change test

location.py

+import numpy as np, pandas as pd
+from sklearn.cluster import DBSCAN
+from shapely.geometry import MultiPoint
+import geopandas
+import shapefile
+
+from matplotlib import pyplot as plt
+
+data = pd.read_csv("/Users/mac/Downloads/location.csv")
+data.drop(["device_id", "partition_date"], axis=1, inplace=True)
+
+data = data[["lat", "lng"]]
+data = data.as_matrix().astype("float32", copy=False)#convert to array
+
+plt.title("beijing location")
+plt.scatter(latlngs[:, 0], latlngs[:, 1], s=1, c="black", marker='.')
+border_shape = shapefile.Reader(shape_path)
+border_shape_2 = shapefile.Reader(shape_path_2huan)
+border_shape_5 = shapefile.Reader(shape_path_5huan)
+border = border_shape.shapes()
+border_2 = border_shape_2.shapes()
+border_5 = border_shape_5.shapes()
+
+
+# 聚类中心区域
+def get_centermost_point(cluster):
+    centroid = (MultiPoint(cluster).centroid.x, MultiPoint(cluster).centroid.y)
+    print(centroid)
+    return tuple(centroid)
+
+
+# #渲染聚类结果
+for border_detail in clusters:
+    x, y = [], []
+    for cell in border_detail:
+        x.append(cell[0])
+        y.append(cell[1])
+    plt.scatter(x, y, marker='o')
+plt.show()
+
+
 # coding=utf-8
 import numpy as np
 from scipy.spatial.distance import cdist
@@ -51,4 +92,4 @@ for (label, color) in zip(unique_labels, colors):
 plt.title("DBSCAN on beijing_users")
 plt.xlabel("lat (scaled)")
 plt.ylabel("lng (scaled)")
-plt.savefig("results/(0.9,15)dbscan_wholesale.png", format="PNG")
+# plt.savefig("results/(0.9,15)dbscan_wholesale.png", format="PNG")

tensnsorflow/ctr.py

+import pandas as pd
+import pymysql
+import datetime
+
+
+def con_sql(db,sql):
+    cursor = db.cursor()
+    cursor.execute(sql)
+    result = cursor.fetchone()[0]
+    db.close()
+    return result
+
+
+def get_ctr():
+    db = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_prod')
+    yesterday = (datetime.date.today() - datetime.timedelta(days=1)).strftime("%Y-%m-%d")
+    print(yesterday)
+    sql = "select count(*) from data_feed_exposure_precise where stat_date = '{}'".format(yesterday)
+    exposures = con_sql(db, sql)
+    sql = "select count(*) from data_feed_exposure_precise where stat_date = '{}'".format(yesterday)
+    clicks = con_sql(db, sql)
+    print(exposures)
+    print(clicks)
+    print(exposures/clicks)
+
+
+
+
+if __name__ == "__main__":
+    get_ctr()
\ No newline at end of file

tensnsorflow/device_read_time_normal.py

-import pandas as pd
-import pymysql
-from sklearn.preprocessing import MinMaxScaler
-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 normal():
-    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select * from device_read_time"
-    df = con_sql(db, sql)
-    df = df.rename(columns={0:"device_id",1:"kongbai",2:"eye",3:"simi",4:"zitizhifang",5:"banyongjiu",6:"teeth",
-                            7:"kouchun",8:"ear",9:"nose",10:"banyongjiuzhuang",11:"qita",12:"lunkuo",
-                            13:"shoushen",14:"skin",16:"shenghuo",
-                            17:"breast",18:"hair",19:"kangshuai",20:"shili",21:"chanhou",22:"zhushe"})
-    # device_id = df[["device_id"]]
-    # df = df.drop("device_id",axis=1)
-    # minMax = MinMaxScaler()
-    # result = pd.DataFrame(minMax.fit_transform(df),columns=["0","1","10","1024","1080","11",
-    #                         "12","13","2","2054","2214","3","4","5","6933",
-    #                         "7","9","922","929","971","992"])
-    # result = device_id.join(result)
-    l = list(df.columns)
-    l.remove("device_id")
-    df["sum"] = df.sum(axis=1)
-    for i in l:
-        df[i] = df[i]/df["sum"]
-    df = df.drop("sum",axis=1)
-    yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
-    pd.io.sql.to_sql(df, "device_read_time_normal", yconnect, schema='jerry_test', if_exists='fail', index=False)
-
-
-if __name__ == "__main__":
-    normal()
\ No newline at end of file