def plot_histograms(args):
classifiers = {}
data, labels = [], []
for _file in args.infiles:
label, content = _format_data(_file, args)
labels.append(label)
X, _ = zip(*content)
data.append(X)
plt.hist(data, args.histogram_bins, histtype='bar', stacked=False, label=labels)
plt.legend(loc=args.legend_loc)
set_plot_limits(plt, args)
if args.savefig is not None:
filename = args.savefig
modifiers = []
if args.x_limits:
modifiers.append('X=%d,%d' % tuple(args.x_limits))
if args.y_limits:
modifiers.append('Y=%d,%d' % tuple(args.y_limits))
name, ext = filename.rsplit('.')
new_filename = '{old_name}-{modifiers}.{ext}'.format(old_name=name, modifiers='-'.join(modifiers), ext=ext)
print 'saving figure to - ', new_filename
plt.savefig(new_filename, dpi=320)
plt.clf()
else:
plt.show()
def plot_histograms(args):
classifiers = {}
data, labels = [], []
for _file in args.infiles:
label, content = _format_data(_file, args)
labels.append(label)
X, _ = zip(*content)
data.append(X)
plt.hist(data,
args.histogram_bins,
histtype='bar',
stacked=False,
label=labels)
plt.legend(loc=args.legend_loc)
set_plot_limits(plt, args)
if args.savefig is not None:
filename = args.savefig
modifiers = []
if args.x_limits:
modifiers.append('X=%d,%d' % tuple(args.x_limits))
if args.y_limits:
modifiers.append('Y=%d,%d' % tuple(args.y_limits))
name, ext = filename.rsplit('.')
new_filename = '{old_name}-{modifiers}.{ext}'.format(
old_name=name, modifiers='-'.join(modifiers), ext=ext)
print 'saving figure to - ', new_filename
plt.savefig(new_filename, dpi=320)
plt.clf()
else:
plt.show()
def _plot_hist2d(data, args):
data = data[data[args.hist2d[0]].notnull()][data[args.hist2d[1]].notnull()]
if data.shape[0] < 1000:
sys.exit(1)
plt.hist2d(data[args.hist2d[0]],
data[args.hist2d[1]],
bins=args.histogram_bins,
norm=LogNorm())
plt.colorbar()
set_plot_limits(plt, args)
plt.xlabel(args.hist2d[0])
plt.ylabel(args.hist2d[1])
set_plot_limits(plt, args)
plt.title("N = {}".format(data.shape[0]))
def _plot_hist2d(data, args):
data = data[data[args.hist2d[0]].notnull()][data[args.hist2d[1]].notnull()]
if data.shape[0] < 1000:
sys.exit(1)
plt.hist2d(data[args.hist2d[0]],
data[args.hist2d[1]],
bins=args.histogram_bins,
norm=LogNorm())
plt.colorbar()
set_plot_limits(plt, args)
plt.xlabel(args.hist2d[0])
plt.ylabel(args.hist2d[1])
set_plot_limits(plt, args)
plt.title("N = {}".format(data.shape[0]))
def _plot_hist2d(data, args):
data = data[data[args.hist2d[0]].notnull()][data[args.hist2d[1]].notnull()]
if data.shape[0] < 1000:
sys.exit(1)
df = data.replace([np.inf, -np.inf], np.nan).dropna(subset=args.hist2d)
plt.hist2d(df[args.hist2d[0]].astype(float),
df[args.hist2d[1]].astype(float),
bins=args.histogram_bins,
norm=LogNorm())
plt.colorbar()
set_plot_limits(plt, args)
plt.xlabel(args.hist2d[0])
plt.ylabel(args.hist2d[1])
set_plot_limits(plt, args)
plt.title("N = {}".format(data.shape[0]))
def _plot_hist2d(data, args):
data = data[data[args.hist2d[0]].notnull()][data[args.hist2d[1]].notnull()]
if data.shape[0] < 1000:
sys.exit(1)
df = data.replace([np.inf, -np.inf], np.nan).dropna(subset=args.hist2d)
plt.hist2d(df[args.hist2d[0]].astype(float),
df[args.hist2d[1]].astype(float),
bins=args.histogram_bins,
norm=LogNorm())
plt.colorbar()
set_plot_limits(plt, args)
plt.xlabel(args.hist2d[0])
plt.ylabel(args.hist2d[1])
set_plot_limits(plt, args)
plt.title("N = {}".format(data.shape[0]))
def plot_distribution(args):
if args.csv is not None:
data = pd.read_csv(args.csv)
print ' '.join(list(data.columns.values))
if args.filter_num_rtus:
print 'before filtering size =', data.shape[0]
data = data[data['num_rtus'] == args.filter_num_rtus]
print 'after filtering size =', data.shape[0]
if args.filter_controller:
