def test_empty_breaks():
x = []
assert custom_format()(x) == []
assert comma_format()(x) == []
assert currency_format()(x) == []
assert percent_format()(x) == []
assert scientific_format()(x) == []
assert date_format()(x) == []
assert mpl_format()(x) == []
assert log_format()(x) == []
assert timedelta_format()(x) == []
def test_timedelta_format():
x = [timedelta(days=7 * i) for i in range(5)]
labels = timedelta_format()(x)
assert labels == ['0', '1 week', '2 weeks', '3 weeks', '4 weeks']
x = [pd.Timedelta(seconds=600 * i) for i in range(5)]
labels = timedelta_format()(x)
assert labels == \
['0', '10 minutes', '20 minutes', '30 minutes', '40 minutes']
# specific units
labels = timedelta_format(units='h')(x)
assert labels == \
['0', '0.1667 hours', '0.3333 hours', '0.5000 hours',
'0.6667 hours']
# usetex
x = [timedelta(microseconds=7 * i) for i in range(5)]
labels = timedelta_format(units='us', usetex=True)(x)
assert labels == \
['0', '7$\\mu s$', '14$\\mu s$', '21$\\mu s$', '28$\\mu s$']
def test_empty_breaks():
x = []
assert custom_format()(x) == []
assert comma_format()(x) == []
assert currency_format()(x) == []
assert percent_format()(x) == []
assert scientific_format()(x) == []
assert date_format()(x) == []
assert mpl_format()(x) == []
assert log_format()(x) == []
assert timedelta_format()(x) == []
def test_timedelta_format():
x = [timedelta(days=7*i) for i in range(5)]
labels = timedelta_format()(x)
assert labels == ['0', '1 week', '2 weeks', '3 weeks', '4 weeks']
x = [pd.Timedelta(seconds=600*i) for i in range(5)]
labels = timedelta_format()(x)
assert labels == \
['0', '10 minutes', '20 minutes', '30 minutes', '40 minutes']
# specific units
labels = timedelta_format(units='h')(x)
assert labels == \
['0', '0.1667 hours', '0.3333 hours', '0.5000 hours',
'0.6667 hours']
# usetex
x = [timedelta(microseconds=7*i) for i in range(5)]
labels = timedelta_format(units='us', usetex=True)(x)
assert labels == \
['0', '7$\\mu s$', '14$\\mu s$', '21$\\mu s$', '28$\\mu s$']
])
y_line = x_line * results_2.slope + results_2.intercept
g = (p9.ggplot(
published_date_distances,
p9.aes(x="factor(version_count)", y="time_to_published"),
) + p9.geom_boxplot(fill="#a6cee3") + p9.geom_line(
mapping=p9.aes(x="version_count", y="time_to_published"),
stat="smooth",
method="lm",
linetype="dashed",
se=False,
alpha=1,
size=0.7,
inherit_aes=False,
) + p9.scale_y_timedelta(labels=timedelta_format("d")) + p9.annotate(
"text",
x=9,
y=timedelta(days=1470),
label=f"Y={results_2.slope:.2f}*X+{results_2.intercept:.2f}",
) + p9.labs(x="# of Preprint Versions",
y="Time Elapsed Until Preprint is Published") + p9.theme_seaborn(
context="paper", style="ticks", font="Arial", font_scale=1.3))
# g.save("output/version_count_vs_publication_time.svg", dpi=500)
# g.save("output/version_count_vs_publication_time.png", dpi=500)
print(g)
plt.figure(figsize=(8, 5))
g = sns.boxenplot(
x="version_count",
y="days_to_published",
median_ci_l, median_ci_u = median_ci.values.flatten()
median_ci_l, median_ci_u
# In[9]:
overall_preprint_survival = kmf.survival_function_.reset_index().assign(
label="all_papers")
overall_preprint_survival.head()
# In[10]:
g = (p9.ggplot(
overall_preprint_survival.assign(
timeline=lambda x: pd.to_timedelta(x.timeline, "D")),
p9.aes(x="timeline", y="KM_estimate", color="label"),
) + p9.scale_x_timedelta(labels=timedelta_format("d")) + p9.geom_line() +
p9.ylim(0, 1))
print(g)
# # Calculate Category Survival Function
# This section measures how long it takes for certain categories to get preprints published.
# In[11]:
entire_preprint_df = pd.DataFrame(
[], columns=["timeline", "KM_estimate", "category"])
half_life = []
for cat, grouped_df in preprints_w_published_dates.groupby("category"):
temp_df = preprints_w_published_dates.query(f"category=='{cat}'")
kmf.fit(
median_ci_l, median_ci_u = median_ci.values.flatten()
median_ci_l, median_ci_u
overall_preprint_survival = kmf.survival_function_.reset_index().assign(
label="all_papers"
)
overall_preprint_survival.head()
g = (
p9.ggplot(
overall_preprint_survival.assign(
timeline=lambda x: pd.to_timedelta(x.timeline, "D")
),
p9.aes(x="timeline", y="KM_estimate", color="label"),
)
+ p9.scale_x_timedelta(labels=timedelta_format("d"))
+ p9.geom_line()
+ p9.ylim(0, 1)
)
print(g)
# # Calculate Category Survival Function
# This section measures how long it takes for certain categories to get preprints published.
entire_preprint_df = pd.DataFrame([], columns=["timeline", "KM_estimate", "category"])
half_life = []
for cat, grouped_df in preprints_w_published_dates.groupby("category"):
temp_df = preprints_w_published_dates.query(f"category=='{cat}'")
kmf.fit(
temp_df["time_to_published"].dt.total_seconds() / 60 / 60 / 24,