def cell_cycle_phase_barplot(adata, palette='Set2'):
"""Plots the proportion of cells in each phase of the cell cycle
See also: cell_cycle_phase_pieplot for the matplotlib pie chart
Parameters
-----------
adata: AnnData
The AnnData object being used for the analysis. Must be previously
evaluated by `tl.annotate_cell_cycle`.
Returns
-----------
A plotnine barplot with the total counts of cell in each phase of the
cell cycle.
"""
plt_data = adata.obs.copy()
plt_data['cell_cycle_phase'] = pd.Categorical(
plt_data['cell_cycle_phase'],
categories=['G1 post-mitotic', 'G1 pre-replication', 'S/G2/M'])
cycle_plot = (
ggplot(plt_data, aes('cell_cycle_phase', fill='cell_cycle_phase')) +
geom_bar() + coord_flip() + guides(fill=False) +
labs(y='', x='Cell cycle phase') + theme_light() +
theme(panel_grid_major_y=element_blank(),
panel_grid_minor_y=element_blank(),
panel_grid_major_x=element_line(size=1.5),
panel_grid_minor_x=element_line(size=1.5)) +
scale_fill_brewer(type='qual', palette=palette))
return cycle_plot
def plot_revigo(
rev,
outline=2,
expand_points=(1.05, 1.2),
figure_size=(8, 8),
font_size=8,
point_size=3,
point_alpha=0.7,
palette='RdPu',
dispensability_cutoff=1.,
show_all_labels=False,
text_column='name',
term_size_limit=None,
):
import plotnine as p9
import matplotlib.patheffects as path_effects
pe = [
path_effects.Stroke(linewidth=2, foreground='white'),
path_effects.Normal()
]
if not show_all_labels:
lbl_df = rev[(rev.eliminated == 0)
& (rev.dispensability < dispensability_cutoff)]
if term_size_limit is not None:
lbl_df = lbl_df[lbl_df.term_size < term_size_limit]
else:
lbl_df = rev
g = (p9.ggplot(p9.aes(x='plot_X', y='plot_Y'), data=rev) +
p9.geom_point(p9.aes(fill='neglog10', size='frequency'),
color='black',
alpha=point_alpha) +
p9.geom_text(p9.aes(label=text_column),
data=lbl_df,
size=font_size,
adjust_text={
'expand_points': expand_points,
'arrowprops': {
'arrowstyle': '-'
},
'x': rev.plot_X.values,
'y': rev.plot_Y.values
},
path_effects=pe) + p9.theme_bw() +
p9.scale_fill_distiller(type='seq', palette=palette, direction=1) +
p9.labs(x='Semantic similarity space',
y='',
fill='-log10(adj. p-value)',
size='Term frequency') +
p9.scale_size_continuous(range=(2, 7), trans='log10') +
p9.theme(figure_size=figure_size,
axis_text_x=p9.element_blank(),
axis_text_y=p9.element_blank(),
axis_ticks=p9.element_blank()))
return g
def plot_violin_plots(
par_id: str,
dims: List[str],
draws: Dict,
log_scale_variables: List[str],
units: Dict[str, str],
confidence_intervals,
measurements,
):
"""Plot and save violin plots of parsed distributions.
:param par_id: Name of the parameter plotted
:param dims: Dimensions of the parameter
:param draws: pd.Dataframe of parameter distribution
indexed by dimensions and contains the population samples
:param log_scale_variables: Parameters that are log-distributed
:param units: Dictionary of units for each parameter
"""
par_units = units[par_id]
x = fill = dims[0] if len(dims) <= 1 else "experiments"
plot = (p9.ggplot(data=draws) + p9.geom_violin(
p9.aes(y=f"{par_id}", x=x, fill=fill),
position="identity",
color="None",
size=0.5,
alpha=0.7,
weight=0.7,
linetype="None",
) + p9.labels.ylab(f"{par_id} {par_units}"))
if par_id in confidence_intervals.keys():
plot += p9.geoms.geom_errorbar(
p9.aes(x=x, ymin="lower_ci", ymax="upper_ci"),
data=confidence_intervals[par_id],
width=0.1,
)
if par_id in measurements.keys():
if len(measurements[par_id]) > 0:
plot += p9.geoms.geom_point(
p9.aes(y="measurement", x=x),
data=measurements[par_id],
)
if len(dims) == 1:
plot += p9.themes.theme(axis_text_x=p9.element_text(angle=70), )
if len(dims) > 1:
plot += p9.facet_wrap(f"~{dims[1]}") + p9.themes.theme(
panel_spacing_y=0.05,
panel_spacing_x=0.35,
axis_title=p9.element_text(size=10),
axis_text=p9.element_text(size=11),
axis_text_y=p9.element_text(size=8, angle=45),
axis_title_x=p9.element_blank(),
axis_text_x=p9.element_blank(),
)
if par_id in log_scale_variables:
plot += p9.scale_y_log10()
return plot
def plot_metrics_comparison_lineplot_grid(dataframe,
models_labels,
metrics_labels,
figure_size=(14, 4)):
"""
We define a function to plot the grid.
