1、相关环境
hadoop-2.10.0
hive-3.1.2
hbase-2.2.2
spark-2.4.4
2、相关表结构
HBase
create 'ctr_user_features', 'cf'
create 'ctr_article_features', 'cf'
Hive
CREATE EXTERNAL TABLE T_CTR_USER_FEATURES(
USER_ID STRING,
CF MAP<STRING, STRING>
)
COMMENT 'CTR USER FEATURES'
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES ("hbase.columns.mapping" = ":key,cf:")
TBLPROPERTIES ("hbase.table.name" = "ctr_user_features");
CREATE EXTERNAL TABLE T_CTR_ARTICLE_FEATURES(
ARTICLE_ID STRING,
CF MAP<STRING, STRING>
)
COMMENT 'CTR ARTICLE FEATURES'
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES ("hbase.columns.mapping" = ":key,cf:")
TBLPROPERTIES ("hbase.table.name" = "ctr_article_features");
3、相关Python实现
# -*- coding:utf-8 -*-
import os
import sys
import numpy as np
from datetime import datetime
BASE_PATH = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.insert(0, os.path.join(BASE_PATH))
print sys.path
from offline import BaseSparkSession
default_encoding = 'utf-8'
if sys.getdefaultencoding() != default_encoding:
reload(sys)
sys.setdefaultencoding(default_encoding)
os.environ['PYSPARK_PYTHON'] = 'F:\develop\python\Python27\python.exe'
os.environ['HADOOP_HOME'] = 'F:\develop\hadoop\hadoop-2.10.0'
os.environ['HADOOP_CONF_DIR'] = 'F:\develop\hadoop\hadoop-2.10.0-conf'
os.environ['SPARK_HOME'] = 'F:\develop\spark\spark-2.4.4-bin-hadoop2.7'
class UserArticleFeaturesGenerator(BaseSparkSession):
def __init__(self):
self.SPARK_APP_NAME = 'user_article_features_generator'
self.SPARK_MASTER_URL = 'yarn'
self.SPARK_YARN_QUEUE = 'queue3'
self.ENABLE_HIVE_SUPPORT = True
self.spark_session = self.create_spark_session()
# 生成用户特征
def gen_user_features(self):
self.spark_session.sql("use portal")
# 获取用户画像 基础数据、偏好喜好数据
sql = "select split(user_id, ':')[1] user_id, basic_info.gender, basic_info.age, preference_info " \
"from t_user_profile"
user_profile_df = self.spark_session.sql(sql)
user_profile_df.show()
# 抽取文章所属频道关键词向量特征
def extract_channel_keyword_feature(partition):
from pyspark.ml.linalg import Vectors
channel_id_list = [1001, 1002, 1003, 1004, 1005, 1006, 1007, 1008]
for row in partition:
for channel_id in channel_id_list:
try:
weights = sorted([row.preference_info[key] for key in row.preference_info.keys()
if key.split(':')[0] == str(channel_id)], reverse=True)[:10]
except Exception as e:
print e.message
weights = [0.0] * 10
yield row.user_id, int(row.gender), int(row.age), channel_id, \
Vectors.dense(weights if weights else [0.0] * 10)
user_profile_df = user_profile_df.rdd.mapPartitions(extract_channel_keyword_feature). \
toDF(["user_id", "gender", "age", "channel_id", "channel_weights"])
# 收集特征
from pyspark.ml.feature import VectorAssembler
user_profile_df = VectorAssembler().setInputCols(["gender", "age", "channel_weights"]) \
.setOutputCol("features") \
.transform(user_profile_df)
# 存储用户特征
def insert_ctr_user_features(partition):
sys.path.insert(0, os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
from recoutils.hbase_utils import HBaseUtils
hbase_utils = HBaseUtils(host="192.168.0.1", port=9090, size=5)
for row in partition:
hbase_utils.insert("ctr_user_features", str(row.user_id).encode(),
{"cf:{}".format(row.channel_id).encode(): str(row.features).encode()})
user_profile_df.foreachPartition(insert_ctr_user_features)
# 生成文章特征
def gen_article_features(self):
self.spark_session.sql("use portal")
# 获取文章画像
article_profile_df = self.spark_session.sql("select * from t_article_profile")
# 抽取文章关键词向量特征
def extract_feature(partition):
from pyspark.ml.linalg import Vectors
for row in partition:
try:
weights = sorted(row.keywords.values(), reverse=True)[:10]
except Exception as e:
print e.message
weights = [0.0] * 10
yield row.article_id, row.channel_id, Vectors.dense(weights if weights else [0.0] * 10)
article_profile_df = article_profile_df.rdd.mapPartitions(extract_feature) \
.toDF(["article_id", "channel_id", "article_weights"])
article_profile_df.show()
# 获取文章向量
article_vector_df = self.spark_session.sql("select article_id, vector from t_article_vector")
