Python, class attribute error - python

I have a set of code that looks like this:
class DataFilter:
def __init__(self, csvData):
# converts csv string data to float lists, if possible
data = []
for line in csvData:
try:
line = line.split(',')
except:
print(line)
return
for i in range( len(line) ):
try:
line[i] = float(line[i])
except ValueError:
pass
data.append(line)
self.data = data
def find_depth_index(self, depth):
for index, line in enumerate( self.data ):
if line[1] > depth:
return index
def remove_above_depth(self, depth):
index = self.find_depth_index( depth )
return self.data[ index: ]
def remove_beyond_depth(self, depth):
index = self.find_depth_index(depth)
return self.data[ :index ]
data = DataFilter(data).remove_above_depth(SURF_CASING_DEPTH)
print('-----------------------')
data = DataFilter(data).remove_beyond_depth(VERTICAL_SEC_DEPTH)
Then it give me an error:
File "C:/Users/Eric Soobin Kim/PycharmProjects/untitled/RAPID_use_filtered_data.py", line 35, in remove_beyond_depth
def remove_beyond_depth(self, depth):
File "C:/Users/Eric Soobin Kim/PycharmProjects/untitled/RAPID_use_filtered_data.py", line 26, in find_depth_index
def find_depth_index(self, depth):
AttributeError: 'DataFilter' object has no attribute 'data'
The thing that I don't understand is that, it ran without a problem for the line:
data = DataFilter(data).remove_above_depth(SURF_CASING_DEPTH)
but its not working for,
data = DataFilter(data).remove_beyond_depth(VERTICAL_SEC_DEPTH)
I think my first filtering somehow alters elements in __ini__(), but i don't know what's going on. Why is this happening, and how can i fix it?

You've reassigned data to be equal to something other than what you want.
data = DataFilter(data).remove_above_depth(SURF_CASING_DEPTH)
This means that now you've lost the pointer to data that you once had. Might I suggest making a copy like
new_data = DataFilter(data).remove_above_depth(SURF_CASING_DEPTH)
new_data2 = DataFilter(data).remove_beyond_depth(VERTICAL_SEC_DEPTH)
This way you still have the reference to the old data variable

Object has no attribute data because you didnt give it the attribute.
atributes are defined by making writing:
self.object = []
instead of:
object = []

Related

Is there a way to give a function access to the (external-scope) name of the variable being passed in? [duplicate]

