as pt ; pt.init()
 import pyt_splade
 
-factory = pyt_splade.SpladeFactory(agg={agg})
+factory = pyt_splade.SpladeFactory(agg={repr(agg)})
 
 doc_pipeline = factory.indexing()