def full_prep_test_ds_to_cust_pred():
test_datas = d.read_imputed_onehot_test_dataset()
data_from = d.read_imputed_onehot_dataset()
data_from['Date'] = p.to_datetime(data_from['Date'], format='%d/%m/%Y')
data_from['Day'] = data_from['Date'].dt.weekday_name
datas = prepare_ds_to_customer_prediction(test_datas, data_from)
d.save_dataset(datas, "test_dataset_for_customers_prediction.csv")
def build_sales_predictor_train_dataset(name):
ds = d.read_imputed_onehot_dataset()
ds = __prepare_sales_train_ds(ds)
d.save_dataset(ds, name)
for i in range(number_of_model):
p = models[i].predict(x, 500).squeeze()
preds += p
preds[preds < 0] = 0
for i in range(min(len(preds), number_print)):
print("PRED: ", preds[i], " y: ", y[i])
print("R2: ", eva.r2(ds, preds, 'NumberOfSales'))
if __name__ == '__main__':
TRAIN = True
LOAD = False
SAVE_DF = False
name = "test"
ds = d.read_imputed_onehot_dataset()
ds = prepare_ds(ds)
d.save_dataset(ds, "fully_preprocessed_ds.csv")
ds_train = utils.get_frame_in_range(ds, 3, 2016, 12, 2017)
ds_test = utils.get_frame_in_range(ds, 1, 2018, 2, 2018)
y = prepare_out(ds_train)
real_y = np.array(y)
dy = np.zeros(y.shape)
x = drop_useless(ds_train)
y_test = prepare_out(ds_test)
if SAVE_DF:
d.save_dataset(ds_test, "dataset_to_predict_sales.csv")
x_test = drop_useless(ds_test)
models = []
for i in range(number_of_model):
def build_cust_predictor_train_dataset(m1, a1, m2, a2):
das = ds.read_imputed_onehot_dataset()
das = __prepare_customers_train_ds(das, m1, a1, m2, a2)
return das
correlation_analysis = False
PCA_analysis = False
PCA_correlation_attributes = False
PCA_analysis_attribute = 'Region_AreaKM2'
sb.set_style("whitegrid")
sb.set(style="white", color_codes=True)
sb.set_context(
rc={
"font.family": 'sans',
"font.size": 5,
"axes.titlesize": 8,
"axes.labelsize": 8
})
data = datasetfun.read_imputed_onehot_dataset()
data_nominal = datasetfun.nominal_only(data)
data_numeric = datasetfun.numeric_only(data)
if correlation_analysis == True:
numeric_corr = data_numeric.corr(method="pearson")
numeric_heatmap = sb.heatmap(numeric_corr,
square=True,
annot=True,
cmap="Blues")
pl.show()
