def test_custom_format():
x = [3.987, 2, 42.42]
labels = ['3.99 USD', '2.00 USD', '42.42 USD']
formatter = custom_format('{:.2f} USD')
assert formatter(x) == labels
formatter = custom_format('%.2f USD', style='old')
assert formatter(x) == labels
formatter = custom_format('%.2f USD', style='ancient')
with pytest.raises(ValueError):
formatter(x)
def test_custom_format():
x = [3.987, 2, 42.42]
labels = ['3.99 USD', '2.00 USD', '42.42 USD']
formatter = custom_format('{:.2f} USD')
assert formatter(x) == labels
formatter = custom_format('%.2f USD', style='old')
assert formatter(x) == labels
formatter = custom_format('%.2f USD', style='ancient')
with pytest.raises(ValueError):
formatter(x)
def plot_bargraph(count_plot_df, plot_df):
"""
Plots the bargraph
Arguments:
count_plot_df - The dataframe that contains lemma counts
plot_df - the dataframe that contains the odds ratio and lemmas
"""
graph = (
p9.ggplot(count_plot_df.astype({"count": int}),
p9.aes(x="lemma", y="count")) +
p9.geom_col(position=p9.position_dodge(width=0.5), fill="#253494") +
p9.coord_flip() + p9.facet_wrap("repository", scales='free_x') +
p9.scale_x_discrete(limits=(plot_df.sort_values(
"odds_ratio", ascending=True).lemma.tolist())) +
p9.scale_y_continuous(labels=custom_format('{:,.0g}')) +
p9.labs(x=None) + p9.theme_seaborn(
context='paper', style="ticks", font="Arial", font_scale=0.95) +
p9.theme(
# 640 x 480
figure_size=(6.66, 5),
strip_background=p9.element_rect(fill="white"),
strip_text=p9.element_text(size=12),
axis_title=p9.element_text(size=12),
axis_text_x=p9.element_text(size=10),
))
return graph
def scatter_plot(df,
xcol,
ycol,
domain,
xname=None,
yname=None,
log=False,
width=6,
height=6,
clamp=True,
tickCount=5):
assert len(domain) == 2
POINT_SIZE = 0.5
DASH_PATTERN = (0, (3, 1))
if xname == None:
xname = xcol
if yname == None:
yname = ycol
# formater for axes' labels
ax_formatter = mizani.custom_format('{:n}')
if clamp: # clamp overflowing values if required
df = df.copy(deep=True)
df.loc[df[xcol] > domain[1], xcol] = domain[1]
df.loc[df[ycol] > domain[1], ycol] = domain[1]
# generate scatter plot
scatter = p9.ggplot(df)
scatter += p9.aes(x=xcol, y=ycol)
scatter += p9.geom_point(size=POINT_SIZE, na_rm=True)
scatter += p9.labs(x=xname, y=yname)
if log: # log scale
scatter += p9.scale_x_log10(limits=domain, labels=ax_formatter)
scatter += p9.scale_y_log10(limits=domain, labels=ax_formatter)
else:
scatter += p9.scale_x_continuous(limits=domain, labels=ax_formatter)
scatter += p9.scale_y_continuous(limits=domain, labels=ax_formatter)
#scatter += p9.theme_xkcd()
scatter += p9.theme_bw()
scatter += p9.theme(
panel_grid_major=p9.element_line(color='#666666', alpha=0.5))
scatter += p9.theme(figure_size=(width, height))
# generate additional lines
scatter += p9.geom_abline(intercept=0, slope=1,
linetype=DASH_PATTERN) # diagonal
scatter += p9.geom_vline(xintercept=domain[1],
linetype=DASH_PATTERN) # vertical rule
scatter += p9.geom_hline(yintercept=domain[1],
linetype=DASH_PATTERN) # horizontal rule
res = scatter
return res
def scatter_plot2(df1, df2, xcol, ycol, domain, color1='black', color2='red', xname=None, yname=None, log=False, width=6, height=6, clamp=True, tickCount=5):
assert len(domain) == 2
POINT_SIZE = 1.5
DASH_PATTERN = (0, (6, 2))
if xname is None:
xname = xcol
if yname is None:
yname = ycol
# formatter for axes' labels
ax_formatter = mizani.custom_format('{:n}')
if clamp: # clamp overflowing values if required
