def ajouter_mails(liste_objets, liste_mail_et_noms):
#On parcourt nos instances d'apprenants dans la liste d'objets apprenants :
for x in liste_objets:
#On boucle sur la liste de mails qui doit être structurée ainsi [ mail, [ nom_généré, prenom_généré]]
for y in liste_mail_et_noms:
#On vérifie si le prénom (nettoyé) de l'objet est égal au prénom généré à partir du mail
if ud(x.prenom.lower()).replace("'", '') == y[1][0]:
#On vérifie si le nom (nettoyé) de l'objet est égal au nom généré à partir du mail
if ud(x.nom.lower()).replace("'", '') == y[1][1]:
#Si tout correspond, on peut attribuer le mail de rang y à l'objet en question.
setattr(x, "mail", y[0])
return liste_objets
def cleanup(d_df):
global f_path, file_list
lis_val = list()
if d_df != 1:
par = None
else:
par = 'utf-8'
with open(f_path + file_list[d_df] + '.csv', encoding=par) as m_file:
reader = csv.reader(m_file)
gh = 0
for item in reader:
gh += 1
if gh == 1 and d_df == 0:
try:
item[0] = ud(item[0]).split('?')[1]
except:
pass
lis_val.append(item)
#Cleaning up list
if d_df == 3 and 'Aggregated engagement metrics for your' in lis_val[0][0]:
lis_val.pop(0)
t_list = list()
for element in lis_val:
t_list.append([])
for items in element:
if len(items) == 0:
k_items = 0
else:
try:
if float(items) == int(float(items)):
k_items = int(float(items))
else:
k_items = float(items)
except:
try:
k_items = str(ud(items))
except:
k_items = str(items)
t_list[-1].append(k_items)
with open(f_path + file_list[d_df] + '.csv', 'w', newline='') as outfile:
mywriter = csv.writer(outfile)
for row in t_list:
mywriter.writerow(row)
def generate_cypher_data(file, info_dict, cur_year):
cypher_create_wrestlers = []
cypher_create_participants = []
cypher_create_elims = []
for inf in info_dict:
#print(inf)
time_val = clean_time_string(inf['time_in'])
#time_val.second
time_val_2 = time_val - dt(1900, 1, 1)
#print(time_val_2.total_seconds())
#print(time_val)
normalized = ud(inf['wrestler'])
alias = normalized.replace(" ", "")
alias = re.sub("\W*", "", alias)
cypher_create_wrestlers.append("MERGE (" + alias +
":Wrestler {name:'" + normalized +
"'})\n")
if 'brand' in inf:
cypher_create_participants.append("CREATE (" + alias +
")-[:WAS_IN{draw:" +
inf['draw'] + ", brand:" +
inf['brand'] + "}]->(RR" +
cur_year + ")\n")
else:
cypher_create_participants.append("CREATE (" + alias +
")-[:WAS_IN{draw:" +
inf['draw'] + "}]->(RR" +
cur_year + ")\n")
#print("time in: " + inf['time_in'])
if type(inf['eliminators']) is list:
for elim in inf['eliminators']:
cypher_create_elims.append("CREATE (" + alias +
")-[:ELIMINATED_BY {order:" +
inf['order'] + ", time:\"" +
str(time_val_2.total_seconds()) +
"\"}]->(" + elim + ")\n")
else:
cypher_create_elims.append("CREATE (" + alias +
")-[:ELIMINATED_BY {order:" +
inf['order'] + ", time:\"" +
str(time_val_2.total_seconds()) +
"\"}]->(" + inf['eliminators'] + ")\n")
for ccw in cypher_create_wrestlers:
file.write(ccw)
file.write("//Participations\n")
for ccp in cypher_create_participants:
file.write(ccp)
file.write("//Eliminations\n")
for cce in cypher_create_elims:
file.write(cce)
file.close()
map(os.makedirs, map(concat_path, subfolders))
if __name__ == '__main__':
parser = get_parser()
args = parser.parse_args()
if args.do == 'alumnifolders':
PATH = join(PATH_D4E, 'alumni')
list_file = join(PATH, 'alumnilist.xlsx')
if exists(list_file):
df = pd.read_excel(list_file,
dtype={
'cu': 'object',
'name': 'object',
'surname': 'object'
})
for i, r in df.iterrows():
if (not pd.isnull(r['name'])) and (not pd.isnull(
r['surname'])):
fname = '_'.join([
str(r['cu']),
ud(r['name'].split(' ')[0]),
ud(r['surname'].split(' ')[0])
])
print(fname)
try:
os.mkdir(join(PATH, fname))
except Exception as e:
print('Ya existe el directorio ' + fname)
import pandas as pd
from unidecode import unidecode as ud
#get driver standings > csv
all_drivers = pd.read_html(
'https://www.formula1.com/en/results.html/2019/drivers.html')
all_drivers = all_drivers[0]
all_drivers = all_drivers.drop(['Unnamed: 0', 'Unnamed: 6'], axis=1)
all_drivers.to_csv('all_drivers.csv')
#create empty DataFrame
f1_2019 = pd.DataFrame()
#get and append individual driver dfs > csv
for i in all_drivers['Driver']:
name = ud(i).split()
tag = name[0][:3].upper() + name[1][:3].upper() + '01'
driver = pd.read_html(
'https://www.formula1.com/en/results.html/2019/drivers/' + tag + '/' +
name[0].lower() + '-' + name[1].lower() + '.html')
driver = driver[0].drop(['Unnamed: 0', 'Unnamed: 6'], axis=1)
driver['Date'] = pd.to_datetime(driver['Date'])
driver['Name'] = name[1]
driver['Total PTS'] = driver['PTS'].cumsum()
f1_2019 = f1_2019.append(driver)
f1_2019.to_csv('f1_2019.csv')
#get fastest lap df > csv
fastest_lap = pd.read_html(
'https://www.formula1.com/en/results.html/2019/fastest-laps.html')
def unidecode(string):
return ud(string)
print(bdd.is_connected())
liste_apprenants = []
curseur.execute('SELECT id_apprenant, nom, prenom, mail FROM apprenants;')
for x in curseur.fetchall():
liste_apprenants.append(x)
objets = []
for x in liste_apprenants:
nouvelle_instance = Apprenant(x)
objets.append(nouvelle_instance)
for x in range(0, len(objets)):
for y in range(0, len(liste_mails)):
if ud(objets[x].prenom.lower()).replace("'",
'') == liste_mails[y][1][0]:
if ud(objets[x].nom.lower()).replace("'",
'') == liste_mails[y][1][1]:
objets[x].mail = liste_mails[y][0]
for x in range(0, len(objets)):
curseur.execute(
f"UPDATE apprenants SET mail = '{objets[x].mail}' WHERE id_apprenant = {objets[x].id};"
)
bdd.commit()
for x in range(0, len(objets)):
print(objets[x].__dict__.items())