Python accumulate errors or secondary data - python

I've trying to find a good way to accumulate errors in case when function returns two values (result, errors)
Example:
def do_something(inp):
"""just for example"""
if type(inp) is not str:
return None, 'inp is not string'
return inp.upper(), None
results_dict = {}
errors = []
r, e = do_something(handler1(inp1))
results_dict[inp1] = r
if e:
errors.append(r)
r, e = do_something(handler2(inp2))
results_dict[inp2] = r
if e:
errors.append(r)
# and so on
Is there the right way to accumulate errors in one string
like this pseudocode
errors = ErrorsAccumulator()
results_dict = {}
results_dict[inp1], errors = do_something(handler1(inp1))
results_dict[inp2], errors = do_something(handler2(inp2))
# and so on
I can't use loop for it because there is a lot different handlers

As I understand it, what you want to do is collect outputs and results in 2 different lists.
As it is written right now, the code will simply replace whatever the variable errors contains:
errors = ErrorsAccumulator()
results_dict = {}
results_dict[inp1], errors = do_something(handler1(inp1))
results_dict[inp2], errors = do_something(handler2(inp2))
Assuming that errors is a list, you could instead do this:
def unpack(t):
# this function will unpack the result and error of
# your calls to do_something
return t[0], [t[1]]
errors = []
results_dict = {}
results_dict[inp1], errors[len(errors):] = unpack(do_something(handler1(inp1)))
results_dict[inp2], errors[len(errors):] = unpack(do_something(handler2(inp2)))
However, that is not very clean (in my opinion). What I propose you do instead is:
inputs_results_errors = []
inputs_results_errors.append(inp1, *do_something(handler1(inp1)))
inputs_results_errors.append(inp1, *do_something(handler2(inp1)))
# append many more ...
# and then separate into lists or dicts
inputs, results, errors = zip(*inputs_results_errors)

Related

Kill dask worker when no result/fail

I am running a dask.distributed Client that gets data from an API with several parameters, parses results and joins/aggregates on each result. This is done with client.map()
Sometimes the API call gives an empty string because the specific combination of input parameters doesn't exist. It doesn't make sense to continue with computations and I would like to just kill that worker (without passing on e.g. a None).
How do I tell Dask to kill a worker if its result is None/error and exclude that future from the following operations?
Please let me know if you need more details.
Thanks.
EDIT:
Added a minimal working example to show the logic: the first map produces a lot of "useless" workers that I would like to kill.
Please notice that this is not my actual use case, I am querying an Influx database via http requests but the general structure of the code is the same. I am open to any comments on how to do that faster/more efficiently.
´´´´python
import requests
import numpy as np
import pandas as pd
from dask.distributed import Client, LocalCluster, as_completed
import dask.dataframe as dd
def fetch_html(pair):
req_string = 'https://www.bitstamp.net/api/v2/order_book/{currency_pair}/'
response = requests.get(req_string.format(currency_pair=pair))
try:
result = response.json()
return result
except Exception as e:
print('Error: {}\nMessage: {}'.format(e,response.reason))
return None
def parse_result(result):
if result:
data = {}
data['prices'] = [e[0] for e in result['bids']]
data['vols'] = [e[1] for e in result['bids']]
data['index'] = [result['timestamp'] for i in data['prices']]
df = pd.DataFrame.from_dict(data).set_index('index')
return df
else:
return pd.DataFrame()
def other_calcs(result):
if not result.empty:
# something
return result
else:
return pd.DataFrame()
def aggregator(res1, res2):
if (not res1.empty) and (not res2.empty):
# something
return res1
elif not res2.empty:
# something
return res2
elif not res1.empty:
return res1
else:
return pd.DataFrame()
if __name__=='__main__':
pairs = [
# legit params (100s of these):
'btcusd',
'btceur',
'btcgbp',
'bateur',
'batbtc',
'umausd',
'xrpusdt',
'eurteur',
'eurtusd',
'manausd',
'sandeur',
'storjusd',
'storjeur',
'adausd',
'adaeur',
# bad params resulting in error / empty result (100s of these)
'foobar',
'foobaz',
'foousd',
'barbaz',
'bazbar',
]
cluster = LocalCluster(n_workers=16, threads_per_worker=1)
client = Client(cluster)
futures_list = client.map(fetch_html, pairs)
futures_list = client.map(parse_result, futures_list)
futures_list = client.map(other_calcs, futures_list)
seq = as_completed(futures_list)
while seq.count() > 1:
f1 = next(seq)
f2 = next(seq)
new = client.submit(aggregator, f1, f2, priority=1)
seq.add(new)
final = next(seq)
final = final.result()
print(final.head())
´´´´

