def plot_heated_stacked_area(df: pd.DataFrame,
lines: str,
heat: str,
backtest: str = None,
reset_y_lim: bool = False,
figsize: Tuple[int, int] = (16, 9),
color_map: str = 'afmhot',
ax: Axis = None,
upper_lower_missing_scale: float = 0.05) -> Axis:
color_function = plt.get_cmap(color_map)
x = df.index
y = df[lines].values
c = df[heat].values
b = df[backtest].values if backtest is not None else None
# assert enough data
assert len(y.shape) > 1 and len(
c.shape) > 1, "lines and heat need to be 2 dimensions!"
# make sure we have one more line as heats
if c.shape[1] == y.shape[1] + 1:
lower = np.full((c.shape[0], 1),
y.min() * (1 - upper_lower_missing_scale))
upper = np.full((c.shape[0], 1),
y.max() * (1 + upper_lower_missing_scale))
y = np.hstack([lower, y, upper])
# check for matching columns
assert y.shape[1] - 1 == c.shape[
1], f'unexpeced shapes: {y.shape[1] - 1} != {c.shape[1]}'
_, ax = plt.subplots(figsize=figsize) if ax is None else (None, ax)
ax.plot(x, y, color='k', alpha=0.0)
for ci in range(c.shape[1]):
for xi in range(len(x)):
ax.fill_between(x[xi - 1:xi + 1],
y[xi - 1:xi + 1, ci],
y[xi - 1:xi + 1, ci + 1],
facecolors=color_function(c[xi - 1:xi + 1, ci]))
if ci > 0:
# todo annotate all first last and only convert date if it is actually a date
ax.annotate(f'{y[-1, ci]:.2f}',
xy=(mdates.date2num(x[-1]), y[-1, ci]),
xytext=(4, -4),
textcoords='offset pixels')
# reset limits
ax.autoscale(tight=True)
if reset_y_lim:
ax.set_ylim(bottom=y[:, 1].min(), top=y[:, -1].max())
# backtest
if backtest:
ax.plot(x, b)
return ax
def plot_interactions(locations: List[str],
latent_graph: ndarray,
map: Basemap,
ax: Axis,
skip_first: bool = False):
"""
Given station ids and latent graph plot edges in different colors
"""
# Transform lan/lot into region-specific values
pixel_coords = [map(*coords) for coords in locations]
# Draw contours and borders
map.shadedrelief()
map.drawcountries()
# m.bluemarble()
# m.etopo()
# Plot Locations of weather stations
for i, (x, y) in enumerate(pixel_coords):
ax.plot(x, y, 'ok', markersize=10, color='yellow')
ax.text(x + 10, y + 10, "Station " + str(i), fontsize=20, color='yellow');
# Infer number of edge types and atoms from latent graph
n_atoms = latent_graph.shape[-1]
n_edge_types = latent_graph.shape[0]
color_map = get_cmap('Set1')
for i in range(n_atoms):
for j in range(n_atoms):
for edge_type in range(n_edge_types):
if latent_graph[edge_type, i, j] > 0.5:
if skip_first and edge_type == 0:
continue
# Draw line between points
x = locations[i]
y = locations[j]
map.drawgreatcircle(x[0], x[1], y[0], y[1],
color=color_map(edge_type - 1),
label=str(edge_type))
handles, labels = ax.get_legend_handles_labels()
unique = [(h, l) for i, (h, l) in enumerate(zip(handles, labels)) if l not in labels[:i]]
ax.legend(*zip(*unique))
return ax
def add_to_plot(self,
ax: Axis,
N: int = 201,
xrange: Tuple[float] = None,
xscale: float = 1,
yscale: float = 1,
**kwargs):
"""Add fit to existing plot axis
Args:
ax: Axis to add plot to
N: number of points to use as x values (to smoothe fit curve)
xrange: Optional range for x values (min, max)
xscale: value to multiple x values by to rescale axis
yscale: value to multiple y values by to rescale axis
kwargs: Additional plot kwargs. By default Fit.plot_kwargs are used
Returns:
plot_handle of fit curve
"""
if xrange is None:
x_vals = self.xvals
x_vals_full = np.linspace(min(x_vals), max(x_vals), N)
else:
x_vals_full = np.linspace(*xrange, N)
y_vals_full = self.fit_result.eval(
**{self.sweep_parameter: x_vals_full})
x_vals_full *= xscale
y_vals_full *= yscale
plot_kwargs = {**self.plot_kwargs, **kwargs}
self.plot_handle, = ax.plot(x_vals_full, y_vals_full, **plot_kwargs)
return self.plot_handle
