def xgboostmodel(self):
df = pd.read_csv(datafile, encoding='utf-8', index_col=0)
print(df.shape)
traindata = df.iloc[:, :].values
x = traindata[:, :-1]
y = traindata[:, -1]
x_train, x_test, y_train, y_test = train_test_split(
x, y, train_size=0.7) # list
if self.params is None:
params = {'max_depth': 80, 'n_estimators': 512}
else:
params = self.params
raw_model = XGBRegressor(max_depth=128,
n_estimators=768,
learning_rate=0.01,
silence=False)
raw_model.fit(x_train, y_train)
raw_model.save_model(self.model_file)
pred = raw_model.predict(x_test)
self.true = y_test
self.pred = pred
self.show_save_figure(fig_path=self.fig_path,
modelname=self.job_name,
detal_idx=500)
t_mean = self.cal_mean(self.true)
p_mean = self.cal_mean(self.pred)
self.save_result(self.result_path, true_mean=t_mean, pred_mean=p_mean)
plt.savefig('C:/Users/leech/OneDrive/Desktop/Analytics RossMann/rossmann-store-sales/image/feature_importance.png')
plt.close()
# Predicting on the testSet
predictions = clf.predict(test_x)
# Calculating the RMSE
rms = math.sqrt(mean_squared_error(test_y.values, predictions))
print(rms)
# Print the discrepancies
combinedResult=pd.DataFrame(data={'Store':testSet['Store'].values.ravel(), 'Date':testSet['Date'].values.ravel(),'predictions': predictions, 'actual': test_y.values.ravel()})
print(combinedResult)
# Show the predictions for store 1
combinedResult1=combinedResult.loc[combinedResult['Store']==1]
# gca stands for 'get current axis'
ax = plt.gca()
# Saving the predicted graph for store 1
combinedResult1.plot(kind='line',x='Date',y='actual',ax=ax)
combinedResult1.plot(kind='line',x='Date',y='predictions', color='red', ax=ax)
plt.savefig('C:/Users/leech/OneDrive/Desktop/Analytics RossMann/rossmann-store-sales/image/store1.png')
plt.show()
plt.close()
# Saving the model
clf.save_model('C:/Users/leech/OneDrive/Desktop/Analytics RossMann/rossmann-store-sales/model/finalmodel.model')
