I have a code
require 'rubygems'
conf_array = []
File.open("C:/My Program Files/readme.txt", "r").each_line do |line|
conf_array << line.chop.split("\t")
end
a = conf_array.index{|s| s.include?("server =")}
puts a
and it doesn't display the index of item. Why?
Array looks like
conf_array = [
["# This file can be used to override the default puppet settings."],
["# See the following links for more details on what settings are available:"],
["# - docs.puppetlabs.com/puppet/latest/reference/config_important_settings.html"],
["# - docs.puppetlabs.com/puppet/latest/reference/config_about_settings.html"],
["# - docs.puppetlabs.com/puppet/latest/reference/config_file_main.html"],
["# - docs.puppetlabs.com/references/latest/configuration.html"], ["[main]"],
["server = server.net.pl"],
["splay = true"],
["splaylimit = 1h"],
["wiatforcert = 30m"],
["http_connect_timeout = 2m"],
["http_read_timeout = 30m"],
["runinterval = 6h"],
["waitforcert = 30m"]
]
And next how to display that item? I mean a = conf_array[#{a}] says syntax error.
I tried also
new_array = []
new_array = conf_array.select! {|s| s.include?("server =")}
and it again does't display found item. Any suggestion?
Perfect use case for Enumerable#grep
File.open("C:/My Program Files/readme.txt", "r")
.each_line
# no need to .flat_map { |l| l.split(/\t/) }
.grep /server =/
#⇒ ["server = server.net.pl"]
The problem is that you don't call String#include?, but Array#include? :
["server = something.pl"].include?('server = ')
# false
"server = something.pl".include?('server = ')
# true
Remove the split("\t").
To read the file into an array, you can just use :
conf_array = File.readlines("C:/My Program Files/readme.txt")
or
conf_array = File.readlines("C:/My Program Files/readme.txt").map(&:chomp)
Related
I'm using HDBSCAN clustering algorithm and using RandomizedSearchCV. When I fit the features with labels, I get error "IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed". Shape of embedding is (5000,4) and of hdb_labels is (5000,). Below is my code
# UMAP
umap_hdb = umap.UMAP(n_components=4, random_state = 42)
embedding = umap_hdb.fit_transform(customer_data_hdb)
# creating HDBSCAN wrapper
class HDBSCANWrapper(hdbscan.HDBSCAN):
def predict(self,X):
return self.labels_.astype(int)
# HBDSCAN
clusterer_hdb = HDBSCANWrapper(min_samples=40, min_cluster_size=1000, metric='manhattan', gen_min_span_tree=True).fit(embedding)
hdb_labels = clusterer_hdb.labels_
# specify parameters and distributions to sample from
param_dist = {'min_samples': [10,30,50,60,100,150],
'min_cluster_size':[100,200,300,400,500],
'cluster_selection_method' : ['eom','leaf'],
'metric' : ['euclidean','manhattan']
}
# validity_scroer
validity_scorer = make_scorer(hdbscan.validity.validity_index,greater_is_better=True)
n_iter_search = 20
random_search = RandomizedSearchCV(clusterer_hdb
,param_distributions=param_dist
,n_iter=n_iter_search
,scoring=validity_scorer
,random_state=42)
random_search.fit(embedding, hdb_labels)
I'm getting an error in the random_search.fit and could not get rid of it. Any suggestions/help would be appreciated.
I’m trying to display a related section based on the article’s tags. Any articles that have similar tags should be displayed.
The idea is to iterate the article’s tags and see if any other articles have those tags.
If yes, then add that article to a related = [] array of articles I can retrieve later.
Article A: tags: [chris, mark, scott]
Article B: tags: [mark, scott]
Article C: tags: [alex, mike, john]
Article A has as related the Article B and vice-versa.
Here’s the code:
files = Dir[ROOT + 'articles/*']
# parse file
def parse(fn)
res = meta(fn)
res[:body] = PandocRuby.new(body(fn), from: 'markdown').to_html
res[:pagedescription] = res[:description]
res[:taglist] = []
if res[:tags]
res[:tags] = res[:tags].map do |x|
res[:taglist] << '%s' % [x, x]
'%s' % [x, x]
end.join(', ')
end
res
end
# get related articles
def related_articles(articles)
related = []
articles[:tags].each do |tag|
articles.each do |item|
if item[:tags] != nil && item[:tags].include?(tag)
related << item unless articles.include?(item)
end
end
end
related
end
articles = files.map {|fn| parse(fn)}.sort_by {|x| x[:date]}
articles = related_articles(articles)
Throws this error:
no implicit conversion of Symbol into Integer (TypeError)
Another thing I tried was this:
# To generate related articles
def related_articles(articles)
related = []
articles.each do |article|
article[:tags].each do |tag|
articles.each do |item|
if item[:tags] != nil && item[:tags].include?(tag)
related << item unless articles.include?(item)
end
end
end
end
related
end
But now the error says:
undefined method `each' for "tagname":String (NoMethodError)
Help a Ruby noob? What am I doing wrong? Thanks!
As an aside to the main question, I tried rewriting the tag section of the code, but still no luck:
res[:taglist] = []
if res[:tags]
res[:tags] = res[:tags].map do |x|
res[:taglist] << '' + x + ''
'' + x + ''
end.join(', ')
end
In your first attempt, the problem is in articles[:tags]. articles is an array, so you cannot access it using a symbol key.