This question already has answers here:
Getting the name of a variable as a string
(32 answers)
Closed 4 months ago.
Is it possible to get the original variable name of a variable passed to a function? E.g.
foobar = "foo"
def func(var):
print var.origname
So that:
func(foobar)
Returns:
>>foobar
EDIT:
All I was trying to do was make a function like:
def log(soup):
f = open(varname+'.html', 'w')
print >>f, soup.prettify()
f.close()
.. and have the function generate the filename from the name of the variable passed to it.
I suppose if it's not possible I'll just have to pass the variable and the variable's name as a string each time.
EDIT: To make it clear, I don't recommend using this AT ALL, it will break, it's a mess, it won't help you in any way, but it's doable for entertainment/education purposes.
You can hack around with the inspect module, I don't recommend that, but you can do it...
import inspect
def foo(a, f, b):
frame = inspect.currentframe()
frame = inspect.getouterframes(frame)[1]
string = inspect.getframeinfo(frame[0]).code_context[0].strip()
args = string[string.find('(') + 1:-1].split(',')
names = []
for i in args:
if i.find('=') != -1:
names.append(i.split('=')[1].strip())
else:
names.append(i)
print names
def main():
e = 1
c = 2
foo(e, 1000, b = c)
main()
Output:
['e', '1000', 'c']
To add to Michael Mrozek's answer, you can extract the exact parameters versus the full code by:
import re
import traceback
def func(var):
stack = traceback.extract_stack()
filename, lineno, function_name, code = stack[-2]
vars_name = re.compile(r'\((.*?)\).*$').search(code).groups()[0]
print vars_name
return
foobar = "foo"
func(foobar)
# PRINTS: foobar
Looks like Ivo beat me to inspect, but here's another implementation:
import inspect
def varName(var):
lcls = inspect.stack()[2][0].f_locals
for name in lcls:
if id(var) == id(lcls[name]):
return name
return None
def foo(x=None):
lcl='not me'
return varName(x)
def bar():
lcl = 'hi'
return foo(lcl)
bar()
# 'lcl'
Of course, it can be fooled:
def baz():
lcl = 'hi'
x='hi'
return foo(lcl)
baz()
# 'x'
Moral: don't do it.
Another way you can try if you know what the calling code will look like is to use traceback:
def func(var):
stack = traceback.extract_stack()
filename, lineno, function_name, code = stack[-2]
code will contain the line of code that was used to call func (in your example, it would be the string func(foobar)). You can parse that to pull out the argument
You can't. It's evaluated before being passed to the function. All you can do is pass it as a string.
#Ivo Wetzel's answer works in the case of function call are made in one line, like
e = 1 + 7
c = 3
foo(e, 100, b=c)
In case that function call is not in one line, like:
e = 1 + 7
c = 3
foo(e,
1000,
b = c)
below code works:
import inspect, ast
def foo(a, f, b):
frame = inspect.currentframe()
frame = inspect.getouterframes(frame)[1]
string = inspect.findsource(frame[0])[0]
nodes = ast.parse(''.join(string))
i_expr = -1
for (i, node) in enumerate(nodes.body):
if hasattr(node, 'value') and isinstance(node.value, ast.Call)
and hasattr(node.value.func, 'id') and node.value.func.id == 'foo' # Here goes name of the function:
i_expr = i
break
i_expr_next = min(i_expr + 1, len(nodes.body)-1)
lineno_start = nodes.body[i_expr].lineno
lineno_end = nodes.body[i_expr_next].lineno if i_expr_next != i_expr else len(string)
str_func_call = ''.join([i.strip() for i in string[lineno_start - 1: lineno_end]])
params = str_func_call[str_func_call.find('(') + 1:-1].split(',')
print(params)
You will get:
[u'e', u'1000', u'b = c']
But still, this might break.
You can use python-varname package
from varname import nameof
s = 'Hey!'
print (nameof(s))
Output:
s
Package below:
https://github.com/pwwang/python-varname
For posterity, here's some code I wrote for this task, in general I think there is a missing module in Python to give everyone nice and robust inspection of the caller environment. Similar to what rlang eval framework provides for R.
import re, inspect, ast
#Convoluted frame stack walk and source scrape to get what the calling statement to a function looked like.
#Specifically return the name of the variable passed as parameter found at position pos in the parameter list.
def _caller_param_name(pos):
#The parameter name to return
param = None
#Get the frame object for this function call
thisframe = inspect.currentframe()
try:
#Get the parent calling frames details
frames = inspect.getouterframes(thisframe)
#Function this function was just called from that we wish to find the calling parameter name for
function = frames[1][3]
#Get all the details of where the calling statement was
frame,filename,line_number,function_name,source,source_index = frames[2]
#Read in the source file in the parent calling frame upto where the call was made
with open(filename) as source_file:
head=[source_file.next() for x in xrange(line_number)]
source_file.close()
#Build all lines of the calling statement, this deals with when a function is called with parameters listed on each line
lines = []
#Compile a regex for matching the start of the function being called
regex = re.compile(r'\.?\s*%s\s*\(' % (function))
#Work backwards from the parent calling frame line number until we see the start of the calling statement (usually the same line!!!)
for line in reversed(head):
lines.append(line.strip())
if re.search(regex, line):
break
#Put the lines we have groked back into sourcefile order rather than reverse order
lines.reverse()
#Join all the lines that were part of the calling statement
call = "".join(lines)