def add_to_plot(self,
ax: Axis,
N: int = 201,
xrange: Tuple[float] = None,
xscale: float = 1,
yscale: float = 1,
**kwargs):
"""Add fit to existing plot axis
Args:
ax: Axis to add plot to
N: number of points to use as x values (to smoothe fit curve)
xrange: Optional range for x values (min, max)
xscale: value to multiple x values by to rescale axis
yscale: value to multiple y values by to rescale axis
kwargs: Additional plot kwargs. By default Fit.plot_kwargs are used
Returns:
plot_handle of fit curve
"""
if xrange is None:
x_vals = self.xvals
x_vals_full = np.linspace(min(x_vals), max(x_vals), N)
else:
x_vals_full = np.linspace(*xrange, N)
y_vals_full = self.fit_result.eval(
**{self.sweep_parameter: x_vals_full})
x_vals_full *= xscale
y_vals_full *= yscale
# Set default plot kwargs while de-aliasing (e.g. 'lw' -> 'linewidth')
# kwargs to prevent duplicate keys
kwargs = {
**self.default_plot_kwargs,
**cbook.normalize_kwargs(kwargs, mlines.Line2D)
}
self.plot_handle, = ax.plot(x_vals_full, y_vals_full, **kwargs)
return self.plot_handle
def control_plot(data: (List[int], List[float], pd.Series, np.array),
upper_control_limit: (int, float),
lower_control_limit: (int, float),
highlight_beyond_limits: bool = True,
highlight_zone_a: bool = True,
highlight_zone_b: bool = True,
highlight_zone_c: bool = True,
highlight_trend: bool = True,
highlight_mixture: bool = True,
highlight_stratification: bool = True,
highlight_overcontrol: bool = True,
ax: Axis = None):
"""
Create a control plot based on the input data.
:param data: a list, pandas.Series, or numpy.array representing the data set
:param upper_control_limit: an integer or float which represents the upper control limit, commonly called the UCL
:param lower_control_limit: an integer or float which represents the upper control limit, commonly called the UCL
:param highlight_beyond_limits: True if points beyond limits are to be highlighted
:param highlight_zone_a: True if points that are zone A violations are to be highlighted
:param highlight_zone_b: True if points that are zone B violations are to be highlighted
:param highlight_zone_c: True if points that are zone C violations are to be highlighted
:param highlight_trend: True if points that are trend violations are to be highlighted
:param highlight_mixture: True if points that are mixture violations are to be highlighted
:param highlight_stratification: True if points that are stratification violations are to be highlighted
:param highlight_overcontrol: True if points that are overcontrol violations are to be hightlighted
:param ax: an instance of matplotlib.axis.Axis
:return: None
"""
data = coerce(data)
if ax is None:
fig, ax = plt.subplots()
ax.plot(data)
ax.set_title('Zone Control Chart')
spec_range = (upper_control_limit - lower_control_limit) / 2
spec_center = lower_control_limit + spec_range
zone_c_upper_limit = spec_center + spec_range / 3
zone_c_lower_limit = spec_center - spec_range / 3
zone_b_upper_limit = spec_center + 2 * spec_range / 3
zone_b_lower_limit = spec_center - 2 * spec_range / 3
zone_a_upper_limit = spec_center + spec_range
zone_a_lower_limit = spec_center - spec_range
ax.axhline(spec_center, linestyle='--', color='red', alpha=0.6)
ax.axhline(zone_c_upper_limit, linestyle='--', color='red', alpha=0.5)
ax.axhline(zone_c_lower_limit, linestyle='--', color='red', alpha=0.5)
ax.axhline(zone_b_upper_limit, linestyle='--', color='red', alpha=0.3)
ax.axhline(zone_b_lower_limit, linestyle='--', color='red', alpha=0.3)
ax.axhline(zone_a_upper_limit, linestyle='--', color='red', alpha=0.2)
ax.axhline(zone_a_lower_limit, linestyle='--', color='red', alpha=0.2)
left, right = ax.get_xlim()
right_plus = (right - left) * 0.01 + right
