I'm unable to generate all entries in Kaltura. An ApiException with the message "Unable to generate list. max matches value was reached" (Error: QUERY_EXCEEDED_MAX_MATCHES_ALLOWED) gets triggered.
I tried to work around such issue by setting my sessionPrivileges to disableentitlement
class class_chk_integrity():
client = None
pagesize = 0
def __init__(self,worker_num, progress):
self.pagesize = 30
self.worker_num = worker_num
self.progress = progress
config = KalturaConfiguration(2723521)
config.serviceUrl = "https://www.kaltura.com/"
self.client = KalturaClient(config)
ks = self.client.session.start("KALTURA_ADMIN_SECRET",
"email#email.com",
KalturaPluginsCore.KalturaSessionType.ADMIN,
"KALTURA_PARTNER_ID",
432000,
"disableentitlement")
self.client.setKs(ks)
I also tried to filter based on the id's. However, I can't manage to put the filter.idNotIn to work properly.
def get_total_reg(self, cont, lastEntryIds, lastEntryCreatedAt):
filter = KalturaPluginsCore.KalturaBaseEntryFilter()
if lastEntryIds != "":
filter.idNotIn = lastEntryIds
filter.orderBy = KalturaBaseEntryOrderBy.CREATED_AT_DESC
pager = KalturaPluginsCore.KalturaFilterPager()
pageIndex = 1
entriesGot = 0
pager.pageSize = self.pagesize
pager.setPageIndex = pageIndex
result = self.client.baseEntry.list(filter, pager)
totalCount = result.totalCount
if totalCount > 10000:
totalCount = 9970
if totalCount <= 0:
cont = False
while entriesGot < totalCount:
pager.pageSize = self.pagesize
pageIndex += 1
pager.pageIndex = pageIndex
result = self.client.baseEntry.list(filter, pager)
entriesGot += len(result.objects)
for e in result.objects:
if lastEntryIds == "":
lastEntryIds.append(e.id)
else:
lastEntryIds.append(e.id)
lastEntryCreatedAt = e.createdAt
return result.totalCount, self.pagesize, cont, lastEntryIds, lastEntryCreatedAt
This is my how I'm calling the functions
if __name__ == '__main__':
try:
log = _ServiceUtils.log()
log.setup('all', 'integrity')
cont = True
lastEntryIds = []
lastEntryCreatedAt = 0
while cont is True:
kmc = class_chk_integrity(0,0)
kmc_total_reg, kmc_page_size, cont, lastEntryIds, lastEntryCreatedAt = kmc.get_total_reg(cont, lastEntryIds, lastEntryCreatedAt)
interval = 10
max_threads = math.ceil(kmc_total_reg / (interval * kmc_page_size))
# max_threads = 1
threads_list = []
print('TOTAL REG : %s | PAGE_SIZE : %s | INTERVAL : %s | THREADS : %s' % (kmc_total_reg,kmc_page_size,interval,max_threads))
progress = class_progress_thread(max_threads)
for index in range(0,max_threads):
page_ini = index * interval
page_end = index * interval + interval
progress.add_worker_progress(index,datetime.now())
threads_list.append(threading.Thread(target=thread_chk_integrity, args=(index, log, index * interval + 1,index * interval + interval,progress)))
threads_list.append(threading.Thread(target=thread_output_progress, args=(progress,max_threads)))
for thread in threads_list:
thread.start()
for thread in threads_list:
thread.join()
while not progress.stop(): time.sleep(30)
except KeyboardInterrupt:
try:
sys.exit(0)
except SystemExit:
os._exit(0)
I'd appreciate any help with this.
Thank you for your attention.
if totalCount > 10000:
totalCount = 9970
I'm curious to know why you are changing the totalCount this way.
Short answer - paging works as long as the result set is up to 10K.
To work around that, sort the result by creation date (as you did), and when you get to 10K, start with a new search where the created_at date in the filter is the last value you got in the previous search. Reset your paging of course.
Related
So for my bot, I am first extracting data via api and storing it in csv. When I run my for loop on data via api, it gives no error and runs smoothly.
But when the csv file is read and run, it gives out of bound error.