#Grab the parameter list from the calling statement for the function we were called from
match = re.search('\.?\s*%s\s*\((.*)\)' % (function), call)
paramlist = match.group(1)
#If the function was called with no parameters raise an exception
if paramlist == "":
raise LookupError("Function called with no parameters.")
#Use the Python abstract syntax tree parser to create a parsed form of the function parameter list 'Name' nodes are variable names
parameter = ast.parse(paramlist).body[0].value
#If there were multiple parameters get the positional requested
if type(parameter).__name__ == 'Tuple':
#If we asked for a parameter outside of what was passed complain
if pos >= len(parameter.elts):
raise LookupError("The function call did not have a parameter at postion %s" % pos)
parameter = parameter.elts[pos]
#If there was only a single parameter and another was requested raise an exception
elif pos != 0:
raise LookupError("There was only a single calling parameter found. Parameter indices start at 0.")
#If the parameter was the name of a variable we can use it otherwise pass back None
if type(parameter).__name__ == 'Name':
param = parameter.id
finally:
#Remove the frame reference to prevent cyclic references screwing the garbage collector
del thisframe
#Return the parameter name we found
return param
If you want a Key Value Pair relationship, maybe using a Dictionary would be better?
...or if you're trying to create some auto-documentation from your code, perhaps something like Doxygen (http://www.doxygen.nl/) could do the job for you?
I wondered how IceCream solves this problem. So I looked into the source code and came up with the following (slightly simplified) solution. It might not be 100% bullet-proof (e.g. I dropped get_text_with_indentation and I assume exactly one function argument), but it works well for different test cases. It does not need to parse source code itself, so it should be more robust and simpler than previous solutions.
#!/usr/bin/env python3
import inspect
from executing import Source
def func(var):
callFrame = inspect.currentframe().f_back
callNode = Source.executing(callFrame).node
source = Source.for_frame(callFrame)
expression = source.asttokens().get_text(callNode.args[0])
print(expression, '=', var)
i = 1
f = 2.0
dct = {'key': 'value'}
obj = type('', (), {'value': 42})
func(i)
func(f)
func(s)
func(dct['key'])
func(obj.value)
Output:
i = 1
f = 2.0
s = string
dct['key'] = value
obj.value = 42
Update: If you want to move the "magic" into a separate function, you simply have to go one frame further back with an additional f_back.
def get_name_of_argument():
callFrame = inspect.currentframe().f_back.f_back
callNode = Source.executing(callFrame).node
source = Source.for_frame(callFrame)
return source.asttokens().get_text(callNode.args[0])
def func(var):
print(get_name_of_argument(), '=', var)
If you want to get the caller params as in #Matt Oates answer answer without using the source file (ie from Jupyter Notebook), this code (combined from #Aeon answer) will do the trick (at least in some simple cases):
def get_caller_params():
# get the frame object for this function call
thisframe = inspect.currentframe()
# get the parent calling frames details
frames = inspect.getouterframes(thisframe)
# frame 0 is the frame of this function
# frame 1 is the frame of the caller function (the one we want to inspect)
# frame 2 is the frame of the code that calls the caller
caller_function_name = frames[1][3]
code_that_calls_caller = inspect.findsource(frames[2][0])[0]
# parse code to get nodes of abstract syntact tree of the call
nodes = ast.parse(''.join(code_that_calls_caller))
# find the node that calls the function
i_expr = -1
for (i, node) in enumerate(nodes.body):
if _node_is_our_function_call(node, caller_function_name):
i_expr = i
break
# line with the call start
idx_start = nodes.body[i_expr].lineno - 1
# line with the end of the call
if i_expr < len(nodes.body) - 1:
# next expression marks the end of the call
idx_end = nodes.body[i_expr + 1].lineno - 1
else:
# end of the source marks the end of the call
idx_end = len(code_that_calls_caller)
call_lines = code_that_calls_caller[idx_start:idx_end]
str_func_call = ''.join([line.strip() for line in call_lines])
str_call_params = str_func_call[str_func_call.find('(') + 1:-1]
params = [p.strip() for p in str_call_params.split(',')]
return params
def _node_is_our_function_call(node, our_function_name):
node_is_call = hasattr(node, 'value') and isinstance(node.value, ast.Call)
if not node_is_call:
return False
function_name_correct = hasattr(node.value.func, 'id') and node.value.func.id == our_function_name
return function_name_correct
You can then run it as this:
def test(*par_values):
par_names = get_caller_params()
for name, val in zip(par_names, par_values):
print(name, val)
a = 1
b = 2
string = 'text'
test(a, b,
string
)
to get the desired output:
a 1
b 2
string text
Since you can have multiple variables with the same content, instead of passing the variable (content), it might be safer (and will be simpler) to pass it's name in a string and get the variable content from the locals dictionary in the callers stack frame. :
def displayvar(name):
import sys
return name+" = "+repr(sys._getframe(1).f_locals[name])
If it just so happens that the variable is a callable (function), it will have a __name__ property.
E.g. a wrapper to log the execution time of a function:
def time_it(func, *args, **kwargs):
start = perf_counter()
result = func(*args, **kwargs)
duration = perf_counter() - start
print(f'{func.__name__} ran in {duration * 1000}ms')
return result