df1 = df1.copy(deep=True)
df1.loc[df1[xcol] > domain[1], xcol] = domain[1]
df1.loc[df1[ycol] > domain[1], ycol] = domain[1]
df2 = df2.copy(deep=True)
df2.loc[df2[xcol] > domain[1], xcol] = domain[1]
df2.loc[df2[ycol] > domain[1], ycol] = domain[1]
# generate scatter plot
scatter = p9.ggplot(df1)
scatter += p9.aes(x=xcol, y=ycol)
scatter += p9.geom_point(size=POINT_SIZE, na_rm=True, color=color1, alpha=0.5)
scatter += p9.geom_point(size=POINT_SIZE, na_rm=True, data=df2, color=color2, alpha=0.5)
scatter += p9.labs(x=xname, y=yname)
# rug plots
scatter += p9.geom_rug(na_rm=True, sides="tr", color=color1, alpha=0.05)
scatter += p9.geom_rug(na_rm=True, sides="tr", data=df2, color=color2, alpha=0.05)
if log: # log scale
scatter += p9.scale_x_log10(limits=domain, labels=ax_formatter)
scatter += p9.scale_y_log10(limits=domain, labels=ax_formatter)
else:
scatter += p9.scale_x_continuous(limits=domain, labels=ax_formatter)
scatter += p9.scale_y_continuous(limits=domain, labels=ax_formatter)
# scatter += p9.theme_xkcd()
scatter += p9.theme_bw()
scatter += p9.theme(panel_grid_major=p9.element_line(color='#666666', alpha=0.5))
scatter += p9.theme(panel_grid_minor=p9.element_blank())
scatter += p9.theme(figure_size=(width, height))
scatter += p9.theme(text=p9.element_text(size=24, color="black"))
# generate additional lines
scatter += p9.geom_abline(intercept=0, slope=1, linetype=DASH_PATTERN) # diagonal
scatter += p9.geom_vline(xintercept=domain[1], linetype=DASH_PATTERN) # vertical rule
scatter += p9.geom_hline(yintercept=domain[1], linetype=DASH_PATTERN) # horizontal rule
res = scatter
return res
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_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 box_plot(df,
x_col,
fill_col,
agg_col,
agg_func='count',
filter_col=None,
filterby=[""],
no_outliers=False,
title=None,
ylabel=None,
grouped=True,
flip=True,
dots=True):
'''
:param df: dataframe,x_col: variable located on x axis,fill_col: variable for coloring the dots,agg_col: name of the column to which the aggregation function is going to perform
:optional agg_fun: for example: sum,min,mean,median,max,etc. filter_col: after groupying filtering option,filterby: list of characters to be filtered out (located in filter column),outliers,title
:return: ggplot graphs of univariate analysis
:type: boxplot
:usage: after cleaning dataframe
'''
# set display texts
fill_label = get_display_text(fill_col)
if grouped:
aux, aux_str = _get_grouped_aux(df, x_col, fill_col, agg_col, agg_func,
filter_col, filterby)
else:
aux = df
aux_str = agg_col
# sort x labels
aux = aux.sort_values(by=[x_col])
xcol_list = aux.astype(str)[x_col].unique().tolist()
# graph creation
graph = (ggplot(aux) + geom_boxplot(aes(x=x_col, y=aux_str)) + theme_bw() +
theme(axis_line_x=element_line(color='gray'),
axis_line_y=element_line(color='gray'),
line=element_line(color='white')) +
scale_fill_manual(values=colors.OFICIAL_COLORS, name=fill_label) +
scale_x_discrete(limits=xcol_list) +
scale_y_continuous(labels=custom_format('{:,.0f}')))
# dots
if dots:
graph += geom_jitter(aes(x=x_col, y=aux_str, fill=fill_col))
# no outliers
aux_describe = aux[aux_str].describe().loc
if no_outliers:
graph += ylim(aux_describe["min"], aux_describe["75%"])
# title
if title != None:
graph += ggtitle("Box plot:" + str(title))
# flip
if flip:
graph += coord_flip()
# set y label
if not ylabel:
ylabel = get_display_text(agg_col)
graph += ylab(ylabel)
# show
graph.draw()
plt.show()