fig, ax1 = plt.subplots() ax1.set_title("Days vs. Traffic & Cases") ax1.set_xlabel("days") ax1.plot(days, cases, color="r") ax1.set_ylabel("traffic") ax2 = ax1.twinx() ax2.set_ylabel("cases") ax2.plot(days, traffic) plt.show() ########################## # Choose optimal KFold print("Performing Cross Validation...") cross_validate.k_folds_cross_validation( 1, cases, traffic, days, pred_type='cases', model_type='knn', Q=1, K=18, C='N/A') # Choose optimal polynomial features cross_validate.poly_feature_cross_validation( 2, cases, traffic, days, pred_type='cases', model_type='knn', folds=2, K=18, C='N/A') # Choose optimal neighbours for KNN = 18 cross_validate.knn_cross_validation( 3, cases, traffic, days, pred_type='cases', model_type='knn', folds=2, Q=1, C='N/A') # TRAFFIC ==> CASES kf = KFold(n_splits=2) pred_array = [] y = [] plt.figure(5) plt.plot(days, cases)
evaluate = EvaluateModels() data = pd.read_csv("../../data/formatted_data_new.csv") days = data.iloc[:, 0] cases = data.iloc[:, 1] traffic = data.iloc[:, 2] cases_df = cases traffic_df = traffic cases = pd.DataFrame(cases).to_numpy() traffic = pd.DataFrame(traffic).to_numpy() cases = cases.reshape(-1, 1) # Choose optimal KFold print("Performing Cross Validation...") cross_validate.k_folds_cross_validation( 1, cases, traffic, days, pred_type='cases', model_type='lasso', Q=1, K='N/A', C=10) # Choose optimal polynomial features cross_validate.poly_feature_cross_validation( 2, cases, traffic, days, pred_type='cases', model_type='lasso', folds=2, K='N/A', C=10) # Choose optimal value for C penalty cross_validate.c_penalty_cross_validation( 3, cases, traffic, days, pred_type='cases', model_type='lasso', folds=2, Q=5, K='N/A') # TRAFFIC ==> CASES kf = KFold(n_splits=5) y = [] p = [] plt.figure(5) plt.plot(days, cases)