predict tractate

src/models/esmm/tractate_model.py

@@ -5,38 +5,37 @@ import tensorflow as tf
 from .fe.tractate_fe import device_tractate_fe
 from .model import _bytes_feature, _float_feature, _int64_feature
 
+_int_columns = [
+    "active_type", "active_days", "card_id", "is_pure_author", "is_have_reply", "is_have_pure_reply", "content_level",
+    "reply_num", "reply_pure_num"
+]
+_float_columns = ["one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr", "history_ctr"]
+_categorical_columns = [
+    "device_id", "past_consume_ability_history", "potential_consume_ability_history", "price_sensitive_history", "show_tag_id",
+    "device_fd", "device_sd", "device_fs", "device_ss", "device_fp", "device_sp", "device_p", "content_fd", "content_sd",
+    "content_fs", "content_ss", "content_fp", "content_sp", "content_p", "fd1", "fd2", "fd3", "sd1", "sd2", "sd3", "fs1", "fs2",
+    "fs3", "ss1", "ss2", "ss3", "fp1", "fp2", "fp3", "sp1", "sp2", "sp3", "p1", "p2", "p3", "click_tractate_id1",
+    "click_tractate_id2", "click_tractate_id3", "click_tractate_id4", "click_tractate_id5"
+]
+
+PREDICTION_ALL_COLUMNS = _int_columns + _float_columns + _categorical_columns
 
 def model_predict_tractate(device_id, tractate_ids, device_dict, tractate_dict, predict_fn):
     try:
         time_1 = timeit.default_timer()
         device_info, tractate_lst, tractate_ids_res = device_tractate_fe(device_id, tractate_ids, device_dict, tractate_dict)
         print("predict check: " + str(len(tractate_lst)) + " " + str(len(tractate_ids_res)))
-        # TODO
-        int_columns = [
-            "active_type", "active_days", "card_id", "is_pure_author", "is_have_reply", "is_have_pure_reply", "content_level",
-            "reply_num", "reply_pure_num"
-        ]
-        float_columns = [
-            "one_ctr", "three_ctr", "seven_ctr", "fifteen_ctr", "thirty_ctr", "sixty_ctr", "ninety_ctr", "history_ctr"
-        ]
-        str_columns = [
-            "device_id", "past_consume_ability_history", "potential_consume_ability_history", "price_sensitive_history",
-            "show_tag_id", "device_fd", "device_sd", "device_fs", "device_ss", "device_fp", "device_sp", "device_p", "content_fd",
-            "content_sd", "content_fs", "content_ss", "content_fp", "content_sp", "content_p", "fd1", "fd2", "fd3", "sd1", "sd2",
-            "sd3", "fs1", "fs2", "fs3", "ss1", "ss2", "ss3", "fp1", "fp2", "fp3", "sp1", "sp2", "sp3", "p1", "p2", "p3",
-            "click_tractate_id1", "click_tractate_id2", "click_tractate_id3", "click_tractate_id4", "click_tractate_id5"
-        ]
         examples = []
         for tractate_info in tractate_lst:
             tmp = {}
             tmp.update(device_info)
             tmp.update(tractate_info)
             features = {}
-            for col in int_columns:
+            for col in _int_columns:
                 features[col] = _int64_feature(int(tmp[col]))
-            for col in float_columns:
+            for col in _float_columns:
                 features[col] = _float_feature(float(tmp[col]))
-            for col in str_columns:
+            for col in _categorical_columns:
                 features[col] = _bytes_feature(str(tmp[col]).encode(encoding="utf-8"))
             example = tf.train.Example(features=tf.train.Features(feature=features))
             examples.append(example.SerializeToString())

src/train_tractate.py

@@ -12,7 +12,7 @@ from sklearn.model_selection import train_test_split
 from models.esmm.fe import click_fe, device_fe, fe, tractate_fe
 from models.esmm.input_fn import esmm_input_fn
 from models.esmm.model import esmm_model_fn, model_export
-from models.esmm.tractate_model import model_predict_tractate
+from models.esmm.tractate_model import (PREDICTION_ALL_COLUMNS, model_predict_tractate)
 
 
 def main():
@@ -58,6 +58,12 @@ def main():
     # save_path = model_export(model, all_features, model_export_path)
     # print("save to: " + save_path)
 
+    tractate_train_columns = set(tractate_fe.INT_COLUMNS + tractate_fe.FLOAT_COLUMNS + tractate_fe.CATEGORICAL_COLUMNS)
+    tractate_predict_columns = set(PREDICTION_ALL_COLUMNS)
+    print(tractate_predict_columns.difference(tractate_train_columns))
+    print(tractate_train_columns.difference(tractate_predict_columns))
+    assert tractate_predict_columns == tractate_train_columns
+
     print("============================================================")
 
     # # save_path = str(Path("~/data/models/tractate/1596089465").expanduser())  # local