Python sql returning list

got some functions with sqlstatements. My first func is fine because i get only 1 result.
My second function returns a large list of errorcodes and i dont know how to get them back for response.
TypeError: <sqlalchemy.engine.result.ResultProxy object at 0x7f98b85ef910> is not JSON serializable
Tried everything need help.
My Code:
def topalarms():
customer_name = request.args.get('customer_name')
machine_serial = request.args.get('machine_serial')
#ts = request.args.get('ts')
#ts_start = request.args.get('ts')
if (customer_name is None) or (machine_serial is None):
return missing_param()
# def form_response(response, session):
# response['customer'] = customer_name
# response['serial'] = machine_serial
# return do_response(customer_name, form_response)
def form_response(response, session):
result_machine_id = machine_id(session, machine_serial)
if not result_machine_id:
response['Error'] = 'Seriennummer nicht vorhanden/gefunden'
return
#response[''] = result_machine_id[0]["id"]
machineid = result_machine_id[0]["id"]
result_errorcodes = error_codes(session, machineid)
response['ErrorCodes'] = result_errorcodes
return do_response(customer_name, form_response)
def machine_id(session, machine_serial):
stmt_raw = '''
SELECT
id
FROM
machine
WHERE
machine.serial = :machine_serial_arg
'''
utc_now = datetime.datetime.utcnow()
utc_now_iso = pytz.utc.localize(utc_now).isoformat()
utc_start = datetime.datetime.utcnow() - datetime.timedelta(days = 30)
utc_start_iso = pytz.utc.localize(utc_start).isoformat()
stmt_args = {
'machine_serial_arg': machine_serial,
}
stmt = text(stmt_raw).columns(
#ts_insert = ISODateTime
)
result = session.execute(stmt, stmt_args)
ts = utc_now_iso
ts_start = utc_start_iso
ID = []
for row in result:
ID.append({
'id': row[0],
'ts': ts,
'ts_start': ts_start,
})
return ID
def error_codes(session, machineid):
stmt_raw = '''
SELECT
name
FROM
identifier
WHERE
identifier.machine_id = :machineid_arg
'''
stmt_args = {
'machineid_arg': machineid,
}
stmt = text(stmt_raw).columns(
#ts_insert = ISODateTime
)
result = session.execute(stmt, stmt_args)
errors = []
for row in result:
errors.append(result)
#({'result': [dict(row) for row in result]})
#errors = {i: result[i] for i in range(0, len(result))}
#errors = dict(result)
return errors
My problem is func error_codes somethiing is wrong with my result.
my Output should be like this:
ABCNormal
ABCSafety
Alarm_G01N01
Alarm_G01N02
Alarm_G01N03
Alarm_G01N04
Alarm_G01N05
I think you need to take a closer look at what you are doing correctly with your working function and compare that to your non-working function.
Firstly, what do you think this code does?
for row in result:
errors.append(result)
This adds to errors one copy of the result object for each row in result. So if you have six rows in result, errors contains six copies of result. I suspect this isn't what you are looking for. You want to be doing something with the row variable.
Taking a closer look at your working function, you are taking the first value out of the row, using row[0]. So, you probably want to do the same in your non-working function:
for row in result:
errors.append(row[0])
I don't have SQLAlchemy set up so I haven't tested this: I have provided this answer based solely on the differences between your working function and your non-working function.
You need a json serializer. I suggest using Marshmallow: https://marshmallow.readthedocs.io/en/stable/
There are some great tutorials online on how to do this.