Python Pickle not saving entire object

I'm trying to pickle out a list of objects where the objects contain a list. When I open the pickled file I can see any data in my objects except from the list. I'm putting code below so this makes more sense.
Object that contains a list.
class TestPickle:
testNumber = None
testList = []
def addNumber(self, value):
self.testNumber = value
def getNumber(self):
return self.testNumber
def addTestList(self, value):
self.testList.append(value)
def getTestList(self):
return self.testList
This example I create a list of the above object (I'm adding one object to keep it brief)
testPKL = TestPickle()
testList = []
testPKL.addNumber(12)
testPKL.addTestList(1)
testPKL.addTestList(2)
testList.append(testPKL)
with open(os.path.join(os.path.curdir, 'test.pkl'), 'wb') as f:
pickle.dump(testList, f)
Here is an example of me opening the pickled file and trying to access the data, I can only retrieve the testNumber from above, the testList returns a empty list.
pklResult = None
with open(os.path.join(os.path.curdir, 'test.pkl'), 'rb') as f:
pklResult = pickle.load(f)
for result in pklResult:
print result.getNumber() # returns 12
print result.testNumber # returns 12
print result.getTestList() # returns []
print result.testList # returns []
I think i'm missing something obvious here but I'm not having any luck spotting it. Thanks for any guidance.
testNumber and testList both are class attributes initially. testNumber is of immutable type hence modifying it create new instance attribute, But testList is of mutable type and can be modified in place. Hence modifying testList doesn't create new instance attribute and it remains as class attribute.
You can verify it -
print testPKL.__dict__
{'testNumber': 12}
print result.__dict__
{'testNumber': 12}
So when you access result.testList, it looks for class attribute TestPickle.testList, which is [] in your case.
Solution
You are storing instance in pickle so use instance attribute. Modify TestPickle class as below -
class TestPickle:
def __init__(self):
self.testNumber = None
self.testList = []
def addNumber(self, value):
self.testNumber = value
def getNumber(self):
return self.testNumber
def addTestList(self, value):
self.testList.append(value)
def getTestList(self):
return self.testList

Error: 'return' outside of function

Error: 'return' outside of function
Why??
def get_all_students(self):
database = open(self.database_path, 'r')
list_of_students = list()
for idx, l in enumerate(database.readlines()):
params = list()
params.append(idx)
params += l.split(self.data_delimiter)
student = Student(*self.item_un_escape(params))
list_of_students.append(student)
return list_of_students
Edit: I'll post the rest of the class, I'm pretty sure it's correctly indented though. Can't seem to find the error, I can bet it's probably something silly. Apologies, first time coding in python but this error has been annoying me for like an hour or so! haha
Edit2: It's throwing an error on params.append(idx) saying unexpected indentation?
from student import Student
database_path = 'C:/Users/Alan/Desktop/flask/flask/app/database'
class Database(object):
data_delimiter = ','
#staticmethod
def escape_new_lines(value):
if type(value) == str:
value = value.replace('\n', '#n-nl#')
value = value.replace('\r', '#r-nl#')
return value
#staticmethod
def un_escape_new_lines(value):
if type(value) == str:
value = value.replace('#n-nl#', '\n')
value = value.replace('#r-nl#', '\r')
return value
def __init__(self, database_path=database_path):
self.database_path = database_path
def get_all_students(self):
database = open(self.database_path, 'r')
list_of_students = list()
for idx, l in enumerate(database.readlines()):
params = list()
params.append(idx)
params += l.split(self.data_delimiter)
student = Student(*self.item_un_escape(params))
list_of_students.append(student)
return list_of_students
The code you have posted is fine. Your likely error is from missing an indent before a return statement. EDIT: As #Anonymous has noted in the comments, another possibility as that you're mixing tab indents with space indents. Check your indentations.