print 'before filtering size =', data.shape[0]
data = data[data['controller_id'] == args.filter_controller]
print 'after filtering size =', data.shape[0]
if 'controller_id' in data:
print 'total controller_ids included =', len(
set(data['controller_id']))
if 'num_rtus' in data:
print 'distinct num_rtus =', len(set(data['num_rtus'])), set(
data['num_rtus'])
else:
cursor = args.db_connection.cursor()
cursor.execute(
"select relname from pg_class where relkind='r' and relname !~ '^(pg_|sql_)';"
) # noqa
if args.query:
with open(args.query, 'r') as infile:
sql = ''.join(list(infile))
else:
sql = """
SELECT {select} FROM {table};
""".format(select='*', table=args.table)
print sql
cursor.execute(sql)
colnames = [desc[0] for desc in cursor.description]
data = pd.DataFrame(cursor.fetchall(), columns=colnames)
# Set args.data, so we can pass only args to functions
args.data = data
data_size = data.shape[0]
if args.scatter is not None:
if args.labels:
interesting_data = data[[
args.scatter[0], args.scatter[1], args.labels
]]
different_labels = set(data[args.labels])
for label, color in zip(different_labels,
matplotlib.colors.cnames.keys()):
df = interesting_data.query('{column} == "{label}"'.format(
column=args.labels, label=label))
plt.scatter(df[args.scatter[0]],
df[args.scatter[1]],
c=color,
label=label)
else:
plt.scatter(data[args.scatter[0]], data[args.scatter[1]], c=color)
plt.xlabel(args.scatter[0])
plt.ylabel(args.scatter[1])
elif args.histogram is not None:
if args.labels:
interesting_data = data[[args.histogram, args.labels]]
different_labels = set(data[args.labels])
data_to_plot, colors_to_use, labels_to_show = [], [], []
miscellaneous_labels = set()
misc_frame, misc_color = pd.DataFrame(), None
for label, color in zip(different_labels,
matplotlib.colors.cnames.keys()):
df = interesting_data.query('{column} == "{label}"'.format(
column=args.labels, label=label))
if df.shape[0] < args.miscellaneous_cutoff * data_size:
miscellaneous_labels.add(label)
misc_frame = pd.concat([misc_frame, df[args.histogram]])
misc_color = color
continue
labels_to_show.append('{label} ({count})'.format(
label=label, count=df.shape[0]))
data_to_plot.append(df[args.histogram])
colors_to_use.append(color)
if misc_color is not None:
labels_to_show.append('miscellaneous ({count})'.format(
count=misc_frame.shape[0]))
data_to_plot.append(misc_frame)
# colors_to_use.append(misc_color)
colors_to_use.append('cyan')
plt.hist(data_to_plot,
args.histogram_bins,
histtype='bar',
color=colors_to_use,
label=labels_to_show)
else:
df = data.replace([np.inf, -np.inf],
np.nan).dropna(subset=[args.histogram])
plt.hist(df[args.histogram].astype(float),
bins=args.histogram_bins,
label=args.histogram)
plt.yscale('log')
plt.xlabel(args.histogram)
if args.scale_down:
plt.ylim(ymax=int(data_size * args.miscellaneous_cutoff))
elif args.hist2d is not None:
_plot_hist2d(data, args)
elif args.scatter3d is not None:
plot_scatter3d(data, args)
plt.legend()
if not args.scatter3d and not args.histogram:
set_plot_limits(plt, args)
if args.savefig is not None:
plt.savefig(args.savefig, dpi=320)
plt.clf()
else:
plt.show()
def plot_estimator(args):
estimates = json.load(args.estimates)
dimensions = len(_format_datum(estimates['inliers'][0], args.columns)) - 1
y_limits = None if dimensions != 2 else args.y_limits
inliers = _extract_data(estimates, 'inliers', args.columns, args.x_limits,
y_limits)
outliers = _extract_data(estimates, 'outliers', args.columns,
args.x_limits, y_limits)
all_data = itertools.chain(inliers, outliers)
print 'plotting %d dimensional plot' % dimensions
if dimensions == 1:
if args.restrict_to:
data = _extract_data(estimates, args.restrict_to, args.columns,
args.x_limits, None)
X, _ = zip(*data)
