def main():
import os
data_dir = os.path.dirname(os.path.dirname(os.path.realpath(__file__))) + '/data/'
#data_file = data_dir + 'input_data_full.csv'
#data_file = data_dir + 'InputData_small.csv'
#results_file = data_dir + 'consumer_spending.csv'
#results_file = data_dir + 'Fake_Results.csv'
data = dh.get_all_data(LOAD_FROM_FILE, LOAD_DELTAS, data_dir)
results = data[target_col]
num_data_items = data.shape[0]
season_info = np.zeros([num_data_items,4])
j = 0
for i in range(num_data_items):
season_info[i,j] = 1
j += 1
if j > 3:
j = 0
seasons_df = pd.DataFrame(data=season_info, columns=['SEASON_1', 'SEASON_2', 'SEASON_3', 'SEASON_4'])
seasons_df.index = data.index
if USE_SEASONS:
data = pd.concat([data, seasons_df], axis=1)
if DO_VALIDATION:
model = valid.do_validation(data, results, MODEL_TYPE, USE_ENSEMBLE)
if DO_TEST:
run_tests(model, data, results)
elif DO_FUTURE_FORECAST:
model = mh.get_model_fixed(MODEL_TYPE)
do_fwd_prediction(model,data,results)
else:
model = mh.get_model_fixed(MODEL_TYPE)
#do_fwd_prediction(model,data,results)
run_tests(model, data, results)
end = timer()
print('finished in: ' + str(end - start))
ph.show_plots()
def DisplayFactors():
use_deltas = True
data = dh.get_all_data(LOAD_FROM_FILE, use_deltas)
titles = data.columns
data = data[data.index < START_TEST_DATE]
check_one_forecast_gap(data, 1)
[corr_1fwd, corr_1fwd_delta] = check_one_forecast_gap(data, 1, use_deltas)
[corr_4fwd, corr_4fwd_delta] = check_one_forecast_gap(data, 4, use_deltas)
for i in range(corr_1fwd.shape[0]):
if use_deltas:
print(titles[i] + ' & pch & ' + str(round(corr_1fwd[i, 0], 4)) +
' & ' + str(round(corr_1fwd_delta[i, 0], 4)) + ' & ' +
str(round(corr_4fwd[i, 0], 4)) + ' & ' +
str(round(corr_4fwd_delta[i, 0], 4)) + ' \\\\')
else:
print(titles[i] + ' & pch & ' + str(round(corr_1fwd[i, 0], 4)) +
' & ' + str(round(corr_4fwd[i, 0], 4)) + '\\\\')
ph.draw_hist(
corr_1fwd,
'1 Period Forward Correlations Between Input Variables and Target',
'Correlation Coefficient')
plt.show()