修改测试文件

ctr-56.py

-# -*- coding: UTF-8 -*-
-import redis
-import datetime
-import json
-
-
-if __name__ == "__main__":
-    device_id = "D17A3770-1CC7-4AFB-A9EA-6E667EE051FF"
-    search_qa_recommend_key = "TS:search_recommend_answer_queue:device_id:" + str(device_id)
-    r = redis.StrictRedis.from_url("redis://redis.paas-test.env:6379/1")
-    cids = list(range(529405,529408))
-    cids = [str(i) for i in cids]
-
-    value = json.dumps(cids)
-    r.hset(search_qa_recommend_key,'answer_queue',value)
-
-
-
-    print(1)
-
-
-
-

location.py

+# coding=utf-8
+import numpy as np
+from scipy.spatial.distance import cdist
+import matplotlib.pyplot as plt
+import seaborn as sns
+sns.set()
+
+from sklearn.cluster import DBSCAN
+from sklearn.preprocessing import StandardScaler
+import pandas as pd
+
+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
+
+#数据预处理，特征标准化，每一维是零均值和单位方差
+stscaler = StandardScaler().fit(data)
+data = stscaler.transform(data)
+
+#画出x和y的散点图
+plt.scatter(data[:, 0], data[:, 1])
+plt.xlabel("lat")
+plt.ylabel("lng")
+plt.title("beijng_users")
+# plt.savefig("results/wholesale.png", format="PNG")
+
+dbsc = DBSCAN(eps=0.5, min_samples=15).fit(data)
+
+labels = dbsc.labels_ #聚类得到每个点的聚类标签 -1表示噪点
+#print(labels)
+core_samples = np.zeros_like(labels, dtype=bool) #构造和labels一致的零矩阵,值是false
+core_samples[dbsc.core_sample_indices_] = True
+#print(core_samples)
+
+
+unique_labels = np.unique(labels)
+colors = plt.cm.Spectral(np.linspace(0, 1, len(unique_labels))) #linespace返回在【0,1】之间均匀分布数字是len个，Sepectral生成len个颜色
+
+
+#print(zip(unique_labels,colors))
+for (label, color) in zip(unique_labels, colors):
+    class_member_mask = (labels == label)
+    print(class_member_mask&core_samples)
+    xy = data[class_member_mask & core_samples]
+    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=color, markersize=10)
+
+    xy2 = data[class_member_mask & ~core_samples]
+    plt.plot(xy2[:, 0], xy2[:, 1], 'o', markerfacecolor=color, markersize=5)
+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")

user_data.py

@@ -76,6 +76,15 @@ def get_order():
         r += 10000
         print("insert done")
 
+def get_meigou_tag():
+    sql = "select service_id,tag_id from api_servicetag"
+    df = pd.DataFrame(list(get_mysql_data(host, port, user, passwd, db, sql)))
+    df = df.rename(columns={0: "service_id", 1: "tag_id"})
+
+    pd.io.sql.to_sql(df, "meigou_tag", yconnect, schema='jerry_test', if_exists='append', index=False)
+    print("insert done")
+
+
 def meigou_to_csv():
     sql = "select device_id,service_id,created_time from meigou_order"
     df = pd.DataFrame(list(get_mysql_data(host, port, user, passwd, db, sql)))
@@ -111,21 +120,22 @@ def location_to_csv():
 
 
 if __name__ == "__main__":
-    # host = "172.16.30.141"
-    # port = 3306
-    # user = "work"
-    # passwd = "BJQaT9VzDcuPBqkd"
-    # db = "zhengxing"
-    # yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@172.16.40.170:4000/jerry_test?charset=utf8')
-    # print("end")
-
-    host = "172.16.40.170"
-    port = 4000
-    user = "root"
-    passwd = "3SYz54LS9#^9sBvC"
-    db = "jerry_test"
-
-    location_to_csv()
+    host = "172.16.30.141"
+    port = 3306
+    user = "work"
+    passwd = "BJQaT9VzDcuPBqkd"
+    db = "zhengxing"
+    yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@172.16.40.170:4000/jerry_test?charset=utf8')
+    get_meigou_tag()
+    print("end")
+
+    # host = "172.16.40.170"
+    # port = 4000
+    # user = "root"
+    # passwd = "3SYz54LS9#^9sBvC"
+    # db = "jerry_test"
+
+