Luigi task not writing pandas df to csv - python

I have the following code to simply an excel file and return only the required columns. It written as a luigi task containerized on docker and its not returning the csv file while _SUCCESS flag is being created.
Function Code:
def _save_datasets(simplified, outdir: Path, flag):
out_clean = outdir / 'transformed.csv/'
flag = outdir / flag
simplified.to_csv(str(out_clean), index=False)
# save as csv and create flag file
flag.touch()
#click.command()
#click.option('--in-csv')
#click.option('--out-dir')
#click.option('--flag')
def transform_data(in_csv,out_dir, flag):
out_dir = Path(out_dir)
data=pd.read_csv(in_csv)
req_dp = data[['description','points']]
#simplifying the points according to range
def transform_points_simplified(points):
if points < 84:
return 1
elif points >= 84 and points < 88:
return 2
elif points >= 88 and points < 92:
return 3
elif points >= 92 and points < 96:
return 4
else:
return 5
simplified = req_dp.assign(points_simplified = dp['points'].apply(transform_points_simplified))
_save_datasets(simplified,out_dir, flag)
Luigi Task code:
#Transform
class TransformData(DockerTask):
"""Task to simplify datasets"""
in_path = '/usr/share/data/created_csv/'
in_csv = luigi.Parameter(default= in_path + 'cleaned.csv')
out_dir = luigi.Parameter(default='/usr/share/data/created_csv/')
flag = luigi.Parameter('.SUCCESS_TransformData')
#property
def image(self):
return f'code-chal/transform-data:{VERSION}'
def requires(self):
return CleanData()
#property
def command(self):
return [
'python', 'clean_data.py',
'--in-csv', self.in_csv,
'--out-dir', self.out_dir,
'--flag', self.flag
]
def output(self):
return luigi.LocalTarget(
path=str(Path(self.out_dir) / self.flag)
)
The luigi task moves on to the next task due to the creation of _SUCCESS flag, but the next task fails since its dependent on the transformed.csv file which isn't being created.
Thanks

In your LuigiTask you need a run function that needs to save the file you want using the output target from the output function.
So you need to add:
def run(self):
outfile = open(self.output().path, 'wb') # Notice that it references to the path of the self.output function
transform_data(self.in_csv, outfile, self.flag)

Related

writing to files: switch to new file after X MB file capacity

I have millions of domains which I will send WHOIS query and record WHOIS response on some .txt file.
I would like to set maximum capacity for a single .txt output file. For example, let's say I started recording responses on out0.txt. I want to switch to out1.txt if out0.txt is >= 100mb. Same thing goes for out1.txt, if out1.txt>=100mb then start writing to out2.txtand so on.
I know that I can do if checks after each insertion, but I want my code to be fast: i.e. I thought if checks at each domain can slow down my code. (It will asynchronously query millions of domains).
I imagined a try-except block could solve my issue here, like this:
folder_name = "out%s.txt"
folder_number = 0
folder_name = folder_name % folder_number
f = open(folder_name, 'w+')
for domain in millions_of_domains:
try:
response_json = send_whois_query(domain)
f.write(response_json)
except FileGreaterThan100MbException:
folder_number += 1
folder_name = folder_name % folder_number
f = open(folder_name, 'w+')
f.write(response_json)
Any suggestions will be appreciated. Thank you for your time.
You can create a wrapper object that tracks how much data has been written, and opens a new file if you reached a limit:
class MaxSizeFileWriter(object):
def __init__(self, filenamepattern, maxdata=2**20, # default 1Mb
start=0, mode='w', *args, **kwargs):
self._pattern = filenamepattern
self._counter = start
self._mode = mode
self._args, self._kwargs = args, kwargs
self._max = maxdata
self._openfile = None
self._written = 0
def _open(self):
if self._openfile is not None:
filename = self._pattern.format(self._counter)
self._counter += 1
self._openfile = open(filename, mode=self._mode, *self._args, **self._kwargs)
def _close(self):
if self._openfile is not None:
self._openfile.close()
def __enter__(self):
return self
def __exit__(self, *args, **kwargs):
if self._openfile is not None:
self._openfile.close()
def write(self, data):
if self._written + len(data) > self._max:
# current file too full to fit data too, close it
# This will trigger a new file to be opened.
self._close()
self._open() # noop if already open
self._openfile.write(data)
self._written += len(data)
The above is a context manager, and can be used just like a regular file. Pass in a filename with a {} placeholder for the number to be inserted into:
folder_name = "out{}.txt"
with MaxSizeFileWriter(folder_name, maxdata=100 * 2**10) as f:
for domain in millions_of_domains:
response_json = send_whois_query(domain)
f.write(response_json)

