Skip to content

G
gm_strategy_cvr
Commit 1a32da74 authored by 赵威's avatar 赵威
Browse files
Options

retrain

parent 883c544f
Show whitespace changes
Inline Side-by-side
Showing with 153 additions and 153 deletions
src/models/esmm/diary_model.py
View file @ 1a32da74
......@@ -72,22 +72,6 @@ _int_columns = [
"sixty_browse_user_num",
"ninety_browse_user_num",
"history_browse_user_num",
"one_vote_pure_rate",
"three_vote_pure_rate",
"seven_vote_pure_rate",
"fifteen_vote_pure_rate",
"thirty_vote_pure_rate",
"sixty_vote_pure_rate",
"ninety_vote_pure_rate",
"history_vote_pure_rate",
"one_reply_pure_rate",
"three_reply_pure_rate",
"seven_reply_pure_rate",
"fifteen_reply_pure_rate",
"thirty_reply_pure_rate",
"sixty_reply_pure_rate",
"ninety_reply_pure_rate",
"history_reply_pure_rate",
]
_float_columns = [
"one_ctr",
......@@ -98,6 +82,22 @@ _float_columns = [
"sixty_ctr",
"ninety_ctr",
"history_ctr",
# "one_vote_pure_rate",
# "three_vote_pure_rate",
# "seven_vote_pure_rate",
# "fifteen_vote_pure_rate",
# "thirty_vote_pure_rate",
# "sixty_vote_pure_rate",
# "ninety_vote_pure_rate",
# "history_vote_pure_rate",
# "one_reply_pure_rate",
# "three_reply_pure_rate",
# "seven_reply_pure_rate",
# "fifteen_reply_pure_rate",
# "thirty_reply_pure_rate",
# "sixty_reply_pure_rate",
# "ninety_reply_pure_rate",
# "history_reply_pure_rate",
]
_categorical_columns = [
"device_id", "past_consume_ability_history", "potential_consume_ability_history", "price_sensitive_history", "device_fd",
......
src/models/esmm/fe/diary_fe.py
View file @ 1a32da74
......@@ -70,22 +70,22 @@ DIARY_COLUMNS = [
"sixty_browse_user_num",
"ninety_browse_user_num",
"history_browse_user_num",
"one_vote_pure_rate",
"three_vote_pure_rate",
"seven_vote_pure_rate",
"fifteen_vote_pure_rate",
"thirty_vote_pure_rate",
"sixty_vote_pure_rate",
"ninety_vote_pure_rate",
"history_vote_pure_rate",
"one_reply_pure_rate",
"three_reply_pure_rate",
"seven_reply_pure_rate",
"fifteen_reply_pure_rate",
"thirty_reply_pure_rate",
"sixty_reply_pure_rate",
"ninety_reply_pure_rate",
"history_reply_pure_rate",
# "one_vote_pure_rate",
# "three_vote_pure_rate",
# "seven_vote_pure_rate",
# "fifteen_vote_pure_rate",
# "thirty_vote_pure_rate",
# "sixty_vote_pure_rate",
# "ninety_vote_pure_rate",
# "history_vote_pure_rate",
# "one_reply_pure_rate",
# "three_reply_pure_rate",
# "seven_reply_pure_rate",
# "fifteen_reply_pure_rate",
# "thirty_reply_pure_rate",
# "sixty_reply_pure_rate",
# "ninety_reply_pure_rate",
# "history_reply_pure_rate",
"one_ctr",
"three_ctr",
"seven_ctr",
......@@ -173,22 +173,22 @@ FLOAT_COLUMNS = [
"sixty_ctr",
"ninety_ctr",
"history_ctr",
"one_vote_pure_rate",
"three_vote_pure_rate",
"seven_vote_pure_rate",
"fifteen_vote_pure_rate",
"thirty_vote_pure_rate",
"sixty_vote_pure_rate",
"ninety_vote_pure_rate",
"history_vote_pure_rate",
"one_reply_pure_rate",
"three_reply_pure_rate",
"seven_reply_pure_rate",
"fifteen_reply_pure_rate",
"thirty_reply_pure_rate",
"sixty_reply_pure_rate",
"ninety_reply_pure_rate",
"history_reply_pure_rate",
# "one_vote_pure_rate",
# "three_vote_pure_rate",
# "seven_vote_pure_rate",
# "fifteen_vote_pure_rate",
# "thirty_vote_pure_rate",
# "sixty_vote_pure_rate",
# "ninety_vote_pure_rate",
# "history_vote_pure_rate",
# "one_reply_pure_rate",
# "three_reply_pure_rate",
# "seven_reply_pure_rate",
# "fifteen_reply_pure_rate",
# "thirty_reply_pure_rate",
# "sixty_reply_pure_rate",
# "ninety_reply_pure_rate",
# "history_reply_pure_rate",
]
CATEGORICAL_COLUMNS = [
"device_id", "active_type", "past_consume_ability_history", "potential_consume_ability_history", "price_sensitive_history",
......
