Merge branch 'master' of http://git.wanmeizhensuo.com/ML/ffm-baseline

tensnsorflow/es/feature.py

@@ -95,7 +95,6 @@ def get_data():
         train[i] = train[i].map(value_map)
         test[i] = test[i].map(value_map)
 
-    print(train[["clevel2_id", "channel","app_list"]].head(6))
     print("train shape")
     print(train.shape)
     print("test shape")

tensnsorflow/test.py

@@ -7,8 +7,23 @@ from pyspark.sql import SQLContext
 from pyspark.sql import SparkSession
 from py4j.java_gateway import java_import
 import pytispark.pytispark as pti
+import pandas as pd
+import pymysql
 
 
+def con_sql(db,sql):
+    cursor = db.cursor()
+    try:
+        cursor.execute(sql)
+        result = cursor.fetchall()
+        df = pd.DataFrame(list(result))
+    except Exception:
+        print("发生异常", Exception)
+        df = pd.DataFrame()
+    finally:
+        db.close()
+    return df
+
 
 def test():
         conf = SparkConf().setAppName("My App").set("spark.io.compression.codec", "lzf")
@@ -48,4 +63,10 @@ def esmm_pre():
 
 
 if __name__ == '__main__':
-        esmm_pre()
+    try:
+        db = pymysql.connect(host='10.66.157.11', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    except Exception:
+        db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select max(stat_date) from esmm_train_data"
+    validate_date = con_sql(db, sql)[0].values.tolist()[0]
+    print("validate_date:" + validate_date)
\ No newline at end of file