The second attempt fails because article[:tags] is a string (from the parse function, you get the original tags, transform to HTML and then join). The :taglist key instead contains an array, you could use it.
Finally, the "related" array should be per-article so neither implementation could possibly solve your issue, as both return a single array for all your set of articles.
You probably need a two pass:
def parse(fn)
res = meta(fn)
res[:body] = PandocRuby.new(body(fn), from: 'markdown').to_html
res[:pagedescription] = res[:description]
res[:tags] ||= [] # and don't touch it
res[:tags_as_links] = res[:tags].map { |x| "#{x}" }
res[:tags_as_string] = res[:tags_as_links].join(', ')
res
end
articles = files.map { |fn| parse(fn) }
# convert each article into a hash like
# {tag1 => [self], tag2 => [self]}
# and then reduce by merge
taggings = articles
.map { |a| a[:tags].product([[a]]).to_h }
.reduce { |a, b| a.merge(b) { |_, v1, v2| v1 | v2 } }
# now read them back into the articles
articles.each do |article|
article[:related] = article[:tags]
.flat_map { |tag| taggings[tag] }
.uniq
# remove the article itself
article[:related] -= [article]
end
Can someone guide me to do this in the best possible way using matlab.
i have files with names 001_g_01.sig...001_g_08.sig, 002_g_01.sig...002_g_010.sig, 003_g_01.sig...003_g_08, upto n files.
what i want to do is assigning labels to files belong to one user (i.e.001_g_01.sig...001_g_08.sig as "User1", 002_g_01.sig...002_g_010.sig as "User2" and so on).
i have the following code to read the files.
dirName= '/FolderPath';
files = dir( fullfile(dirName,'001_g_1.Sig') );
files = {files.name};
dirName1= '/FolderPath';
files1 = dir( fullfile(dirName1,'*.Sig') );
files1 = {files1.name};
for i=1:length(files)
fname = fullfile(dirName,files{i});
%# some calculation
for j=i+1:length(files1)
fname1 = fullfile(dirName1,files1{j});
%# some calculation
end
end
files1 =
'001_g_01.sig'
'001_g_08.sig'
'003_g_01.sig'
.
.
If files1 is a cell like above, then you can write:
userlabel = {'001','002','003'};
f = cellstr(files1);
for ii = 1:3
result{ii} = strncmp(userlabel(ii),f,3);
end
You can do it in this way:
label = [repmat('User1',size(files,1),1); repmat('User2',size(files1,1),1) ];
This will create a array of labels containing 'User1' and 'User2'. If you need it separately, you can do it:
label1 = [repmat('User1',size(files,1),1)];
In Waf how can I create multiple custom tasks, that can run parallel (with --jobs=JOBS)?
Sources = ["C:\\src1.c", "C:\\Mod1\src2.c", ... 30pcs] # one per call
Incl_Paths = ["Mod1". "Mod1"] # list all of them in all call
INCL_ST = "-I%s" # how to format an include path in an argument
Ext_out = "_loc" # output file extension
The goal:
C:\\LOC.exe -IMod1 -IMod2 C:\\src1.c > build\\src1.c_loc //or better src1_loc
C:\\LOC.exe -IMod1 -IMod2 C:\\Mod1\src2.c > build\\src2.c_loc //or better src2_loc
...
I couldn't get it work
def build(bld):
for i in Sources:
bld.new_task_gen(
source = i,
rule='C:\\LOC.exe ${INCL_ST:Incl_Paths} ${SRC} > ' + i + Ext_out,
)
Also I couldn't extract the exe
# find_program(self, filename, path_list=[], var=None, environ=None, exts=''):
cfg.find_program("C:\\LOC.exe", var='LOC')
To change from:
rule='C:\\LOC.exe ...'
To:
rule='${LOC} ...'
Something like this should work with waf 1.7:
from waflib.Task import Task
from waflib.TaskGen import extension
Ext_out = "_loc" # output file extension
def configure(conf):
# loc.exe must be in the system path for this to work
conf.find_program(
'loc',
var = "LOC",
)
conf.env.Incl_Paths = ["Mod1", "Mod1"]
conf.env.INCL_ST = "-I%s"
#extension('.c')
def process_loc(self, node):
out_node = node.change_ext(Ext_out)
tsk = self.create_task('loc')
tsk.set_inputs(node)
tsk.set_outputs(out_node)
class loc_task(Task):
ext_in = ['.c']
ext_out = ['_loc']
run_str = "${LOC} ${INCL_ST:Incl_Paths} ${SRC} > ${TGT}"
def build(bld):
bld(source = ["src1.c", "src2.c"])
Well it works for me on linux faking loc ...
It's supposed to save each line in the text file into a list and split it based on commas and categorize them into multiple different lists. The error occurs at the while loop stating that the index is out of range.
lineCounter = 0
j = 0
file = open("savefile.txt","r")
with open('savefile.txt', 'r') as f:
string = [line.strip() for line in f]
for line in file:
lineCounter += 1
while(j<lineCounter):
tempList = string[j].split(',')
firstName[j] = tempList[0]
lastName[j] = tempList[1]
postition[j] = tempList[2]
department[j] = tempList[3]
seniority[j] = tempList[4]
vacationWeeks[j] = tempList[5]
sickDays[j] = tempList[6]
iD[j] = tempList[7]
status[j] = tempList[8]
j += 1
print firstName
file.close() # close the text file
NVM the problem was that the list needed to be appended rather than replaced.