src/models/esmm/fe/tractate_fe.py
View file @ 1a32da74
......@@ -62,22 +62,22 @@ TRACTATE_COLUMNS = [
"sixty_browse_user_num",
"ninety_browse_user_num",
"history_browse_user_num",
"one_vote_pure_rate",
"three_vote_pure_rate",
"seven_vote_pure_rate",
"fifteen_vote_pure_rate",
"thirty_vote_pure_rate",
"sixty_vote_pure_rate",
"ninety_vote_pure_rate",
"history_vote_pure_rate",
"one_reply_pure_rate",
"three_reply_pure_rate",
"seven_reply_pure_rate",
"fifteen_reply_pure_rate",
"thirty_reply_pure_rate",
"sixty_reply_pure_rate",
"ninety_reply_pure_rate",
"history_reply_pure_rate",
# "one_vote_pure_rate",
# "three_vote_pure_rate",
# "seven_vote_pure_rate",
# "fifteen_vote_pure_rate",
# "thirty_vote_pure_rate",
# "sixty_vote_pure_rate",
# "ninety_vote_pure_rate",
# "history_vote_pure_rate",
# "one_reply_pure_rate",
# "three_reply_pure_rate",
# "seven_reply_pure_rate",
# "fifteen_reply_pure_rate",
# "thirty_reply_pure_rate",
# "sixty_reply_pure_rate",
# "ninety_reply_pure_rate",
# "history_reply_pure_rate",
"one_ctr",
"three_ctr",
"seven_ctr",
......@@ -157,22 +157,22 @@ FLOAT_COLUMNS = [
"sixty_ctr",
"ninety_ctr",
"history_ctr",
"one_vote_pure_rate",
"three_vote_pure_rate",
"seven_vote_pure_rate",
"fifteen_vote_pure_rate",
"thirty_vote_pure_rate",
"sixty_vote_pure_rate",
"ninety_vote_pure_rate",
"history_vote_pure_rate",
"one_reply_pure_rate",
"three_reply_pure_rate",
"seven_reply_pure_rate",
"fifteen_reply_pure_rate",
"thirty_reply_pure_rate",
"sixty_reply_pure_rate",
"ninety_reply_pure_rate",
"history_reply_pure_rate",
# "one_vote_pure_rate",
# "three_vote_pure_rate",
# "seven_vote_pure_rate",
# "fifteen_vote_pure_rate",
# "thirty_vote_pure_rate",
# "sixty_vote_pure_rate",
# "ninety_vote_pure_rate",
# "history_vote_pure_rate",
# "one_reply_pure_rate",
# "three_reply_pure_rate",
# "seven_reply_pure_rate",
# "fifteen_reply_pure_rate",
# "thirty_reply_pure_rate",
# "sixty_reply_pure_rate",
# "ninety_reply_pure_rate",
# "history_reply_pure_rate",
]
CATEGORICAL_COLUMNS = [
"device_id", "active_type", "past_consume_ability_history", "potential_consume_ability_history", "price_sensitive_history",
......
src/models/esmm/tractate_model.py
View file @ 1a32da74
......@@ -73,22 +73,22 @@ _float_columns = [
"sixty_ctr",
"ninety_ctr",
"history_ctr",
"one_vote_pure_rate",
"three_vote_pure_rate",
"seven_vote_pure_rate",
"fifteen_vote_pure_rate",
"thirty_vote_pure_rate",
"sixty_vote_pure_rate",
"ninety_vote_pure_rate",
"history_vote_pure_rate",
"one_reply_pure_rate",
"three_reply_pure_rate",
"seven_reply_pure_rate",
"fifteen_reply_pure_rate",
"thirty_reply_pure_rate",
"sixty_reply_pure_rate",
"ninety_reply_pure_rate",
"history_reply_pure_rate",
# "one_vote_pure_rate",
# "three_vote_pure_rate",
# "seven_vote_pure_rate",
# "fifteen_vote_pure_rate",
# "thirty_vote_pure_rate",
# "sixty_vote_pure_rate",
# "ninety_vote_pure_rate",
# "history_vote_pure_rate",
# "one_reply_pure_rate",
# "three_reply_pure_rate",
# "seven_reply_pure_rate",
# "fifteen_reply_pure_rate",
# "thirty_reply_pure_rate",
# "sixty_reply_pure_rate",
# "ninety_reply_pure_rate",
# "history_reply_pure_rate",
]
_categorical_columns = [
"device_id", "past_consume_ability_history", "potential_consume_ability_history", "price_sensitive_history", "show_tag_id",
......
