I am trying the following code:
import inspect
def fn1(x):
print(1*x)
print(inspect.stack()[0][4]) #print fn1
def fn2(x):
print(2*x*x)
print(inspect.stack()[0][4]) #print fn2
def fn3(x):
print(3*x*x*x)
print(inspect.stack()[0][4]) #print fn3
class printFuncName():
def __init__(fn):
self.fn = fn
self.fn(12)
if __name__ == '__main__':
funcs = [fn1, fn2, fn3]
for ii in funcs:
printFuncName(ii)
But the print(inspect.stack()[0][4]) doesn't print the name of function. It prints ''.
I was expecting it to print 'fn1', 'fn2', 'fn3'
Edit:
Sorry seems like it was answered while I was editing the question
You could instead access the function attribute directly:
import inspect
def fn1(x):
print(1*x)
print(inspect.stack()[0].function)
def fn2(x):
print(2*x*x)
print(inspect.stack()[0].function)
def fn3(x):
print(3*x*x*x)
print(inspect.stack()[0].function)
funcs = [fn1, fn2, fn3]
for ii in funcs:
ii(12)
Outputs:
12
fn1
288
fn2
5184
fn3
Related
I have a dataframe like this:
name
cluster
'sock'
1
'graceful'
2
'disgrace'
2
'fixture'
3
'winnow'
4
'window'
4
and a function common_substring that takes in two strings and returns the longest common substring.
I want to return
name
cluster
'sock'
1
'grace'
2
'fixture'
3
'win'
4
I know I'm supposed to group by cluster, but I'm struggling with how to aggregate and apply a function that takes two values.
Based on the #jezrael and the link:
from functools import partial, reduce
from itertools import chain
from typing import Iterator
def ngram(seq: str, n: int) -> Iterator[str]:
return (seq[i: i+n] for i in range(0, len(seq)-n+1))
def allngram(seq: str) -> set:
lengths = range(len(seq))
ngrams = map(partial(ngram, seq), lengths)
return set(chain.from_iterable(ngrams))
def func(a, b):
seqs_ngrams = map(allngram, [a,b])
intersection = reduce(set.intersection, seqs_ngrams)
longest = max(intersection, key=len)
return longest
def f(x):
try:
return func(x.iat[0], x.iat[1])
except:
return 'Unique value'
df = df.groupby('cluster')['name'].agg(f).reset_index()
print (df)
Demonstration:
df = pd.DataFrame({'name':['winnow', 'window'], 'cluster':[4,4]})
df = df.groupby('cluster')['name'].agg(f).reset_index()
output:
For, any length input:
from functools import partial, reduce
from itertools import chain
from typing import Iterator
def ngram(seq: str, n: int) -> Iterator[str]:
return (seq[i: i+n] for i in range(0, len(seq)-n+1))
def allngram(seq: str) -> set:
lengths = range(len(seq)+1)
ngrams = map(partial(ngram, seq), lengths)
return set(chain.from_iterable(ngrams))
def func(seq):
seq=seq.values
seqs_ngrams = map(allngram, seq)
intersection = reduce(set.intersection, seqs_ngrams)
longest = max(intersection, key=len)
return longest
def f(x):
return func(x)
df = pd.DataFrame({'name':['winnow', 'window', 'win', 'sock', 'graceful', 'disgrace','fixture'], 'cluster':[4,4,4,1,2,2,3]})
df = df.groupby('cluster')['name'].agg(f).reset_index()
Ooutput:
Use GroupBy.agg with aggregate function for pass function if length of group is not 1, then pass all values in column in list:
#https://stackoverflow.com/questions/40556491
from functools import partial, reduce
from itertools import chain
from typing import Iterator
def ngram(seq: str, n: int) -> Iterator[str]:
return (seq[i: i+n] for i in range(0, len(seq)-n+1))
def allngram(seq: str) -> set:
lengths = range(len(seq)+1)
ngrams = map(partial(ngram, seq), lengths)
return set(chain.from_iterable(ngrams))
def func(x):
seqs_ngrams = map(allngram, x.tolist())
intersection = reduce(set.intersection, seqs_ngrams)
longest = max(intersection, key=len)
return longest
df['name'] = df['name'].str.strip("'")
df = df.groupby('cluster')['name'].agg(func).reset_index()
print (df)
cluster name
0 1 sock
1 2 grace
2 3 fixture
3 4 win
I am trying to scrape a html file that has a json object with all the required test case data , but processing of the json happens in "find" and "parseTestCaseDetails" method where iteratively i get the test case details , which i finally parse in "findInterestedFields" , so my requirement is to yield the details of test cases to a json file from the the last method called in the hierarchy i.e findInterestedFields , is it possible to achieve this??
