def run_diagnostics(self, decimal=3):
"""Run all currently implemented diagnostics for the exposure and outcome models. Each
`run_diagnostics` provides results for all implemented diagnostics for ease of the user. For publication
quality presentations, I recommend calling each diagnostic function individually and utilizing the optional
parameters
Note
----
The plot presented cannot be edited. To edit the plots, call `plot_kde` or `plot_love` directly. Those
functions return an axes object
Parameters
----------
decimal : int, optional
Number of decimal places to display. Default is 3
Returns
-------
None
"""
if not self._fit_outcome_ or not self._fit_exposure_:
raise ValueError("The exposure_model and outcome_model function must be ran before any diagnostics")
# Weight diagnostics
print('\tExposure Model Diagnostics')
self.positivity(decimal=decimal)
print('\n======================================================================')
print(' Standardized Mean Differences')
print('======================================================================')
print(self.standardized_mean_differences().set_index(keys='labels'))
print('======================================================================\n')
# Outcome accuracy diagnostics
print('\tOutcome Model Diagnostics')
v = self._predicted_y_ - self.df[self.outcome]
outcome_accuracy(true=self.df[self.outcome], predicted=self._predicted_y_, decimal=decimal)
df = self.df.copy()
df['_ipw_'] = np.where(df[self.exposure] == 1, 1 / df['_g1_'], 1 / (1 - df['_g1_']))
plt.figure(figsize=[8, 6])
plt.subplot(221)
plot_love(df=df, treatment=self.exposure, weight='_ipw_', formula=self.__mweight)
plt.title("Love Plot")
plt.subplot(223)
plot_kde(df=df, treatment=self.exposure, probability='_g1_')
plt.title("Kernel Density of Propensity Scores")
plt.subplot(222)
plot_kde_accuracy(values=v.dropna(), color='green')
plt.title("Kernel Density of Accuracy")
plt.tight_layout()
plt.show()
def plot_kde(self, bw_method='scott', fill=True, color='b'):
"""Generates a Kernel Density plot of the accuracy of the model predicted outcomes. The plot compares the
model predicted outcome to the observed outcome. This can be used as a diagnostic for the g-formula.
Parameters
----------
bw_method : str, optional
Method used to estimate the bandwidth. Following SciPy, either 'scott' or 'silverman' are valid options
fill : bool, optional
Whether to color the area under the density curves. Default is true
color : str, optional
Color of the line/area. Default is blue
Returns
-------
matplotlib axes
"""
if self._predicted_y_ is None:
raise ValueError(
"The outcome_model function must be ran before any diagnostics"
)
v = self._predicted_y_ - self.gf[self.outcome]
return plot_kde_accuracy(values=v.dropna(),
bw_method=bw_method,
fill=fill,
color=color)
def plot_kde(self,
to_plot,
bw_method='scott',
fill=True,
color='g',
color_e='b',
color_u='r'):
"""Generates density plots that can be used to check predictions qualitatively. Density plots can be generated
for assess either positivity violations of the exposure model or the accuracy in predicting the outcome for
the outcome model. The kernel density used is SciPy's Gaussian kernel. Either Scott's Rule or
Silverman's Rule can be implemented.
Parameters
------------
to_plot : str, optional
The plot to generate. Specifying 'exposure' returns only the density plot for treatment probabilities,
and 'outcome' returns only the density plot for the outcome accuracy
bw_method : str, optional
Method used to estimate the bandwidth. Following SciPy, either 'scott' or 'silverman' are valid options
fill : bool, optional
Whether to color the area under the density curves. Default is true
color : str, optional
Color of the line/area for predicted outcomes minus observed outcomes. Default is Green
color_e : str, optional
Color of the line/area for the treated group. Default is Blue
color_u : str, optional
Color of the line/area for the treated group. Default is Red
Returns
---------------
matplotlib axes
"""
if to_plot == 'exposure':
ax = plot_kde(df=self.df,
treatment=self.exposure,
probability='_g1_',
bw_method=bw_method,
fill=fill,
color_e=color_e,
color_u=color_u)
ax.set_title("Kernel Density of Propensity Scores")
elif to_plot == 'outcome':
v = self._predicted_y_ - self.df[self.outcome]
ax = plot_kde_accuracy(values=v.dropna(),
bw_method=bw_method,
fill=fill,
color=color)
ax.set_title("Kernel Density of Accuracy")
else:
raise ValueError(
"Please use one of the following options for `to_plot`; 'treatment', 'outcome'"
)
return ax