模型调试

train/down_vocab_tfrecord.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
+
+if len(sys.argv) == 2:
+    save_dir = sys.argv[1]
+else:
+    save_dir = '/data/files/wideAndDeep/'
+
+print('save_dir: ', save_dir)
+if not os.path.exists(save_dir):
+    print('mkdir save_dir: ', save_dir)
+    os.makedirs(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 = list(filter(lambda x: x != '', eval(texts[0])))
+        print('texts: ', len(texts))
+        f.write('\n'.join(texts))
+
+os.system("hdfs dfs -getmerge /strategy/train_samples_tfrecord {save_dir}train_samples.tfrecord".format(save_dir = save_dir))
+os.system("hdfs dfs -getmerge /strategy/eval_samples_tfrecord {save_dir}eval_samples.tfrecord".format(save_dir = save_dir))
+