Check that a key from json output exists

I keep getting the following error when trying to parse some json:
Traceback (most recent call last):
File "/Users/batch/projects/kl-api/api/helpers.py", line 37, in collect_youtube_data
keywords = channel_info_response_data['items'][0]['brandingSettings']['channel']['keywords']
KeyError: 'brandingSettings'
How do I make sure that I check my JSON output for a key before assigning it to a variable? If a key isn’t found, then I just want to assign a default value. Code below:
try:
channel_id = channel_id_response_data['items'][0]['id']
channel_info_url = YOUTUBE_URL + '/channels/?key=' + YOUTUBE_API_KEY + '&id=' + channel_id + '&part=snippet,contentDetails,statistics,brandingSettings'
print('Querying:', channel_info_url)
channel_info_response = requests.get(channel_info_url)
channel_info_response_data = json.loads(channel_info_response.content)
no_of_videos = int(channel_info_response_data['items'][0]['statistics']['videoCount'])
no_of_subscribers = int(channel_info_response_data['items'][0]['statistics']['subscriberCount'])
no_of_views = int(channel_info_response_data['items'][0]['statistics']['viewCount'])
avg_views = round(no_of_views / no_of_videos, 0)
photo = channel_info_response_data['items'][0]['snippet']['thumbnails']['high']['url']
description = channel_info_response_data['items'][0]['snippet']['description']
start_date = channel_info_response_data['items'][0]['snippet']['publishedAt']
title = channel_info_response_data['items'][0]['snippet']['title']
keywords = channel_info_response_data['items'][0]['brandingSettings']['channel']['keywords']
except Exception as e:
raise Exception(e)
You can either wrap all your assignment in something like
try:
keywords = channel_info_response_data['items'][0]['brandingSettings']['channel']['keywords']
except KeyError as ignore:
keywords = "default value"
or, let say, use .has_key(...). IMHO In your case first solution is preferable
suppose you have a dict, you have two options to handle the key-not-exist situation:
1) get the key with default value, like
d = {}
val = d.get('k', 10)
val will be 10 since there is not a key named k
2) try-except
d = {}
try:
val = d['k']
except KeyError:
val = 10
This way is far more flexible since you can do anything in the except block, even ignore the error with a pass statement if you really don't care about it.
How do I make sure that I check my JSON output
At this point your "JSON output" is just a plain native Python dict
for a key before assigning it to a variable? If a key isn’t found, then I just want to assign a default value
Now you know you have a dict, browsing the official documention for dict methods should answer the question:
https://docs.python.org/3/library/stdtypes.html#dict.get
get(key[, default])
Return the value for key if key is in the dictionary, else default. If default is not given, it defaults to None, so that this method never raises a KeyError.
so the general case is:
var = data.get(key, default)
Now if you have deeply nested dicts/lists where any key or index could be missing, catching KeyErrors and IndexErrors can be simpler:
try:
var = data[key1][index1][key2][index2][keyN]
except (KeyError, IndexError):
var = default
As a side note: your code snippet is filled with repeated channel_info_response_data['items'][0]['statistics'] and channel_info_response_data['items'][0]['snippet'] expressions. Using intermediate variables will make your code more readable, easier to maintain, AND a bit faster too:
# always set a timeout if you don't want the program to hang forever
channel_info_response = requests.get(channel_info_url, timeout=30)
# always check the response status - having a response doesn't
# mean you got what you expected. Here we use the `raise_for_status()`
# shortcut which will raise an exception if we have anything else than
# a 200 OK.
channel_info_response.raise_for_status()
# requests knows how to deal with json:
channel_info_response_data = channel_info_response.json()
# we assume that the response MUST have `['items'][0]`,
# and that this item MUST have "statistics" and "snippets"
item = channel_info_response_data['items'][0]
stats = item["statistics"]
snippet = item["snippet"]
no_of_videos = int(stats.get('videoCount', 0))
no_of_subscribers = int(stats.get('subscriberCount', 0))
no_of_views = int(stats.get('viewCount', 0))
avg_views = round(no_of_views / no_of_videos, 0)
try:
photo = snippet['thumbnails']['high']['url']
except KeyError:
photo = None
description = snippet.get('description', "")
start_date = snippet.get('publishedAt', None)
title = snippet.get('title', "")
try:
keywords = item['brandingSettings']['channel']['keywords']
except KeyError
keywords = ""
You may also want to learn about string formatting (contatenating strings is quite error prone and barely readable), and how to pass arguments to requests.get()