plt.hist(X, args.histogram_bins, label=args.restrict_to)
else:
inliers = list(inliers)
outliers = list(outliers)
X1, _ = zip(*inliers)
X2, _ = zip(*outliers)
n, bins, patches = plt.hist([X1, X2],
args.histogram_bins,
histtype='bar',
stacked=args.stacked_hist,
label=['inliers', 'outliers'],
color=['blue', 'red'])
bin_width = bins[1] - bins[0]
print 'plotted a curve with bin width =', bin_width
if args.plot_scores:
# Plot the estimate
combined_X, scores = zip(
*sorted(itertools.chain(inliers, outliers)))
scaling_factor = bin_width * (len(estimates['inliers']) +
len(estimates['outliers']))
sign = 1. if scores[0] > 0 else -1
scaling_factor *= sign
scaled_scores = [scaling_factor * y for y in scores]
plt.plot(combined_X,
scaled_scores,
color='magenta',
label='est distribution',
lw=1.1)
elif dimensions == 2:
if args.restrict_to:
data = _extract_data(estimates, args.restrict_to, args.columns,
args.x_limits, args.y_limits)
else:
data = all_data
X, Y, _ = zip(*data)
plt.hist2d(X, Y, bins=args.histogram_bins, norm=LogNorm())
plt.colorbar()
plt.legend(loc=args.legend_loc)
set_plot_limits(plt, args)
if args.savefig is not None:
if args.savefig == SAVEFIG_INFER_VALUE:
name = os.path.basename(args.estimates.name).rsplit('.')[0]
filename = 'target/plots/{}.png'.format(name)
else:
filename = args.savefig
modifiers = []
if args.restrict_to:
modifiers.append(args.restrict_to)
if args.estimates:
modifiers.append('estimates')
if args.x_limits:
modifiers.append('X=%d,%d' % tuple(args.x_limits))
if args.y_limits:
modifiers.append('Y=%d,%d' % tuple(args.y_limits))
name, ext = filename.rsplit('.')
new_filename = '{old_name}-{modifiers}.{ext}'.format(
old_name=name, modifiers='-'.join(modifiers), ext=ext)
print 'saving figure to - ', new_filename
plt.savefig(new_filename, dpi=320)
plt.clf()
else:
plt.show()
def plot_distribution(args):
if args.csv is not None:
data = pd.read_csv(args.csv)
print ' '.join(list(data.columns.values))
if args.filter_num_rtus:
print 'before filtering size =', data.shape[0]
data = data[data['num_rtus'] == args.filter_num_rtus]
print 'after filtering size =', data.shape[0]
if args.filter_controller:
print 'before filtering size =', data.shape[0]
data = data[data['controller_id'] == args.filter_controller]
print 'after filtering size =', data.shape[0]
if 'controller_id' in data:
print 'total controller_ids included =', len(set(data['controller_id']))
if 'num_rtus' in data:
print 'distinct num_rtus =', len(set(data['num_rtus'])), set(data['num_rtus'])
else:
cursor = args.db_connection.cursor()
cursor.execute("select relname from pg_class where relkind='r' and relname !~ '^(pg_|sql_)';") # noqa
if args.query:
with open(args.query, 'r') as infile:
sql = ''.join(list(infile))
else:
sql = """
SELECT {select} FROM {table};
""".format(select='*', table=args.table)
print sql
cursor.execute(sql)
colnames = [desc[0] for desc in cursor.description]
data = pd.DataFrame(cursor.fetchall(), columns=colnames)
# Set args.data, so we can pass only args to functions
args.data = data
data_size = data.shape[0]
if args.scatter is not None:
if args.labels:
interesting_data = data[[args.scatter[0], args.scatter[1], args.labels]]
different_labels = set(data[args.labels])
for label, color in zip(different_labels,
matplotlib.colors.cnames.keys()):
df = interesting_data.query('{column} == "{label}"'.format(
column=args.labels, label=label))
plt.scatter(df[args.scatter[0]], df[args.scatter[1]],
c=color, label=label)
else:
plt.scatter(data[args.scatter[0]], data[args.scatter[1]],
c=color)
plt.xlabel(args.scatter[0])
plt.ylabel(args.scatter[1])
elif args.histogram is not None:
if args.labels:
interesting_data = data[[args.histogram, args.labels]]
different_labels = set(data[args.labels])