Thanks in advance!
import scrapy
import datetime
import json
import re
import collections
import time
import os
import js2xml
from scrapy.selector import HtmlXPathSelector
class AltiplanoAVInprogressTCSpiderTest(scrapy.Spider):
name = "AltiplanoAVInprogressTCSpiderTest"
buildNumber = []
FormatedBuildTime = []
keys = []
testcaseName=''
testcaseSuit=''
testcaseDoc=''
def start_requests(self):
print os.environ["jenkinsdomain"]
urls = [
os.environ["jenkinsdomain"] + "/job/InprogressFlakyAndBlockedTestCaseDetails/lastSuccessfulBuild/"
]
for url in urls:
print url
yield scrapy.Request(url=url, callback=self.parse, errback=self.parseerror)
def parseerror(self, failure):
print failure
def parse(self, response):
hxs = HtmlXPathSelector(response)
buildNumberString = hxs.select('normalize-space(//*[#id="main-panel"]/h1/text())').extract_first()
self.buildNumber = buildNumberString.split("#")[-1].split("(")[0].strip()
buildTimeUnformatd = buildNumberString.split("(")[-1].split(")")[0].strip().replace("PM", "").replace("AM", "")
buildTimeUnformatd = buildTimeUnformatd.strip()
t = time.strptime(buildTimeUnformatd, "%b %d, %Y %I:%M:%S")
self.FormatedBuildTime = time.strftime('%d %b %y %H:%M IST', t)
static_testDetailsUrl = os.environ[
"jenkinsdomain"] + "XX/Inprogress-ANV.html"
yield scrapy.Request(url=static_testDetailsUrl, callback=self.parseTestDetails, errback=self.parseerror)
def find(self, key, dictionary):
for k, v in dictionary.iteritems():
if k == key:
yield v
self.parseTestCaseDetails(v)
elif isinstance(v, dict):
for result in self.find(key, v):
yield result
elif isinstance(v, list):
for d in v:
for result in self.find(key, d):
yield result
def parseTestCaseDetails(self, testcases):
# get the list of test cases and again parse them one by one to get the name and other fields
for testcase in testcases:
self.findInterestedFields(testcase)
def findInterestedFields(self, dictionary):
jsonLoad = json.dumps(dictionary, indent=4)
loaded_json = json.loads(jsonLoad)
readabledatetime = datetime.datetime.now().strftime("%d %b %y %H:%M IST")
for k, v in loaded_json.iteritems():
if k == "name":
testcaseName = v
if k == "fullName":
testcaseSuit = v
if k == "doc":
testcaseDoc = v
yield {"name":"avInprogresstestcases",'avInprogresstestcases':{
'testcaseName':testcaseName
}}
def parseTestDetails(self, response):
data = response.xpath('//script[4]/text()').extract_first().strip()
jstree = js2xml.parse(data)
testDetailsInJson = js2xml.jsonlike.getall(jstree)
jsonLoad = json.dumps(testDetailsInJson[0], indent=4)
loaded_json = json.loads(jsonLoad)
list(self.find('tests', loaded_json))
I want to perform a binary-search using e.g. np.searchsorted, however, I do not want to create an explicit array containing values. Instead, I want to define a function giving the value to be expected at the desired position of the array, e.g. p(i) = i, where i denotes the position within the array.
Generating an array of values regarding the function would, in my case, be neither efficient nor elegant. Is there any way to achieve this?
What about something like:
import collections
class GeneratorSequence(collections.Sequence):
def __init__(self, func, size):
self._func = func
self._len = size
def __len__(self):
return self._len
def __getitem__(self, i):
if 0 <= i < self._len:
return self._func(i)
else:
raise IndexError
def __iter__(self):
for i in range(self._len):
yield self[i]
This would work with np.searchsorted(), e.g.:
import numpy as np
gen_seq = GeneratorSequence(lambda x: x ** 2, 100)
np.searchsorted(gen_seq, 9)
# 3
You could also write your own binary search function, you do not really need NumPy in this case, and it can actually be beneficial:
def bin_search(seq, item):
first = 0
last = len(seq) - 1
found = False
while first <= last and not found:
midpoint = (first + last) // 2
if seq[midpoint] == item:
first = midpoint
found = True
else:
if item < seq[midpoint]:
last = midpoint - 1
else:
first = midpoint + 1
return first
Which gives identical results:
all(bin_search(gen_seq, i) == np.searchsorted(gen_seq, i) for i in range(100))
# True
Incidentally, this is also WAY faster:
gen_seq = GeneratorSequence(lambda x: x ** 2, 1000000)
%timeit np.searchsorted(gen_seq, 10000)
# 1 loop, best of 3: 1.23 s per loop
%timeit bin_search(gen_seq, 10000)
# 100000 loops, best of 3: 16.1 µs per loop
Inspired by #norok2 comment, I think you can use something like this:
def f(i):
return i*2 # Just an example
class MySeq(Sequence):
def __init__(self, f, maxi):
self.maxi = maxi
self.f = f
def __getitem__(self, x):
if x < 0 or x > self.maxi:
raise IndexError()
return self.f(x)
def __len__(self):
return self.maxi + 1
In this case f is your function while maxi is the maximum index. This of course only works if the function f return values in sorted order.
