def plot_jpt(self, other: 'MultiCategoryPTMixin', **kwargs) -> Axes:
"""
Plot a joint probability table of self and other.
:param other: Another MultiCategoryPTMixin to plot against.
:param kwargs: See utils.plots.plot_pt
"""
if isinstance(other, MultiCategoryPTMixin):
other_data = other.make_features(naming='{{choice}}')
else:
# assume single category
other_data = other.data
jpt = create_jpt(data_1=self.make_features(naming='{{choice}}'),
data_2=other_data,
prob_1_name=self.name,
prob_2_name=other.name,
prob_1_order=self.categories,
prob_2_order=other.categories)
if 'transpose' not in kwargs.keys():
kwargs['transpose'] = False
if 'var_sep' not in kwargs.keys():
kwargs['var_sep'] = ','
if 'dividers' not in kwargs.keys():
kwargs['dividers'] = False
ax = plot_pt(pt=jpt, **kwargs)
return ax
def plot_jpt(self,
item_name: str = 'item',
value_name: str = 'value',
item_names: Optional[List[str]] = None,
**kwargs) -> Axes:
"""
Plot a joint probability table of the answer values for each question
with the key to the question.
:param item_name: Name for the collection of questions or attributes to
condition on.
:param value_name: Name for the collection of values to calculate
conditional probability of.
:param item_names: Optional list of names for the questions or
attributes instead of the keys.
:param kwargs: See utils.plots.plot_pt
"""
jpt = self.jpt(item_name=item_name,
value_name=value_name,
item_names=item_names)
if 'transpose' not in kwargs.keys():
kwargs['transpose'] = True
if 'var_sep' not in kwargs:
kwargs['var_sep'] = ','
if 'dividers' not in kwargs:
kwargs['dividers'] = False
ax = plot_pt(pt=jpt, **kwargs)
return ax
def plot_jct(self, other: 'SingleCategoryPTMixin',
significance: bool = False,
sig_colors: Tuple[str, str] = ('#00ff00', '#ff0000'),
sig_values: Tuple[float, float] = (0.945, 0.055),
**kwargs) -> Axes:
"""
Plot a joint count table of self and other.
:param other: Another SingleCategory to plot against.
:param significance: Whether to add significance markers to the plot.
Equal to p(X=x1,Y=y1) > p(X≠x1, Y≠y1).
:param sig_colors: Tuple of (high, low) colors for highlighting
significance.
:param sig_values: Tuple of (high, low) values for assessing
significance.
:param kwargs: See utils.plots.plot_pt
"""
if self.name == other.name:
raise ValueError('categoricals must have different names')
if isinstance(other, SingleCategoryPTMixin):
other_data = other.data
else:
# assume multi category
other_data = other.make_features(naming='{{choice}}')
# calculate jpt
jct = create_jct(
data_1=self.data, data_2=other_data,
count_1_name=self.name, count_2_name=other.name,
count_1_order=self.category_names,
count_2_order=other.category_names
)
if 'transpose' not in kwargs.keys():
kwargs['transpose'] = False
if 'var_sep' not in kwargs.keys():
kwargs['var_sep'] = '&'
if 'dividers' not in kwargs.keys():
kwargs['dividers'] = False
kwargs['as_percent'] = False
kwargs['precision'] = 0
if 'p_max' not in kwargs.keys():
kwargs['p_max'] = None
ax = plot_pt(pt=jct, **kwargs)
# draw significance values
if significance and isinstance(other, SingleCategoryPTMixin):
self._draw_significance_values(
other=other,
sig_colors=sig_colors,
sig_values=sig_values,
transpose=kwargs['transpose'],
ax=ax
)
return ax
def plot_distribution(self, **kwargs) -> Axes:
"""
Plot the Conditional Probability Table as a heatmap.
:param kwargs: See utils.plots.plot_pt
"""
# calculate create_cpt and fix labels
if 'transpose' not in kwargs.keys():
kwargs['transpose'] = True
if 'var_sep' not in kwargs:
kwargs['var_sep'] = '|'
ax = plot_pt(pt=self._data, **kwargs)
return ax
def plot_jpt(self, prob_1: Union[str, Categorical],
prob_2: Union[str, Categorical], **kwargs) -> Axes:
"""
Plot a joint probability table.
:param prob_1: The question or attribute to find probability of.
:param prob_2: The question or attribute to condition on.
:param kwargs: See survey.utils.plots.plot_pt.
"""
# calculate create_cpt and fix labels
jpt = self.jpt(prob_1, prob_2)
if 'var_sep' not in kwargs:
kwargs['var_sep'] = ','
ax = plot_pt(pt=jpt, **kwargs)
return ax
def plot_cpt(self, probability: Union[str, Categorical],
condition: Union[str, Categorical], **kwargs) -> Axes:
"""
Plot a conditional probability table.
:param probability: The question or attribute to find probability of.
:param condition: The question or attribute to condition on.
"""
# calculate create_cpt and fix labels
cpt = self.cpt(probability, condition)
if 'transpose' not in kwargs.keys():
kwargs['transpose'] = False
if 'var_sep' not in kwargs:
kwargs['var_sep'] = '|'
ax = plot_pt(pt=cpt, **kwargs)
return ax
def plot_cpt(self, condition: 'MultiCategoryPTMixin', **kwargs) -> Axes:
"""
Plot a conditional probability table of self and other.
:param condition: Another MultiCategoryPTMixin to condition on.