data_to_plot, colors_to_use, labels_to_show = [], [], []
miscellaneous_labels = set()
misc_frame, misc_color = pd.DataFrame(), None
for label, color in zip(different_labels,
matplotlib.colors.cnames.keys()):
df = interesting_data.query('{column} == "{label}"'.format(
column=args.labels, label=label))
if df.shape[0] < args.miscellaneous_cutoff * data_size:
miscellaneous_labels.add(label)
misc_frame = pd.concat([misc_frame, df[args.histogram]])
misc_color = color
continue
labels_to_show.append('{label} ({count})'.format(label=label,
count=df.shape[0]))
data_to_plot.append(df[args.histogram])
colors_to_use.append(color)
if misc_color is not None:
labels_to_show.append('miscellaneous ({count})'.format(
count=misc_frame.shape[0]))
data_to_plot.append(misc_frame)
# colors_to_use.append(misc_color)
colors_to_use.append('cyan')
plt.hist(data_to_plot, args.histogram_bins, histtype='bar',
color=colors_to_use, label=labels_to_show)
else:
df = data.replace([np.inf, -np.inf], np.nan).dropna(subset=[args.histogram])
plt.hist(df[args.histogram].astype(float),
bins=args.histogram_bins,
label=args.histogram)
plt.yscale('log')
plt.xlabel(args.histogram)
if args.scale_down:
plt.ylim(ymax=int(data_size * args.miscellaneous_cutoff))
elif args.hist2d is not None:
_plot_hist2d(data, args)
elif args.scatter3d is not None:
plot_scatter3d(data, args)
plt.legend()
if not args.scatter3d and not args.histogram:
set_plot_limits(plt, args)
if args.savefig is not None:
plt.savefig(args.savefig, dpi=320)
plt.clf()
else:
plt.show()
def plot_estimator(args):
estimates = json.load(args.estimates)
dimensions = len(_format_datum(estimates['inliers'][0], args.columns)) - 1
y_limits = None if dimensions != 2 else args.y_limits
inliers = _extract_data(estimates, 'inliers', args.columns,
args.x_limits, y_limits)
outliers = _extract_data(estimates, 'outliers', args.columns,
args.x_limits, y_limits)
all_data = itertools.chain(inliers, outliers)
print 'plotting %d dimensional plot' % dimensions
if dimensions == 1:
if args.restrict_to:
data = _extract_data(estimates, args.restrict_to, args.columns,
args.x_limits, None)
X, _ = zip(*data)
plt.hist(X, args.histogram_bins,
label=args.restrict_to)
else:
inliers = list(inliers)
outliers = list(outliers)
X1, _ = zip(*inliers)
X2, _ = zip(*outliers)
n, bins, patches = plt.hist([X1, X2], args.histogram_bins,
histtype='bar',
stacked=args.stacked_hist,
label=['inliers', 'outliers'],
color=['blue', 'red'])
bin_width = bins[1] - bins[0]
print 'plotted a curve with bin width =', bin_width
if args.plot_scores:
# Plot the estimate
combined_X, scores = zip(*sorted(itertools.chain(inliers, outliers)))
scaling_factor = bin_width * (len(estimates['inliers']) +
len(estimates['outliers']))
sign = 1. if scores[0] > 0 else -1
scaling_factor *= sign
scaled_scores = [scaling_factor * y for y in scores]
plt.plot(combined_X, scaled_scores,
color='magenta', label='est distribution', lw=1.1)
elif dimensions == 2:
if args.restrict_to:
data = _extract_data(estimates, args.restrict_to, args.columns,
args.x_limits, args.y_limits)
else:
data = all_data
X, Y, _ = zip(*data)
plt.hist2d(X, Y,
bins=args.histogram_bins,
norm=LogNorm())
plt.colorbar()
plt.legend(loc=args.legend_loc)
set_plot_limits(plt, args)
if args.savefig is not None:
if args.savefig == SAVEFIG_INFER_VALUE:
name = os.path.basename(args.estimates.name).rsplit('.')[0]
filename = 'target/plots/{}.png'.format(name)
else:
filename = args.savefig
modifiers = []
if args.restrict_to:
modifiers.append(args.restrict_to)
if args.estimates:
modifiers.append('estimates')
if args.x_limits:
modifiers.append('X=%d,%d' % tuple(args.x_limits))
if args.y_limits:
modifiers.append('Y=%d,%d' % tuple(args.y_limits))
name, ext = filename.rsplit('.')
