def reorder_attributes(ds, list_order):
new = p.DataFrame(index=ds.index)
for attr in list_order:
try:
new[attr] = p.Series(d.to_numpy(ds[[attr]]).squeeze(), index=new.index)
except Exception:
new[attr] = p.Series(np.zeros(len(new)), index=new.index)
return new
def drop_useless(ds):
x = d.to_numpy(
ds.drop([
'NumberOfSales', 'StoreID', 'Date', 'IsOpen', 'Region',
'CloudCover', 'Max_Sea_Level_PressurehPa', 'WindDirDegrees',
'Max_Dew_PointC', 'Mean_Sea_Level_PressurehPa',
'Min_Sea_Level_PressurehPa', 'Day'
],
axis=1))
return x
def predict(self, row):
sc = (row['StoreType_Shopping Center'] == 1).all()
clean_row = data_manager.to_numpy(
row.drop([
'NumberOfSales', 'Month', 'NumberOfCustomers', 'StoreID',
'Date', 'IsOpen', 'Region', 'CloudCover',
'Max_Sea_Level_PressurehPa', 'WindDirDegrees',
'Max_Dew_PointC', 'Mean_Sea_Level_PressurehPa',
'Min_Sea_Level_PressurehPa', 'Day'
],
axis=1)).squeeze()
clean_row = clean_row.reshape([1, -1])
if sc:
return self.predict_sc(clean_row).squeeze()
else:
return self.predict_oth(clean_row).squeeze()
def opendaybeforegeneralplot(df, storeID, show=True, save=False):
IsOpenList = list(to_numpy(df["IsOpen"]).squeeze())
IsOpenList.pop()
IsOpenList.insert(0, 1)
dftoplot = pd.DataFrame(np.array(IsOpenList).reshape(523021, 1),
columns=["OpenDayBefore"])
dftoplot = df.assign(OpenDayBefore=dftoplot)
dftoplotpershop = dftoplot[dftoplot["StoreID"] == storeID]
dftoplotpershop = dftoplot[dftoplot["IsOpen"] == 1]
sb.boxplot(x="OpenDayBefore", y="NumberOfSales",
data=dftoplotpershop).set_title("Sales / Shop Availability")
fig = plt.gcf()
fig.set_size_inches(18, 9)
if show:
plt.show()
if save:
fig.savefig("opendaybeforegeneralplot.png")
def opendaybeforeonweekplot(df, storeID, show=True, save=False):
df['Date'] = pd.to_datetime(df['Date'], format='%d/%m/%Y')
df['Day'] = df['Date'].dt.weekday_name
df = df.drop(df[df["Day"] == "Sunday"].index)
IsOpenList = list(to_numpy(df["IsOpen"]).squeeze())
IsOpenList.pop()
IsOpenList.insert(0, 1)
dftoplot = pd.DataFrame(np.array(IsOpenList).reshape(448375, 1),
columns=["OpenDayBefore"])
dftoplot = df.assign(OpenDayBefore=dftoplot)
dftoplotpershop = dftoplot[dftoplot["StoreID"] == storeID]
dftoplotpershop = dftoplot[dftoplot["IsOpen"] == 1]
sb.boxplot(
x="OpenDayBefore", y="NumberOfSales",
data=dftoplotpershop).set_title("Sales / Shop Availability (-Sun)")
fig = plt.gcf()
fig.set_size_inches(18, 9)
if show:
plt.show()
if save:
fig.savefig("opendaybeforeonweekplot.png")
def gen_pandas_cols():
shops_col = []
months_col = []
sales_col = []
for i in range(len(shops)):
for j in range(len(months)):
shops_col.append(shops[i])
months_col.append(months[j])
sales_col.append(totp[i][j])
return np.array(shops_col), np.array(months_col), np.array(sales_col)
name_precitions_csv = "final_sales_predictions_new1.csv"
name_original_csv = "final_for_sales_test_r.csv"
preds = d.to_numpy(d.read_dataset(name_precitions_csv)).squeeze()
orig = d.read_dataset(name_original_csv)
dates = d.to_numpy(orig[['Date']]).squeeze()
regions = d.to_numpy(orig[['Region']]).squeeze()
ids = d.to_numpy(orig[['StoreID']]).squeeze()
error, totp, totr, shops, months = eva.region_error(preds, preds, regions, ids, dates, True)
print(error)
print(totp)
print(shops)
print(months)
def tss(df, attr):
arr = d.to_numpy(df[[attr]]).squeeze()
mean = arr.mean()
return np.sum(np.square(arr - mean))
def rss(df, preds, attr):
arr = d.to_numpy(df[[attr]]).squeeze()
return np.sum(np.square(arr - preds))
def prepare_out(ds):
y = d.to_numpy(ds[['NumberOfSales']])
return y
import evaluation.evaluation as ev_cust
import dataset.utility as utils
import pandas
import sklearn.neural_network as nn
def excluded_feats():
return [
"Month", 'Max_Humidity', 'Max_TemperatureC', 'Max_VisibilityKm',
'Max_Wind_SpeedKm_h', 'Min_Dew_PointC', 'Min_Humidity',
'Min_TemperatureC', 'Min_VisibilitykM', 'NumberOfCustomers'
]
datas = d.read_dataset("final_sales_only_train.csv")
regions = d.to_numpy(datas[['Region']]).squeeze()
dates = d.to_numpy(datas[['Date']]).squeeze()
ids = d.to_numpy(datas[['StoreID']]).squeeze()
data = sb.SetBuilder(target='NumberOfSales', autoexclude=True, df=datas.copy(), split=(3, 2016, 2, 2018, 12, 2018, 12, 2018))\
.exclude_list(excluded_feats())\
.build()
it = 1
yy = []
models = []
for i in range(it):
bagx, bagy = data.xtr, data.ytr
dt = nn.MLPRegressor(hidden_layer_sizes=(400, 3),
activation='identity',
solver='adam',
def prepare_out(df):
y = ds.to_numpy(df[['NumberOfCustomers']]).squeeze()
return y
def prepare_out(ds):
y = d.to_numpy(ds[['NumberOfCustomers']])
return y
df = ds.read_dataset("best_for_customers.csv")
sb.lmplot(x="meancustshop",
y="meancust_std_shop",
data=df,
hue="StoreType_Shopping Center")
fig = plt.gcf()
fig.set_size_inches(18, 9)
if show:
plt.show()
if save:
fig.savefig("meanstdscatterpershop.png")
if __name__ == '__main__':
import dataset.dataset as d
import dataset.utility as utils
import pandas as pd
ds = d.read_imputed_onehot_dataset()
monthlyplot(ds)
y = 2016
m = 3
while y != 2018 or m != 3:
sub_ds = utils.get_frame_in_range(ds, m, y, m, y)
expected_out = d.to_numpy(sub_ds[['NumberOfSales']]).squeeze()
print(str(m) + "/" + str(y) + ": ", expected_out.sum())
m += 1
if m == 13:
m = 1
y += 1
def min_per_shop(df, id):
temp = df[(df[['StoreID']] == id).all(axis=1)]
temp = d.to_numpy(temp[['NumberOfSales']])
return temp.min()
def max_cust_per_shop(df, id):
temp = df[(df[['StoreID']] == id).all(axis=1)]
temp = d.to_numpy(temp[['NumberOfCustomers']])
return temp.max()
