模型调试

spark/featureEngSk.py

@@ -435,6 +435,7 @@ def dataVocabToRedis(dataVocab):
 
 def saveVocab(key, vocab):
     conn = getRedisConn()
+    conn.delete(key)
     conn.lpush(key,vocab)
     conn.expire(FEATURE_VOCAB_KEY,60 * 60 * 24)
 
@@ -1030,7 +1031,7 @@ if __name__ == '__main__':
     for multi_categoty_field in multi_categoty_fields:
         output_file = "file:///home/gmuser/" + multi_categoty_field + "_vocab"
         # train_samples.selectExpr("explode(split({multi_categoty_field},','))".format(multi_categoty_field = multi_categoty_field)).where(F.col(multi_categoty_field) != '-1').distinct().write.mode("overwrite").options(header="false").csv(output_file)
-        multi_categoty_field_rows = train_samples.selectExpr("explode(split({multi_categoty_field},',')) as {multi_categoty_field}".format(multi_categoty_field = multi_categoty_field)).where(F.col(multi_categoty_field) != '-1').distinct().collect()
+        multi_categoty_field_rows = train_samples.selectExpr("explode(split({multi_categoty_field},',')) as {multi_categoty_field}".format(multi_categoty_field = multi_categoty_field)).where(F.col(multi_categoty_field) != '-1').where(F.col(multi_categoty_field) != '').distinct().collect()
         vocab_redis_keys.append("strategy:" + multi_categoty_field + ":vocab")
         saveVocab(vocab_redis_keys[-1], list(map(lambda row: row[multi_categoty_field], multi_categoty_field_rows)))
 

train/down_vocab.py

 import redis
+import sys
+import os
+import json
+
+def getRedisConn():
+    # pool = redis.ConnectionPool(host="172.16.50.145",password="XfkMCCdWDIU%ls$h",port=6379,db=0)
+    # conn = redis.Redis(connection_pool=pool)
+    # conn = redis.Redis(host="172.16.50.145", port=6379, password="XfkMCCdWDIU%ls$h",db=0)
+    conn = redis.Redis(host="172.18.51.10", port=6379, db=0, decode_responses = True) #test
+    return conn
+
+save_dir = sys.argv[1]
+
+print('save_dir: ', save_dir)
+
+conn = getRedisConn()
+vocab_keys = conn.lrange("strategy:all:vocab", 0, -1)
+print("vocab_keys: ", vocab_keys[0])
+vocab_keys = eval(vocab_keys[0])
+
+
+
+for vocab_key in vocab_keys:
+    print('vocab_key: ', vocab_key)
+    splits = vocab_key.split(":")
+    field = splits[1]
+    filename = field + "_vocab.csv"
+
+    print('filename: ', filename)
+    with open(os.path.join(save_dir, filename), 'w') as f:
+        texts = conn.lrange(vocab_key, 0, -1)
+        texts = eval(texts[0])
+        print('texts: ', len(texts))
+        f.write('\n'.join(texts))
+