How should I Execute this Python Script in powershell

I've solved the problem. The problem is related my %PATH%
I have a script which work with an argument. In powershell I've tried the command you can see below;
.\dsrf2csv.py C:\Python27\a\DSR_testdata.tsv.gz
And also you can see the script below,
def __init__(self, dsrf2csv_arg):
self.dsrf_filename = dsrf2csv_arg
dsrf_path, filename = os.path.split(self.dsrf_filename)
self.report_outfilename = os.path.join(dsrf_path, filename.replace('DSR', 'Report').replace('tsv', 'csv'))
self.summary_outfilename = os.path.join(dsrf_path, filename.replace('DSR', 'Summary').replace('tsv.gz', 'csv'))
But when I try to run this script there is no any action. How should I run this script with a file? (example : testdata.tsv.gz)
Note : Script and file in same location.
Full Scritp;
import argparse
import atexit
import collections
import csv
import gzip
import os
SKIP_ROWS = ['HEAD', '#HEAD', '#SY02', '#SY03', '#AS01', '#MW01', '#RU01',
'#SU03', '#LI01', '#FOOT']
REPORT_HEAD = ['Asset_ID', 'Asset_Title', 'Asset_Artist', 'Asset_ISRC',
'MW_Asset_ID', 'MW_Title', 'MW_ISWC', 'MW_Custom_ID',
'MW_Writers', 'Views', 'Owner_name', 'Ownership_Claim',
'Gross_Revenue', 'Amount_Payable', 'Video_IDs', 'Video_views']
SUMMARY_HEAD = ['SummaryRecordId', 'DistributionChannel',
'DistributionChannelDPID', 'CommercialModel', 'UseType',
'Territory', 'ServiceDescription', 'Usages', 'Users',
'Currency', 'NetRevenue', 'RightsController',
'RightsControllerPartyId', 'AllocatedUsages', 'AmountPayable',
'AllocatedNetRevenue']
class DsrfConverter(object):
"""Converts DSRF 3.0 to YouTube CSV."""
def __init__(self, dsrf2csv_arg):
""" Creating output file names """
self.dsrf_filename = dsrf2csv_arg
dsrf_path, filename = os.path.split(self.dsrf_filename)
print(dsrf_filename)
input("Press Enter to continue...")
self.report_outfilename = os.path.join(dsrf_path, filename.replace(
'DSR', 'Report').replace('tsv', 'csv'))
self.summary_outfilename = os.path.join(dsrf_path, filename.replace(
'DSR', 'Summary').replace('tsv.gz', 'csv'))
def parse_blocks(self, reader):
"""Generator for parsing all the blocks from the file.
Args:
reader: the handler of the input file
Yields:
block_lines: A full block as a list of rows.
"""
block_lines = []
current_block = None
for line in reader:
if line[0] in SKIP_ROWS:
continue
# Exit condition
if line[0] == 'FOOT':
yield block_lines
raise StopIteration()
line_block_number = int(line[1])
if current_block is None:
# Initialize
current_block = line_block_number
if line_block_number > current_block:
# End of block, yield and build a new one
yield block_lines
block_lines = []
current_block = line_block_number
block_lines.append(line)
# Also return last block
yield block_lines
def process_single_block(self, block):
"""Handles a single block in the DSR report.
Args:
block: Block as a list of lines.
Returns:
(summary_rows, report_row) tuple.
"""
views = 0
gross_revenue = 0
summary_rows = []
owners_data = {}
# Create an ordered dictionary with a key for every column.
report_row_dict = collections.OrderedDict(
[(column_name.lower(), '') for column_name in REPORT_HEAD])
for line in block:
if line[0] == 'SY02': # Save the financial Summary
summary_rows.append(line[1:])
continue
if line[0] == 'AS01': # Sound Recording information
report_row_dict['asset_id'] = line[3]
report_row_dict['asset_title'] = line[5]
report_row_dict['asset_artist'] = line[7]
report_row_dict['asset_isrc'] = line[4]
if line[0] == 'MW01': # Composition information
