pandas 映射

tensnsorflow/feature_engineering.py

@@ -65,6 +65,11 @@ def get_data():
         train[i] = train[i].map(value_map)
         test[i] = test[i].map(value_map)
 
+    print("train shape")
+    print(train.shape)
+    print("test shape")
+    print(test.shape)
+
     train.to_csv(path + "tr.csv", index=False)
     test.to_csv(path + "va.csv", index=False)
 
@@ -86,6 +91,9 @@ def get_predict(date,value_map):
 
     df["stat_date"] = date
 
+    print("predict shape")
+    print(df.shape)
+
     features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
                 "channel", "top", "level2_ids", "time", "stat_date"]
     for i in features:

tensnsorflow/test.py

@@ -26,6 +26,7 @@ def gen_tfrecords(in_file):
     out_file = os.path.join(FLAGS.output_dir, basename)
     tfrecord_out = tf.python_io.TFRecordWriter(out_file)
     df = pd.read_csv(in_file)
+    print(df.head(2))
 
     for i in range(df.shape[0]):
         features = tf.train.Features(feature={