Getting wrong result from JSON - Python 3

Im working on a small project of retrieving information about books from the Google Books API using Python 3. For this i make a call to the API, read out the variables and store those in a list. For a search like "linkedin" this works perfectly. However when i enter "Google", it reads the second title from the JSON input. How can this happen?
Please find my code below (Google_Results is the class I use to initialize the variables):
import requests
def Book_Search(search_term):
parms = {"q": search_term, "maxResults": 3}
r = requests.get(url="https://www.googleapis.com/books/v1/volumes", params=parms)
print(r.url)
results = r.json()
i = 0
for result in results["items"]:
try:
isbn13 = str(result["volumeInfo"]["industryIdentifiers"][0]["identifier"])
isbn10 = str(result["volumeInfo"]["industryIdentifiers"][1]["identifier"])
title = str(result["volumeInfo"]["title"])
author = str(result["volumeInfo"]["authors"])[2:-2]
publisher = str(result["volumeInfo"]["publisher"])
published_date = str(result["volumeInfo"]["publishedDate"])
description = str(result["volumeInfo"]["description"])
pages = str(result["volumeInfo"]["pageCount"])
genre = str(result["volumeInfo"]["categories"])[2:-2]
language = str(result["volumeInfo"]["language"])
image_link = str(result["volumeInfo"]["imageLinks"]["thumbnail"])
dict = Google_Results(isbn13, isbn10, title, author, publisher, published_date, description, pages, genre,
language, image_link)
gr.append(dict)
print(gr[i].title)
i += 1
except:
pass
return
gr = []
Book_Search("Linkedin")
I am a beginner to Python, so any help would be appreciated!
It does so because there is no publisher entry in volumeInfo of the first entry, thus it raises a KeyError and your except captures it. If you're going to work with fuzzy data you have to account for the fact that it will not always have the expected structure. For simple cases you can rely on dict.get() and its default argument to return a 'valid' default entry if an entry is missing.
Also, there are a few conceptual problems with your function - it relies on a global gr which is bad design, it shadows the built-in dict type and it captures all exceptions guaranteeing that you cannot exit your code even with a SIGINT... I'd suggest you to convert it to something a bit more sane:
def book_search(search_term, max_results=3):
results = [] # a list to store the results
parms = {"q": search_term, "maxResults": max_results}
r = requests.get(url="https://www.googleapis.com/books/v1/volumes", params=parms)
try: # just in case the server doesn't return valid JSON
for result in r.json().get("items", []):
if "volumeInfo" not in result: # invalid entry - missing volumeInfo
continue
result_dict = {} # a dictionary to store our discovered fields
result = result["volumeInfo"] # all the data we're interested is in volumeInfo
isbns = result.get("industryIdentifiers", None) # capture ISBNs
if isinstance(isbns, list) and isbns:
for i, t in enumerate(("isbn10", "isbn13")):
if len(isbns) > i and isinstance(isbns[i], dict):
result_dict[t] = isbns[i].get("identifier", None)
result_dict["title"] = result.get("title", None)
authors = result.get("authors", None) # capture authors
if isinstance(authors, list) and len(authors) > 2: # you're slicing from 2
result_dict["author"] = str(authors[2:-2])
result_dict["publisher"] = result.get("publisher", None)
result_dict["published_date"] = result.get("publishedDate", None)
result_dict["description"] = result.get("description", None)
result_dict["pages"] = result.get("pageCount", None)
genres = result.get("authors", None) # capture genres
if isinstance(genres, list) and len(genres) > 2: # since you're slicing from 2
result_dict["genre"] = str(genres[2:-2])
result_dict["language"] = result.get("language", None)
result_dict["image_link"] = result.get("imageLinks", {}).get("thumbnail", None)
# make sure Google_Results accepts keyword arguments like title, author...
# and make them optional as they might not be in the returned result
gr = Google_Results(**result_dict)
results.append(gr) # add it to the results list
except ValueError:
return None # invalid response returned, you may raise an error instead
return results # return the results
Then you can easily retrieve as much info as possible for a term:
gr = book_search("Google")
And it will be far more tolerant of data omissions, provided that your Google_Results type makes most of the entries optional.
Following #Coldspeed's recommendation it became clear that missing information in the JSON file caused the exception to run. Since I only had a "pass" statement there it skipped the entire result. Therefore I will have to adapt the "Try and Except" statements so errors do get handled properly.
Thanks for the help guys!