Python: List is replaced by the new list

I got a question regarding list within python. I use the append method to actually append values to my list, now it only replaced the list with new values.
This is my code:
def init(serial):
serial_number = serial
api_call = "http://wwww.herecomesmyhyperlink/"+serial_number
result = []
with open('allserials.csv') as csvfile:
reader = csv.reader(csvfile, delimiter=';', quotechar='|')
for row in reader:
if row[0].strip() == api_call:
result.append(row[1].strip())
call_api(serial_number,result)
return
def call_api(get_serial,get_result):
list_serial = []
for i in range(len(get_result)):
# do an api call
....
# get result of api call
list_serial.append(api_result)
sort_serials(list_serial)
return
def sort_serials(get_list_serial)
sorted_list_serial = sorted(get_list_serial, reverse=True)
print(sorted_list_serial)
max_results = 10
length_of_sorted_list_serial = len(get_list_serial)
if length_of_sorted_list_serial < max_results:
get_first_list_element = sorted_list_serial[0]
get_second_element_of_that_list = get_first_list_element[1]
init(get_second_element_of_that_list)
else:
print("it is not smaller")
return
print(init('1320739'))
sorted_list_serial would contain something like: [rankingid,serial,title].
get_second_element_of_that_list: [serial]
The thing is that when I run my code I got the following results:
s: 1320739, max result:10 length of the list:3
s: 1523039, max result:10 length of the list:9
What the code does is that instead of having a list of 12 items, it replace the list with the 3 items with the new list of 9 items.
What I want is to actually have a new list containing 12 items, so that the first 3 items are still within the list and the 9 other elements are added to the original list.
The list is scoped to the function call_api() so pull it out, or pass it to each function, or create a class.
def init(serial):
serial_number = serial
result = []
with open('allserials.csv') as csvfile:
result.append()
return result
def call_api(get_serial,get_result):
# list_serial = []
#
# Move this out
# Or pass it along to each function
for i in range(len(get_result)):
# do an api call
....
# get result of api call
list_serial.append(api_result)
return list_serial
def sort_serials(get_list_serial)
sorted_list_serial = sorted(get_list_serial, reverse=True)
max_results = 10
length_of_sorted_list_serial = len(get_list_serial)
if length_of_sorted_list_serial < max_results:
get_first_list_element = sorted_list_serial[0]
get_second_element_of_that_list = get_first_list_element[1]
else:
print("it is not smaller")
return {'get_second_element_of_that_list':get_second_element_of_that_list, 'sorted_serial_list':sorted_serial_list}
So scope it to the same function, and have the other functions return results:
def run():
list_serial = []
serial_number = '1320739'
result = init(serial_number)
# here the items get set
list_serial = call_api(serial_number,result)
# here they get sorted
serial_sorted = sort_serials(list_serial)
# list serial is now the sorted list
list_serial = serial_sorted['sorted_serial_list']
get_second_element_of_that_list = serial_sorted['get_second_element_of_that_list']
init(get_second_element_of_that_list)
Or redefine how its passed:
serial_number = '1320739'
init(serial_number, list_serial)
call_api(serial_number,result, list_serial)
sort_serials(list_serial)
init(get_second_element_of_that_list, list_serial)
Or just pull it out:
.
.
.
list_serial = []
print(init('1320739'))
Or create a class:
class SomeClassNameHere(object):
def __init__(self,serialnumber=None, item2=''):
self.serialnumber = serialnumber
self.item3 = item2
self.listserial = []
self.run(item2)
def doOtherStuff(self):
# self.listserial will be updated
self.listserial = [1,2,3]
print(self.item3)
print(self.serialnumber)
def run(self,passeditem2):
print('Item2 has been passed: {0}'.format(passeditem2))
print('listserial not updated:',self.listserial)
self.doOtherStuff()
print('listserial updated:',self.listserial)
here = SomeClassNameHere(serialnumber='456',item2='somestring')
print(here.serialnumber)
print(here.item3)
here.run()
here.doOtherStuff()

