service model 优化

spark/featureEng2.py

@@ -260,14 +260,11 @@ def splitAndSaveTrainingTestSamplesByTimeStamp(samples,splitTimestamp, file_path
     test.write.option("header", "true").option("delimiter", "|").mode('overwrite').csv(testSavePath)
 
 def collectColumnToVocab(samples,column):
-    pd.DataFrame()[""].tolist()
-    list(set(samples[column].tolist()))
     datas = samples.select(column).distinct().collect()
     vocabSet = set()
     for d in datas:
         if d[column]:
             vocabSet.add(str(d[column]))
-    vocabSet.add("-1")  # 空值的默认
     return list(vocabSet)
 
 def collectMutiColumnToVocab(samples,column):