def plot_wikipedia_pmfs():
"""
https://en.wikipedia.org/wiki/Geometric_distribution#/media/
File:Geometric_pmf.svg
"""
axf = AxesFormatter(width=12, height=9)
Geometric(p=0.2).plot(k=k,
kind='line',
color='gray',
ax=axf.axes,
marker='o',
mfc='orange')
Geometric(p=0.5).plot(k=k,
kind='line',
color='gray',
ax=axf.axes,
marker='o',
mfc='purple')
Geometric(p=0.8).plot(k=k,
kind='line',
color='gray',
ax=axf.axes,
marker='o',
mfc='lightblue')
axf.set_text(x_label='x',
y_label='P(X=x)',
title='Probability mass function').set_x_lim(0, 10).set_y_lim(
0, 1)
axf.axes.legend(loc='upper right')
plt.show()
def __init__(self, axes: ndarray):
"""
Create a new AxesFormatterArray
:param axes: Array of Axes instances.
"""
self._axes = empty_like(axes, dtype=AxesFormatter)
if axes.ndim == 1:
for i in range(axes.shape[0]):
self._axes[i] = AxesFormatter(axes[i])
elif axes.ndim == 2:
for i in range(axes.shape[0]):
for j in range(axes.shape[1]):
self._axes[i, j] = AxesFormatter(axes[i, j])
def x_axes(self) -> Union[AxisFormatter, AxisFormatterArray]:
"""
Return an AxisFormatter or AxisFormatterArray for the X-Axis or X-Axes
of the wrapped Axes.
"""
if not self._has_array:
return AxesFormatter(self._axes).x_axis
else:
axes = empty_like(self._axes, dtype=AxisFormatter)
if axes.ndim == 1:
for i in range(self._axes.shape[0]):
axes[i] = AxisFormatter(
axis=self._axes[i].xaxis,
direction='x',
axes=self._axes[i]
)
elif axes.ndim == 2:
for i in range(axes.shape[0]):
for j in range(axes.shape[1]):
axes[i, j] = AxisFormatter(
axis=self._axes[i, j].xaxis,
direction='x',
axes=self._axes[i, j]
)
return AxisFormatterArray(axes)
def single(self) -> AxesFormatter:
"""
Return an AxesFormatter for the wrapped Axes.
"""
if not self._has_array:
return AxesFormatter(self._axes)
else:
raise TypeError('FigureFormatter holds an array of Axes.')
def plot_distribution(self,
data: Optional[Series] = None,
transpose: bool = False,
bins: Optional[Bins] = None,
color: str = 'C0',
pct_size: int = None,
grid: bool = False,
title: Optional[str] = None,
x_label: Optional[str] = None,
y_label: Optional[str] = None,
ax: Optional[Axes] = None) -> Axes:
"""
Plot a histogram of the distribution of the response data.
:param data: The answers given by Respondents to the Question.
:param transpose: True to plot horizontally.
:param bins: Value for hist bins. Leave as None for integer bins.
:param color: Color or list of colors for the bars.
:param pct_size: Font size for the percent markers.
:param grid: Whether to show a plot grid or not.
:param title: Optional title for the plot.
:param x_label: Label for the x-axis.
:param y_label: Label for the y-axis.
:param ax: Optional matplotlib axes to plot on.
"""
ax = ax or new_axes()
data = data if data is not None else self._data
if data is None:
raise ValueError('No data!')
orientation = 'horizontal' if transpose else 'vertical'
bins = bins or self._default_hist(data)
data.plot(kind='hist',
ax=ax,
bins=bins,
orientation=orientation,
color=color)
# add percentages
hist, edges = histogram(data, bins=bins)
item_counts = Series(index=0.5 * (edges[1:] + edges[:-1]), data=hist)
item_pcts = 100 * item_counts / item_counts.sum()
label_bar_plot_pcts(item_counts=item_counts,
item_pcts=item_pcts,
ax=ax,
transpose=transpose,
font_size=pct_size)
# add titles and grid
ax.set_title(self.text)
AxesFormatter(ax).set_text(
title=title, x_label=x_label,
y_label=y_label).set_axis_below(True).grid(grid)
if transpose and not x_label:
ax.set_xlabel('# Respondents')
elif not transpose and not y_label:
ax.set_ylabel('# Respondents')
return ax
def axes(self) -> Union[AxesFormatter, AxesFormatterArray]:
"""
Return an AxesFormatter or AxesFormatterArray for the wrapped Axes or
array of Axes.
