01-delayed-groupby.py

# This is just one possible solution, there are
# several ways to do this using `delayed`

sums = []
counts = []
for fn in filenames:
    # Read in file
    df = delayed(pd.read_csv)(fn)

    # Groupby origin airport
    by_origin = df.groupby('Origin')

    # Sum of all departure delays by origin
    total = by_origin.DepDelay.sum()

    # Number of flights by origin
    count = by_origin.DepDelay.count()

    # Save the intermediates
    sums.append(total)
    counts.append(count)

# Compute the intermediates
sums, counts = compute(sums, counts)

# Combine intermediates to get total mean-delay-per-origin
total_delays = sum(sums)
n_flights = sum(counts)
mean = total_delays / n_flights