How to Build a dictionary from a text file in Python

I have a text file with entries that look like this :
JohnDoe
Assignment 9
Reading: NO
header: NO
HW: NO
Solutions: 0
show: NO
Journals: NO
free: NO
Finished: NO
Quiz: 0
Done
Assignment 3
E-book: NO
HW: NO
Readings: NO
Show: 0
Journal: NO
Study: NO
Test: NO
Finished: NO
Quiz: 0
Done
This is a small sample. The file has several students in it. Each student has two assignments under their name and they only pass if the line that starts with "Finished" in each assignment reads "Finished: YES". All of the data under each assignment is disorganized, but somewhere under each assignment a line will say "Finished: YES (or NO)" I need a way to read the file and say whether or not any of the students have passed. So far, I have
def get_entries( file ):
with open( "dicrete.txt.rtf", 'rt') as file:
for line in file:
if "Finished" in line:
finished, answer = line.split(':')
yield finished, answer
# dict takes a sequence of `(key, value)` pairs and turns in into a dict
print dict(get_entries( file ))
I can only get this code to return a single entry (the first "Finished" it reads as key and "YES or NO" as value, which is what I want, but I want it to return Every line in the file that that starts with "Finished". So the sample data I provided I want to return a dict with 2 entries {Finished:"NO" , Finished:"NO"}
Dictionaries can only store one mapping per key. So, you can never have a dictionary that has two different entries for the same key.
Consider using a list of two-tuples instead, like [("Finished", "NO"), ("Finished", "NO")].
Sounds like you need a better data model! Let's look at that, shall we?
Let's define an Assignment class that we can call with all the lines of text between Assignment: # and Finished: YES/NO.
class Assignment(object):
def __init__(self, id, *args, **kwargs):
self.id = id
for key,val in kwargs.items():
setattr(self, key.lower(), val)
finished = getattr(self, 'finished', None)
if finished is None:
raise AttributeError("All assignments must have a 'finished' value")
else:
self.finished = True if finished.lower() == "yes" else False
#classmethod
def from_string(cls, s):
"""Builds an Assignment object from a string
a = Assignment.from_string('''Assignment: 1\nAttributes: Go Here\nFinished: yes''')
>>> a.id
1
>>> a.finished
True"""
d = dict()
id = None
for line in s.splitlines():
key,*val = map(str.strip, line.split(":"))
val = ' '.join(val) or None
if key.lower().startswith('assignment'):
id = int(key.split()[-1])
continue
d[key.lower()] = val
if id is not None:
return cls(id, **d)
else:
raise ValueError("No 'Assignment' field in string {}".format(s))
Once you have your model, you'll need to parse your input. Luckily this is actually pretty simple.
def splitlineson(s, sentinel):
"""splits an iterable of strings into a newline separated string beginning with each sentinel.
>>> s = ["Garbage", "lines", "SENT$", "first", "group", "SENT$", "second", "group"]
>>> splitlineson(s, "SENT$")
iter("SENT$\nfirst\ngroup",
"SENT$\nsecond\ngroup")"""
lines = []
for line in s:
if line.lower().strip().startswith(sentinel.lower()):
if any((sentinel.lower() in line.lower() for line in lines)):
yield "\n".join(lines)
lines = [line.strip()]
else:
if line:
lines.append(line.strip())
yield "\n".join(lines)
with open('path/to/textfile.txt') as inf:
assignments = splitlineson(inf, "assignment ")
assignment_list = [Assignment.from_string(a) for a in assignments]

Categories