美购精排模型耗时优化

spark/featureEng.py

@@ -665,12 +665,12 @@ if __name__ == '__main__':
     timestmp1 = int(round(time.time()))
     samplesWithItemFeatures = addItemFeatures(ratingSamplesWithLabel, itemDF)
     timestmp2 = int(round(time.time()))
-    print("处理item特征,size:{} 耗时s:{}".format(samplesWithItemFeatures.count(),timestmp2 - timestmp1))
+    print("处理item特征, 耗时s:{}".format(timestmp2 - timestmp1))
 
     print("处理user特征...")
     samplesWithUserFeatures = addUserFeatures(samplesWithItemFeatures)
     timestmp3 = int(round(time.time()))
-    print("处理user特征,size:{} 耗时s:{}".format(samplesWithUserFeatures.count(),timestmp3 - timestmp2))
+    print("处理user特征, 耗时s:{}".format(timestmp3 - timestmp2))
 
     # user columns
     user_columns = [c for c in samplesWithUserFeatures.columns if c.startswith("user")]