def gen_syn_adv(self):
adv = random.choice(self.advs)
synAdv = ""
if random.random() < 0.2:
synAdv = self.gen_syn_adv()
return utility.concat(synAdv, adv)
def gen_syn_adj(self):
synAdv = ""
adj = random.choice(self.adjs)
if random.random() < 0.2:
synAdv = self.gen_syn_adv()
return utility.concat(synAdv, adj)
def gen_syn_nominale(self):
article = random.choice(self.articles)
nom = random.choice(self.noms)
prep = ""
adj = ""
# Structure optionnel ajoutée au hasard
if random.random() < 0.3:
prep = self.gen_syn_prep()
if random.random() < 0.3:
adj = self.gen_syn_adj()
return utility.concat(article, nom, prep, adj)
def prep_dummy_csv():
from hashlib import sha256
# We need to hash customer emails as a semi-unique identifier
def hash(inp):
bytes=inp.encode('utf-8')
h_e = sha256()
h_e.update(bytes)
return h_e.hexdigest()[:6]
concat = u.concat('CSV_Files')
to_dummy_csv = u.clean(concat)
email_hashes = [hash(i) for i in to_dummy_csv['Email_Billing']]
to_dummy_csv['Email_Billing'] = email_hashes
to_dummy_csv[['Full_Name_Billing', 'Full_Name_Shipping', 'Address_1_Shipping']]='Restricted'
to_dummy_csv.drop('Unnamed:_0', axis=1, inplace=True)
to_dummy_csv['State_Name_Shipping'].loc[to_dummy_csv['State_Name_Shipping'].isna()] = 'Missing'
to_dummy_csv['Discount_Amount'].loc[to_dummy_csv['Discount_Amount'].isna()] = to_dummy_csv['Discount_Amount'].mean()
print(to_dummy_csv.isna().sum())
to_dummy_csv.dropna(inplace=True)
to_dummy_csv= to_dummy_csv.loc[to_dummy_csv['Order_Date']<='2020-12-31-23:59']
print(to_dummy_csv.head(5))
print(to_dummy_csv.columns)
print(to_dummy_csv.tail(5))
to_dummy_csv.to_csv('dummy.csv')
def serve_frame(file):
frame = u.concat(file)
frame = u.clean(frame)
return frame
dfa = ma.DataframeAnalysis(frame)
dfa.avg_discount_rate()
elif sys.argv[1] == 'pcp':
frame = serve_frame('CSV_Files')
dfpa = ma.ProductAnalysis(frame)
dfpa.highest_positive_product_change_over_month_analysis()
elif sys.argv[1] == 'pcp':
frame = serve_frame('CSV_Files')
dfpa = ma.ProductAnalysis(frame)
dfpa.highest_negative_product_change_over_month_analysis()
elif sys.argv[1] == 'plg':
frame = serve_frame('CSV_Files')
dfpa = ma.ProductAnalysis(frame)
dfpa.product_line_change_over_month_graph()
file = u.concat('CSV_FIles')
# Test slice for functionality
file = u.clean(file)
cp1 = u.FieldLoader(file)
u.date_difference()
u.date_difference_email_list_compiler()
#profiles_master_init()
'''Work log:
2/25
functionality and indexing for time: reading, saving and analyzing time fields (completed?)
Streamline initializations: maybe make a initialization function in Analysis so we can simply click on the py file
and run the program
**As of now customer_profile line 63 should protect from repeated inputs of sales information. This will need to be tested.
def gen_syn_verbale(self):
verbe = self.gen_verbe_conjugue()
complement = self.gen_syn_nominale()
return utility.concat(verbe, complement)
def gen_phrase(self):
nominal = self.gen_syn_nominale()
verbal = self.gen_syn_verbale()
return utility.concat(nominal, verbal +
".") # On ajoute un point pour finir la phrase
def gen_syn_prep(self):
prep = random.choice(self.preps)
syn_nominal = self.gen_syn_nominale()
return utility.concat(prep, syn_nominal)