I have a python code which works for doing data analytics from csv file. I want to run my python code to be run periodically on a docker container. Every 15 seconds, it should automatically look at a folder A, if there is a csv file in it, it should process it and put an html report with the same name in folder B.
HERE IS MY PYTHON CODE .
#This program pulls data from csv file and displays it as html file.
#csv file contains device names, card names and temperatures of cards
#The html file contains: how many devices, how many cards are in the system, which
#device has the highest temperature card, and in the table below is how many cards are
#there in summary for each device, how many have a temperature of 70 and above, the
#highest and average card what are the temperatures
#NOTE: The print functions in the program are written for trial purposes.
from enum import unique
from re import A, T
import pandas as pd
from prettytable import PrettyTable, PLAIN_COLUMNS
table = PrettyTable() #create a table for device
table2 = PrettyTable() #create a table for summary
table.field_names = ["Device -", "Total # of Cards - ", "High Temp. Cards # - ", "Max Temperature - ", "Avg. Temperature "]
table2.field_names = [" "," "]
df = pd.read_csv("cards.csv", sep=';', usecols = ['Device','Card','Temperature'])""", index_col=["Device","Card"]"""
print(type(df))
print(df["Device"].nunique(),"\n\n") # number of unique server
total_devices = df["Device"].nunique() # NUMBER OF DEVICES IN DIFFERENT TYPES
print(total_devices)
print(df["Device"].loc[1],"\n\n")
print(df['Temperature'].max(),"\n\n")
maxTemp = df['Temperature'].max() #finding max temperature
print("total card ", )
i= 0
j=1
#Finding the card with the max temperature and the server where the card is located
while j > 0:
if df["Temperature"].loc[i] == df["Temperature"].max():
print(df["Device"].loc[i])
print(df["Card"].loc[i])
deviceName = df["Device"].loc[i]
cardName = df["Card"].loc[i]
j= 0
else :
i = i 1
dev_types = df["Device"].unique() # Server's names
print("\n\n")
newstr = cardName "/" deviceName
#Summary tablosunu olusturma
table2.add_row(["Total Devices ", total_devices] )
table2.add_row(["Total Cads ", len(df["Card"])])
table2.add_row(["Max Card Temperature ", df["Temperature"].max()])
table2.add_row(["Hottest Card / Device " ,newstr])
print(table2)
row_num = len(df)
print(row_num)
#I pulled the data from the file according to the device type so that the server cards and temperatures were sorted, I found the max temp from here
dn = pd.read_csv("cards.csv", sep=';', index_col=["Device"], usecols = ['Device','Card','Temperature'])
sum = []
high = []
#print("max temp: ", dn["Temperature"].loc[dev_types[1]].max())
for x in range(total_devices): # total devices (according the file = 3 )
print("\n")
cardCount = 0 # counts the number of cards belonging to the device
count2 = 0 # Counts the number of cards with a temperature greater than 70
tempcount = 0
print(dev_types[x])
for y in range(row_num):
if dev_types[x] == df["Device"].loc[y]:
print(df["Temperature"].loc[y])
tempcount = tempcount df["Temperature"].loc[y] # the sum of the temperatures of the cards(used when calculating the average)
cardCount = cardCount 1
if df["Temperature"].loc[y] >= 70:
count2 = count2 1
maxT = dn["Temperature"].loc[dev_types[x]].max() #Finding the ones with the max temperature from the cards belonging to the server
avg = str(tempcount/cardCount)
print("avg",avg)
table.add_row([dev_types[x], cardCount, count2, maxT,avg ]) # I added the information to the "devices" table
print("num of cards" , cardCount)
print("high temp cards" , count2)
print("\n\n")
print("\n\n")
print(table)
htmlCode = table.get_html_string()
htmlCode2 = table2.get_html_string()
f= open('devices.html', 'w')
f.write("SUMMARY")
f.write(htmlCode2)
f.write("DEVICES")
f.write(htmlCode)
CodePudding user response：
Whether or not the code is run in Docker doesn't matter.
