add exp

tensnsorflow/exp_channel.py

@@ -37,7 +37,26 @@ def exp():
     print(sorted(channel_map.items(), key=lambda x: x[1]))
 
 
+def clean():
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select device_id,device_type,manufacturer,channel,city_id from user_feature"
+    df = con_sql(db, sql)
+    df = df.rename(columns={0: "device_id",1: "device_type", 2: "manufacturer", 3: "channel", 4: "city_id"})
+    n = df.shape[0]
+    manufacturer = df["manufacturer"].unique()
+    for i in manufacturer:
+       if df.loc[df["manufacturer"]==i].shape[0]/n < 0.0005:
+           df.loc[df["manufacturer"] == i,["manufacturer"]] = "other"
+    print(df["manufacturer"].unique())
+    channel = df["channel"].unique()
+    for i in channel:
+        if df.loc[df["channel"] == i].shape[0] / n < 0.0001:
+            df.loc[df["channel"] == i, ["channel"]] = "other"
+
+    print(df["channel"].unique())
+
+
 if __name__ == "__main__":
-    exp()
+    clean()