def test_errorbarh_aesthetics():
p = (ggplot(df, aes(xmin='ymin', xmax='ymax')) +
geom_errorbarh(aes(y='x'), size=2) +
geom_errorbarh(aes(y='x+1', alpha='z'), height=0.2, size=2) +
geom_errorbarh(aes(y='x+2', linetype='factor(z)'), size=2) +
geom_errorbarh(aes(y='x+3', color='factor(z)'), size=2) +
geom_errorbarh(aes(y='x+4', size='z')))
assert p + _theme == 'errorbarh_aesthetics'
def test_errorbarh_aesthetics():
p = (ggplot(df, aes(xmin='ymin', xmax='ymax')) +
geom_errorbarh(aes(y='x'), size=2) +
geom_errorbarh(aes(y='x+1', alpha='z'), height=0.2, size=2) +
geom_errorbarh(aes(y='x+2', linetype='factor(z)'), size=2) +
geom_errorbarh(aes(y='x+3', color='factor(z)'), size=2) +
geom_errorbarh(aes(y='x+4', size='z'))
)
assert p + _theme == 'errorbarh_aesthetics'
def scatterplot(cls, df):
Utils.check_and_make_dir("Figures/Scatterplots")
df = df[(df['index'] != 'Overall') &
(df['index'] != 'No ROI')] # Remove No ROI and Overall rows
df = df.groupby([config.table_cols, config.table_rows]).apply(
lambda x: x.sort_values(['Mean'])) # Group by parameters and sort
df = df.reset_index(drop=True) # Reset index to remove grouping
scatterplots = ['roi_ordered', 'stat_ordered']
if config.table_row_order == 'roi':
scatterplots.remove('stat')
elif config.table_row_order == 'statorder':
scatterplots.remove('roi_ordered')
for scatterplot in scatterplots:
if config.verbose:
print(f"Saving {scatterplot} scatterplot!")
if scatterplot == 'roi_ordered':
roi_ord = pd.Categorical(df['index'],
categories=df['index'].unique()
) # Order rows based on first facet
else:
roi_ord = pd.Categorical(
df.groupby(['MB', 'SENSE'
]).cumcount()) # Order each facet individually
figure_table = (
pltn.ggplot(df, pltn.aes(x="Mean", y=roi_ord)) +
pltn.geom_point(na_rm=True, size=1) + pltn.geom_errorbarh(
pltn.aes(xmin="Mean-Conf_Int_95", xmax="Mean+Conf_Int_95"),
na_rm=True,
height=None) + pltn.xlim(0, None) +
pltn.scale_y_discrete(labels=[]) +
pltn.ylab(config.table_y_label) +
pltn.xlab(config.table_x_label) +
pltn.facet_grid('{rows}~{cols}'.format(rows=config.table_rows,
cols=config.table_cols),
drop=True,
labeller="label_both") +
pltn.theme_538() # Set theme
+ pltn.theme(
panel_grid_major_y=pltn.themes.element_line(alpha=0),
panel_grid_major_x=pltn.themes.element_line(alpha=1),
panel_background=pltn.element_rect(fill="gray", alpha=0.1),
dpi=config.plot_dpi))
figure_table.save(
f"Figures/Scatterplots/{scatterplot}_scatterplot.png",
height=config.plot_scale,
width=config.plot_scale * 3,
verbose=False,
limitsize=False)
def add_mirna_g(g,df, str_name,str_start,str_end,dis_pos,l_s,l_e,l_score=[]):
# print(str_name,str_start,str_end,dis_pos,l_s,l_e)
df[str_start]= pd.Series(l_s)
df[str_end] = pd.Series(l_e)
g+= pt.annotate("text", x=0,y=dis_pos,label=str_name)
g+= pt.geom_errorbarh(df,pt.aes(xmin=str_start,y=(dis_pos),xmax=str_end,color='mi_name'))
g+= pt.geom_segment(df,pt.aes(x=str_start,y=(dis_pos),yend=0,xend=str_start,color='mi_name'))
if(l_score):
# print(l_score)
# pd.options.display.float_format = '{:.1f}'.format
score_column_name = 'score'+str_name
# print(l_score,score_column_name,str_start,dis_pos)
df[score_column_name] = pd.Series(l_score,dtype=np.float).map('{:.0f}'.format)
g+= pt.geom_text(df, pt.aes(x=str_start,y=dis_pos,label=score_column_name,color='mi_name'),
nudge_x=0.1, nudge_y=0.1)#,adjust_text=adjust_text_dict)
def plot_pointgraph(
plot_df,
x_axis_label,
left_arrow_label,
right_arrow_label,
left_arrow_start=-0.5,
left_arrow_height=38.5,
right_arrow_start=0.5,
right_arrow_height=1.5,
arrow_length=2,
left_arrow_label_x=-1.5,
left_arrow_label_y=-1.5,
right_arrow_label_x=-1.5,
right_arrow_label_y=-1.5,
limits=(-3, 3),
):
"""
This function is designed to plot the an errorbar graph to show each token's odd ratio.
