def create_predictions_sales(train, test, load_or_run='run'):
sub = train.drop(['Customers', 'Date'], axis=1)
subtest = test.drop(['Sales', 'Customers', 'Date'], axis=1)
subtest.Open = subtest.Open.astype('int')
for c in sub.columns:
if sub[c].dtype == 'object' or sub[c].dtype.name == 'category':
print(c)
lbl = preprocessing.LabelEncoder()
lbl.fit(list(sub[c].values))
sub[c] = lbl.transform(sub[c].values)
for c in subtest.columns:
if subtest[c].dtypes == 'object' or subtest[c].dtype.name == 'category':
print(c)
lbl = preprocessing.LabelEncoder()
lbl.fit(list(subtest[c].values))
subtest[c] = lbl.transform(subtest[c].values)
target = np.array(sub.Sales)
sub = sub.drop('Sales', axis=1)
traincols = sub.columns
sub = np.array(sub)
subtest = np.array(subtest)
trn, tst, trgt_train, trgt_test = train_test_split(sub,
target,
test_size=.3,
random_state=42)
def rmse(preds, target):
error = np.sqrt(((preds - target)**2).mean())
print(error)
return (error)
def mae(preds, target):
error = np.mean(abs(preds - target))
print(error)
return (error)
if load_or_run == 'load':
xg = joblib.load("sales2.joblib.dat")
print('loaded')
else:
param_grid = {
'n_jobs': [4],
'learning_rate': [.05, .1, .2],
'max_depth': [8, 10],
'n_estimators': [500],
'booster': ['gbtree'],
'gamma': [0],
'subsample': [1],
'colsample_bytree': [1]
}
xg = XGBRegressor(silent=0)
xg = GridSearchCV(xg, param_grid)
xg.fit(X=trn, y=trgt_train)
xg.Features = traincols
joblib.dump(xg, "sales2.joblib.dat")
print('ran')
# feats = pd.DataFrame({'feats': traincols, 'importances':xg2.feature_importances_})
# feats.plot.bar( )
print(xg.best_estimator_)
preds = xg.predict(tst)
rmse(preds, trgt_test)
mae(preds, trgt_test)
testpreds = xg.predict(subtest)
trainpreds = xg.predict(sub)
#
# rf = RandomForestRegressor(n_estimators = 500, random_state = 42, n_jobs = 4)
# rf.fit(trn, trgt_train)
# preds = rf.predict(tst)
# rmse(preds, trgt_test)
# mae(preds, trgt_test)
return (trainpreds, testpreds)
