Commit ccf12cf3 authored by 张彦钊's avatar 张彦钊

add test

parent 2239d1e1
...@@ -71,23 +71,23 @@ def sort_app(): ...@@ -71,23 +71,23 @@ def sort_app():
n = df.shape[0] n = df.shape[0]
for i in category.keys(): for i in category.keys():
df[i] = df["app_list"].apply(lambda x: 1 if len(x & category[i]) > 0 else 0) df[i] = df["app_list"].apply(lambda x: 1 if len(x & category[i]) > 0 else 0)
print(i) # print(i)
print(df.loc[df[i]==1].shape[0]/n) # print(df.loc[df[i]==1].shape[0]/n)
df = df.drop("app_list",axis=1) df = df.drop("app_list",axis=1)
# yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8') yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
# print(df.shape) print(df.shape)
# n = 200000 n = 200000
# for i in range(0,df.shape[0],n): for i in range(0,df.shape[0],n):
# print(i) print(i)
# if i == 0: if i == 0:
# temp = df.loc[0:n] temp = df.loc[0:n]
# elif i+n > df.shape[0]: elif i+n > df.shape[0]:
# temp = df.loc[i+1:] temp = df.loc[i+1:]
# else: else:
# temp = df.loc[i+1:i+n] temp = df.loc[i+1:i+n]
# pd.io.sql.to_sql(temp, "app_list_sort", yconnect, schema='jerry_test', if_exists='append', index=False) pd.io.sql.to_sql(temp, "app_list_sort", yconnect, schema='jerry_test', if_exists='append', index=False)
# print("insert done") print("insert done")
......
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