Creating loop for __main__ - python

I am new to Python, and I want your advice on something.
I have a script that runs one input value at a time, and I want it to be able to run a whole list of such values without me typing the values one at a time. I have a hunch that a "for loop" is needed for the main method listed below. The value is "gene_name", so effectively, i want to feed in a list of "gene_names" that the script can run through nicely.
Hope I phrased the question correctly, thanks! The chunk in question seems to be
def get_probes_from_genes(gene_names)
import json
import urllib2
import os
import pandas as pd
api_url = "http://api.brain-map.org/api/v2/data/query.json"
def get_probes_from_genes(gene_names):
if not isinstance(gene_names,list):
gene_names = [gene_names]
#in case there are white spaces in gene names
gene_names = ["'%s'"%gene_name for gene_name in gene_names]**
api_query = "?criteria=model::Probe"
api_query= ",rma::criteria,[probe_type$eq'DNA']"
api_query= ",products[abbreviation$eq'HumanMA']"
api_query= ",gene[acronym$eq%s]"%(','.join(gene_names))
api_query= ",rma::options[only$eq'probes.id','name']"
data = json.load(urllib2.urlopen(api_url api_query))
d = {probe['id']: probe['name'] for probe in data['msg']}
if not d:
raise Exception("Could not find any probes for %s gene. Check " \
"http://help.brain- map.org/download/attachments/2818165/HBA_ISH_GeneList.pdf? version=1&modificationDate=1348783035873 " \
"for list of available genes."%gene_name)
return d
def get_expression_values_from_probe_ids(probe_ids):
if not isinstance(probe_ids,list):
probe_ids = [probe_ids]
#in case there are white spaces in gene names
probe_ids = ["'%s'"%probe_id for probe_id in probe_ids]
api_query = "? criteria=service::human_microarray_expression[probes$in%s]"% (','.join(probe_ids))
data = json.load(urllib2.urlopen(api_url api_query))
expression_values = [[float(expression_value) for expression_value in data["msg"]["probes"][i]["expression_level"]] for i in range(len(probe_ids))]
well_ids = [sample["sample"]["well"] for sample in data["msg"] ["samples"]]
donor_names = [sample["donor"]["name"] for sample in data["msg"] ["samples"]]
well_coordinates = [sample["sample"]["mri"] for sample in data["msg"] ["samples"]]
return expression_values, well_ids, well_coordinates, donor_names
def get_mni_coordinates_from_wells(well_ids):
package_directory = os.path.dirname(os.path.abspath(__file__))
frame = pd.read_csv(os.path.join(package_directory, "data", "corrected_mni_coordinates.csv"), header=0, index_col=0)
return list(frame.ix[well_ids].itertuples(index=False))
if __name__ == '__main__':
probes_dict = get_probes_from_genes("SLC6A2")
expression_values, well_ids, well_coordinates, donor_names = get_expression_values_from_probe_ids(probes_dict.keys())
print get_mni_coordinates_from_wells(well_ids)

whoa, first things first. Python ain't Java, so do yourself a favor and use a nice """xxx\nyyy""" string, with triple quotes to multiline.
api_query = """?criteria=model::Probe"
,rma::criteria,[probe_type$eq'DNA']
...
"""
or something like that. you will get white spaces as typed, so you may need to adjust.
If, like suggested, you opt to loop on the call to your function through a file, you will need to either try/except your data-not-found exception or you will need to handle missing data without throwing an exception. I would opt for returning an empty result myself and letting the caller worry about what to do with it.
If you do opt for raise-ing an Exception, create your own, rather than using a generic exception. That way your code can catch your expected Exception first.
class MyNoDataFoundException(Exception):
pass
#replace your current raise code with...
if not d:
raise MyNoDataFoundException(your message here)
clarification about catching exceptions, using the accepted answer as a starting point:
if __name__ == '__main__':
with open(r"/tmp/genes.txt","r") as f:
for line in f.readlines():
#keep track of your input data
search_data = line.strip()
try:
probes_dict = get_probes_from_genes(search_data)
except MyNoDataFoundException, e:
#and do whatever you feel you need to do here...
print "bummer about search_data:%s:\nexception:%s" % (search_data, e)
expression_values, well_ids, well_coordinates, donor_names = get_expression_values_from_probe_ids(probes_dict.keys())
print get_mni_coordinates_from_wells(well_ids)

You may want to create a file with Gene names, then read content of the file and call your function in the loop. Here is an example below
if __name__ == '__main__':
with open(r"/tmp/genes.txt","r") as f:
for line in f.readlines():
probes_dict = get_probes_from_genes(line.strip())
expression_values, well_ids, well_coordinates, donor_names = get_expression_values_from_probe_ids(probes_dict.keys())
print get_mni_coordinates_from_wells(well_ids)

Related

Generate a text file according to the successful steps. - Possible improvement of the code or other way of doing it?

