Рассчитать среднее время печати в файле журнала с помощью команд Linux (или python)?

Вот скрипт Python, использующий регулярное выражение:

import re

# Open the file and get the data in a string
f = open('your_log', 'r')
text = f.read()

# Use regex to find the pattern
matches = re.findall(r'Estimate the time: (d+.d+)s', text)
if matches:
    times = [float(time) for time in matches] # Convert str in float
    mean = sum(times) / len(times) # Calculate the mean with built-in methods
    print(mean)
else:
    print("no data")

sum=0
cnt=0
for log in logs:
  if "Estimate the time" in log:
    sum += extractSecondFromLog()
    cnt += 1
print(sum/cnt)

awk '/[info] Estimate the time:/ { map[cnt++]=+$5 } END { for (i in map) { cnt1++;tot=tot+map[i] } print tot/cnt1 }' logfile

Пояснение:

awk '/[info] Estimate the time:/ {                # Process lines that contain "[info] Estimate the time:"
                 map[cnt++]=+$5                     # Create an array called map with an incrementing index and the 5th space delimited field as the value
               } 
           END {                                    # Process at the end of the file
                 for (i in map) { 
                    cnt1++;                         # Loop through the array and increment a counter with each iteration
                    tot=tot+map[i]                  # Create a running total variable
                 } 
                 print tot/cnt1                     # Print the running total divided by the count.
                }' logfile