report_row_dict['mw_asset_id'] = line[2]
report_row_dict['mw_title'] = line[4]
report_row_dict['mw_iswc'] = line[3]
report_row_dict['mw_writers'] = line[6]
if line[0] == 'RU01': # Video level information
report_row_dict['video_ids'] = line[3]
report_row_dict['video_views'] = line[4]
if line[0] == 'SU03': # Usage data of Sound Recording Asset
# Summing up views and revenues for each sub-period
views += int(line[5])
gross_revenue += float(line[6])
report_row_dict['views'] = views
report_row_dict['gross_revenue'] = gross_revenue
if line[0] == 'LI01': # Ownership information
# if we already have parsed a LI01 line with that owner
if line[3] in owners_data:
# keep only the latest ownership
owners_data[line[3]]['ownership'] = line[6]
owners_data[line[3]]['amount_payable'] += float(line[9])
else:
# need to create the entry for that owner
data_dict = {'custom_id': line[5],
'ownership': line[6],
'amount_payable': float(line[9])}
owners_data[line[3]] = data_dict
# get rid of owners which do not have an ownership or an amount payable
owners_to_write = [o for o in owners_data
if (owners_data[o]['ownership'] > 0
and owners_data[o]['amount_payable'] > 0)]
report_row_dict['owner_name'] = '|'.join(owners_to_write)
report_row_dict['mw_custom_id'] = '|'.join([owners_data[o]
['custom_id']
for o in owners_to_write])
report_row_dict['ownership_claim'] = '|'.join([owners_data[o]
['ownership']
for o in owners_to_write])
report_row_dict['amount_payable'] = '|'.join([str(owners_data[o]
['amount_payable'])
for o in owners_to_write])
# Sanity check. The number of values must match the number of columns.
assert len(report_row_dict) == len(REPORT_HEAD), 'Row is wrong size :/'
return summary_rows, report_row_dict
def run(self):
finished = False
def removeFiles():
if not finished:
os.unlink(self.report_outfilename)
os.unlink(self.summary_outfilename)
atexit.register(removeFiles)
with gzip.open(self.dsrf_filename, 'rb') as dsr_file, gzip.open(
self.report_outfilename, 'wb') as report_file, open(
self.summary_outfilename, 'wb') as summary_file:
dsr_reader = csv.reader(dsr_file, delimiter='\t')
report_writer = csv.writer(report_file)
summary_writer = csv.writer(summary_file)
report_writer.writerow(REPORT_HEAD)
summary_writer.writerow(SUMMARY_HEAD)
for block in self.parse_blocks(dsr_reader):
summary_rows, report_row = self.process_single_block(block)
report_writer.writerow(report_row.values())
summary_writer.writerows(summary_rows)
finished = True
if __name__ == '__main__':
arg_parser = argparse.ArgumentParser(
description='Converts DDEX DSRF UGC profile reports to Standard CSV.')
required_args = arg_parser.add_argument_group('Required arguments')
required_args.add_argument('dsrf2csv_arg', type=str)
args = arg_parser.parse_args()
dsrf_converter = DsrfConverter(args.dsrf2csv_arg)
dsrf_converter.run()
In general to execute a python script in powershell like this .\script.py has two requirements:
Add the path to the python binaries to your %path%: $env:Path = $env:Path + ";C:\Path\to\python\binaries\"
Add the ending .py to the pathtext environment variable: $env:PATHEXT += ";.PY"
The latter will only be used in the current powershell session. If you want to add it to all future powershell sessions, add this line to your powershell profile (f.e. notepad $profile).
In your case there is also an issue with the python script you are trying to excute. def __init__(self) is an constructor for a class, like:
class Foo:
def __init__(self):
print "foo"
Did you give us your complete script?

