def DeadFish(c):
subgroup_data = next(sg for sg in d.available_subgroups if sg['subgroup'] == 'DeadFish')
if not subgroup_data:
print("None Found")
#user_id = '64513'
user_id = subgroup_data['nyaa_id']
title_regex = subgroup_data['regex']['title']
quality_regex = subgroup_data['regex']['quality']
#title_regex = r'(?<=\[HorribleSubs\] ).*(?= \- \d{2,3} \[)'
#quality_regex = r'(?<=\[)\d*p(?=\])'
param = {}
anime_list = []
i = 1
input_title = input('Anime name: ').replace(' ', '+')
# Used to query all pages from RSS feed.
while True:
results = feedparser.parse(utils.get_rss_feed(input_title, user_id, i))
i = i + 1
if not results['entries']:
break
for hit in results['entries']:
try:
parsed_title = re.search(title_regex, hit['title']).group(0)
parsed_quality = re.search(quality_regex, hit['title']).group(0)
except Exception as e:
parsed_title = ''
parsed_quality = ''
pass
title_found = False
#optimize this
if parsed_title:
if anime_list:
for t in anime_list:
if t[0] == parsed_title and parsed_quality:
t[1].append(parsed_quality) if parsed_quality not in t[1] else None
title_found = True
if not title_found and parsed_quality:
anime_list.append((parsed_title, [parsed_quality]))
if anime_list:
print('Found titles: ')
utils.selection(list([i[0] for i in anime_list]))
#asks for input for title choice
anime_selection = anime_list[utils.selector('Select the title: ', len(anime_list))]
param['title'] = anime_selection[0]
#asks for input for quality choice
print('Available qualities: ')
utils.selection(anime_selection[1])
param['quality'] = anime_selection[1][utils.selector('Quality: ', len(anime_selection[1]))]
try:
c.execute("INSERT INTO DeadFish VALUES('%s', '%s');" %(param['title'].replace("'","''"), param['quality']))
except Exception as e:
print(e)
else:
print("No title found under %s" %input_title)
def get_position_avgcpc_based_on_maxcpc(data, maxcpc_relation):
logger = logging.getLogger(ms.LOGNAME)
logger.info("msg=get relations")
fields_check = rs.FILTER + ['avgposition', 'avgcpc']
check = [i for i in fields_check if i in list(data.columns)]
if len(fields_check) != len(check):
logger.error('error=cannot find all records in data')
raise ValueError(
"Error get_position_cpc: I cannot find all records in data")
groups = data[rs.FILTER].drop_duplicates().values
df_ret = pd.DataFrame() # initialization to avoid PEP8 warning
for i in range(0, groups.shape[0]):
selected, selected_maxcpc = utils.selection(
data=data,
group=groups[i],
metric='maxcpc_avgcpc',
maxcpc_relation=maxcpc_relation)
selected = selected[pd.notnull(selected['avgcpc'])]
if selected.shape[0] >= 2:
x = np.array(selected['maxcpc'])
x = np.log(x[:, np.newaxis] + 1)
y = np.array(selected['avgcpc'])
coeffs, _, _, _ = np.linalg.lstsq(x, y, rcond=None)
avg_cpc = list(coeffs[0] * np.log(selected_maxcpc['maxcpc'] + 1))
else:
avg_cpc = [np.nan] * rs.ACPCPOS_N_POINTS
avg_position = [
round(x, 1) for x in list(
np.linspace(1.0, rs.ACPCPOS_MAX_POS, rs.ACPCPOS_N_POINTS))
]
feed_dict, feed_dict_input_data = utils.format_output(
group=groups[i],
metric='maxcpc_avgcpc',
metric_data=avg_cpc,
position=avg_position,
selected_metric_data=selected['maxcpc'],
selected_position=selected['avgposition'],
selected_data=selected)
df_aux = pd.DataFrame(feed_dict)
df_aux_input_data = pd.DataFrame(feed_dict_input_data)
if i == 0:
df_ret = df_aux
else:
df_ret = df_ret.append(df_aux)
logger.info("msg=finish")
