Commit 1a134790 authored by 张彦钊's avatar 张彦钊

add data

parent e7e1fa67
...@@ -45,7 +45,14 @@ def get_data(): ...@@ -45,7 +45,14 @@ def get_data():
df["y"].values.tolist(),df["z"].values.tolist()], sep=",") df["y"].values.tolist(),df["z"].values.tolist()], sep=",")
df = df.drop("z", axis=1) df = df.drop("z", axis=1)
print(df.head()) print(df.head())
transform(df) print("shape")
print(df.shape)
df = pd.merge(df,get_statistics(),on="device_id",how='left').fillna(0)
print("merge")
print(df.head())
print("shape")
print(df.shape)
# transform(df)
def transform(df): def transform(df):
...@@ -91,14 +98,10 @@ def get_statistics(): ...@@ -91,14 +98,10 @@ def get_statistics():
sql = "select device_id,device_type,channel,total,精选,直播,鼻部,眼部,微整,牙齿,轮廓,美肤抗衰," \ sql = "select device_id,device_type,channel,total,精选,直播,鼻部,眼部,微整,牙齿,轮廓,美肤抗衰," \
"吸脂,脂肪填充,隆胸,私密,毛发管理,公立,韩国 from home_tab_click" "吸脂,脂肪填充,隆胸,私密,毛发管理,公立,韩国 from home_tab_click"
df = con_sql(db, sql) df = con_sql(db, sql)
df = df.rename(columns={0:"device_id",1:"device_type",2:"channel",3:"total"}) df = df.rename(columns={0:"device_id",1:"device_type",2:"channel",3:"total"})
print(df.head())
for i in df.columns.difference(["device_id", "device_type","channel","total"]): for i in df.columns.difference(["device_id", "device_type","channel","total"]):
df[i] = df[i]/df["total"] df[i] = df[i]/df["total"]
print(df.head()) return df
class multiFFMFormatPandas: class multiFFMFormatPandas:
...@@ -208,5 +211,5 @@ class multiFFMFormatPandas: ...@@ -208,5 +211,5 @@ class multiFFMFormatPandas:
if __name__ == "__main__": if __name__ == "__main__":
path = "/home/gmuser/ffm/" path = "/home/gmuser/ffm/"
# get_data() get_data()
get_statistics()
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