src/online_prediction.py
View file @ 1a32da74
......@@ -45,13 +45,13 @@ if __name__ == "__main__":
diary_save_path = get_essm_model_save_path("diary")
if not diary_save_path:
diary_save_path = "/home/gmuser/data/models/diary/1597050209"
diary_save_path = "/home/gmuser/data/models/diary/1597379800"
print(diary_save_path + "!!!!!!!!!!!!!!!!!!!!!!!!!!!")
diary_predict_fn = tf.contrib.predictor.from_saved_model(diary_save_path)
tractate_save_path = get_essm_model_save_path("tractate")
if not tractate_save_path:
tractate_save_path = "/home/gmuser/data/models/tractate/1596509299"
tractate_save_path = "/home/gmuser/data/models/tractate/1597378202"
print(tractate_save_path + "!!!!!!!!!!!!!!!!!!!!!!!!!!!")
tractate_predict_fn = tf.contrib.predictor.from_saved_model(tractate_save_path)
......
src/train_diary.py
View file @ 1a32da74
......@@ -9,8 +9,7 @@ from pathlib import Path
import tensorflow as tf
from sklearn.model_selection import train_test_split
from models.esmm.diary_model import (PREDICTION_ALL_COLUMNS,
model_predict_diary)
from models.esmm.diary_model import PREDICTION_ALL_COLUMNS, model_predict_diary
from models.esmm.fe import click_fe, device_fe, diary_fe, fe
from models.esmm.input_fn import esmm_input_fn
from models.esmm.model import esmm_model_fn, model_export
......@@ -24,65 +23,66 @@ def main():
# os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
# diary_train_columns = set(diary_fe.INT_COLUMNS + diary_fe.FLOAT_COLUMNS + diary_fe.CATEGORICAL_COLUMNS)
# print("features: " + str(len(diary_train_columns)))
# diary_predict_columns = set(PREDICTION_ALL_COLUMNS)
# print(diary_predict_columns.difference(diary_train_columns))
# print(diary_train_columns.difference(diary_predict_columns))
# assert diary_predict_columns == diary_train_columns
# # dataset_path = Path("~/data/cvr_data").expanduser() # local
# dataset_path = Path("/srv/apps/node2vec_git/cvr_data/") # server
# diary_df, diary_click_df, diary_conversion_df = diary_fe.read_csv_data(dataset_path)
# # print(diary_df.sample(1))
# diary_df = diary_fe.diary_feature_engineering(diary_df)
# # print(diary_df.sample(1))
# device_df = device_fe.read_csv_data(dataset_path)
# # print(diary_df.sample(1))
# device_df = device_fe.device_feature_engineering(device_df, "diary")
# # print(device_df.sample(1))
# cc_df = click_fe.click_feature_engineering(diary_click_df, diary_conversion_df)
# # print(cc_df.sample(1))
# df = diary_fe.join_features(device_df, diary_df, cc_df)
# # print(df.sample(1))
# # print(df.dtypes)
# train_df, test_df = train_test_split(df, test_size=0.2)
# train_df, val_df = train_test_split(train_df, test_size=0.2)
# all_features = fe.build_features(df, diary_fe.INT_COLUMNS, diary_fe.FLOAT_COLUMNS, diary_fe.CATEGORICAL_COLUMNS)
# params = {"feature_columns": all_features, "hidden_units": [64, 32], "learning_rate": 0.1}
# model_path = str(Path("~/data/model_tmp/diary/").expanduser())
# if os.path.exists(model_path):
# shutil.rmtree(model_path)
# session_config = tf.compat.v1.ConfigProto()
# session_config.gpu_options.allow_growth = True
# session_config.gpu_options.per_process_gpu_memory_fraction = 0.9
# estimator_config = tf.estimator.RunConfig(session_config=session_config)
# model = tf.estimator.Estimator(model_fn=esmm_model_fn, params=params, model_dir=model_path, config=estimator_config)
# train_spec = tf.estimator.TrainSpec(input_fn=lambda: esmm_input_fn(train_df, shuffle=True), max_steps=50000)
# eval_spec = tf.estimator.EvalSpec(input_fn=lambda: esmm_input_fn(val_df, shuffle=False))
# res = tf.estimator.train_and_evaluate(model, train_spec, eval_spec)