"""
if not self._has_array:
return AxesFormatter(self._axes)
else:
return AxesFormatterArray(self._axes)
def plot_wikipedia_pmfs():
"""
https://en.wikipedia.org/wiki/Hypergeometric_distribution#/media/
File:HypergeometricPDF.png
"""
axf = AxesFormatter(width=12, height=9)
HyperGeometric(N=500, K=50, n=100).plot(
k=k, kind='line', color='blue',
ax=axf.axes, marker='o', mfc='blue'
)
HyperGeometric(N=500, K=60, n=200).plot(
k=k, kind='line', color='green',
ax=axf.axes, marker='o', mfc='green'
)
HyperGeometric(N=500, K=70, n=300).plot(
k=k, kind='line', color='red',
ax=axf.axes, marker='o', mfc='red'
)
axf.set_text(
x_label='k', y_label='P(X=k)', title='Probability mass function'
).set_x_lim(0, 60).set_y_lim(0, 0.15)
axf.axes.legend(loc='upper right')
plt.show()
def plot_wikipedia_cdfs():
"""
https://en.wikipedia.org/wiki/Hypergeometric_distribution#/media/
File:HypergeometricCDF.png
"""
axf = AxesFormatter(width=12, height=9)
HyperGeometric(N=500, K=50, n=100).cdf().plot(
k=k, kind='line', color='blue',
ax=axf.axes, marker='o', mfc='blue'
)
HyperGeometric(N=500, K=60, n=200).cdf().plot(
k=k, kind='line', color='green',
ax=axf.axes, marker='o', mfc='green'
)
HyperGeometric(N=500, K=70, n=300).cdf().plot(
k=k, kind='line', color='red',
ax=axf.axes, marker='o', mfc='red'
)
axf.set_text(
x_label='x', y_label='P(X≤x)', title='Cumulative distribution function'
).set_x_lim(0, 60).set_y_lim(0, 1)
axf.axes.legend(loc='lower right')
plt.show()
def plot_scipy_pmf():
"""
https://docs.scipy.org/doc/scipy/reference/generated/
scipy.stats.betabinom.html#scipy.stats.betabinom
"""
bb = BetaBinomial(n=5, alpha=2.3, beta=0.63)
axf = AxesFormatter()
bb.pmf().plot(k=range(0, 5), kind='line', ls='',
marker='o', color='blue', vlines=True, ax=axf.axes)
axf.set_x_lim(-0.5, 4.5)
axf.show()
def plot_comparison(self, ax: Axes = None, **kwargs) -> Axes:
"""
Plot a comparison between the different question ratings.
:param ax: Optional matplotlib axes.
"""
ax = ax or new_axes()
if 'cmap' not in kwargs:
kwargs['cmap'] = 'Blues'
data = DataFrame(
{k: q.value_counts()
for k, q in self.item_dict.items()})
heatmap(data=data, ax=ax, annot=True, fmt='d', **kwargs)
AxesFormatter(ax).set_text(x_label='Question',
y_label='Rating').invert_y_axis()
draw_vertical_dividers(ax)
return ax
def plot_wikipedia_cdfs():
"""
https://en.wikipedia.org/wiki/File:Beta-binomial_cdf.png
"""
axf = AxesFormatter(width=12, height=9)
for alpha, beta, color in zip(alpha_wiki, beta_wiki, colors_wiki):
BetaBinomial(n=10, alpha=alpha, beta=beta).cdf().plot(
k=k_wiki, color=color, kind='line', ax=axf.axes,
marker='o'
)
axf.add_legend()
axf.show()
def plot_distribution(self,
data: Optional[Series] = None,
drop_na: bool = True,
transpose: bool = True,
color: str = 'C0',
pct_size: int = None,
significance: bool = False,
sig_colors: Tuple[str, str] = ('#00ff00', '#ff0000'),
label_mappings: Optional[Dict[str, str]] = None,
grid: bool = False,
max_axis_label_chars: Optional[int] = None,
title: Optional[str] = None,
x_label: Optional[str] = None,
y_label: Optional[str] = None,
ax: Optional[Axes] = None,
**kwargs) -> Axes:
"""
Plot the distribution of answers to the Question.
:param data: The answers given by Respondents to the Question.
:param drop_na: Whether to drop null responses from the dataset
(affects % calculations).
:param transpose: Whether to transpose the labels to the y-axis.
:param ax: Optional matplotlib axes to plot on.
:param color: Color or list of colors for the bars.
:param pct_size: Font size for the percent markers.
:param significance: Whether to highlight significant categories.
:param sig_colors: Tuple of (high, low) colors for highlighting
significance.
:param label_mappings: Optional dict of replacements for labels.
:param grid: Whether to show a plot grid or not.
:param max_axis_label_chars: Maximum number of characters in axis labels
before wrapping.
:param title: Axes title.
:param x_label: Label for the x-axis.
:param y_label: Label for the y-axis.