ax.text(right_plus, upper_control_limit, s='UCL', va='center')
ax.text(right_plus, lower_control_limit, s='LCL', va='center')
ax.text(right_plus, (spec_center + zone_c_upper_limit) / 2,
s='Zone C',
va='center')
ax.text(right_plus, (spec_center + zone_c_lower_limit) / 2,
s='Zone C',
va='center')
ax.text(right_plus, (zone_b_upper_limit + zone_c_upper_limit) / 2,
s='Zone B',
va='center')
ax.text(right_plus, (zone_b_lower_limit + zone_c_lower_limit) / 2,
s='Zone B',
va='center')
ax.text(right_plus, (zone_a_upper_limit + zone_b_upper_limit) / 2,
s='Zone A',
va='center')
ax.text(right_plus, (zone_a_lower_limit + zone_b_lower_limit) / 2,
s='Zone A',
va='center')
plot_params = {'alpha': 0.3, 'zorder': -10, 'markersize': 14}
if highlight_beyond_limits:
beyond_limits_violations = control_beyond_limits(
data=data,
upper_control_limit=upper_control_limit,
lower_control_limit=lower_control_limit)
if len(beyond_limits_violations):
plot_params['zorder'] -= 1
plot_params['markersize'] -= 1
ax.plot(beyond_limits_violations,
'o',
color='red',
label='beyond limits',
**plot_params)
if highlight_zone_a:
zone_a_violations = control_zone_a(
data=data,
upper_control_limit=upper_control_limit,
lower_control_limit=lower_control_limit)
if len(zone_a_violations):
plot_params['zorder'] -= 1
plot_params['markersize'] -= 1
ax.plot(zone_a_violations,
'o',
color='orange',
label='zone a violations',
**plot_params)
if highlight_zone_b:
zone_b_violations = control_zone_b(
data=data,
upper_control_limit=upper_control_limit,
lower_control_limit=lower_control_limit)
if len(zone_b_violations):
plot_params['zorder'] -= 1
plot_params['markersize'] -= 1
ax.plot(zone_b_violations,
'o',
color='blue',
label='zone b violations',
**plot_params)
if highlight_zone_c:
zone_c_violations = control_zone_c(
data=data,
upper_control_limit=upper_control_limit,
lower_control_limit=lower_control_limit)
if len(zone_c_violations):
plot_params['zorder'] -= 1
plot_params['markersize'] -= 1
ax.plot(zone_c_violations,
'o',
color='green',
label='zone c violations',
**plot_params)
if highlight_trend:
zone_trend_violations = control_zone_trend(data=data)
if len(zone_trend_violations):
plot_params['zorder'] -= 1
plot_params['markersize'] -= 1
ax.plot(zone_trend_violations,
'o',
color='purple',
label='trend violations',
**plot_params)
if highlight_mixture:
zone_mixture_violations = control_zone_mixture(
data=data,
upper_control_limit=upper_control_limit,
lower_control_limit=lower_control_limit)
if len(zone_mixture_violations):
plot_params['zorder'] -= 1
plot_params['markersize'] -= 1
ax.plot(zone_mixture_violations,
'o',
color='brown',
label='mixture violations',
**plot_params)
if highlight_stratification:
zone_stratification_violations = control_zone_stratification(
data=data,
upper_control_limit=upper_control_limit,
lower_control_limit=lower_control_limit)
if len(zone_stratification_violations):
plot_params['zorder'] -= 1
plot_params['markersize'] -= 1
ax.plot(zone_stratification_violations,
'o',
color='orange',
label='stratification violations',
**plot_params)
if highlight_overcontrol:
zone_overcontrol_violations = control_zone_overcontrol(
data=data,
upper_control_limit=upper_control_limit,
lower_control_limit=lower_control_limit)
if len(zone_overcontrol_violations):
plot_params['zorder'] -= 1
plot_params['markersize'] -= 1
ax.plot(zone_overcontrol_violations,
'o',
color='blue',
label='overcontrol violations',
**plot_params)
ax.legend()
def ppk_plot(data: (List[int], List[float], pd.Series, np.array),
upper_control_limit: (int, float),
lower_control_limit: (int, float),
threshold_percent: float = 0.001,
ax: Axis = None):
"""
Shows the statistical distribution of the data along with CPK and limits.