At this point you can use an object of type MySeq inside np.searchsorted.
Here is the code that I copy from another .py file and I got a TypeError
#coding:utf-8
import serial
import sys
import time
import logging
class TestRemoteControl(object):
def __init__(self,com):
self.ser = serial.Serial(com,115200)
self.ser.bytesize = 8
self.ser.stopbits = 1
self.logger = logging.getLogger()
self.logger.setLevel(logging.INFO)
self.formatter = logging.Formatter('%(asctime)-25s - %(name)s - %(levelname)s - %(message)s')
self.ch = logging.StreamHandler()
self.ch.setLevel(logging.INFO)
self.fh = logging.FileHandler('Test.txt')
self.fh.setLevel(logging.INFO)
self.fh.setFormatter(self.formatter)
self.ch.setFormatter(self.formatter)
self.logger.addHandler(self.ch)
self.logger.addFilter(self.fh)
def start_esc(self):
self.logger.info("开启电机")
self.ser.write("####1")
def stop_esc(self):
self.logger.info("关闭电机")
self.ser.write("####1")
time.sleep(0.4)
self.ser.write("####1")
time.sleep(0.4)
self.ser.write("####1")
time.sleep(0.4)
def speed_up(self):
self.logger.info("电机加速")
self.ser.write("####3")
def speed_down(self):
self.logger.info("电机减速")
self.ser.write("####2")
def main():
logging.basicConfig(level=logging.DEBUG,
format = '%(asctime)s %(filename)s[line:%(lineno)d] %(levelname)s %(message)s',
datefmt = '%a, %d %b %Y %H:%M:%S',
filename = 'myapp.log',
filemode = 'w')
print("please enter com num:")
a = raw_input()
temp_com = "com"+a
test_RC = TestRemoteControl(temp_com)
count = 1
max_count = int(raw_input('Please enter on-off counts'))
while count < max_count:
test_RC.start_esc()
# time.sleep(10)
# test_RC.speed_up()
time.sleep(2)
test_RC.stop_esc()
print "complete ",count," times "
time.sleep(1)
count += 1
if __name__ == "__main__":
main()
Here is the error, I don't kown why. Help me please.
TypeError:
unbound method init() must be called with TestRemoteControl instance as first argument (got nothing instead)
This code is OK.All the problem is the IDE "pycharm" that I can only run the unittest because I used the name "TestRemoteControl"
Considder the following interactive example
>>> l=imap(str,xrange(1,4))
>>> list(l)
['1', '2', '3']
>>> list(l)
[]
Does anyone know if there is already an implementation somewhere out there with a version of imap (and the other itertools functions) such that the second time list(l) is executed you get the same as the first. And I don't want the regular map because building the entire output in memory can be a waste of memory if you use larger ranges.
I want something that basically does something like
class cmap:
def __init__(self, function, *iterators):
self._function = function
self._iterators = iterators
def __iter__(self):
return itertools.imap(self._function, *self._iterators)
def __len__(self):
return min( map(len, self._iterators) )
But it would be a waste of time to do this manually for all itertools if someone already did this.
ps.
Do you think containers are more zen then iterators since for an iterator something like
for i in iterator:
do something
implicitly empties the iterator while a container you explicitly need to remove elements.
You do not have to build such an object for each type of container. Basically, you have the following:
mkimap = lambda: imap(str,xrange(1,4))
list(mkimap())
list(mkimap())
Now you onlky need a nice wrapping object to prevent the "ugly" function calls. This could work this way:
class MultiIter(object):
def __init__(self, f, *a, **k):
if a or k:
self.create = lambda: f(*a, **k)
else: # optimize
self.create = f
def __iter__(self):
return self.create()
l = MultiIter(lambda: imap(str, xrange(1,4)))
# or
l = MultiIter(imap, str, xrange(1,4))
# or even
#MultiIter
def l():
return imap(str, xrange(1,4))
# and then
print list(l)
print list(l)
(untested, hope it works, but you should get the idea)
For your 2nd question: Iterators and containers both have their uses. You should take whatever best fits your needs.
You may be looking for itertools.tee()
Iterators are my favorite topic ;)
from itertools import imap
class imap2(object):
def __init__(self, f, *args):
self.g = imap(f,*args)
self.lst = []
self.done = False
def __iter__(self):
while True:
try: # try to get something from g
x = next(self.g)
except StopIteration:
if self.done:
# give the old values
for x in self.lst:
yield x
else:
# g was consumed for the first time
self.done = True
return
else:
self.lst.append(x)
yield x
l=imap2(str,xrange(1,4))
print list(l)
print list(l)