问如何总结pandas数据帧

EN

# Define a function to get routes' relationship (origin vs destination)
def get_routes(x):
    if 'transfer' not in x.type.tolist(): # if no 'transfer' type in group, leave it as 0 (we'll remove them afterwards)
        return 0
    x = x[x.type == 'transfer'] # select target type
    date = df[df.cardNumber=='999'].Date.dt.strftime('%m/%d/%Y').unique()
    if date.size == 1: # if there is more than one date by passenger, you'll need to change this code
        date = date[0]
    else:
        raise Exception("There are more than one date per passenger, please adapt your code.")
    s_from = x.routeName[x.Date.idxmin()] # get route from the first date
    s_to = x.routeName[x.Date.idxmax()] # get route from the last date
    return date, s_from, s_to

# Define a function to get the routes' daily average
def get_daily_avg(date_group):
    daily_avg = (
        date_group.groupby(['From', 'To'], as_index=False) # group the day by routes
        .apply(lambda route: route.shape[0] / date_group.shape[0]) # divide the total of trips of that route by the total trips of that day
    )
    return daily_avg

# Get route's relationship
routes_series = df.groupby('cardNumber').apply(get_routes) # retrive routes per passenger
routes_series = routes_series[routes_series!=0] # remove groups without the target type

# Create a named dataframe from the series output
routes_df = pd.DataFrame(routes_series.tolist(), columns=['Date', 'From', 'To'])

# Create dataframe, perform filter and calculations
daily_routes_df = (
    routes_df.query('From != To') # remove routes with same destination as the origin
    .groupby('Date').apply(get_daily_avg) # calculate the mean per date
    .rename(columns={None: 'Avg. Daily'}) # set name to previous output
    .drop(['From','To'], axis = 1) # drop out redundant info since there's such info at the index
    .reset_index() # remove MultiIndex to get a tidy dataframe
)

# Visualize results
print(daily_routes_df)

         Date From To  Avg. Daily
0  08/01/2020    2  1         1.0

# srot the dataframe so you can use first/last
df_sorted= df.sort_values(['cardNumber', 'Date']).reset_index(drop=True)

# calculate the counts do the counts, but only
# from the defined types
indexer_trip_points= df_sorted['type'].isin(['transfer'])
df_from_to= df_sorted[indexer_trip_points].groupby('cardNumber').agg(
                  start_date=('Date', 'first'),
                  trip_start=('routeName', 'first'), 
                  trip_end=('routeName', 'last'),
)
                      
df_from_to['start_date']= df_from_to['start_date'].dt.date
df_counts= df_from_to.groupby(['trip_start', 'trip_end', 'start_date']).agg(
    count=('trip_start', 'count')
)
df_counts.reset_index(drop=False, inplace=True)
df_counts.groupby(['trip_start', 'trip_end']).agg(
    avg=('count', 'mean')
)

                     avg
trip_start trip_end     
2          1           1
3          3           1