def array_to_vector(partition):
from pyspark.ml.linalg import Vectors
for row in partition:
yield row.article_id, Vectors.dense(row.vector)
article_vector_df = article_vector_df.rdd.mapPartitions(array_to_vector).toDF(["article_id", "article_vector"])
article_vector_df.show()
article_profile_df = article_profile_df.join(article_vector_df, on=["article_id"], how="inner")
# 收集特征
from pyspark.ml.feature import VectorAssembler
article_profile_df = VectorAssembler().setInputCols(["channel_id", "article_weights", "article_vector"]) \
.setOutputCol("features") \
.transform(article_profile_df)
article_profile_df.show()
# 存储文章特征
def insert_ctr_article_features(partition):
sys.path.insert(0, os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
from recoutils.hbase_utils import HBaseUtils
hbase_utils = HBaseUtils(host="192.168.0.1", port=9090, size=5)
for row in partition:
hbase_utils.insert("ctr_article_features", str(row.article_id).encode(),
{"cf:{}".format(row.article_id).encode(): str(row.features).encode()})
article_profile_df.foreachPartition(insert_ctr_article_features)
if __name__ == '__main__':
user_article_features_generator = UserArticleFeaturesGenerator()
user_article_features_generator.gen_user_features()
user_article_features_generator.gen_article_features()
针对上一章节的CTR排序模型LR可以做一些优化处理
def gen_lr_sort_model_optimize(self):
self.spark_session.sql("use portal")
# 获取用户特征数据
ctr_user_features_df = self.spark_session.sql("select * from t_ctr_user_features")
def extract_user_features(partition):
for row in partition:
for item in row.cf.items():
yield row.user_id, item[0], eval(item[1])
ctr_user_features_df = ctr_user_features_df.rdd.mapPartitions(extract_user_features) \
.toDF(["user_id", "channel_id", "user_features"])
ctr_user_features_df.show()
# 获取文章特征数据
ctr_article_features_df = self.spark_session.sql("select * from t_ctr_article_features")
def extract_article_features(partition):
for row in partition:
for item in row.cf.items():
yield row.article_id, eval(item[1])
ctr_article_features_df = ctr_article_features_df.rdd.mapPartitions(extract_article_features) \
.toDF(["article_id", "article_features"])
ctr_article_features_df.show()
# 用户文章点击行为
sql = "select user_id, article_id, channel_id, click_flag from t_user_behaviour"
user_article_click_df = self.spark_session.sql(sql)
user_article_click_df.show()
# 关联用户、文章特征
user_article_click_df = user_article_click_df.join(ctr_user_features_df, ["user_id", "channel_id"], "left")
user_article_click_df = user_article_click_df.join(ctr_article_features_df, ["article_id"], "left")
input_cols = ["channel_id", "gender", "age", "channel_weights", "article_weights", "article_vector"]
# 收集特征
def assemble_featrues(partition):
from pyspark.ml.linalg import Vectors
for row in partition:
features = []
features.append(row.channel_id)
features.extend(row.user_features)
features.extend(row.article_features[1:] if row.article_features else [0.0] * 110)
yield row.user_id, row.article_id, row.click_flag, Vectors.dense(features)
user_article_click_df = user_article_click_df.rdd.mapPartitions(assemble_featrues) \
.toDF(["user_id", "article_id", "click_flag", "features"])
user_article_click_df.show()
# Logistic Regression
from pyspark.ml.classification import LogisticRegression
logistic_regression = LogisticRegression()
logistic_regression_model = logistic_regression.setFeaturesCol("features") \
.setLabelCol("click_flag") \
.fit(user_article_click_df)
logistic_regression_model.write().overwrite().save(
"hdfs://192.168.0.1:9000/user/models/logistic_regression/lr.model")
from pyspark.ml.classification import LogisticRegressionModel
logistic_regression_model = LogisticRegressionModel.load(
"hdfs://192.168.0.1:9000/user/models/logistic_regression/lr.model")
logistic_regression_result = logistic_regression_model.transform(user_article_click_df)
logistic_regression_result.select(["click_flag", "probability", "prediction"]).show()