The main idea for this graph is to show which corpora a token is enriched
Args:
plot_df - the data frame to plot,
x_axis_label - the label of the x axis,
left_arrow_label - the label for the left arrow,
right_arrow_label - the label for the right arrow,
left_arrow_start - the start of the left arrow to be plotted
left_arrow_height - the height at which the arrow needs to be plotted
right_arrow_start - the start of the right arrow to be plotted
right_arrow_height - - the height at which the arrow needs to be plotted
arrow_length - the length of the arrow
left_arrow_label_x - the x axis position for the label of the left arrow
left_arrow_label_y - the y axis position for the label of the left arrow
right_arrow_label_x - the x axis position for the label of the right arrow
right_arrow_label_y - the y axis position for the label of the right arrow
limits=(-3,3)
"""
graph = (p9.ggplot(
plot_df.assign(lemma=lambda x: pd.Categorical(x.lemma.tolist())),
p9.aes(
y="lemma",
xmin="lower_odds",
x="odds_ratio",
xmax="upper_odds",
yend="lemma",
),
) + p9.geom_errorbarh(color="#253494") + p9.scale_y_discrete(limits=(
plot_df.sort_values("odds_ratio", ascending=True).lemma.tolist())) +
p9.scale_x_continuous(limits=limits) +
p9.geom_vline(p9.aes(xintercept=0), linetype="--", color="grey") +
p9.annotate(
"segment",
x=left_arrow_start,
xend=left_arrow_start - arrow_length,
y=left_arrow_height,
yend=left_arrow_height,
colour="black",
size=0.5,
alpha=1,
arrow=p9.arrow(length=0.1),
) + p9.annotate(
"text",
label=left_arrow_label,
x=left_arrow_label_x,
y=left_arrow_label_y,
size=12,
alpha=0.7,
) + p9.annotate(
"segment",
x=right_arrow_start,
xend=right_arrow_start + arrow_length,
y=right_arrow_height,
yend=right_arrow_height,
colour="black",
size=0.5,
alpha=1,
arrow=p9.arrow(length=0.1),
) + p9.annotate(
"text",
label=right_arrow_label,
x=right_arrow_label_x,
y=right_arrow_label_y,
size=12,
alpha=0.7,
) + p9.theme_seaborn(
context="paper",
style="ticks", font_scale=1, font="Arial") + p9.theme(
figure_size=(11, 8.5),
panel_grid_minor=p9.element_blank(),
text=p9.element_text(size=12),
) + p9.labs(y=None, x=x_axis_label))
return graph
odds_ratio=lambda x: x.odds_ratio.apply(lambda x: np.log2(x)),
lower_odds=lambda x: x.lower_odds.apply(lambda x: np.log2(x)),
upper_odds=lambda x: x.upper_odds.apply(lambda x: np.log2(x)),
))
plot_df.head()
g = (p9.ggplot(
plot_df.assign(lemma=lambda x: pd.Categorical(x.lemma.tolist())),
p9.aes(
y="lemma",
xmin="lower_odds",
x="odds_ratio",
xmax="upper_odds",
yend="lemma",
),
) + p9.geom_errorbarh(color="#253494") + p9.scale_y_discrete(limits=(
plot_df.sort_values("odds_ratio", ascending=True).lemma.tolist())) +
p9.scale_x_continuous(limits=(-3, 3)) +
p9.geom_vline(p9.aes(xintercept=0), linetype="--", color="grey") +
p9.annotate(
"segment",
x=0.5,
xend=2.5,
y=1.5,
yend=1.5,
colour="black",
size=0.5,
alpha=1,
arrow=p9.arrow(length=0.1),
) + p9.annotate(
"text", label="bioRxiv Enriched", x=1.5, y=2.5, size=18, alpha=0.7) +