# TODO: WHY COPY???
return df_ret
def get_position_avgcpc(data):
logger = logging.getLogger(ms.LOGNAME)
logger.info("msg=get relations")
fields_check = rs.FILTER + ['avgposition', 'avgcpc']
check = [i for i in fields_check if i in list(data.columns)]
if len(fields_check) != len(check):
logger.error('error=cannot find all records in data')
raise ValueError(
"Error get_position_cpc: I cannot find all records in data")
groups = data[rs.FILTER].drop_duplicates().values
df_ret = pd.DataFrame() # initialization to avoid PEP8 warning
for i in range(0, groups.shape[0]):
selected, _ = utils.selection(data=data,
group=groups[i],
metric='maxcpc')
selected = selected[pd.notnull(selected['avgcpc'])]
if selected.shape[0] >= 2:
x = list(selected['avgposition'])
y = list(selected['avgcpc'])
# force the logarithm to be 0 at position 5
x = x + [rs.ACPCPOS_MAX_CONVERGENCE] * 20
y = y + [0] * 20
coeffs = np.polyfit(np.log(x), y, deg=1)
avg_cpc = list(coeffs[0] * np.log(
np.linspace(1.0, rs.ACPCPOS_MAX_POS, rs.ACPCPOS_N_POINTS)) +
coeffs[1])
else:
avg_cpc = [np.nan] * rs.ACPCPOS_N_POINTS
avg_position = [
round(x, 1) for x in list(
np.linspace(1.0, rs.ACPCPOS_MAX_POS, rs.ACPCPOS_N_POINTS))
]
feed_dict, _ = utils.format_output(group=groups[i],
metric='avgcpc',
metric_data=avg_cpc,
position=avg_position)
df_aux = pd.DataFrame(feed_dict)
if i == 0:
df_ret = df_aux
else:
df_ret = df_ret.append(df_aux)
logger.info("msg=finish")
return df_ret
def main():
#get stuff stuff from configs
DB_NAME, DB_USER = cfg.database_name, cfg.database_user
try:
connection = psycopg2.connect("dbname=%s user=%s" %(DB_NAME, DB_USER))
except Exception as e:
print(e)
utils.init_tables()
cursor = connection.cursor()
#cursor.execute("SELECT * FROM subgroups;")
available_groups = list(i['subgroup'] for i in d.available_subgroups)
if not available_groups:
print("No Subgroups configured")
return False
print("Subgroups available: ")
utils.selection(available_groups)
eval('subgroups.%s(cursor)' %available_groups[utils.selector('Select Subgroup: ', len(available_groups))])
#subgroups.HorribleSubs(cursor)
connection.commit()
connection.close()
def get_position_ctr(data):
logger = logging.getLogger(ms.LOGNAME)
logger.info("msg=get relations")
fields_check = rs.FILTER + ['avgposition', 'clickthroughrate']
check = [i for i in fields_check if i in list(data.columns)]
if len(fields_check) != len(check):
logger.error('error=cannot find all records in data')
raise ValueError(
"Error get_position_cpc: I cannot find all records in data")
groups = data[rs.FILTER].drop_duplicates().values
df_ret = pd.DataFrame() # initialization to avoid PEP8 warning
for i in range(0, groups.shape[0]):
selected, _ = utils.selection(data=data, group=groups[i], metric='ctr')
if selected.shape[0] >= 2:
selected_avgposition = list(
selected['avgposition']) + [rs.CTR_MAX_CONVERGENCE] * 20
selected_clickthroughrate = list(
selected['clickthroughrate']) + [0] * 20
x = list(
1 /
selected['avgposition']) + [1 / rs.CTR_MAX_CONVERGENCE] * 20
y = list(selected['clickthroughrate']) + [0] * 20
w = list(selected['impressions']
) + [np.mean(selected['impressions'])] * 20
coeffs = np.polyfit(x, y, deg=1)
ctr = list((coeffs[0] * 1 /
np.linspace(1.0, rs.CTR_MAX_POS, rs.CTR_N_POINTS)) +
coeffs[1])
check_decreasing = all(x1 >= x2 for x1, x2 in zip(ctr, ctr[1:]))
if not check_decreasing:
coeffsw = np.polyfit(x, y, w=w, deg=1)
ctr = list(
(coeffsw[0] * 1 /
np.linspace(1.0, rs.CTR_MAX_POS, rs.CTR_N_POINTS)) +
coeffsw[1])
check_decreasing2 = all(x1 >= x2
for x1, x2 in zip(ctr, ctr[1:]))
if not check_decreasing2:
logger.info(
"msg=NON DECREASING SHAPE FOR CLICKTHROUGHRATE")
check_negatives = [1 for xi in ctr if xi < 0]
if len(check_negatives) > 0:
msg = "NON DECREASING SHAPE FOR CLICKTHROUGHRATE: " + str(
groups[i][0]) + ' ' + str(groups[i][1])
logger.info("msg= " + msg)
else:
ctr = [np.nan] * rs.CTR_N_POINTS
selected_avgposition = list(selected['avgposition'])
selected_clickthroughrate = list(selected['clickthroughrate'])
avg_position = [
round(x, 1)
for x in list(np.linspace(1.0, rs.CTR_MAX_POS, rs.CTR_N_POINTS))
]
feed_dict, feed_dict_input_data = utils.format_output(
group=groups[i],
metric='ctr',
metric_data=ctr,
position=avg_position,
selected_data=selected,
selected_metric_data=selected_clickthroughrate,
selected_position=selected_avgposition)
df_aux = pd.DataFrame(feed_dict)
df_aux_input_data = pd.DataFrame(feed_dict_input_data)
if i == 0:
df_ret = df_aux
else:
df_ret = df_ret.append(df_aux)
logger.info("msg=finish")
return df_ret