new_filename = '{old_name}-{modifiers}.{ext}'.format(
old_name=name, modifiers='-'.join(modifiers), ext=ext)
print 'saving figure to - ', new_filename
plt.savefig(new_filename, dpi=320)
plt.clf()
else:
plt.show()
def plot_score_contours(args):
weights = []
centers = []
sigmas = []
if args.centers and args.covariances and args.weights:
# normalize weights to sum to 1.
weights = json.load(args.weights)
weights = [w / sum(weights) for w in weights]
weights = [0.4 * w / max(weights) for w in weights]
centers = load_cluster_parameters(args.centers)
sigmas = load_cluster_parameters(args.covariances)
fig = plt.figure(0)
ax = fig.add_subplot(111)
for i in range(len(centers)):
w, h, angle = get_ellipse_from_covariance(sigmas[i])
e = patches.Ellipse(centers[i], w, h, angle=angle)
e.set_alpha(weights[i])
ax.add_artist(e)
print i, weights[i], centers[i], sigmas[i]
set_ax_limits(ax, args)
x, y = zip(*centers)
plt.scatter(x, y, s=weights)
X, Y, Z = load_json_dump(args.scored_grid)
if args.score_cap:
Z = [min(z, args.score_cap) for z in Z]
if args.score_lower_limit:
Z = [max(z, args.score_lower_limit) for z in Z]
size = int(math.sqrt(len(Z)))
X = np.reshape(X, (size, size))
Y = np.reshape(Y, (size, size))
Z = np.reshape(Z, (size, size))
def format_args(i):
kwargs = {}
kwargs['mux'] = centers[i][0]
kwargs['muy'] = centers[i][1]
kwargs['sigmax'] = math.sqrt(sigmas[i][0][0])
kwargs['sigmay'] = math.sqrt(sigmas[i][1][1])
kwargs['sigmaxy'] = sigmas[i][0][1]
return kwargs
if len(weights):
Zgaussians = weights[0] * mlab.bivariate_normal(X, Y, **format_args(0))
for i in range(1, len(centers)):
Zgaussians += weights[i] * mlab.bivariate_normal(
X, Y, **format_args(i))
if args.plot == 'components':
CS = plt.contour(X, Y, Zgaussians, linewidth=10000, inline=1)
elif args.plot == 'density':
CS = plt.contour(X, Y, Z, linewidth=10000, inline=1)
elif args.plot == 'difference':
CS = plt.contour(X, Y, Z - Zgaussians, linewidth=10000, inline=1)
if args.plot != 'noop':
plt.clabel(CS, inline=1)
set_plot_limits(plt, args)
if args.csv and args.hist2d:
args.data = pd.read_csv(args.csv)
_plot_hist2d(args.data, args)
if args.savefig:
if args.savefig == SAVEFIG_INFER_VALUE:
name = os.path.basename(args.scored_grid).rsplit('.')[0]
filename = 'target/plots/{}.png'.format(name)
else:
filename = args.savefig
print 'saving figure to - ', filename
plt.savefig(filename, dpi=320)
else:
plt.show()
def plot_score_contours(args):
weights = []
centers = []
sigmas = []
if args.centers and args.covariances and args.weights:
# normalize weights to sum to 1.
weights = json.load(args.weights)
weights = [w / sum(weights) for w in weights]
weights = [0.4 * w / max(weights) for w in weights]
centers = load_cluster_parameters(args.centers)
sigmas = load_cluster_parameters(args.covariances)
fig = plt.figure(0)
ax = fig.add_subplot(111)
for i in range(len(centers)):
w, h, angle = get_ellipse_from_covariance(sigmas[i])
e = patches.Ellipse(centers[i], w, h, angle=angle)
e.set_alpha(weights[i])
ax.add_artist(e)
print i, weights[i], centers[i], sigmas[i]
set_ax_limits(ax, args)
x, y = zip(*centers)
plt.scatter(x, y, s=weights)
X, Y, Z = load_json_dump(args.scored_grid)
if args.score_cap:
Z = [min(z, args.score_cap) for z in Z]
if args.score_lower_limit:
Z = [max(z, args.score_lower_limit) for z in Z]
size = int(math.sqrt(len(Z)))
X = np.reshape(X, (size, size))
Y = np.reshape(Y, (size, size))
Z = np.reshape(Z, (size, size))
def format_args(i):
kwargs = {}
kwargs['mux'] = centers[i][0]
kwargs['muy'] = centers[i][1]
kwargs['sigmax'] = math.sqrt(sigmas[i][0][0])
kwargs['sigmay'] = math.sqrt(sigmas[i][1][1])
kwargs['sigmaxy'] = sigmas[i][0][1]
return kwargs
if len(weights):
Zgaussians = weights[0] * mlab.bivariate_normal(X, Y, **format_args(0))
for i in range(1, len(centers)):
Zgaussians += weights[i] * mlab.bivariate_normal(X, Y, **format_args(i))
if args.plot == 'components':
CS = plt.contour(X, Y, Zgaussians, linewidth=10000, inline=1)
elif args.plot == 'density':
CS = plt.contour(X, Y, Z, linewidth=10000, inline=1)
elif args.plot == 'difference':
CS = plt.contour(X, Y, Z - Zgaussians, linewidth=10000, inline=1)
if args.plot != 'noop':
plt.clabel(CS, inline=1)
set_plot_limits(plt, args)
if args.csv and args.hist2d:
args.data = pd.read_csv(args.csv)
_plot_hist2d(args.data, args)
if args.savefig:
if args.savefig == SAVEFIG_INFER_VALUE:
name = os.path.basename(args.scored_grid).rsplit('.')[0]
filename = 'target/plots/{}.png'.format(name)
else:
filename = args.savefig
print 'saving figure to - ', filename
plt.savefig(filename, dpi=320)
else:
plt.show()
def plot_distribution(args):
if args.csv is None:
cursor = args.db_connection.cursor()
cursor.execute("select relname from pg_class where relkind='r' and relname !~ '^(pg_|sql_)';") # noqa
print cursor.fetchall()
sql = """
SELECT {select} FROM {table};
""".format(select='*', table=args.table)
print sql
colnames = [desc[0] for desc in cursor.description]
data = pd.DataFrame(cursor.fetchall(), columns=colnames)
else:
data = pd.read_csv(args.csv)
# Set args.data, so we can pass only args to functions
args.data = data
data_size = data.shape[0]
if args.scatter is not None:
if args.labels:
interesting_data = data[[args.scatter[0], args.scatter[1], args.labels]]
different_labels = set(data[args.labels])
for label, color in zip(different_labels,
matplotlib.colors.cnames.keys()):
df = interesting_data.query('{column} == "{label}"'.format(
column=args.labels, label=label))
plt.scatter(df[args.scatter[0]], df[args.scatter[1]],
c=color, label=label)
else:
plt.scatter(data[args.scatter[0]], data[args.scatter[1]],
c=color)
plt.xlabel(args.scatter[0])
plt.ylabel(args.scatter[1])
elif args.histogram is not None:
if args.labels:
interesting_data = data[[args.histogram, args.labels]]
different_labels = set(data[args.labels])
data_to_plot, colors_to_use, labels_to_show = [], [], []
miscellaneous_labels = set()
misc_frame, misc_color = pd.DataFrame(), None
for label, color in zip(different_labels,
matplotlib.colors.cnames.keys()):
df = interesting_data.query('{column} == "{label}"'.format(
column=args.labels, label=label))
if df.shape[0] < args.miscellaneous_cutoff * data_size:
miscellaneous_labels.add(label)
misc_frame = pd.concat([misc_frame, df[args.histogram]])
misc_color = color
continue
labels_to_show.append('{label} ({count})'.format(label=label,
count=df.shape[0]))
data_to_plot.append(df[args.histogram])
colors_to_use.append(color)
if misc_color is not None:
labels_to_show.append('miscellaneous ({count})'.format(
count=misc_frame.shape[0]))
data_to_plot.append(misc_frame)
# colors_to_use.append(misc_color)
colors_to_use.append('cyan')
plt.hist(data_to_plot, args.histogram_bins, histtype='bar',
color=colors_to_use, label=labels_to_show)
else:
plt.hist(data[args.histogram], args.histogram_bins,
label=args.histogram)
plt.xlabel(args.histogram)
if args.scale_down:
plt.ylim(ymax=int(data_size * args.miscellaneous_cutoff))
elif args.hist2d is not None:
_plot_hist2d(data, args)
plt.legend()
set_plot_limits(plt, args)
if args.savefig is not None:
plt.savefig(args.savefig, dpi=320)
plt.clf()
else:
plt.show()