"""
data = data if data is not None else self._data
if data is None:
raise ValueError('No data!')
if len(data) == 0:
return ax
if title is None:
title = self.text
if x_label is None:
x_label = self.name if not transpose else '# Respondents'
if y_label is None:
y_label = '# Respondents' if not transpose else self.name
features = self.make_features(answers=data,
drop_na=drop_na,
naming='{{choice}}')
item_counts: Series = features.sum()
plot_type = 'barh' if transpose else 'bar'
ax = ax or new_axes()
if label_mappings is not None:
item_counts.index = wrap_text(map_text(item_counts.index,
mapping=label_mappings
or {}),
max_width=max_axis_label_chars)
else:
item_counts.index = wrap_text(item_counts.index,
max_width=max_axis_label_chars)
edge_color = None
line_width = None
if significance:
one_vs_any = self.significance_one_vs_any()
edge_color = [
sig_colors[0] if one_vs_any[category] >= 0.945 else
sig_colors[1] if one_vs_any[category] < 0.055 else color
for category in self.category_names
]
line_width = [2 if ec != color else None for ec in edge_color]
item_counts.plot(kind=plot_type,
ax=ax,
color=color,
edgecolor=edge_color,
linewidth=line_width,
**kwargs)
# add percentages
item_pcts = 100 * item_counts.div(len(features))
label_bar_plot_pcts(item_counts=item_counts,
item_pcts=item_pcts,
ax=ax,
transpose=transpose,
font_size=pct_size)
# add titles and grid
AxesFormatter(ax).set_text(
title=title, x_label=x_label,
y_label=y_label).set_axis_below(True).grid(grid)
if transpose and not x_label:
ax.set_xlabel('# Respondents')
elif not transpose and not y_label:
ax.set_ylabel('# Respondents')
return ax
def set_text(
axes_formatter: AxesFormatter, string: str
) -> AxesFormatter:
return axes_formatter.set_y_label_text(string)
def plot_distribution(self,
data: Optional[Series] = None,
transpose: bool = False,
normalize: bool = False,
significance: bool = False,
sig_colors: Tuple[str, str] = ('#00ff00', '#ff0000'),
sig_values: Tuple[float, float] = (0.945, 0.055),
label_mappings: Optional[Dict[str, str]] = None,
ax: Optional[Axes] = None) -> Axes:
"""
Plot the distribution of answers to the Question.
:param data: The answers given by Respondents to the Question.
:param transpose: Whether to transpose the labels to the y-axis.
:param normalize: Whether to normalize number of responses in each
position to total number of responses.
:param significance: Whether to highlight significant choices.
:param sig_colors: Tuple of (high, low) colors for highlighting
significance.
:param sig_values: Tuple of (high, low) values for assessing
significance.
:param label_mappings: Optional dict of replacements for labels.
:param ax: Optional matplotlib axes to plot on.
"""
data = data if data is not None else self._data
if data is None:
raise ValueError('No data!')
order_counts = []
for index, str_user_order in data.iteritems():
if isnull(str_user_order):
continue
user_order = str_user_order.split(CATEGORY_SPLITTER)
for i in range(len(user_order)):
order_counts.append({
'choice': user_order[i],
'rank': i + 1,
})
counts = DataFrame(order_counts).groupby(
['choice',
'rank']).size().reset_index().rename(columns={0: 'count'})
pivot = pivot_table(data=counts,
index='choice',
columns='rank',
values='count').reindex(self.categories)
pivot.index = wrap_text(
map_text(pivot.index, mapping=label_mappings or {}))
if normalize:
fmt = '.2f'
pivot = pivot / len(data)
else:
fmt = '.0f'
if transpose:
pivot = pivot.T
axf = AxesFormatter(axes=ax)
ax = axf.axes
heatmap(data=pivot, annot=True, fmt=fmt, cmap='Blues', ax=ax)
if significance:
cat_sigs = self.significance__one_vs_any()
for category, sig_value in cat_sigs.iteritems():
if sig_values[1] < sig_value < sig_values[0]:
continue
elif sig_value <= sig_values[1]:
color = sig_colors[1]
elif sig_value >= sig_values[0]:
color = sig_colors[0]
if not transpose:
x_min = 0.1
x_max = len(self.categories) - 0.1
y_min = self.categories.index(category) + 0.1
y_max = self.categories.index(category) + 0.9
else:
y_min = 0.1
y_max = len(self.categories) - 0.1
x_min = self.categories.index(category) + 0.1
x_max = self.categories.index(category) + 0.9
ax.plot([x_min, x_max, x_max, x_min, x_min],
[y_min, y_min, y_max, y_max, y_min],
color=color,
linewidth=2)
axf.x_axis.tick_labels.set_ha_center()
axf.y_axis.tick_labels.set_va_center()
if transpose:
draw_vertical_dividers(ax)
else:
draw_horizontal_dividers(ax)
axf.set_title_text(self.text)
return ax