"""
return (
# Define the plot.
p9.ggplot(
dataframe,
p9.aes(x='threshold',
y='value',
group='variable',
color='variable',
shape='variable'))
# Add the points and lines.
+ p9.geom_point() + p9.geom_line()
# Rename the x axis and give some space to left and right.
+ p9.scale_x_discrete(name='Threshold', expand=(0, 0.2))
# Rename the y axis, give some space on top and bottom, and print the tick labels with 2 decimal digits.
+
p9.scale_y_continuous(name='Value',
expand=(0, 0.05),
labels=lambda l: ['{:.2f}'.format(x) for x in l])
# Replace the names in the legend.
+ p9.scale_shape_discrete(
name='Metric', labels=lambda l: [metrics_labels[x] for x in l])
# Define the colors for the metrics for color-blind people.
+
p9.scale_color_brewer(name='Metric',
labels=lambda l: [metrics_labels[x] for x in l],
type='qual',
palette='Set2')
# Place the plots in a grid, renaming the labels for rows and columns.
+ p9.facet_grid('iterations ~ model',
labeller=p9.labeller(
rows=lambda x: f'iters = {x}',
cols=lambda x: f'{models_labels[x]}'))
# Define the theme for the plot.
+ p9.theme(
# Remove the y axis name.
axis_title_y=p9.element_blank(),
# Set the size of x and y tick labels font.
axis_text_x=p9.element_text(size=7),
axis_text_y=p9.element_text(size=7),
# Place the legend on top, without title, and reduce the margin.
legend_title=p9.element_blank(),
legend_position='top',
legend_box_margin=2,
# Set the size for the figure.
figure_size=figure_size,
))
def theme_energinet() -> p9.themes.theme:
"""Create a simple Energinet theme."""
return p9.theme(
text=p9.element_text(family=endktheme.style.font_family()),
axis_line=p9.element_line(color="black"),
plot_background=p9.element_blank(),
panel_background=p9.element_rect(fill="white"),
legend_background=p9.element_rect(fill="white"),
legend_key=p9.element_blank(),
panel_grid=p9.element_blank(),
axis_ticks=p9.element_blank(),
)
def _plot_theme(grid_axis='both', grid_lines='both', theme='bw'):
"""Internal function provides consistent theme across plots.
Currently a slightly modified version of theme_bw() with configurable grid lines.
Args:
grid_axis: controls the axis on which to draw grid lines
- Accepts: None, 'x', 'y', 'both'
- Default: 'both'
grid_lines: controls whether major or minor grid lines are drawn
- Accepts: None, 'major', 'minor', 'both'
- Default: 'both'
theme:
- Accepts: 'bw', 'classic', 'gray', 'grey', 'seaborn', '538', 'dark', 'matplotlib', 'minimal', 'xkcd', 'light'
- Default: 'bw'
Returns:
A theme object to be added to a plotnine.ggplot() object.