I would like to keep track of the steps taken by the program in a text report file. Each step in the code returns a dataframe and there is a dependency between tasks (task n cannot be executed if task n-1 had found nothing).
My programme looks like this:
(kind of pseudo code)
import pandas as pd
step_1 = find_stuff()
if not step_1.empty:
step_2 = find_new_stuff()
if not step_2.empty:
step_3 = find_new_stuff_again()
if not step_3.empty:
report (step_1, step_2, step_3)
else:
report (step_1, step_2, step_3=pd.DataFrame())
else:
report (step_1, step_2=pd.DataFrame(), step_3=pd.DataFrame())
else:
report (step_1=pd.DataFrame(), step_2=pd.DataFrame(), step_3=pd.DataFrame())
def report (step_1, step_2, step_3) :
report_file = open("report.txt", "a")
if not step_1.empty:
report_file.write(f'Here what was found for step 1 \n : { step_1} \n')
if not step_2.empty:
report_file.write(f'Here what was found for step 2 \n : { step_2} \n')
if not step_3.empty:
report_file.write(f'Here what was found for step 3 \n : { step_3} \n')
else:
report_file.write('Nothing was found \n')
This way of doing things is very basic but does what I ask it to do. Though, I was wondering if there was a way to avoid/reduce all these "if" or an alternative way to generate this kind of report?
My answer is similar to #Nik's so that you need to iterate over some functions but I added it to a class so you can have the state together with the functions in the same scope. I also changed you file opening to use with as it is considered the safe way to handle files:
class StepFailedException(Exception): pass
class StuffFinder:
def __init__(self):
self.findings = []
def find_stuff_1(self):
stuff = None
# find stuff
if stuff.empty:
raise StepFailedException
self.findings.append(stuff)
def find_stuff_2(self):
stuff = None
# find stuff
if stuff.empty:
raise StepFailedException
self.findings.append(stuff)
def find_stuff_3(self):
stuff = None
# find stuff
if stuff.empty:
raise StepFailedException
self.findings.append(stuff)
def report(self):
if self.findings:
with open("report.txt", "a") as report_file:
for i,stuff in enumerate(self.findings):
report_file.write(f'Here what was found for step {i+1} \n : { stuff } \n')
def clear(self):
self.findings.clear()
def find_stuff(self):
self.clear()
try:
self.find_stuff_1()
self.find_stuff_2()
self.find_stuff_3()
except StepFailedException as e:
# handle exception if necessary
pass
self.report()
sf = StuffFinder() # you could add some initial values as argument to the constructor
sf.find_stuff()
# OR go step by step
sf.clear()
sf.find_stuff_1()
# sf.find_stuff_2() let's skip this one
sf.find_stuff_3()
sf.report()
In principle, I think your code is readable and gets the job done. However, if you have a lot of steps, you might want to iterate over them.
Here is an example:
import pandas as pd
def report(steps):
report_file = open("report.txt", "a")
for i, s in enumerate(steps):
report_file.write(f"Here what was found for step {i+1} \n : { s} \n")
steps = []
find_functions = [find_stuff, find_new_stuff, find_new_stuff_again]
for f in find_functions:
found_stuff = f()
if found_stuff.empty:
break
steps.append(found_stuff)
report(steps)
Also, mind that you are currently opening your report in "a" mode, so it will append results if you rerun the code.

Weird sequence when writing into txt document

Hi everyone this is my first time here, and I am a beginner in Python. I am in the middle of writing a program that returns a txt document containing information about a stock (Watchlist Info.txt), based on the input of another txt document containing the company names (Watchlist).
To achieve this, I have written 3 functions, of which 2 functions reuters_ticker() and stock_price() are completed as shown below:
def reuters_ticker(desired_search):
#from company name execute google search for and return reuters stock ticker
try:
from googlesearch import search
except ImportError:
print('No module named google found')
query = desired_search + ' reuters'
for j in search(query, tld="com.sg", num=1, stop=1, pause=2):
result = j
ticker = re.search(r'\w+\.\w+$', result)
return ticker.group()
Stock Price:
def stock_price(company, doc=None):
ticker = reuters_ticker(company)
request = 'https://www.reuters.com/companies/' + ticker
raw_main = pd.read_html(request)
data1 = raw_main[0]
data1.set_index(0, inplace=True)
data1 = data1.transpose()
data2 = raw_main[1]
data2.set_index(0, inplace=True)
data2 = data2.transpose()
stock_info = pd.concat([data1,data2], axis=1)
if doc == None:
print(company + '\n')
print('Previous Close: ' + str(stock_info['Previous Close'][1]))
print('Forward PE: ' + str(stock_info['Forward P/E'][1]))
print('Div Yield(%): ' + str(stock_info['Dividend (Yield %)'][1]))
else:
from datetime import date
with open(doc, 'a') as output:
output.write(date.today().strftime('%d/%m/%y') + '\t' + str(stock_info['Previous Close'][1]) + '\t' + str(stock_info['Forward P/E'][1]) + '\t' + '\t' + str(stock_info['Dividend (Yield %)'][1]) + '\n')
output.close()
The 3rd function, watchlist_report(), is where I am getting problems with writing the information in the format as desired.
def watchlist_report(watchlist):
with open(watchlist, 'r') as companies, open('Watchlist Info.txt', 'a') as output:
searches = companies.read()
x = searches.split('\n')
for i in x:
output.write(i + ':\n')
stock_price(i, doc='Watchlist Info.txt')
output.write('\n')
When I run watchlist_report('Watchlist.txt'), where Watchlist.txt contains 'Apple' and 'Facebook' each on new lines, my output is this:
26/04/20 275.03 22.26 1.12
26/04/20 185.13 24.72 --
Apple:
Facebook:
Instead of what I want and would expect based on the code I have written in watchlist_report():
Apple:
26/04/20 275.03 22.26 1.12
Facebook:
26/04/20 185.13 24.72 --
Therefore, my questions are:
1) Why is my output formatted this way?
2) Which part of my code do I have to change to make the written output in my desired format?
Any other suggestions about how I can clean my code and any libraries I can use to make my code nicer are also appreciated!
You handle two different file-handles - the file-handle inside your watchlist_report gets closed earlier so its being written first, before the outer functions file-handle gets closed, flushed and written.
Instead of creating a new open(..) in your function, pass the current file handle:
def watchlist_report(watchlist):
with open(watchlist, 'r') as companies, open('Watchlist Info.txt', 'a') as output:
searches = companies.read()
x = searches.split('\n')
for i in x:
output.write(i + ':\n')
stock_price(i, doc = output) # pass the file handle
output.write('\n')
Inside def stock_price(company, doc=None): use the provided filehandle:
def stock_price(company, output = None): # changed name here
# [snip] - removed unrelated code for this answer for brevity sake
if output is None: # check for None using IS
print( ... ) # print whatever you like here
else:
from datetime import date
output.write( .... ) # write whatever you want it to write
# output.close() # do not close, the outer function does this
Do not close the file handle in the inner function, the context handling with(..) of the outer function does that for you.
The main takeaway for file handling is that things you write(..) to your file are not neccessarily placed there immediately. The filehandler chooses when to actually persist data to your disk, the latests it does that is when it goes out of scope (of the context handler) or when its internal buffer reaches some threshold so it "thinks" it is now prudent to alter to data on your disc. See How often does python flush to a file? for more infos.

I am trying to write data into file

When I run then i get error.why print man gave error and also os.getwd() also give error.But when i comment that then there is no error.code works according to expectation
from __future__ import print_function;
import os
man=[]
other = []
print os.getcwd()
try:
data = open("sketch.txt")
for each_line in data:
try:
(role,line_spoken) = each_line.split(':',1)
line_spoken = line_spoken.strip()
if role=='Man':
man.append(line_spoken)
elif role =='Other Man':
other.append(line_spoken)
except ValueError:
pass
data.close()
except IOError:
print ("The Data File is Missing")
print man
print other
try:
man_file = open('man_data.txt','w')
other_file = open('other_data.txt','w')
print (man,file = man_file)
print (other,file = other_file)
other_file.close()
man_file.close()
except IOError:
pass
You should call print as function, because you import print_function:
from __future__ import print_function
print("Hello World")
As far as I see the following.
1) In the first line there is a ';' that could be removed.
2) the second line 'import...' and the rest to the bottom have tabs that should be removed. These lines should be in the same col that line 1 ('from ...')
3) when you use 'print' (as other people are saying) you should use '(' & ')'.
4) for coherence you should get used to follow the same approach in all your code (good practiceS), if there are no spaces between function names and parameters (i.e. line 7: data = open("sketch...) then go on with them. The same for strings, the code compile, but it is better if you use ' or " not mix them along the code.
looking forward to help!

Python refresh file from disk

I have a python script that calls a system program and reads the output from a file out.txt, acts on that output, and loops. However, it doesn't work, and a close investigation showed that the python script just opens out.txt once and then keeps on reading from that old copy. How can I make the python script reread the file on each iteration? I saw a similar question here on SO but it was about a python script running alongside a program, not calling it, and the solution doesn't work. I tried closing the file before looping back but it didn't do anything.
EDIT:
I already tried closing and opening, it didn't work. Here's the code:
import subprocess, os, sys
filename = sys.argv[1]
file = open(filename,'r')
foo = open('foo','w')
foo.write(file.read().rstrip())
foo = open('foo','a')
crap = open(os.devnull,'wb')
numSolutions = 0
while True:
subprocess.call(["minisat", "foo", "out"], stdout=crap,stderr=crap)
out = open('out','r')
if out.readline().rstrip() == "SAT":
numSolutions += 1
clause = out.readline().rstrip()
clause = clause.split(" ")
print clause
clause = map(int,clause)
clause = map(lambda x: -x,clause)
output = ' '.join(map(lambda x: str(x),clause))
print output
foo.write('\n'+output)
out.close()
else:
break
print "There are ", numSolutions, " solutions."
You need to flush foo so that the external program can see its latest changes. When you write to a file, the data is buffered in the local process and sent to the system in larger blocks. This is done because updating the system file is relatively expensive. In your case, you need to force a flush of the data so that minisat can see it.
foo.write('\n'+output)
foo.flush()
I rewrote it to hopefully be a bit easier to understand:
import os
from shutil import copyfile
import subprocess
import sys
TEMP_CNF = "tmp.in"
TEMP_SOL = "tmp.out"
NULL = open(os.devnull, "wb")
def all_solutions(cnf_fname):
"""
Given a file containing a set of constraints,
generate all possible solutions.
"""
# make a copy of original input file
copyfile(cnf_fname, TEMP_CNF)
while True:
# run minisat to solve the constraint problem
subprocess.call(["minisat", TEMP_CNF, TEMP_SOL], stdout=NULL,stderr=NULL)
# look at the result
with open(TEMP_SOL) as result:
line = next(result)
if line.startswith("SAT"):
# Success - return solution
line = next(result)
solution = [int(i) for i in line.split()]
yield solution
else:
# Failure - no more solutions possible
break
# disqualify found solution
with open(TEMP_CNF, "a") as constraints:
new_constraint = " ".join(str(-i) for i in sol)
constraints.write("\n")
constraints.write(new_constraint)
def main(cnf_fname):
"""
Given a file containing a set of constraints,
count the possible solutions.
"""
count = sum(1 for i in all_solutions(cnf_fname))
print("There are {} solutions.".format(count))
if __name__=="__main__":
if len(sys.argv) == 2:
main(sys.argv[1])
else:
print("Usage: {} cnf.in".format(sys.argv[0]))
You take your file_var and end the loop with file_var.close().
for ... :
ga_file = open(out.txt, 'r')
... do stuff
ga_file.close()
Demo of an implementation below (as simple as possible, this is all of the Jython code needed)...
__author__ = ''
import time
var = 'false'
while var == 'false':
out = open('out.txt', 'r')
content = out.read()
time.sleep(3)
print content
out.close()
generates this output:
2015-01-09, 'stuff added'
2015-01-09, 'stuff added' # <-- this is when i just saved my update
2015-01-10, 'stuff added again :)' # <-- my new output from file reads
I strongly recommend reading the error messages. They hold quite a lot of information.
I think the full file name should be written for debug purposes.

For loop function call file parsing

I recognize that this code is wildly inefficient.
I'm at a complete loss here, and I'm planning to remove the function and just make the code procedural in main. But I'm hoping someone can explain what I'm seeing here. The loop in main() runs and calls matchName(). matchName() executes it's loop then, when it should return for the next "vtRow", instead it just stops executing. So the output is the first record of vtData and every record from adData.
import csv, re
def main():
#1st word
oneWord = re.compile( '\A([\w]+)' )
#1st 3
first3 = re.compile( '\A([\w]{3})' )
#last 3
last3 = re.compile( '(?=([\w]{3})$)' )
mArray = [ oneWord, first3, last3 ]
adFile = open('adData.csv', 'rb')
adFields = ('lName','fName','cNum','addy','city','state','zip','phone','sex')
adData = csv.reader(adFile, dialect='excel')
vtFile = open('data360.csv','rb')
vtFields = ('ref','fName','lName')
vtData = csv.reader(vtFile, dialect='excel')
for vtRow in vtData:
matchName(vtRow, adData, mArray) # appears that this runs once and exits
def matchName(curVtRow, adData, mArr):
lName = curVtRow[4].lower()
fName = curVtRow[3].lower()
Posib = []
for row in adData:
cName = row[0].lower()
print "vt " + lName + " ; ad " + cName
return 1
if __name__ == "__main__":
main()
The issue is that looping with adData causes adFile to be read, and so after the first call to matchName() the file will have been read all the way and thus adData won't be looped over as adData.next() won't result in anything (and thus the print statement will not be executed). I suggest placing adFile.seek(0) after the call to matchName(). Note that just recreating adData won't work; I discovered recently that a csv reader updates its underlying object's file position rather than keeping track of it on its own.

Categories

Resources