Trying to run a defined function with a delay

I am trying to incrementally load values from the first column of a csv file into a URL and request the URL one at a time with a 5 second delay. Each value in the first column should replace "theid"
This is my code so far:
# I have a defined function
def withid (theid):
""""""
global cache
dupe = False
theurl = "{0}{1}{2}".format(OMDBURL, "?i=", theid)
response = urllib2.urlopen(theurl)
movdata = json.load(response)
for mov in cache:
if movdata[MKEY[1]] == mov[MKEY[1]]:
dupe = True
if not dupe:
cache.append(movdata)
outfile2 = open('outputrows2-shortened.csv', 'rb')
for row in outfile2:
theid = outfile2(row[0])
time.sleep(5)
output: TypeError: 'file' object is not callable
Your withid() function never returns anything. Try adding return movdata at the end of it.
Here is a rewritten version which may be helpful:
import csv
import json
import time
import urllib2
PAGE_DELAY = 5. # time between loading pages
PAGE_LOAD = 0.3 # how long it takes to load a page
make_url = 'http://www.imdb.com/title/tt{}/'.format
def get_csv_column(csv_fname, col, **kwargs):
with open(csv_fname, 'rb') as inf:
incsv = csv.reader(inf, **kwargs)
column = [row[col] for row in incsv]
return column
def get_data_by_id(id):
url = make_url(id)
response = urllib2.urlopen(url)
data = json.load(response)
return id,data
def delayed(delay, fn, *args):
time.sleep(delay)
return fn(*args)
def human_time(seconds):
if seconds >= 86400:
return '{:0.1f} days'.format(seconds / 86400.)
elif seconds >= 3600:
return '{:0.1f} hours'.format(seconds / 3600.)
elif seconds >= 60:
return '{:0.1f} minutes'.format(minutes / 60.)
else:
return '{:0.1f} seconds'.format(seconds)
def main():
ids = get_csv_column('outputrows2.csv', 0)
expected = (PAGE_DELAY + PAGE_LOAD) * len(ids)
print('This will take about {}.'.format(human_time(expected)))
results = (delayed(PAGE_DELAY, get_data_by_id, id) for id in ids)
moviedata = dict(results) # => gives dict of {id:data}
if __name__=="__main__":
main()

Converting an UNIX python program to work in windows [closed]