:param data: a list, pandas.Series, or numpy.array representing the data set
:param upper_control_limit: an integer or float which represents the upper control limit, commonly called the UCL
:param lower_control_limit: an integer or float which represents the upper control limit, commonly called the UCL
:param threshold_percent: the threshold at which % of units above/below the number will display on the plot
:param ax: an instance of matplotlig.axis.Axis
:return: None
"""
data = coerce(data)
mean = data.mean()
std = data.std()
if ax is None:
fig, ax = plt.subplots()
ax.hist(data, density=True, label='data', alpha=0.3)
x = np.linspace(mean - 4 * std, mean + 4 * std, 100)
pdf = stats.norm.pdf(x, mean, std)
ax.plot(x, pdf, label='normal fit', alpha=0.7)
bottom, top = ax.get_ylim()
ax.axvline(mean, linestyle='--')
ax.text(mean, top * 1.01, s='$\mu$', ha='center')
ax.axvline(mean + std, alpha=0.6, linestyle='--')
ax.text(mean + std, top * 1.01, s='$\sigma$', ha='center')
ax.axvline(mean - std, alpha=0.6, linestyle='--')
ax.text(mean - std, top * 1.01, s='$-\sigma$', ha='center')
ax.axvline(mean + 2 * std, alpha=0.4, linestyle='--')
ax.text(mean + 2 * std, top * 1.01, s='$2\sigma$', ha='center')
ax.axvline(mean - 2 * std, alpha=0.4, linestyle='--')
ax.text(mean - 2 * std, top * 1.01, s='-$2\sigma$', ha='center')
ax.axvline(mean + 3 * std, alpha=0.2, linestyle='--')
ax.text(mean + 3 * std, top * 1.01, s='$3\sigma$', ha='center')
ax.axvline(mean - 3 * std, alpha=0.2, linestyle='--')
ax.text(mean - 3 * std, top * 1.01, s='-$3\sigma$', ha='center')
ax.fill_between(x,
pdf,
where=x < lower_control_limit,
facecolor='red',
alpha=0.5)
ax.fill_between(x,
pdf,
where=x > upper_control_limit,
facecolor='red',
alpha=0.5)
lower_percent = 100.0 * stats.norm.cdf(lower_control_limit, mean, std)
lower_percent_text = f'{lower_percent:.02f}% < LCL' if lower_percent > threshold_percent else None
higher_percent = 100.0 - 100.0 * stats.norm.cdf(upper_control_limit, mean,
std)
higher_percent_text = f'{higher_percent:.02f}% > UCL' if higher_percent > threshold_percent else None
left, right = ax.get_xlim()
bottom, top = ax.get_ylim()
cpk = calc_ppk(data,
upper_control_limit=upper_control_limit,
lower_control_limit=lower_control_limit)
lower_sigma_level = (mean - lower_control_limit) / std
if lower_sigma_level < 6.0:
ax.axvline(lower_control_limit,
color='red',
alpha=0.25,
label='limits')
ax.text(lower_control_limit,
top * 0.95,
s=f'$-{lower_sigma_level:.01f}\sigma$',
ha='center')
else:
ax.text(left, top * 0.95, s=f'limit > $-6\sigma$', ha='left')
upper_sigma_level = (upper_control_limit - mean) / std
if upper_sigma_level < 6.0:
ax.axvline(upper_control_limit, color='red', alpha=0.25)
ax.text(upper_control_limit,
top * 0.95,
s=f'${upper_sigma_level:.01f}\sigma$',
ha='center')
else:
ax.text(right, top * 0.95, s=f'limit > $6\sigma$', ha='right')
strings = [f'Ppk = {cpk:.02f}']
strings.append(f'$\mu = {mean:.3g}$')
strings.append(f'$\sigma = {std:.3g}$')
if lower_percent_text:
strings.append(lower_percent_text)
if higher_percent_text:
strings.append(higher_percent_text)
props = dict(boxstyle='round',
facecolor='white',
alpha=0.75,
edgecolor='grey')
ax.text(right - (right - left) * 0.05,
0.85 * top,
'\n'.join(strings),
bbox=props,
ha='right',
va='top')
ax.legend(loc='lower right')