add eda file

tensnsorflow/eda.py

+import pymysql
+import pandas as pd
+from multiprocessing import Pool
+import numpy as np
+import datetime
+import time
+
+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(days):
+    start = (temp - datetime.timedelta(days)).strftime("%Y-%m-%d")
+    print(start)
+    sql = "select (select count(*) from train_data where stat_date = '{}' and y = 0)/(select count(*) " \
+          "from train_data where stat_date = '{}' and z = 1)".format(start)
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    exp = con_sql(db, sql)[0].values.tolist()[0]
+    sql = "select (select count(*) from train_data where stat_date = '{}' and y = 1 and z = 0)/(select count(*) " \
+          "from train_data where stat_date = '{}' and z = 1)".format(start)
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    click = con_sql(db, sql)[0].values.tolist()[0]
+    return start,exp,click
+
+
+if __name__ == "__main__":
+    temp = datetime.datetime.strptime("2019-03-14", "%Y-%m-%d")
+    DIRECTORY_PATH = "/home/gmuser/"
+    output_path = DIRECTORY_PATH + "eda.csv"
+    for i in range(1,41):
+        a,b,c = test(i)
+        with open(output_path, 'a+') as f:
+            line = str(a) + ',' + str(b)+ ',' + str(c) + '\n'
+            f.write(line)
+

tensnsorflow/es/feature.py

@@ -79,7 +79,7 @@ def get_data():
     value_map = dict(zip(unique_values,temp))
 
     df = df.drop("device_id", axis=1)
-    train = df
+    train = df[df["stat_date"] != validate_date+"stat_date"]
     test = df[df["stat_date"] == validate_date+"stat_date"]
     for i in ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
                 "channel", "top", "l1", "time", "stat_date","l2"]:

tensnsorflow/ffm.py

@@ -9,18 +9,7 @@ import time
 from sqlalchemy import create_engine
 
 
-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():
 #     sql = "select max(update_time) from ffm_diary_queue"
@@ -285,6 +274,35 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
     # print("nearby_pre shape")
     # print(nearby_pre.shape)
 
+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(days):
+    start = (temp - datetime.timedelta(days)).strftime("%Y-%m-%d")
+    print(start)
+    sql = "select (select count(*) from train_data where stat_date = '{}' and y = 0)/(select count(*) " \
+          "from train_data where stat_date = '{}' and z = 1)".format(start)
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    exp = con_sql(db, sql)[0].values.tolist()[0]
+    sql = "select (select count(*) from train_data where stat_date = '{}' and y = 1 and z = 0)/(select count(*) " \
+          "from train_data where stat_date = '{}' and z = 1)".format(start)
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    click = con_sql(db, sql)[0].values.tolist()[0]
+    return start,exp,click
+
+
+
 
 
 if __name__ == "__main__":