Python:计算一段时间内数据帧中的累计量

这里非常复杂的部分是填写日期。我用了一个应用程序,但我不确定这是最好的方式

import pandas as pd

data = [{"game_id":"Racing","user_id":"ABC123","amt":5,"date":"2020-01-01"},
        {"game_id":"Racing","user_id":"ABC123","amt":1,"date":"2020-01-04"},
        {"game_id":"Racing","user_id":"CDE123","amt":1,"date":"2020-01-04"},
        {"game_id":"DH","user_id":"CDE123","amt":100,"date":"2020-01-03"},
        {"game_id":"DH","user_id":"CDE456","amt":10,"date":"2020-01-02"},
        {"game_id":"DH","user_id":"CDE789","amt":5,"date":"2020-01-02"},
        {"game_id":"DH","user_id":"CDE456","amt":1,"date":"2020-01-03"},
        {"game_id":"DH","user_id":"CDE456","amt":1,"date":"2020-01-03"}]

df = pd.DataFrame(data)
# we want datetime not object
df["date"] = df["date"].astype("M8[us]")

# we will need to merge this at the end
grp = df.groupby("game_id")['user_id']\
        .nunique()\
        .reset_index(name="Total_unique_payers_per_game")

# sum amt per game_id date
df = df.groupby(["game_id", "date"])["amt"].sum().reset_index()

# dates from 2020-01-01 till the max date in df
dates = pd.DataFrame({"date": pd.date_range("2020-01-01", df["date"].max())})

# add missing dates
def expand_dates(x):
    x = pd.merge(dates, x.drop("game_id", axis=1), how="left")
    x["amt"] = x["amt"].fillna(0)
    return x

df = df.groupby("game_id")\
       .apply(expand_dates)\
       .reset_index().drop("level_1", axis=1)

df["Cum_rev"] = df.groupby("game_id")['amt'].transform("cumsum")

# this is equivalent as long as data is sorted
# df["Cum_rev"] = df.groupby("game_id")['amt'].cumsum()

# merge unique payers per game
df = pd.merge(df, grp, how="left")

# dates difference
df["Age"] = "2020-01-01"
df["Age"] = df["Age"].astype("M8[us]")
df["Age"] = (df["date"]-df["Age"]).dt.days


# then you can eventually filter
df = df[["game_id", "Age", 
         "Cum_rev", "Total_unique_payers_per_game"]]\
       .rename(columns={"game_id":"Game"})