def test_pointrange_aesthetics():
p = (ggplot(df, aes('x')) +
geom_pointrange(aes(y='y', ymin='ymin', ymax='ymax'), size=2) +
geom_pointrange(aes(y='y+1', ymin='ymin+1', ymax='ymax+1', alpha='z'),
size=2) +
geom_pointrange(aes(
y='y+2', ymin='ymin+2', ymax='ymax+2', linetype='factor(z)'),
size=2) +
geom_pointrange(aes(y='y+3', ymin='ymin+3', ymax='ymax+3', color='z'),
size=2) +
geom_pointrange(aes(y='y+4', ymin='ymin+4', ymax='ymax+4', size='z')))
assert p + _theme == 'pointrange_aesthetics'
def plot_pointplot(plot_df, y_axis_label="", use_log10=False, limits=[0, 3.2]):
"""
Plots the pointplot
Arguments:
plot_df - the dataframe that contains the odds ratio and lemmas
y_axis_label - the label for the y axis
use_log10 - use log10 for the y axis?
"""
graph = (
p9.ggplot(plot_df, p9.aes(x="lemma", y="odds_ratio")) +
p9.geom_pointrange(p9.aes(ymin="lower_odds", ymax="upper_odds"),
position=p9.position_dodge(width=1),
size=0.3,
color="#253494") +
p9.scale_x_discrete(limits=(plot_df.sort_values(
"odds_ratio", ascending=True).lemma.tolist())) +
(p9.scale_y_log10() if use_log10 else p9.scale_y_continuous(
limits=limits)) +
p9.geom_hline(p9.aes(yintercept=1), linetype='--', color='grey') +
p9.coord_flip() + p9.theme_seaborn(
context='paper', style="ticks", font_scale=1, font='Arial') +
p9.theme(
# 640 x 480
figure_size=(6.66, 5),
panel_grid_minor=p9.element_blank(),
axis_title=p9.element_text(size=12),
axis_text_x=p9.element_text(size=10)) +
p9.labs(x=None, y=y_axis_label))
return graph
np.sqrt(np.diag(event_study_formula.cov_params().loc[lags][lags]))
]),
'mean':
np.concatenate([
event_study_formula.params[leads],
np.array([0]), event_study_formula.params[lags]
]),
'label':
np.arange(-9, 6)
})
leadslags_plot['lb'] = leadslags_plot['mean'] - leadslags_plot['sd'] * 1.96
leadslags_plot['ub'] = leadslags_plot['mean'] + leadslags_plot['sd'] * 1.96
# This version has a point-range at each
# estimated lead or lag
# comes down to stylistic preference at the
# end of the day!
p.ggplot(leadslags_plot, p.aes(x = 'label', y = 'mean',
ymin = 'lb',
ymax = 'ub')) +\
p.geom_hline(yintercept = 0.035169444, color = "red") +\
p.geom_pointrange() +\
p.theme_minimal() +\
p.xlab("Years before and after castle doctrine expansion") +\
p.ylab("log(Homicide Rate)") +\
p.geom_hline(yintercept = 0,
linetype = "dashed") +\
p.geom_vline(xintercept = 0,
linetype = "dashed")
]
]
)
category_sim_df.head()
category_sim_df.to_csv("output/category_cossim_95_ci.tsv", sep="\t", index=False)
g = (
p9.ggplot(category_sim_df)
+ p9.aes(
x="category",
y="pca1_cossim",
ymin="pca1_cossim_lower",
ymax="pca1_cossim_upper",
)
+ p9.geom_pointrange()
+ p9.coord_flip()
+ p9.theme_bw()
+ p9.scale_x_discrete(limits=category_sim_df.category.tolist()[::-1])
+ p9.theme(
figure_size=(11, 8.5),
text=p9.element_text(size=12),
panel_grid_major_y=p9.element_blank(),
)
+ p9.labs(y="PC1 Cosine Similarity")
)
g.save("output/pca_plots/figures/category_pca1_95_ci.png", dpi=500)
print(g)
g = (
p9.ggplot(category_sim_df)
]])
category_sim_df.head()
# In[10]:
category_sim_df.to_csv("output/category_cossim_95_ci.tsv",
sep="\t",
index=False)
# In[11]:
g = (p9.ggplot(category_sim_df) + p9.aes(x="category",
y="pca1_cossim",
ymin="pca1_cossim_lower",
ymax="pca1_cossim_upper") +
p9.geom_pointrange() + p9.coord_flip() + p9.theme_bw() +
p9.scale_x_discrete(limits=category_sim_df.category.tolist()[::-1]) +
p9.theme(figure_size=(11, 7),
text=p9.element_text(size=12),
panel_grid_major_y=p9.element_blank()) +
p9.labs(y="PC1 Cosine Similarity"))
g.save("output/pca_plots/figures/category_pca1_95_ci.svg", dpi=500)
g.save("output/pca_plots/figures/category_pca1_95_ci.png", dpi=500)
print(g)
# In[12]:
g = (p9.ggplot(category_sim_df) + p9.aes(x="category",
y="pca2_cossim",
ymax="pca2_cossim_upper",
ymin="pca2_cossim_lower") +