- Wrap all of that current logic (well, not the imports and so on) in a function, say,
def process_cards(). - Call that function forever, in a loop:
import logging
def process_cards():
table = PrettyTable()
...
def main():
logging.basicConfig()
while True:
try:
process_cards()
except Exception:
logging.exception("Failed processing")
time.sleep(15)
if __name__ == "__main__":
main()
As an aside, your data processing code can be vastly simplified:
import pandas as pd
from prettytable import PrettyTable
def get_summary_table(df):
summary_table = PrettyTable() # create a table for summary
total_devices = df["Device"].nunique()
hottest_card = df.loc[df["Temperature"].idxmax()]
hottest_device_desc = f"{hottest_card.Card}/{hottest_card.Device}"
summary_table.add_row(["Total Devices", total_devices])
summary_table.add_row(["Total Cards", len(df["Card"])])
summary_table.add_row(["Max Card Temperature", df["Temperature"].max()])
summary_table.add_row(["Hottest Card / Device ", hottest_device_desc])
return summary_table
def get_devices_table(df):
devices_table = PrettyTable(
[
"Device",
"Total # of Cards",
"High Temp. Cards #",
"Max Temperature",
"Avg. Temperature",
]
)
for device_name, group in df.groupby("Device"):
count = len(group)
avg_temp = group["Temperature"].mean()
max_temp = group["Temperature"].max()
high_count = group[group.Temperature >= 70]["Temperature"].count()
print(f"{device_name=} {avg_temp=} {max_temp=} {high_count=}")
devices_table.add_row([device_name, count, high_count, max_temp, avg_temp])
return devices_table
def do_processing(csv_file="cards.csv", html_file="devices.html"):
# df = pd.read_csv(csv_file, sep=';', usecols=['Device', 'Card', 'Temperature'])
# (Just some random example data)
df = pd.DataFrame({
"Device": [f"Device {1 x // 3}" for x in range(10)],
"Card": [f"Card {x 1}" for x in range(10)],
"Temperature": [59.3, 77.2, 48.5, 60.1, 77.2, 61.1, 77.4, 65.8, 71.2, 60.3],
})
summary_table = get_summary_table(df)
devices_table = get_devices_table(df)
with open(html_file, "w") as f:
f.write(
"<style>table, th, td {border: 1px solid black; border-collapse: collapse;}</style>"
)
f.write("SUMMARY")
f.write(summary_table.get_html_string(header=False))
f.write("DEVICES")
f.write(devices_table.get_html_string())
do_processing()
CodePudding user response：
i have an example of repeat decorator for run your function every seconds or minutes ...
i hope this sample helps you
from typing import Optional, Callable, Awaitable
import asyncio
from functools import wraps
def repeat_every(*, seconds: float, wait_first: bool = False)-> Callable:
def decorator(function: Callable[[], Optional[Awaitable[None]]]):
is_coroutine = asyncio.iscoroutinefunction(function)
@wraps(function)
async def wrapped():
async def loop():
if wait_first:
await asyncio.sleep(seconds)
while True:
try:
if is_coroutine:
await function()
else:
await asyncio.run_in_threadpool(function)
except Exception as e:
raise e
await asyncio.sleep(seconds)
asyncio.create_task(loop())
return wrapped
print("Repeat every working well.")
return decorator
@repeat_every(seconds=2)
async def main():
print(2*2)
try:
loop = asyncio.get_running_loop()
except RuntimeError:
loop = None
if loop and loop.is_running():
print('Async event loop already running.')
tsk = loop.create_task(main())
tsk.add_done_callback(
lambda t: print(f'Task done with result= {t.result()}'))
else:
print('Starting new event loop')
asyncio.run(main())
and there is an option that you can make an entrypoint which has cronjob