score = 1 if score == True else \
-1 if score == False else \
score
if lesson not in lessons:
print("{} not in lessons!".format(lesson))
lessons[lesson] = 0.5
tmp[0] += fr(score) * ft(score) * fp(lessons[lesson])**score * percentage
tmp[1] += fr(score) * fp(lessons[lesson])**score
d[user] = tmp
dict_student_problem = {}
with codecs.open(get_file_name_from_dates('logs_player_filtered', dates), 'r',
"utf-8-sig") as fin:
for line in fin:
i += 1
if time.time() - start_time > 10:
print("i", i)
start_time = time.time()
m = re.search(
"\(([0-9]+), '([^']+)', ([0-9]+), '([^']+)', '([^']+)', datetime\.datetime\(([^\)]+)\), '([^']+)', ([0-9]+)\)",
line)
try:
userid, name, id, eventName, eventType, datetime, JSONParams, contextualInfoId = m.groups(
)
type=str)
args = parser.parse_args()
IP = args.ip + ":" + str(args.port)
username = get_value_from_file('config.txt', 'username')
password = get_value_from_file('config.txt', 'password')
DBname = args.db
file_type = {
"collaborative": "download_collaborative",
"AR": "download_AR",
"competitive": "download_player"
}
file_name = get_file_name_from_dates(file_type[args.type], args.date)
if os.path.isfile(file_name):
print("file with name {} already exists".format(file_name))
exit(0)
conn = pymssql.connect(server=IP,
user=username,
password=password,
database=DBname)
print("successfully connected to server (IP:{}, username:{} DBname:{})".format(
IP, username, DBname))
cursor = conn.cursor()
def generate_query(dates, type):
score = 1 if score == True else \
-1 if score == False else \
score
if lesson not in lessons:
print("{} not in lessons!".format(lesson))
lessons[lesson] = 0.8
tmp[0] += fr(score) * ft(score) * fp(lessons[lesson])**score * percentage
tmp[1] += fr(score) * fp(lessons[lesson])**score
d[user] = tmp
with codecs.open(get_file_name_from_dates('logs_collaborative', dates), 'r',
"utf-8-sig") as fin:
for i, line in enumerate(fin):
if time.time() - start_time > 10:
print("i", i)
start_time = time.time()
m = re.search(
"\(([0-9]+), '([^']+)', ([0-9]+), '([^']+)', '([^']+)', datetime\.datetime\(([^\)]+)\), '([^']+)', ([0-9]+)\)",
line)
try:
userid, name, id, eventName, eventType, datetime, JSONParams, contextualInfoId = m.groups(
)
description="Removes unnesesary quotes that some logs might have.")
parser.add_argument('date',
help="dates (dd.mm.YYYY)",
type=lambda x: datetime.strptime(x, '%d.%m.%Y'),
nargs='+')
args = parser.parse_args()
dates = args.date
print("reading started")
start_time = time.time()
i = 0
j = 0
with codecs.open(get_file_name_from_dates('slashes_player', dates), 'r',
"utf-8-sig") as fin:
with codecs.open(get_file_name_from_dates('logs_player', dates), 'w',
"utf-8-sig") as fout:
for line in fin:
i += 1
if time.time() - start_time > 10:
print("i", i)
start_time = time.time()
line = line.replace('"[', '[')
line = line.replace(']"', ']')
line = line.replace('"Provjeri"', r'\"Provjeri\"')
fout.write(line)
password = get_value_from_file('config.txt', 'password')
type_tag = {"collaborative": "", "AR": "_AR", "competitive": "_player"}
users = set()
print("copying _real files to _tmp files")
for file_name in glob.glob('tmp/users/results/*_real.txt'):
new_file_name = "{}_tmp.txt".format(file_name[:-9])
copyfile(file_name, new_file_name)
i = 0
print("adding data to _tmp files")
for date in dates:
file = get_file_name_from_dates("users", [date],
prefix="tmp/users/logs/",
suffix="{}.txt".format(type_tag[type]))
if os.path.isfile(file):
with codecs.open(file, "r", "utf-8-sig") as flog:
for line in flog:
user, grade = line.strip().split(":")
with open(
"tmp/users/results/{}{}_tmp.txt".format(
user, type_tag[type]), "a") as fuser:
fuser.write("{}:{}\n".format(date.strftime("%d.%m.%Y"),
grade))
users.add(user)
return query
for type in args.types:
dates = []
query = generate_query(type, args.sd, args.ed)
print("executing query ({})".format(query))
cursor.execute(query)
print("query executed")
i = 0
start_time = time.time()
file_name = get_file_name_from_dates('dates_{}'.format(type), [args.sd, args.ed])
print("writing to {}".format('dates_{}.txt'.format(type)))
with codecs.open(file_name, 'w', "utf-8-sig") as f:
for row in cursor:
i += 1
if time.time() - start_time > 10:
start_time = time.time()
print("i", i)
f.write("{}\n".format(row[0]))
dates.append(row[0].strip())
print("i", i)
print("finished writing to {}".format('dates_{}.txt'.format(type)))
nargs='+')
args = parser.parse_args()
dates = args.date
print("reading started")
regex = r'(.*)<img([^>]+)([^\\>])"(.*)'
ct = r'\1<img\2\3\"\4'
i = 0
i2 = 0
j = 0
start_time = time.time()
with codecs.open(get_file_name_from_dates('download_collaborative', dates),
'r', "utf-8-sig") as fin:
with codecs.open(get_file_name_from_dates('slashes_collaborative', dates),
'w', "utf-8-sig") as fout:
for line in fin:
j += 1
if time.time() - start_time > 10:
print("i", i)
print("j", j)
start_time = time.time()
if "\\" in line:
while "\\\"" in line:
line = re.sub(r'\\\"', "\"", line)
import re
import time
from utils import get_file_name_from_dates
import argparse
from datetime import datetime
parser = argparse.ArgumentParser(description="Removes unnesesary slashes that some logs might have.")
parser.add_argument('date', help="dates (dd.mm.YYYY)", type=lambda x: datetime.strptime(x, '%d.%m.%Y'), nargs='+')
args = parser.parse_args()
dates = args.date
from pprint import pprint
print("reading started")
start_time = time.time()
with codecs.open(get_file_name_from_dates('download_AR', dates), 'r', "utf-8-sig") as fin:
with codecs.open(get_file_name_from_dates('logs_AR', dates), 'w', "utf-8-sig") as fout:
for i, line in enumerate(fin):
line = line.replace('":""Lijepu našu" je napisao?"', '":"\\"Lijepu našu\\" je napisao?"')
line = line.replace('"Tko je pokrenuo prve novine na hrvatskom jeziku "Novine horvatske" i prilog "Danica"?"', '"Tko je pokrenuo prve novine na hrvatskom jeziku \\"Novine horvatske\\" i prilog \\"Danica\\"?"')
line = line.replace('"Koji politicar je pokrenuo "Novine horvatske"', '"Koji politicar je pokrenuo \\"Novine horvatske\\"')
line = line.replace('""Ljubav i zloba" je opera koju je napisao?"', '"\\"Ljubav i zloba\\" je opera koju je napisao?"')
line = line.replace('"Tko je pokrenuo "Novine horvatske", prve novine na hrvatskom jeziku?"', '"Tko je pokrenuo \\"Novine horvatske\\", prve novine na hrvatskom jeziku?"')
fout.write(line)
print("reading ended")
description="Removes unnesesary quotes that some logs might have.")
parser.add_argument('date',
help="dates (dd.mm.YYYY)",
type=lambda x: datetime.strptime(x, '%d.%m.%Y'),
nargs='+')
args = parser.parse_args()
dates = args.date
print("reading started")
start_time = time.time()
i = 0
j = 0
with codecs.open(get_file_name_from_dates('slashes_collaborative', dates), 'r',
"utf-8-sig") as fin:
with codecs.open(get_file_name_from_dates('quotes_collaborative', dates),
'w', "utf-8-sig") as fout:
for line in fin:
i += 1
if time.time() - start_time > 10:
print("i", i)
start_time = time.time()
line = line.replace('"[', '[')
line = line.replace(']"', ']')
line = line.replace('"Provjeri"', r'\"Provjeri\"')
fout.write(line)
score = 1 if score == True else \
-1 if score == False else \
score
if user not in users:
if len(str(user)) < 20: print("{} not in users!".format(user))
users[user] = 0.5
tmp[0] += fr(score) * ft(score) * fp(users[user])**score * percentage
tmp[1] += fr(score) * fp(users[user])**score
d[lesson] = tmp
with codecs.open(get_file_name_from_dates('logs_AR', dates), 'r',
"utf-8-sig") as fin:
for line in fin:
i += 1
if time.time() - start_time > 10:
print("i", i)
start_time = time.time()
m = re.search(
"\(([0-9]+), '([^']+)', ([0-9]+), '([^']+)', '([^']+)', datetime\.datetime\(([^\)]+)\), '([^']+)', ([0-9]+)\)",
line)
try:
userid, name, id, eventName, eventType, datetime, JSONParams, contextualInfoId = m.groups(
)
parser.add_argument('-port', help="PORT of the database", default=1955, type=int)
parser.add_argument('-db', help="Database name", default="ExperientialSampling1", type=str)
action = parser.add_mutually_exclusive_group(required=True)
action.add_argument('-t', help='calculate lessons/users (train system)', type=int)
action.add_argument('-e', help='evaluate users\' score', action='store_true')
args = parser.parse_args()
# get all dates in range
arguments = ["-types", args.type, "-sd", args.starting_date.strftime("%d.%m.%Y"), "-ed", args.ending_date.strftime("%d.%m.%Y"), "-ip", args.ip, "-port", args.port, "-db", args.db]
if args.f: arguments += ["-f", args.f]
execute_python_script("get_dates.py", arguments)
dates_file_name = get_file_name_from_dates("dates_{}".format(args.type), [args.starting_date, args.ending_date])
if not os.path.isfile(get_file_name_from_dates("dates_{}".format(args.type), [args.starting_date, args.ending_date])):
print("ERROR: get_dates.py didn't create {}".format(dates_file_name))
exit(1)
preprocess = {
"AR": "quotes_AR.py",
"competitive": "slashes_quotes_filter_player.py",
"collaborative": "slashes_qoutes_commas.py"
}
analyse_users = {
"AR": "analyseUsers_AR.py",
"competitive": "analyseUsers_player.py",
"collaborative": "analyseUsers.py",
}
score = 1 if score == True else \
-1 if score == False else \
score
if user not in users:
print("{} not in users!".format(user))
users[user] = 0.5
tmp[0] += fr(score) * ft(score) * fp(users[user])**score * percentage
tmp[1] += fr(score) * fp(users[user])**score
d[lesson] = tmp
dict_student_problem = {}
with codecs.open(get_file_name_from_dates('logs_player_filtered', dates), 'r', "utf-8-sig") as fin:
for line in fin:
i += 1
if time.time() - start_time > 10:
print("i", i)
start_time = time.time()
m = re.search("\(([0-9]+), '([^']+)', ([0-9]+), '([^']+)', '([^']+)', datetime\.datetime\(([^\)]+)\), '([^']+)', ([0-9]+)\)", line)
try:
userid, name, id, eventName, eventType, datetime, JSONParams, contextualInfoId = m.groups();
name = name.strip()
year, month, day, *rest = [int(item) for item in datetime.split(', ')]