Python - is there an elegant way to avoid dozens try/except blocks while getting data out of a json object?

I'm looking for ways to write functions like get_profile(js) but without all the ugly try/excepts.
Each assignment is in a try/except because occasionally the json field doesn't exist. I'd be happy with an elegant solution which defaulted everything to None even though I'm setting some defaults to [] and such, if doing so would make the overall code much nicer.
def get_profile(js):
""" given a json object, return a dict of a subset of the data.
what are some cleaner/terser ways to implement this?
There will be many other get_foo(js), get_bar(js) functions which
need to do the same general type of thing.
"""
d = {}
try:
d['links'] = js['entry']['gd$feedLink']
except:
d['links'] = []
try:
d['statisitcs'] = js['entry']['yt$statistics']
except:
d['statistics'] = {}
try:
d['published'] = js['entry']['published']['$t']
except:
d['published'] = ''
try:
d['updated'] = js['entry']['updated']['$t']
except:
d['updated'] = ''
try:
d['age'] = js['entry']['yt$age']['$t']
except:
d['age'] = 0
try:
d['name'] = js['entry']['author'][0]['name']['$t']
except:
d['name'] = ''
return d
Replace each of your try catch blocks with chained calls to the dictionary get(key [,default]) method. All calls to get before the last call in the chain should have a default value of {} (empty dictionary) so that the later calls can be called on a valid object, Only the last call in the chain should have the default value for the key that you are trying to look up.
See the python documentation for dictionairies http://docs.python.org/library/stdtypes.html#mapping-types-dict
For example:
d['links'] = js.get('entry', {}).get('gd$feedLink', [])
d['published'] = js.get('entry', {}).get('published',{}).get('$t', '')
Use get(key[, default]) method of dictionaries
Code generate this boilerplate code and save yourself even more trouble.
Try something like...
import time
def get_profile(js):
def cas(prev, el):
if hasattr(prev, "get") and prev:
return prev.get(el, prev)
return prev
def getget(default, *elements):
return reduce(cas, elements[1:], js.get(elements[0], default))
d = {}
d['links'] = getget([], 'entry', 'gd$feedLink')
d['statistics'] = getget({}, 'entry', 'yt$statistics')
d['published'] = getget('', 'entry', 'published', '$t')
d['updated'] = getget('', 'entry', 'updated', '$t')
d['age'] = getget(0, 'entry', 'yt$age', '$t')
d['name'] = getget('', 'entry', 'author', 0, 'name' '$t')
return d
print get_profile({
'entry':{
'gd$feedLink':range(4),
'yt$statistics':{'foo':1, 'bar':2},
'published':{
"$t":time.strftime("%x %X"),
},
'updated':{
"$t":time.strftime("%x %X"),
},
'yt$age':{
"$t":"infinity years",
},
'author':{0:{'name':{'$t':"I am a cow"}}},
}
})
It's kind of a leap of faith for me to assume that you've got a dictionary with a key of 0 instead of a list but... You get the idea.
You need to familiarise yourself with dictionary methods Check here for how to handle what you're asking.
Two possible solutions come to mind, without knowing more about how your data is structured:
if k in js['entry']:
something = js['entry'][k]
(though this solution wouldn't really get rid of your redundancy problem, it is more concise than a ton of try/excepts)
or
js['entry'].get(k, []) # or (k, None) depending on what you want to do
A much shorter version is just something like...
for k,v in js['entry']:
d[k] = v
But again, more would have to be said about your data.

Categories