def main(filename):
plotname = filename[:-4] # remove ".csv"
x, y, ids = util.process_csv_list(filename)
heatmap, xedges, yedges = np.histogram2d(x, y, bins=(10, 4))
heatmap = heatmap[::-1]
extent = [xedges[0], xedges[-1], yedges[0], yedges[-1]]
plt.imshow(heatmap, extent=extent, interpolation='nearest')
plt.colorbar()
plt.savefig(plotname)
print "Generated heatmap image %s.png" % plotname
def main(filename):
plotname = filename[:-4] # remove ".csv"
x, y, ids = util.process_csv_list(filename)
heatmap, xedges, yedges = np.histogram2d(x, y, bins=(10, 4))
heatmap = heatmap[::-1]
extent = [xedges[0], xedges[-1], yedges[0], yedges[-1]]
plt.imshow(heatmap, extent=extent, interpolation='nearest')
plt.colorbar()
plt.savefig(plotname)
print "Generated heatmap image %s.png" % plotname
def main(dirname):
filenames = os.listdir(dirname)
for filename in filenames:
if not ".json" in filename:
continue
filename = filename[:-5] + ".csv"
print "Processing %s... " % filename[:-4],
x, y, ids = util.process_csv_list(os.path.join(dirname, filename))
new_x, new_y, removed = mahalanobis.remove_outliers(x, y)
print "done"
print "Removed %d outlying point(s)" % (len(x) - len(new_x))
print "Average error: %f, standard error: %f" % (rmse.calculate_rmse(new_x, new_y))
print
def make_arrays(dirname):
data, predictions, boost_labels, maxent_labels = [], [], [], []
filenames = os.listdir(dirname)
for filename in filenames:
if not ".json" in filename:
continue
print "Collecting data from %s... " % filename[:-5],
conditions = util.process_json(os.path.join(dirname, filename))
x, y, idx = util.process_csv_list(
os.path.join(dirname, filename[:-5] + ".csv"))
for i in range(len(x)):
tempd, tempp = [0] * (util.num_conditions +
1), [0] * (util.num_conditions + 1)
for j in conditions:
tempd[j] = 1
tempp[j] = -1
data.append(tempd)
predictions.append(tempp)
error = rmse.get_single_rmse(x[i], y[i])
if error <= util.base_error / 2:
boost_labels.append(1)
maxent_labels.append(1)
else:
boost_labels.append(-1)
maxent_labels.append(0)
print "done"
print
data = np.array(data)
predictions = np.array(predictions)
boost_labels = np.array(boost_labels)
maxent_labels = np.array(maxent_labels)
return (data, predictions, boost_labels, maxent_labels)
def make_arrays(dirname):
data, predictions, boost_labels, maxent_labels = [], [], [], []
filenames = os.listdir(dirname)
for filename in filenames:
if not ".json" in filename:
continue
print "Collecting data from %s... " % filename[:-5],
conditions = util.process_json(os.path.join(dirname, filename))
x, y, idx = util.process_csv_list(os.path.join(dirname, filename[:-5] + ".csv"))
for i in range(len(x)):
tempd, tempp = [0] * (util.num_conditions + 1), [0] * (util.num_conditions + 1)
for j in conditions:
tempd[j] = 1
tempp[j] = -1
data.append(tempd)
predictions.append(tempp)
error = rmse.get_single_rmse(x[i], y[i])
if error <= util.base_error / 2:
boost_labels.append(1)
maxent_labels.append(1)
else:
boost_labels.append(-1)
maxent_labels.append(0)
print "done"
print
data = np.array(data)
predictions = np.array(predictions)
boost_labels = np.array(boost_labels)
maxent_labels = np.array(maxent_labels)
return (data, predictions, boost_labels, maxent_labels)
def main(filename):
actual, data = util.process_csv_list(filename)
print "average error: %f \nstandard error: %f" % (calculate_rmse(
actual, data))
def main(filename):
x, y = util.process_csv_list(filename)
dm = calculate_mahalanobis(x, y)
dm.sort()
print dm
def main(filename):
x, y = util.process_csv_list(filename)
dm = calculate_mahalanobis(x, y)
dm.sort()
print dm
def main(filename):
actual, data = util.process_csv_list(filename)
print "average error: %f \nstandard error: %f" % (calculate_rmse(actual, data))