This is my function to generate data:
full_list = pd.DataFrame(columns=("date","open","high","low","close","volume","ticker","RSI","ADX","20_sma","max_100"))
def stock_data(ticker):
create_data = fetchOHLC(ticker,'minute',60)
create_data["ticker"] = ticker
create_data["RSI"] = round(rsi(create_data,25),2)
create_data["ADX"] = round(adx(create_data,14),2)
create_data["20_sma"] = round(create_data.close.rolling(10).mean().shift(),2)
create_data["max_100"] = create_data.close.rolling(100).max().shift()
create_data.dropna(inplace=True,axis=0)
create_data.reset_index(inplace=True)
return create_data
stocklist = open("stocklist.txt","r+")
tickers = stocklist.readlines()
for x in tickers:
try:
full_list = full_list.append(stock_data(x.strip()))
except:
print(f'{x.strip()} did not work')
full_list.to_csv("All_Data")
full_list
So when I run the same code below on dataframe created I got no error. But when I run the same code on the csv file, I get out of bound error.
list_tickers = full_list["ticker"].unique()
for y in list_tickers[:2]:
main = full_list[full_list["ticker"]==y]
pos = 0
num = 0
tick = y
signal_time = 0
signal_rsi = 0
signal_adx = 0
buy_time = 0
buy_price = 0
sl = 0
#to add trailing sl in this.
for x in main.index:
maxx = main.iloc[x]["max_100"]
rsi = main.iloc[x]["RSI"]
adx = main.iloc[x]["ADX"]
sma = main.iloc[x]["20_sma"]
close = main.iloc[x]["close"]
high = main.iloc[x]["high"]
if rsi > 80 and adx > 35 and close > maxx:
if pos == 0:
buy_price = main.iloc[x+1]["open"]
buy_time = main.iloc[x+1]["date"]
pos=1
signal_time = main.iloc[x]["date"]
signal_rsi = main.iloc[x]["RSI"]
signal_adx = main.iloc[x]["ADX"]
elif close < sma:
if pos == 1:
sell_time = main.iloc[x]["date"]
sell_price = sma*.998
pos=0
positions.loc[positions.shape[0]] = [y,signal_time,signal_rsi,signal_adx,buy_time,buy_price,sell_time,sell_price]
Any idea why?
Here is a cleanup and file call code:
full_list = pd.read_csv("All_data")
full_list.dropna(inplace=True,axis=0)
full_list.drop(labels="Unnamed: 0",axis=1) < index of previous dataframe
full_list.head(5)
Thanks
I have the following code
global total_pds
total_pds = []
ksplit = wr.s3.list_objects(pred_path)
ksplit = list(ksplit)
def process(x):
dk = wr.s3.read_parquet(path = pred_path+x,dataset=False)
return dk
def log_result(result):
print(len(total_pds), end = ' ')
total_pds.append(result)
def error_back(error):
print('error', error)
pool = mp.Pool(processes=4,maxtasksperchild=10)
dcms_info = [pool.apply_async(process, args=(spl,), callback = log_result, error_callback = error_back) for spl in ksplit]
for x in dcms_info:
x.wait()
pool.close()
pool.join()
dataset = pd.concat(total_pds, ignore_index=True)
the last element throw me this error:
error("'i' format requires -2147483648 <= number <= 2147483647"
Thank you
I tried to use multiprocessing on this for loop:
def segment_features(segment_pixels):
features = []
npixels, nbands = segment_pixels.shape
for b in range(nbands):
stats = scipy.stats.describe(segment_pixels[:, b])
band_stats = list(stats.minmax) + list(stats)[2:]
if npixels == 1:
# in this case the variance = nan, change it 0.0
band_stats[3] = 0.0
features += band_stats
return features
segment_ids = np.unique(segments)
objects = []
object_ids = []
for id in segment_ids:
segment_pixels = img[segments == id]
object_features = segment_features(segment_pixels)
objects.append(object_features)
object_ids.append(id)
By replacing the for loop section with this:
def segment_features_calc(segment_pixels):
segment_pixels = img[segments == id]
object_features = segment_features(segment_pixels)
objects.append(object_features)
object_ids.append(id)
print("segment "+str(id)+" features calculated")
n=mp.cpu_count()
if__name__ == '__main__':
p = mp.Pool(processes = n)
start = time.time()
async_result = p.map_async(segment_features_calc,list(segment_ids))
p.close()
p.join()
print("Complete")
end = time.time()
print('total time (s)= ' + str(end-start))
However, the multiprocessing does not get executed properly (multiprocessing stops after 0.17 seconds whereas the items to loop are close to 270,000+ segment IDs). Any insights on how to solve the issue?
Right now, my code is correctly spitting out the first game (identified by start_id) in games. I am trying to increment in the bottom two lines, but the while loop doesn't seem to read the fact that I'm incrementing. So the input of this with start_id 800 and end_id 802 is just the information from 800, for some reason.
Am I using the incrementers correctly? Should I be initializing one of i or start_id elsewhere?
games = console(start_id, end_id)
final_output = []
while start_id < (end_id + 1):
single_game = []
i = 0
game_id = games[i][0]
time_entries = games[i][1][2][0]
play_entries = games[i][1][2][1]
score_entries = games[i][1][2][2]
team_entries = games[i][1][2][3]
bovada = games[i][1][0][0][0]
at_capacity = games[i][1][0][1]
idisagree_yetrespect_thatcall = games[i][1][0][2][0]
imsailingaway = games[i][1][1][0][0]
homeiswheretheheartis = games[i][1][1][1][0]
zipper = zip(time_entries, play_entries, score_entries, team_entries)
for play_by_play in zipper:
single_game.append(game_id)
single_game.append(play_by_play)
single_game.append(bovada)
single_game.append(at_capacity)
single_game.append(idisagree_yetrespect_thatcall)
single_game.append(imsailingaway)
single_game.append(homeiswheretheheartis)
start_id += 1
i += 1
final_output.append(single_game)
return final_output
Your problem is that you initialize the increment-er i inside the while loop so every time your loop iterates i is reset to zero.
Try changing it to:
i = 0
while start_id < (end_id + 1):
...
At beginning i wanna say i'm newbie in use Python and everything I learned it came from tutorials.
My problem concerning reference to the value. I'm writing some script which is scrapping some information from web sites. I defined some function:
def MatchPattern(count):
sock = urllib.urlopen(Link+str(count))
htmlSource = sock.read()
sock.close()
root = etree.HTML(htmlSource)
root = etree.HTML(htmlSource)
result = etree.tostring(root, pretty_print=True, method="html")
expr1 = check_reg(root)
expr2 = check_practice(root)
D_expr1 = no_ks(root)
D_expr2 = Registred_by(root)
D_expr3 = Name_doctor(root)
D_expr4 = Registration_no(root)
D_expr5 = PWZL(root)
D_expr6 = NIP(root)
D_expr7 = Spec(root)
D_expr8 = Start_date(root)
#-----Reg_practice-----
R_expr1 = Name_of_practise(root)
R_expr2 = TERYT(root)
R_expr3 = Street(root)
R_expr4 = House_no(root)
R_expr5 = Flat_no(root)
R_expr6 = Post_code(root)
R_expr7 = City(root)
R_expr8 = Practice_no(root)
R_expr9 = Kind_of_practice(root)
#------Serv_practice -----
S_expr1 = TERYT2(root)
S_expr2 = Street2(root)
S_expr3 = House_no2(root)
S_expr4 = Flat_no2(root)
S_expr5 = Post_code2(root)
S_expr6 = City2(root)
S_expr7 = Phone_no(root)
return expr1
return expr2
return D_expr1
return D_expr2
return D_expr3
return D_expr4
return D_expr5
return D_expr6
return D_expr7
return D_expr8
#-----Reg_practice-----
return R_expr1
return R_expr2
return R_expr3
return R_expr4
return R_expr5
return R_expr6
return R_expr7
return R_expr8
return R_expr9
#------Serv_practice -----
return S_expr1
return S_expr2
return S_expr3
return S_expr4
return S_expr5
return S_expr6
return S_expr7
So now inside the script I wanna check value of the expr1 returned by my fynction. I don't know how to do that. Can u guys help me ? Is my function written correct ?
EDIT:
I can't add answer so I edit my current post
This is my all script. Some comments are in my native language but i add some in english
#! /usr/bin/env python
#encoding:UTF-8-
# ----------------------------- importujemy potrzebne biblioteki i skrypty -----------------------
# ------------------------------------------------------------------------------------------------
import urllib
from lxml import etree, html
import sys
import re
import MySQLdb as mdb
from TOR_connections import *
from XPathSelection import *
import os
# ------------------------------ Definiuje xPathSelectors ------------------------------------------
# --------------------------------------------------------------------------------------------------
# -------Doctors -----
check_reg = etree.XPath("string(//html/body/div/table[1]/tr[3]/td[2]/text())") #warunek Lekarz
check_practice = etree.XPath("string(//html/body/div/table[3]/tr[4]/td[2]/text())") #warunek praktyka
no_ks = etree.XPath("string(//html/body/div/table[1]/tr[1]/td[2]/text())")
Registred_by = etree.XPath("string(//html/body/div/table[1]/tr[4]/td[2]/text())")
Name_doctor = etree.XPath("string(//html/body/div/table[2]/tr[2]/td[2]/text())")
Registration_no = etree.XPath("string(//html/body/div/table[2]/tr[3]/td[2]/text())")
PWZL = etree.XPath("string(//html/body/div/table[2]/tr[4]/td[2]/text())")
NIP = etree.XPath("string(//html/body/div/table[2]/tr[5]/td[2]/text())")
Spec = etree.XPath("string(//html/body/div/table[2]/tr[18]/td[2]/text())")
Start_date = etree.XPath("string(//html/body/div/table[2]/tr[20]/td[2]/text())")
#-----Reg_practice-----
Name_of_practise = etree.XPath("string(//html/body/div/table[2]/tr[1]/td[2]/text())")
TERYT = etree.XPath("string(//html/body/div/table[2]/tr[7]/td[2]/*/text())")
Street = etree.XPath("string(//html/body/div/table[2]/tr[8]/td[2]/text())")
House_no = etree.XPath("string(//html/body/div/table[2]/tr[9]/td[2]/*/text())")
Flat_no = etree.XPath("string(//html/body/div/table[2]/tr[10]/td[2]/*/text())")
Post_code = etree.XPath("string(//html/body/div/table[2]/tr[11]/td[2]/*/text())")
City = etree.XPath("string(//html/body/div/table[2]/tr[12]/td[2]/*/text())")
Practice_no = etree.XPath("string(//html/body/div/table[3]/tr[4]/td[2]/text())")
Kind_of_practice = etree.XPath("string(//html/body/div/table[3]/tr[5]/td[2]/text())")
#------Serv_practice -----
TERYT2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[2]/td[2]/*/text())")
Street2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[3]/td[2]/text())")
House_no2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[4]/td[2]/*/text())")
Flat_no2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[5]/td[2]/i/text())")
Post_code2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[6]/td[2]/*/text())")
City2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[7]/td[2]/*/text())")
Phone_no = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[8]/td[2]/text())")
# --------------------------- deklaracje zmiennych globalnych ----------------------------------
# ----------------------------------------------------------------------------------------------
decrease = 9
No = 1
Link = "http://rpwdl.csioz.gov.pl/rpz/druk/wyswietlKsiegaServletPub?idKsiega="
# --------------------------- funkcje zdefiniowane ----------------------------------
# ----------------------------------------------------------------------------------------------
def MatchPattern(count):
sock = urllib.urlopen(Link+str(count))
htmlSource = sock.read()
sock.close()
root = etree.HTML(htmlSource)
root = etree.HTML(htmlSource)
result = etree.tostring(root, pretty_print=True, method="html")
expr1 = check_reg(root)
expr2 = check_practice(root)
D_expr1 = no_ks(root)
D_expr2 = Registred_by(root)
D_expr3 = Name_doctor(root)
D_expr4 = Registration_no(root)
D_expr5 = PWZL(root)
D_expr6 = NIP(root)
D_expr7 = Spec(root)
D_expr8 = Start_date(root)
#-----Reg_practice-----
R_expr1 = Name_of_practise(root)
R_expr2 = TERYT(root)
R_expr3 = Street(root)
R_expr4 = House_no(root)
R_expr5 = Flat_no(root)
R_expr6 = Post_code(root)
R_expr7 = City(root)
R_expr8 = Practice_no(root)
R_expr9 = Kind_of_practice(root)
#------Serv_practice -----
S_expr1 = TERYT2(root)
S_expr2 = Street2(root)
S_expr3 = House_no2(root)
S_expr4 = Flat_no2(root)
S_expr5 = Post_code2(root)
S_expr6 = City2(root)
S_expr7 = Phone_no(root)
return expr1
return expr2
return D_expr1
return D_expr2
return D_expr3
return D_expr4
return D_expr5
return D_expr6
return D_expr7
return D_expr8
#-----Reg_practice-----
return R_expr1
return R_expr2
return R_expr3
return R_expr4
return R_expr5
return R_expr6
return R_expr7
return R_expr8
return R_expr9
#------Serv_practice -----
return S_expr1
return S_expr2
return S_expr3
return S_expr4
return S_expr5
return S_expr6
return S_expr7