:param kwargs: See utils.plots.plot_pt
"""
if isinstance(condition, MultiCategoryPTMixin):
cond_data = condition.make_features(naming='{{choice}}')
else:
# assume single category
cond_data = condition.data
jpt = create_cpt(prob_data=self.make_features(naming='{{choice}}'),
cond_data=cond_data,
prob_name=self.name,
cond_name=condition.name,
prob_order=self.categories,
cond_order=condition.categories)
if 'var_sep' not in kwargs.keys():
kwargs['var_sep'] = '|'
ax = plot_pt(pt=jpt, **kwargs)
return ax
def plot_cpt(self,
condition: 'SingleCategoryPTMixin',
significance: Optional[str] = None,
sig_colors: Tuple[str, str] = ('#00ff00', '#ff0000'),
sig_values: Tuple[float, float] = (0.945, 0.055),
**kwargs) -> Axes:
"""
Plot a conditional probability table of self and other.
:param condition: Another SingleCategory to condition on.
:param significance: One of ['prob', 'cond'].
'prob' gives p(X=x1|Y=y1) > p(X≠x1|Y=y1)
'cond' gives p(X=x1|Y=y1) > p(X=x1|Y≠y1)
:param sig_colors: Tuple of (high, low) colors for highlighting
significance.
Equal to p(X=x1,Y=y1) > p(X≠x1, Y≠y1).
:param sig_values: Tuple of (high, low) values for assessing
significance.
:param kwargs: See utils.plots.plot_pt
"""
if self.name == condition.name:
raise ValueError('categoricals must have different names')
if isinstance(condition, SingleCategoryPTMixin):
condition_data = condition.data
else:
# assume multi category
condition_data = condition.make_features(naming='{{choice}}')
jpt = create_cpt(
prob_data=self.data, cond_data=condition_data,
prob_name=self.name, cond_name=condition.name,
prob_order=self.category_names, cond_order=condition.category_names
)
if 'var_sep' not in kwargs.keys():
kwargs['var_sep'] = '|'
if not 'transpose' in kwargs.keys():
kwargs['transpose'] = True
ax = plot_pt(pt=jpt, **kwargs)
# draw significance values
if significance is not None:
counts = count_coincidences(
data_1=self.data, data_2=condition_data,
column_1=self.name, column_2=condition.name,
column_1_order=self.category_names,
column_2_order=condition.category_names
)
if isinstance(condition, SingleCategoryPTMixin):
results = []
if significance == 'prob':
for cond_cat in condition.category_names:
n_cond = counts.loc[cond_cat].sum()
for prob_cat in self.category_names:
m_prob_cond = counts.loc[cond_cat, prob_cat]
m_any = (
(n_cond - m_prob_cond) /
(len(self.category_names) - 1)
)
p = (
BetaBinomialConjugate(
alpha=1, beta=1, n=n_cond, k=m_prob_cond
).posterior() > BetaBinomialConjugate(
alpha=1, beta=1, n=n_cond, k=m_any
).posterior()
)
results.append({
self.name: prob_cat,
condition.name: cond_cat,
'p': p
})
elif significance == 'cond':
n = counts.sum().sum()
for prob_cat in self.category_names:
n_prob = counts[prob_cat].sum()
for cond_cat in condition.category_names:
n_cond = counts.loc[cond_cat].sum()
m_prob_cond = counts.loc[cond_cat, prob_cat]
m_any = n_prob - m_prob_cond
n_any = n - n_cond
p = (
BetaBinomialConjugate(
n=n_cond, k=m_prob_cond, alpha=1, beta=1,
).posterior() > BetaBinomialConjugate(
n=n_any, k=m_any, alpha=1, beta=1
).posterior()
)
results.append({
self.name: prob_cat,
condition.name: cond_cat,
'p': p
})
else:
raise ValueError(
"significance must be one of ['prob', 'cond']"
)
results_data = DataFrame(results)
else:
raise NotImplementedError(
'significance not implemented for MultiCategories'
)
min_add = 0.1
max_add = 0.9
line_width = 2
for _, row in results_data.iterrows():
color = None
if row['p'] >= sig_values[0]:
color = sig_colors[0]
elif row['p'] < sig_values[1]:
color = sig_colors[1]
if color is None:
continue
if not kwargs['transpose']:
x = self.category_names.index(row[self.name])
y = condition.category_names.index(row[condition.name])
if significance == 'prob':
ax.plot([x + min_add, x + min_add],
[y + min_add, y + max_add],
color, linewidth=line_width)
ax.plot([x + max_add, x + max_add],
[y + min_add, y + max_add],
color, linewidth=line_width)
elif significance == 'cond':
ax.plot([x + min_add, x + max_add],
[y + min_add, y + min_add],
color, linewidth=line_width)
ax.plot([x + min_add, x + max_add],
[y + max_add, y + max_add],
color, linewidth=line_width)
else:
y = self.category_names.index(row[self.name])
x = condition.category_names.index(row[condition.name])
if significance == 'prob':
ax.plot([x + min_add, x + max_add],
[y + min_add, y + min_add],
color, linewidth=line_width)
ax.plot([x + min_add, x + max_add],
[y + max_add, y + max_add],
color, linewidth=line_width)
elif significance == 'cond':
ax.plot([x + min_add, x + min_add],
[y + min_add, y + max_add],
color, linewidth=line_width)
ax.plot([x + max_add, x + max_add],
[y + min_add, y + max_add],
color, linewidth=line_width)
return ax