This question is unlikely to help any future visitors; it is only relevant to a small geographic area, a specific moment in time, or an extraordinarily narrow situation that is not generally applicable to the worldwide audience of the internet. For help making this question more broadly applicable, visit the help center.
Closed 9 years ago.
I need to make a program that drives a DYMO LabelManager PnP label printing device. DYMO provides a SDK for this purpose, but after some desperate trying, I'd say the SDK is useless. Then I found a program which is just what I need, written by a guy named S.Bronner. But the problem is that his program is made for Python in UNIX, and I would need it to work in Windows with python. So I'm asking, is there anyone who could examine this code and convert it to work in windows for me? My Python skills are not good enough to accomplish this. Here is the code which should be converted:
#!/usr/bin/env python
DEV_CLASS = 3
DEV_VENDOR = 0x0922
DEV_PRODUCT = 0x1001
DEV_NODE = None
DEV_NAME = 'Dymo LabelManager PnP'
FONT_FILENAME = '/usr/share/fonts/truetype/ttf-bitstream-vera/Vera.ttf'
FONT_SIZERATIO = 7./8
import Image
import ImageDraw
import ImageFont
import array
import fcntl
import os
import re
import struct
import subprocess
import sys
import termios
import textwrap
class DymoLabeler:
"""
Create and work with a Dymo LabelManager PnP object.
This class contains both mid-level and high-level functions. In general,
the high-level functions should be used. However, special purpose usage
may require the mid-level functions. That is why they are provided.
However, they should be well understood before use. Look at the
high-level functions for help. Each function is marked in its docstring
with 'HLF' or 'MLF' in parentheses.
"""
def __init__(self, dev):
"""Initialize the LabelManager object. (HLF)"""
self.maxBytesPerLine = 8 # 64 pixels on a 12mm-tape
self.ESC = 0x1b
self.SYN = 0x16
self.cmd = []
self.rsp = False
self.bpl = None
self.dtb = 0
if not os.access(dev, os.R_OK | os.W_OK): return False
self.dev = open(dev, 'r+')
def sendCommand(self):
"""Send the already built command to the LabelManager. (MLF)"""
if len(self.cmd) == 0: return
cmdBin = array.array('B', self.cmd)
cmdBin.tofile(self.dev)
self.cmd = []
if not self.rsp: return
self.rsp = False
rspBin = self.dev.read(8)
rsp = array.array('B', rspBin).tolist()
return rsp
def resetCommand(self):
"""Remove a partially built command. (MLF)"""
self.cmd = []
self.rsp = False
def buildCommand(self, cmd):
"""Add the next instruction to the command. (MLF)"""
self.cmd += cmd
def statusRequest(self):
"""Set instruction to get the device's status. (MLF)"""
cmd = [self.ESC, ord('A')]
self.buildCommand(cmd)
self.rsp = True
def dotTab(self, value):
"""Set the bias text height, in bytes. (MLF)"""
if value < 0 or value > self.maxBytesPerLine: raise ValueError
cmd = [self.ESC, ord('B'), value]
self.buildCommand(cmd)
self.dtb = value
self.bpl = None
def tapeColor(self, value):
"""Set the tape color. (MLF)"""
if value < 0: raise ValueError
cmd = [self.ESC, ord('C'), value]
self.buildCommand(cmd)
def bytesPerLine(self, value):
"""Set the number of bytes sent in the following lines. (MLF)"""
if value < 0 or value + self.dtb > self.maxBytesPerLine: raise ValueError
if value == self.bpl: return
cmd = [self.ESC, ord('D'), value]
self.buildCommand(cmd)
self.bpl = value
def cut(self):
"""Set instruction to trigger cutting of the tape. (MLF)"""
cmd = [self.ESC, ord('E')]
self.buildCommand(cmd)
def line(self, value):
"""Set next printed line. (MLF)"""
self.bytesPerLine(len(value))
cmd = [self.SYN] + value
self.buildCommand(cmd)
def chainMark(self):
"""Set Chain Mark. (MLF)"""
self.dotTab(0)
self.bytesPerLine(self.maxBytesPerLine)
self.line([0x99] * self.maxBytesPerLine)
def skipLines(self, value):
"""Set number of lines of white to print. (MLF)"""
if value <= 0: raise ValueError
self.bytesPerLine(0)
cmd = [self.SYN] * value
self.buildCommand(cmd)
def initLabel(self):
"""Set the label initialization sequence. (MLF)"""
cmd = [0x00] * 8
self.buildCommand(cmd)
def getStatus(self):
"""Ask for and return the device's status. (HLF)"""
self.statusRequest()
rsp = self.sendCommand()
print rsp
def printLabel(self, lines, dotTab):
"""Print the label described by lines. (HLF)"""
self.initLabel
self.tapeColor(0)
self.dotTab(dotTab)
for line in lines:
self.line(line)
self.skipLines(56) # advance printed matter past cutter
self.skipLines(56) # add symmetric margin
self.statusRequest()
rsp = self.sendCommand()
print rsp
def die(message=None):
if message: print >> sys.stderr, message
sys.exit(1)
def pprint(par, fd=sys.stdout):