# print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
# print(res[0])
# print("ctr_auc: " + str(res[0]["ctr_auc"]))
# print("ctcvr_auc: " + str(res[0]["ctcvr_auc"]))
# print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
# model_export_path = str(Path("~/data/models/diary").expanduser())
# save_path = model_export(model, all_features, model_export_path)
# print("save to: " + save_path)
# set_essm_model_save_path("diary", save_path)
# print("============================================================")
diary_train_columns = set(diary_fe.INT_COLUMNS + diary_fe.FLOAT_COLUMNS + diary_fe.CATEGORICAL_COLUMNS)
print("features: " + str(len(diary_train_columns)))
diary_predict_columns = set(PREDICTION_ALL_COLUMNS)
print(diary_predict_columns.difference(diary_train_columns))
print(diary_train_columns.difference(diary_predict_columns))
assert diary_predict_columns == diary_train_columns
# dataset_path = Path("~/data/cvr_data").expanduser() # local
dataset_path = Path("/srv/apps/node2vec_git/cvr_data/") # server
diary_df, diary_click_df, diary_conversion_df = diary_fe.read_csv_data(dataset_path)
# print(diary_df.sample(1))
diary_df = diary_fe.diary_feature_engineering(diary_df)
# print(diary_df.sample(1))
device_df = device_fe.read_csv_data(dataset_path)
# print(diary_df.sample(1))
device_df = device_fe.device_feature_engineering(device_df, "diary")
# print(device_df.sample(1))
cc_df = click_fe.click_feature_engineering(diary_click_df, diary_conversion_df)
# print(cc_df.sample(1))
df = diary_fe.join_features(device_df, diary_df, cc_df)
# print(df.sample(1))
# print(df.dtypes)
train_df, test_df = train_test_split(df, test_size=0.2)
train_df, val_df = train_test_split(train_df, test_size=0.2)
all_features = fe.build_features(df, diary_fe.INT_COLUMNS, diary_fe.FLOAT_COLUMNS, diary_fe.CATEGORICAL_COLUMNS)
params = {"feature_columns": all_features, "hidden_units": [64, 32], "learning_rate": 0.1}
model_path = str(Path("~/data/model_tmp/diary/").expanduser())
if os.path.exists(model_path):
shutil.rmtree(model_path)
session_config = tf.compat.v1.ConfigProto()
session_config.gpu_options.allow_growth = True
session_config.gpu_options.per_process_gpu_memory_fraction = 0.9
estimator_config = tf.estimator.RunConfig(session_config=session_config)
model = tf.estimator.Estimator(model_fn=esmm_model_fn, params=params, model_dir=model_path, config=estimator_config)
train_spec = tf.estimator.TrainSpec(input_fn=lambda: esmm_input_fn(train_df, shuffle=True), max_steps=50000)
eval_spec = tf.estimator.EvalSpec(input_fn=lambda: esmm_input_fn(val_df, shuffle=False))
res = tf.estimator.train_and_evaluate(model, train_spec, eval_spec)
print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
print(res[0])
print("ctr_auc: " + str(res[0]["ctr_auc"]))
print("ctcvr_auc: " + str(res[0]["ctcvr_auc"]))
print("@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@")
model_export_path = str(Path("~/data/models/diary").expanduser())
save_path = model_export(model, all_features, model_export_path)
print("save to: " + save_path)
set_essm_model_save_path("diary", save_path)
print("============================================================")
# save_path = str(Path("~/Desktop/models/1596012827").expanduser()) # local
# save_path = "/home/gmuser/data/models/diary/1596083349" # server
# tf.saved_model.load
save_path = get_essm_model_save_path("diary")
# save_path = get_essm_model_save_path("diary")
# print("load path: " + save_path)
predict_fn = tf.contrib.predictor.from_saved_model(save_path)
device_dict = device_fe.get_device_dict_from_redis()
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment