Pandas: Average value for the past n days

Question

I have a Pandas data frame like this:

test = pd.DataFrame({ \'Date\' : [\'2016-04-01\',\'2016-04-01\',\'2016-04-02\',
                                   


        

Answer 1

n = 2

# Cast your dates as timestamps.
test['Date'] = pd.to_datetime(test.Date)

# Create a daily index spanning the range of the original index.
idx = pd.date_range(test.Date.min(), test.Date.max(), freq='D')

# Pivot by Dates and Users.
df = test.pivot(index='Date', values='Value', columns='User').reindex(idx)
>>> df.head(3)
User        John  Mike
2016-04-01     2   1.0
2016-04-02     3   1.0
2016-04-03   NaN   4.5

# Apply a rolling mean on the above dataframe and reset the index.
df2 = (pd.rolling_mean(df.shift(), n, min_periods=1)
       .reset_index()
       .drop_duplicates())

# For Pandas 0.18.0+
df2 = (df.shift().rolling(window=n, min_periods=1).mean()
       .reset_index()
       .drop_duplicates())

# Melt the result back into the original form.
df3 = (pd.melt(df2, id_vars='Date', value_name='Value')
       .sort_values(['Date', 'User'])
       .reset_index(drop=True))
>>> df3.head()
        Date  User  Value
0 2016-04-01  John    NaN
1 2016-04-01  Mike    NaN
2 2016-04-02  John    2.0
3 2016-04-02  Mike    1.0
4 2016-04-03  John    2.5

# Merge the results back into the original dataframe.
>>> test.merge(df3, on=['Date', 'User'], how='left', 
               suffixes=['', '_Average_past_{0}_days'.format(n)])

        Date  User  Value  Value_Average_past_2_days
0 2016-04-01  Mike    1.0                        NaN
1 2016-04-01  John    2.0                        NaN
2 2016-04-02  Mike    1.0                       1.00
3 2016-04-02  John    3.0                       2.00
4 2016-04-03  Mike    4.5                       1.00
5 2016-04-04  Mike    1.0                       2.75
6 2016-04-05  Mike    2.0                       2.75
7 2016-04-06  Mike    3.0                       1.50
8 2016-04-06  John    6.0                        NaN

Summary

n = 2
test['Date'] = pd.to_datetime(test.Date)
idx = pd.date_range(test.Date.min(), test.Date.max(), freq='D')
df = test.pivot(index='Date', values='Value', columns='User').reindex(idx)
df2 = (pd.rolling_mean(df.shift(), n, min_periods=1)
       .reset_index()
       .drop_duplicates())
df3 = (pd.melt(df2, id_vars='Date', value_name='Value')
       .sort_values(['Date', 'User'])
       .reset_index(drop=True))
test.merge(df3, on=['Date', 'User'], how='left', 
           suffixes=['', '_Average_past_{0}_days'.format(n)])