rows, columns = struct.unpack('HH', fcntl.ioctl(sys.stderr, termios.TIOCGWINSZ, struct.pack('HH', 0, 0)))
print >> fd, textwrap.fill(par, columns)
def getDeviceFile(classID, vendorID, productID):
# find file containing the device's major and minor numbers
searchdir = '/sys/bus/hid/devices'
pattern = '^%04d:%04X:%04X.[0-9A-F]{4}$' % (classID, vendorID, productID)
deviceCandidates = os.listdir(searchdir)
foundpath = None
for devname in deviceCandidates:
if re.match(pattern, devname):
foundpath = os.path.join(searchdir, devname)
break
if not foundpath: return
searchdir = os.path.join(foundpath, 'hidraw')
devname = os.listdir(searchdir)[0]
foundpath = os.path.join(searchdir, devname)
filepath = os.path.join(foundpath, 'dev')
# get the major and minor numbers
f = open(filepath, 'r')
devnums = [int(n) for n in f.readline().strip().split(':')]
f.close()
devnum = os.makedev(devnums[0], devnums[1])
# check if a symlink with the major and minor numbers is available
filepath = '/dev/char/%d:%d' % (devnums[0], devnums[1])
if os.path.exists(filepath):
return os.path.realpath(filepath)
# check if the relevant sysfs path component matches a file name in
# /dev, that has the proper major and minor numbers
filepath = os.path.join('/dev', devname)
if os.stat(filepath).st_rdev == devnum:
return filepath
# search for a device file with the proper major and minor numbers
for dirpath, dirnames, filenames in os.walk('/dev'):
for filename in filenames:
filepath = os.path.join(dirpath, filename)
if os.stat(filepath).st_rdev == devnum:
return filepath
def access_error(dev):
pprint('You do not have sufficient access to the device file %s:' % dev, sys.stderr)
subprocess.call(['ls', '-l', dev], stdout=sys.stderr)
print >> sys.stderr
pprint('You probably want to add a rule in /etc/udev/rules.d along the following lines:', sys.stderr)
print >> sys.stderr, ' SUBSYSTEM=="hidraw", \\'
print >> sys.stderr, ' ACTION=="add", \\'
print >> sys.stderr, ' DEVPATH=="/devices/pci[0-9]*/usb[0-9]*/0003:0922:1001.*/hidraw/hidraw0", \\'
print >> sys.stderr, ' GROUP="plugdev"'
print >> sys.stderr
pprint('Following that, turn off your device and back on again to activate the new permissions.', sys.stderr)
# get device file name
if not DEV_NODE:
dev = getDeviceFile(DEV_CLASS, DEV_VENDOR, DEV_PRODUCT)
else:
dev = DEV_NODE
if not dev: die("The device '%s' could not be found on this system." % DEV_NAME)
# create dymo labeler object
lm = DymoLabeler(dev)
if not lm: die(access_error(dev))
# check for any text specified on the command line
labeltext = [arg.decode(sys.stdin.encoding) for arg in sys.argv[1:]]
if len(labeltext) == 0: die("No label text was specified.")
# create an empty label image
labelheight = lm.maxBytesPerLine * 8
lineheight = float(labelheight) / len(labeltext)
fontsize = int(round(lineheight * FONT_SIZERATIO))
font = ImageFont.truetype(FONT_FILENAME, fontsize)
labelwidth = max(font.getsize(line)[0] for line in labeltext)
labelbitmap = Image.new('1', (labelwidth, labelheight))
# write the text into the empty image
labeldraw = ImageDraw.Draw(labelbitmap)
for i, line in enumerate(labeltext):
lineposition = int(round(i * lineheight))
labeldraw.text((0, lineposition), line, font=font, fill=255)
del labeldraw
# convert the image to the proper matrix for the dymo labeler object
labelrotated = labelbitmap.transpose(Image.ROTATE_270)
labelstream = labelrotated.tostring()
labelstreamrowlength = labelheight/8 + (1 if labelheight%8 != 0 else 0)
if len(labelstream)/labelstreamrowlength != labelwidth: die('An internal problem was encountered while processing the label bitmap!')
labelrows = [labelstream[i:i+labelstreamrowlength] for i in range(0, len(labelstream), labelstreamrowlength)]
labelmatrix = [array.array('B', labelrow).tolist() for labelrow in labelrows]
# optimize the matrix for the dymo label printer
dottab = 0
while max(line[0] for line in labelmatrix) == 0:
labelmatrix = [line[1:] for line in labelmatrix]
dottab += 1
for line in labelmatrix:
while len(line) > 0 and line[-1] == 0:
del line[-1]
# print the label
lm.printLabel(labelmatrix, dottab)
FONT_FILENAME = '/usr/share/fonts/truetype/ttf-bitstream-vera/Vera.ttf'
// should be changed to path to the font on your system
won't work because of filesystem differences.
searchdir = '/sys/bus/hid/devices'
// take a look at "pywinusb" library (?)
won't work either, you have to get the devices in a different way. Not sure from where though. The same problem is
filepath = '/dev/char/%d:%d' % (devnums[0], devnums[1])
this isn't accessible in Windows and you have to do in a different way.
Besides that everything else looks OS independent. If you have any errors after fixing previous 3 problems, then edit them into your question please.

