def main(features_fpath, tag_categ_fpath, tseries_fpath, num_days_to_use,
assign_fpath, out_foldpath):
X, feature_ids, _ = \
create_input_table(features_fpath, tseries_fpath, tag_categ_fpath,
num_days_to_use)
X = scale(X)
y_clf = np.genfromtxt(assign_fpath)
y_regr = scale(np.genfromtxt(tseries_fpath)[:, 1:].sum(axis=1))
run_experiment(X, y_clf, y_regr, feature_ids, out_foldpath)
def main(features_fpath, tag_categ_fpath, tseries_fpath, num_days_to_use,
assign_fpath, out_foldpath):
X, feature_ids, _ = \
create_input_table(features_fpath, tseries_fpath, tag_categ_fpath,
num_days_to_use)
X = scale(X)
y_clf = np.genfromtxt(assign_fpath)
y_regr = scale(np.genfromtxt(tseries_fpath)[:,1:].sum(axis=1))
run_experiment(X, y_clf, y_regr, feature_ids, out_foldpath)
def main(partial_features_fpath, tag_categ_fpath, tseries_fpath,
num_days_to_use, assign_fpath, out_foldpath):
X, feature_ids, feature_names = \
create_input_table(partial_features_fpath, tseries_fpath,
tag_categ_fpath, num_pts = num_days_to_use)
#Sort X by upload date
up_date_col = feature_names['A_UPLOAD_DATE']
sort_by_date = X[:, up_date_col].argsort()
X = X[sort_by_date].copy()
y_clf = np.genfromtxt(assign_fpath)[sort_by_date]
y_regr = np.genfromtxt(tseries_fpath)[:, 1:].sum(axis=1)[sort_by_date]
run_experiment(X, y_clf, y_regr, feature_ids, out_foldpath)
def main(partial_features_fpath, tag_categ_fpath, tseries_fpath,
num_days_to_use, assign_fpath, out_foldpath):
X, feature_ids, feature_names = \
create_input_table(partial_features_fpath, tseries_fpath,
tag_categ_fpath, num_pts = num_days_to_use)
#Sort X by upload date
up_date_col = feature_names['A_UPLOAD_DATE']
sort_by_date = X[:,up_date_col].argsort()
X = X[sort_by_date].copy()
y_clf = np.genfromtxt(assign_fpath)[sort_by_date]
y_regr = np.genfromtxt(tseries_fpath)[:,1:].sum(axis=1)[sort_by_date]
run_experiment(X, y_clf, y_regr, feature_ids, out_foldpath)
def main(features_fpath, tag_categ_fpath, tseries_fpath, assign_fpath):
X, feature_ids, _ = \
create_input_table(features_fpath, None, tag_categ_fpath,-1)
y_clf = np.genfromtxt(assign_fpath)
y_rgr = np.genfromtxt(tseries_fpath)[:,1:].sum(axis=1)
for feat_id in range(len(feature_ids)):
print(feature_ids[feat_id], end=',')
print('TREND', end=',')
print('FINAL_VIEWS')
M = np.column_stack((X, y_clf, y_rgr))
np.savetxt(sys.stdout, M, '%d', delimiter=',')
def main(features_fpath, tag_categ_fpath, tseries_fpath, assign_fpath):
X, feature_ids, _ = \
create_input_table(features_fpath, None, tag_categ_fpath,-1)
y_clf = np.genfromtxt(assign_fpath)
y_rgr = np.genfromtxt(tseries_fpath)[:, 1:].sum(axis=1)
for feat_id in range(len(feature_ids)):
print(feature_ids[feat_id], end=',')
print('TREND', end=',')
print('FINAL_VIEWS')
M = np.column_stack((X, y_clf, y_rgr))
np.savetxt(sys.stdout, M, '%d', delimiter=',')
def main(features_fpath, tseries_fpath, tags_fpath, classes_fpath, clf_name):
X, params = create_input_table(features_fpath, tseries_fpath, tags_fpath)
y = np.loadtxt(classes_fpath)
clf = create_grid_search(clf_name)
class_matrices, conf_matrices = run_classifier(clf, X, y)
metric_means = np.mean(class_matrices, axis=0)
metric_ci = hci(class_matrices, .95, axis=0)
print(clf_summary(metric_means, metric_ci))
print()
conf_means = np.mean(conf_matrices, axis=0)
conf_ci = hci(conf_matrices, .95, axis=0)
print("Average confusion matrix with .95 confidence interval")
print(" \ttrue ")
print("predic")
for i in range(conf_means.shape[0]):
print(i, end="\t \t")
for j in range(conf_means.shape[1]):
print('%.3f +- %.3f' % (conf_means[i, j], conf_ci[i, j]), end="\t")
print()
def main(features_fpath, tseries_fpath, tags_fpath, classes_fpath, clf_name):
X, params = create_input_table(features_fpath, tseries_fpath, tags_fpath)
y = np.loadtxt(classes_fpath)
clf = create_grid_search(clf_name)
class_matrices, conf_matrices = run_classifier(clf, X, y)
metric_means = np.mean(class_matrices, axis=0)
metric_ci = hci(class_matrices, .95, axis=0)
print(clf_summary(metric_means, metric_ci))
print()
conf_means = np.mean(conf_matrices, axis=0)
conf_ci = hci(conf_matrices, .95, axis=0)
print("Average confusion matrix with .95 confidence interval")
print(" \ttrue ")
print("predic")
for i in xrange(conf_means.shape[0]):
print(i, end="\t \t")
for j in xrange(conf_means.shape[1]):
print('%.3f +- %.3f' % (conf_means[i, j], conf_ci[i, j]), end="\t")
print()