# --------------------------- ustanawiamy polaczenie z baza danych -----------------------------
# ----------------------------------------------------------------------------------------------
con = mdb.connect('localhost', 'root', '******', 'SANBROKER', charset='utf8');
# ---------------------------- początek programu -----------------------------------------------
# ----------------------------------------------------------------------------------------------
with con:
cur = con.cursor()
cur.execute("SELECT Old_num FROM SANBROKER.Number_of_records;")
Old_num = cur.fetchone()
count = Old_num[0]
counter = input("Input number of rows: ")
# ----------------------- pierwsze połączenie z TORem ------------------------------------
# ----------------------------------------------------------------------------------------
#connectTor()
#conn = httplib.HTTPConnection("my-ip.heroku.com")
#conn.request("GET", "/")
#response = conn.getresponse()
#print(response.read())
while count <= counter: # co dziesiata liczba
# --------------- pierwsze wpisanie do bazy danych do Archive --------------------
with con:
cur = con.cursor()
cur.execute("UPDATE SANBROKER.Number_of_records SET Archive_num=%s",(count))
# ---------------------------------------------------------------------------------
if decrease == 0:
MatchPattern(count)
# Now I wanna check some expresions (2 or 3)
# After that i wanna write all the values into my database
#------- ostatnie czynności:
percentage = count / 100
print "rekordów: " + str(count) + " z: " + str(counter) + " procent dodanych: " + str(percentage) + "%"
with con:
cur = con.cursor()
cur.execute("UPDATE SANBROKER.Number_of_records SET Old_num=%s",(count))
decrease = 10-1
count +=1
else:
MatchPattern(count)
# Now I wanna check some expresions (2 or 3)
# After that i wanna write all the values into my database
# ------ ostatnie czynności:
percentage = count / 100
print "rekordów: " + str(count) + " z: " + str(counter) + " procent dodanych: " + str(percentage) + "%"
with con:
cur = con.cursor()
cur.execute("UPDATE SANBROKER.Number_of_records SET Old_num=%s",(count))
decrease -=1
count +=1
Well, I'm assuming check_reg is a function that returns a boolean (either True or False).
If that's the case, to check the return:
if expr1:
print "True."
else:
print "False"
There's more than one way to do it, but basically, if expr1: is all you need to do the checking.
To capture the return value of a function, assign the function to a name with an equal sign, like this:
return_value = somefunction(some_value)
print('The return value is ',return_value)
Keep in mind that when the first return statement is encountered, the function will exit. So if you have more than one return statement after each other, only the first will execute.
If you want to return multiple things, add them to a list and then return the list.
Here is an improved version of your function:
def match_pattern(count):
sock = urllib.urlopen(Link+str(count))
htmlsource = sock.read()
sock.close()
root = etree.HTML(htmlSource)
# root = etree.HTML(htmlSource) - duplicate line
# result = etree.tostring(root, pretty_print=True, method="html")
function_names = [check_reg, check_practice, no_ks, Registered_by, \
Name_doctor, Registration_no, PWZL, NIP, Spec, Start_date, \
Name_of_practise, TERYT, Street, House_no2, Flat_no, \
Post_code2, City2, Phone_no]
results = []
for function in function_names:
results.append(function(root))
return results
r = match_pattern(1)
print r[0] # this will be the result of check_reg(root)
The code you have posted is quite ambigous. Can you please fix the ident to let us know what belongs to the function and which part is the script.
A function can returns only one value. You cannot do :
return something
return something_else
return ...
The function will ends when first value will be returned.
What you can do is returning a list, tuple or dict containing all your values.
For instance :
return (something,something_else,...)
or
return [something,something_else,...]
In your case, it seems better to create a class that would have all values you want as attributes, and turn this function into a method that would set the attributes values.
class Example(object):
def __init__ ( self , link , count ):
sock = urllib.urlopen(link+str(count))
htmlSource = sock.read()
sock.close()
root = etree.HTML(htmlSource)
root = etree.HTML(htmlSource)
result = etree.tostring(root, pretty_print=True, method="html")
self.expr1 = check_reg(root)
self.expr2 = check_practice(root)
self.D_expr1 = no_ks(root)
...
self.D_expr8 = Start_date(root)
#-----Reg_practice-----
self.R_expr1 = Name_of_practise(root)
...
self.R_expr9 = Kind_of_practice(root)
#------Serv_practice -----
self.S_expr1 = TERYT2(root)
...
self.S_expr7 = Phone_no(root)
Then you will be able to use this class like :
exampleInstance = Example ( "link you want to use" , 4 ) # the second argument is your 'count' value
# Now you can use attributes of your class to get the values you want
print exampleInstance . expr1
print exampleInstance . S_expr7