Commit 1918ceb9 authored by 张彦钊's avatar 张彦钊

add exp

parent be0e6bfd
import pandas as pd import pandas as pd
import pymysql import pymysql
def con_sql(db,sql): def con_sql(db,sql):
cursor = db.cursor() cursor = db.cursor()
try: try:
...@@ -14,9 +15,29 @@ def con_sql(db,sql): ...@@ -14,9 +15,29 @@ def con_sql(db,sql):
db.close() db.close()
return df return df
def exp(): def exp():
db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test') db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
sql = "select manufacturer,channel from user_feature" sql = "select manufacturer,channel from user_feature"
df = con_sql(db, sql) df = con_sql(db, sql)
n = df.shape[0]
manufacturer = df[0].unique()
manufacturer_map = {}
print("manufacturer unique") print("manufacturer unique")
print(len(df[0].unique())) print(len(manufacturer))
\ No newline at end of file for i in manufacturer:
manufacturer_map[i] = df.loc[df[0]==i].shape[0]/n
print(sorted(manufacturer_map.items(),key = lambda x:x[1]))
channel = df[1].unique()
channel_map = {}
print("channel unique")
print(len(channel))
for i in channel:
channel_map[i] = df.loc[df[1] == i].shape[0] / n
print(sorted(channel_map.items(), key=lambda x: x[1]))
if __name__ == "__main__":
exp()
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment