def get_team_schedule(team, year):
"""
:param team: string
:param year: string or int
:return: pandas.DataFrame containing the schedule of the team for the given year
"""
base_url = "https://www.sports-reference.com/cbb/schools/"
url = base_url + team + '/' + str(year) + '-schedule.html'
r = get_request(url, headers={"User-Agent": "Mozilla/5.0"})
if r is None:
return None
soup = BeautifulSoup(r.text, 'lxml')
for caption in soup.find_all('caption'):
if caption.get_text() == 'Schedule and Results Table':
table = caption.find_parent('table')
data = parse_table(table)
columns = get_table_header(table)
df = pd.DataFrame(data, index=np.arange(1, len(data) + 1), columns=columns)
return df
def get_schools_stats(year):
"""
:param year: string or int
:return: pandas.DataFrame containing statistics for each team for a given year
"""
base_url = "https://www.sports-reference.com/cbb/seasons/"
url = base_url + str(year) + '-school-stats.html'
r = get_request(url, headers={"User-Agent": "Mozilla/5.0"})
if r is None:
return None
soup = BeautifulSoup(r.text, 'lxml')
table = soup.find_all('table')[0]
hrefs = table.find_all('a', href=True)
link_names = []
for href in hrefs:
link_names.append(href['href'].split('/')[3])
data = parse_table(table)
columns = get_table_header(table, index=1)
df = pd.DataFrame(data, index=np.arange(1, len(data) + 1), columns=columns)
df['NCAA'] = [el.endswith('NCAA') for el in df[df.columns[0]]]
df[df.columns[0]] = df[df.columns[0]].str.replace('NCAA', '').str.strip()
df['Link names'] = link_names
return df
def parse(self, msg):
t = utils.parse_table(msg)
for k, v in t.iteritems():
if k == 'frame':
self.d['frame_string'] = v
self.d['frame'] = frame.Frame.parse_from(v)
elif k == 'deaths':
self.d['deaths'] = utils.parse_list(v)
else:
self.d[k] = v
def parse_membership_fees(self):
res = {}
membership_fees = self.main_soup.select_one(".tab-content")
tabs_ids = ["hot_desk", "dedicated_desk", "private_office"]
for tab_id in tabs_ids:
table = self.main_soup.select_one("#%s table" % tab_id)
data = parse_table(table)
res["tab_id"] = data
return res
def test_cinder_lvs_volume_on_node(host):
# get list of volumes and associated hosts from utility container
cmd = "{} cinder list --all-t --fields os-vol-host-attr:host '".format(
os_pre)
vol_table = host.run(cmd).stdout
vol_hosts = utils.parse_table(vol_table)[1]
for vol, chost in vol_hosts:
chost = chost.split('@')[0].split('.')[0]
# VOLEXISTS test
cmd = "{} {} lvs | grep volume-{}".format(ssh_pre, chost, vol)
host.run_expect([0], cmd)
cmd = "{} cinder snapshot-list --all- --volume-id={} '".format(
os_pre, vol)
snap_table = host.run(cmd).stdout
snaps = utils.parse_table(snap_table)[1]
for snap in snaps:
# SNAPEXISTS test
snap_vol = snap[1]
cmd = "{} {} lvs | grep _snapshot-{}".format(
ssh_pre, chost, snap_vol)
host.run_expect([0], cmd)
def team_extractor(local=False):
soup = get_html_soup(LOCAL_PATH, LINK, local)
con = soup.find(id='pageContent').find(attrs={'class': 'content'})
tables = con.find_all('table')
data = []
for t in tables:
data.extend(parse_table(t))
teams = {}
for team in data:
if len(team) > 0:
teams[normalize(team[-4])] = [team[-1], team[-2], team[-3]]
return teams
def team_rate_extractor(local=False):
soup = get_html_soup(LOCAL_PATH, LINK, local)
con = soup.find(id='pageContent').find(attrs={'class': 'content'})
tables = con.find_all('table')
data = []
for t in tables:
data.extend(parse_table(t))
teamrating = []
for team in data:
if len(team) > 0:
if len(team) >= 5:
teamrating.append([normalize(team[-5]), team[-1]])
else:
teamrating.append([normalize(team[-2]), team[-1]])
teamrating = sorted(teamrating, key=lambda x: float(x[1]), reverse=True)
teamrating = list(zip(*teamrating))[0]
return teamrating
def test_cinder_verify_attach(host):
# get list of volumes and server attatchments from utility container
cmd = "{} cinder list --all-t '".format(os_pre)
vol_table = host.run(cmd).stdout
vol_list = utils.parse_table(vol_table)[1]
for vol in vol_list:
vol_id = vol[0]
attach_id = vol[7]
if not attach_id:
continue
cmd1 = "{} openstack server show {} -f json '".format(
os_pre, attach_id)
res = host.run(cmd1)