Successive multiprocessing

I am filtering huge text files using multiprocessing.py. The code basically opens the text files, works on it, then closes it.
Thing is, I'd like to be able to launch it successively on multiple text files. Hence, I tried to add a loop, but for some reason it doesn't work (while the code works on each file). I believe this is an issue with:
if __name__ == '__main__':
However, I am looking for something else. I tried to create a Launcher and a LauncherCount files like this:
LauncherCount.py:
def setLauncherCount(n):
global LauncherCount
LauncherCount = n
and,
Launcher.py:
import os
import LauncherCount
LauncherCount.setLauncherCount(0)
os.system("OrientedFilterNoLoop.py")
LauncherCount.setLauncherCount(1)
os.system("OrientedFilterNoLoop.py")
...
I import LauncherCount.py, and use LauncherCount.LauncherCount as my loop index.
Of course, this doesn't work too as it edits the variable LauncherCount.LauncherCount locally, so it won't be edited in the imported version of LauncherCount.
Is there any way to edit globally a variable in an imported file? Or, is there any way to do this in any other way? What I need is running a code multiple times, in changing one value, and without using any loop apparently.
Thanks!
Edit: Here is my main code if necessary. Sorry for the bad style ...
import multiprocessing
import config
import time
import LauncherCount
class Filter:
""" Filtering methods """
def __init__(self):
print("launching methods")
# Return the list: [Latitude,Longitude] (elements are floating point numbers)
def LatLong(self,line):
comaCount = []
comaCount.append(line.find(','))
comaCount.append(line.find(',',comaCount[0] + 1))
comaCount.append(line.find(',',comaCount[1] + 1))
Lat = line[comaCount[0] + 1 : comaCount[1]]
Long = line[comaCount[1] + 1 : comaCount[2]]
try:
return [float(Lat) , float(Long)]
except ValueError:
return [0,0]
# Return a boolean:
# - True if the Lat/Long is within the Lat/Long rectangle defined by:
# tupleFilter = (minLat,maxLat,minLong,maxLong)
# - False if not
def LatLongFilter(self,LatLongList , tupleFilter) :
if tupleFilter[0] <= LatLongList[0] <= tupleFilter[1] and
tupleFilter[2] <= LatLongList[1] <= tupleFilter[3]:
return True
else:
return False
def writeLine(self,key,line):
filterDico[key][1].write(line)
def filteringProcess(dico):
myFilter = Filter()
while True:
try:
currentLine = readFile.readline()
except ValueError:
break
if len(currentLine) ==0: # Breaks at the end of the file
break
if len(currentLine) < 35: # Deletes wrong lines (too short)
continue
LatLongList = myFilter.LatLong(currentLine)
for key in dico:
if myFilter.LatLongFilter(LatLongList,dico[key][0]):
myFilter.writeLine(key,currentLine)
###########################################################################
# Main
###########################################################################
# Open read files:
readFile = open(config.readFileList[LauncherCount.LauncherCount][1], 'r')
# Generate writing files:
pathDico = {}
filterDico = config.filterDico
# Create outputs
for key in filterDico:
output_Name = config.readFileList[LauncherCount.LauncherCount][0][:-4]
+ '_' + key +'.log'
pathDico[output_Name] = config.writingFolder + output_Name
filterDico[key] = [filterDico[key],open(pathDico[output_Name],'w')]
p = []
CPUCount = multiprocessing.cpu_count()
CPURange = range(CPUCount)
startingTime = time.localtime()
if __name__ == '__main__':
### Create and start processes:
for i in CPURange:
p.append(multiprocessing.Process(target = filteringProcess ,
args = (filterDico,)))
p[i].start()
### Kill processes:
while True:
if [p[i].is_alive() for i in CPURange] == [False for i in CPURange]:
readFile.close()
for key in config.filterDico:
config.filterDico[key][1].close()
print(key,"is Done!")
endTime = time.localtime()
break
print("Process started at:",startingTime)
print("And ended at:",endTime)
To process groups of files in sequence while working on files within a group in parallel:
#!/usr/bin/env python
from multiprocessing import Pool
def work_on(args):
"""Process a single file."""
i, filename = args
print("working on %s" % (filename,))
return i
def files():
"""Generate input filenames to work on."""
#NOTE: you could read the file list from a file, get it using glob.glob, etc
yield "inputfile1"
yield "inputfile2"
def process_files(pool, filenames):
"""Process filenames using pool of processes.
Wait for results.
"""
for result in pool.imap_unordered(work_on, enumerate(filenames)):
#NOTE: in general the files won't be processed in the original order
print(result)
def main():
p = Pool()
# to do "successive" multiprocessing
for filenames in [files(), ['other', 'bunch', 'of', 'files']]:
process_files(p, filenames)
if __name__=="__main__":
main()
Each process_file() is called in sequence after the previous one has been complete i.e., the files from different calls to process_files() are not processed in parallel.

Categories

Resources