def prepare_ds(ds):
ds['Date'] = p.to_datetime(ds['Date'], format='%d/%m/%Y')
ds['Day'] = ds['Date'].dt.weekday_name
ds = imp.one_hot(ds, 'Day', header='Day_')
ds = pre_u.mean_std_cust_per_shop_per_day(ds)
ds = pre_u.eliminate_IsOpen_zeros(ds)
ds = pre_u.add_avg_cust_per_shop(ds)
ds = pre_u.add_std_cust_per_shop(ds)
ds = pre_u.add_max_cust_per_shop(ds)
ds = pre_u.add_min_cust_per_shop(ds)
return ds
def prepare_ds(ds):
ds['Date'] = p.to_datetime(ds['Date'], format='%d/%m/%Y')
ds['Day'] = ds['Date'].dt.weekday_name
ds = imp.one_hot(ds, 'Day', header='Day_')
ds = pre_u.mean_std_sales_per_shop_per_day(ds)
print(ds[['StoreID', 'MeanSalesPerShopPerDay', 'StdSalesPerShopPerDay']])
ds = pre_u.eliminate_IsOpen_zeros(ds)
ds = pre_u.add_avg_per_shop(ds)
ds = pre_u.add_std_per_shop(ds)
ds = pre_u.add_max_per_shop(ds)
ds = pre_u.add_min_per_shop(ds)
return ds
def __prepare_sales_train_ds(ds):
ds['Date'] = p.to_datetime(ds['Date'], format='%d/%m/%Y')
ds['Day'] = ds['Date'].dt.weekday_name
ds['Date'] = ds['Date'].apply(lambda x: x.strftime('%Y-%m-%d'))
ds['Month'] = ds['Date']
ds['Month'] = ds['Month'].apply(lambda x: x.split("-")[1])
ds = imp.one_hot_numeric(ds, 'Month', 'Month_')
ds = imp.one_hot_numeric(ds, 'Region', 'Region_')
ds = imp.one_hot(ds, 'Day', header='Day_')
ds = pre_u.eliminate_IsOpen_zeros(ds)
ds = pre_u.mean_std_sales_per_shop_per_day(ds)
ds = pre_u.add_avg_per_shop(ds)
ds = pre_u.add_std_per_shop(ds)
ds = pre_u.add_max_per_shop(ds)
ds = pre_u.add_min_per_shop(ds)
ds = pre_u.mean_sales_per_month_per_region(ds)
return ds
def __prepare_customers_train_ds(das, m1, a1, m2, a2):
das['Date'] = pandas.to_datetime(das['Date'], format='%d/%m/%Y')
das['Day'] = das['Date'].dt.weekday_name
das['Date'] = das['Date'].apply(lambda x: x.strftime('%Y-%m-%d'))
das['Month'] = das['Date']
das['Month'] = das['Month'].apply(lambda x: x.split("-")[1])
das = imp.one_hot(das, 'Day', header='Day_')
das = imp.one_hot_numeric(das, 'Month', 'Month_')
das = imp.one_hot_numeric(das, 'Region', 'Region_')
dfrom = utils.get_frame_out_of_range(das, m1, a1, m2, a2)
das = preu.eliminate_IsOpen_zeros(das)
das = preu.mean_std_cust_per_shop_per_day(das, dfrom)
das = preu.add_avg_cust_per_shop(das, dfrom)
das = preu.add_std_cust_per_shop(das, dfrom)
das = preu.add_max_cust_per_shop(das, dfrom)
das = preu.add_min_cust_per_shop(das, dfrom)
das = preu.mean_cust_per_month_per_shop(das, dfrom)
das = preu.mean_cust_per_month_per_region(das, dfrom)
return das
def __prepare_customers_test_ds(ds, dfrom):
ds['NumberOfSales'] = p.Series(np.zeros(len(ds)), ds.index)
ds['NumberOfCustomers'] = p.Series(np.zeros(len(ds)), ds.index)
ds['Date'] = p.to_datetime(ds['Date'], format='%d/%m/%Y')
ds['Day'] = ds['Date'].dt.weekday_name
ds['Date'] = ds['Date'].apply(lambda x: x.strftime('%Y-%m-%d'))
ds['Month'] = ds['Date']
ds['Month'] = ds['Month'].apply(lambda x: x.split("-")[1])
ds = imp.one_hot(ds, 'Day', header='Day_')
ds = imp.one_hot_numeric(ds, 'Month', 'Month_')
ds = imp.one_hot_numeric(ds, 'Region', 'Region_')
ds = pre_u.eliminate_IsOpen_zeros(ds)
ds = pre_u.mean_std_cust_per_shop_per_day(ds, dfrom)
ds = pre_u.add_avg_cust_per_shop(ds, dfrom)
ds = pre_u.add_std_cust_per_shop(ds, dfrom)
ds = pre_u.add_max_cust_per_shop(ds, dfrom)
ds = pre_u.add_min_cust_per_shop(ds, dfrom)
ds = pre_u.mean_cust_per_month_per_shop(ds, dfrom)
ds = pre_u.mean_cust_per_month_per_region(ds, dfrom)
return ds