server = json.loads(res.stdout)
hypervisor = server['OS-EXT-SRV-ATTR:hypervisor_hostname'].split(
'.')[0]
instance_name = server['OS-EXT-SRV-ATTR:instance_name']
# ATTATCHED test
cmd2 = "{} {} virsh dumpxml {} | grep {}".format(
ssh_pre, hypervisor, instance_name, vol_id)
host.run_expect([0], cmd2)
def get_ken_pomeroys_rating(year):
"""
:param year: string or int
:return: pandas.DataFrame containing Ken Pomeroy’s ratings for a given year
"""
base_url = "https://kenpom.com/index.php?y="
url = base_url + str(year)
r = get_request(
url,
headers={
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/7046A194A"
})
if r is None:
return None
soup = BeautifulSoup(r.text, 'lxml')
table = soup.find_all('table')[0]
data = parse_table(table)
columns = get_table_header(table, index=1)
data = np.array(data)
cleaned_data = []
for i in data:
mask = [1, 2, 3, 4, 5, 7, 9, 11, 13, 15, 17, 19]
cleaned_data.append(i[mask])
df = pd.DataFrame(cleaned_data,
index=np.arange(1,
len(data) + 1),
columns=columns)
df[df.columns[0]] = df[df.columns[0]].str.strip('0123456789 ')
return df
def get_espn_bpi(year):
"""
:param year: string or int
:return: pandas.DataFrame
"""
base_url = "http://www.espn.com/mens-college-basketball/bpi/_/view/bpi/season/"
data = []
for i in range(1, 9):
url = base_url + str(year) + '/page/' + str(i)
r = get_request(
url,
headers={
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/7046A194A"
})
if r is None:
return data
soup = BeautifulSoup(r.text, 'lxml')
try:
table = soup.find_all('table')[1]
except:
break
data.extend(parse_table(table))
columns = ['ranking'] + get_table_header(table, index=0)
df = pd.DataFrame(data, columns=columns)
return df
import inspect
from pprint import pprint
from itertools import product
from config import *
import ROOT as R
from ROOT import RooFit as RF
R.RooRandom.randomGenerator().SetSeed(54321)
import shapes
import utils
local_dir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
efficiencies = utils.parse_table("../efficiencies/Efficiencies.txt",nBins_Y, nBins_PT)[0]
efficiencies_err = utils.parse_table("../efficiencies/Efficiencies.txt",nBins_Y, nBins_PT)[1]
yields = utils.parse_table("../fitting/Signal_Yields.txt",nBins_Y, nBins_PT)[0]
yields_err = utils.parse_table("../fitting/Signal_Yields.txt",nBins_Y, nBins_PT)[1]
yield_distr = R.TH2F("yield_distr", "Yield distribution", nBins_Y, x_Y_LL , x_Y_UL , nBins_PT, x_PT_LL , x_PT_UL )
yield_distr.GetXaxis().SetTitle("#eta")
yield_distr.GetYaxis().SetTitle("P^{T} [GeV/c]")
yield_distr_table = [[0 for x in xrange(nBins_Y)] for x in xrange(nBins_PT)]
yield_distr_table_err = [[0 for x in xrange(nBins_Y)] for x in xrange(nBins_PT)]
for i, j in product(range(nBins_Y), range(nBins_PT)):
yield_distr_table[i][j]=float(yields[i][j])/float(efficiencies[i][j])
yield_distr_table_err[i][j] = float(yields[i][j])/float(efficiencies[i][j])*R.TMath.sqrt((float(efficiencies_err[i][j])/float(efficiencies[i][j]))**2+(float(yields_err[i][j])/float(yields[i][j]))**2)
yield_distr.SetBinContent(i+1, j+1, yield_distr_table[i][j])
def get_list(self):
out = subprocess.check_output([self._binpath, 'list'])
return parse_table(out)
import inspect
from pprint import pprint
from itertools import product
from config import *
import ROOT as R
from ROOT import RooFit as RF
R.RooRandom.randomGenerator().SetSeed(54321)
import shapes
import utils
local_dir = os.path.dirname(
os.path.abspath(inspect.getfile(inspect.currentframe())))
efficiencies = utils.parse_table("../efficiencies/Efficiencies.txt", nBins_Y,
nBins_PT)[0]
efficiencies_err = utils.parse_table("../efficiencies/Efficiencies.txt",
nBins_Y, nBins_PT)[1]
yields = utils.parse_table("../fitting/Signal_Yields.txt", nBins_Y,
nBins_PT)[0]
yields_err = utils.parse_table("../fitting/Signal_Yields.txt", nBins_Y,
nBins_PT)[1]
yield_distr = R.TH2F("yield_distr", "Yield distribution", nBins_Y, x_Y_LL,
x_Y_UL, nBins_PT, x_PT_LL, x_PT_UL)
yield_distr.GetXaxis().SetTitle("#eta")
yield_distr.GetYaxis().SetTitle("P^{T} [GeV/c]")
yield_distr_table = [[0 for x in xrange(nBins_Y)] for x in xrange(nBins_PT)]
yield_distr_table_err = [[0 for x in xrange(nBins_Y)]
for x in xrange(nBins_PT)]