"""
import plotnine as gg
assert (grid_axis in [None, 'x', 'y', 'both'])
assert (grid_lines in [None, 'major', 'minor', 'both'])
assert (theme in [
'bw', 'classic', 'gray', 'grey', 'seaborn', '538', 'dark',
'matplotlib', 'minimal', 'xkcd', 'light'
])
drop_grid = set()
if grid_axis is None or grid_lines is None:
drop_grid.update(['panel_grid_major', 'panel_grid_minor'])
elif grid_axis == 'x':
drop_grid.update(['panel_grid_major_y', 'panel_grid_minor_y'])
if grid_lines == 'major':
drop_grid.add('panel_grid_minor_y')
elif grid_lines == 'minor':
drop_grid.add('panel_grid_major_y')
elif grid_axis == 'y':
drop_grid.update(['panel_grid_major_x', 'panel_grid_minor_x'])
if grid_lines == 'major':
drop_grid.add('panel_grid_minor_x')
elif grid_lines == 'minor':
drop_grid.add('panel_grid_major_x')
grid_opt = dict()
for x in drop_grid:
grid_opt[x] = gg.element_blank()
return getattr(gg, 'theme_'+theme)() + \
gg.theme(panel_border = gg.element_blank(),
axis_line = gg.element_line(color = "black"),
**grid_opt)
def create_confidence_plot(conf_df):
plt = (ggplot(conf_df) + aes(x='x', color='Method', fill='Method') +
geom_density(alpha=.45) + facet_wrap('Task', nrow=4) +
xlab('Confidence') + scale_color_manual(values=COLORS) +
scale_fill_manual(values=COLORS) + theme_fs() + theme(
axis_text_y=element_blank(),
axis_ticks_major_y=element_blank(),
axis_title_y=element_blank(),
legend_title=element_blank(),
legend_position='top',
legend_box='horizontal',
))
return plt
def setup_heatmap0(df: pd.DataFrame, format_string, axis_text):
# https://stackoverflow.com/a/62161556/819272
# Plotnine does not support changing the position of any axis.
return (p9.ggplot(df, p9.aes(y='row', x='col')) + p9.coord_equal() +
p9.geom_tile(p9.aes(fill='scale')) + p9.geom_text(
p9.aes(label='value'), format_string=format_string, size=7) +
p9.scale_y_discrete(drop=False) + p9.scale_x_discrete(drop=False) +
p9.scale_fill_gradientn(colors=['#63BE7B', '#FFEB84', '#F8696B'],
na_value='#CCCCCC',
guide=False) +
p9.theme(axis_text=p9.element_blank()
if not axis_text else p9.element_text(face='bold'),
axis_ticks=p9.element_blank(),
axis_title=p9.element_blank(),
panel_grid=p9.element_blank()))
def plot_preprocessing_boxplot_bymodel(dataframe,
models_labels,
metrics_labels,
groups_labels,
figure_size=(14, 4)):
"""
We define a function to plot the grid.
"""
return (
# Define the plot.
p9.ggplot(dataframe, p9.aes(x='variable', y='value', fill='group'))
# Add the boxplots.
+ p9.geom_boxplot(position='dodge')
# Rename the x axis.
+ p9.scale_x_discrete(name='Metric',
labels=lambda l: [metrics_labels[x] for x in l])
# Rename the y axis.
+ p9.scale_y_continuous(
name='Value',
expand=(0, 0.05),
# breaks=[-0.25, 0, 0.25, 0.5, 0.75, 1], limits=[-0.25, 1],
labels=lambda l: ['{:.2f}'.format(x) for x in l])
# Define the colors for the metrics for color-blind people.
+ p9.scale_fill_brewer(name='Group',
labels=lambda l: [groups_labels[x] for x in l],
type='qual',
palette='Set2')
# Place the plots in a grid, renaming the labels.
+ p9.facet_grid(
'model ~ .',
scales='free_y',
labeller=p9.labeller(rows=lambda x: f'{models_labels[x]}'))
# Define the theme for the plot.
+ p9.theme(
# Remove the x and y axis names.
axis_title_x=p9.element_blank(),
axis_title_y=p9.element_blank(),
# Set the size of x and y tick labels font.
axis_text_x=p9.element_text(size=7),
axis_text_y=p9.element_text(size=7),
# Place the legend on top, without title, and reduce the margin.
legend_title=p9.element_blank(),
legend_position='top',
legend_box_margin=2,
# Set the size for the figure.
figure_size=figure_size,
))
def getErrorPlot(self, msg="Error Occured"):
df = DataFrame({"x": [10], "y": [2], "label": [msg]})
p = ggplot(df , aes(x="x" , y="y" , label="label")) + geom_text(color="white") \
+ THEME.cat_colors_lines \
+ THEME.mt \
+ theme(figure_size=(20,4) ,axis_text=element_blank(), panel_grid_major=element_blank() , panel_grid_minor=element_blank())
return p
def plot_downstream(clwe, table, output, ylim):
df = pd.read_csv(data_file(table))
df = df[df.clwe == clwe]
df = df.assign(
refine=pd.Categorical(df['refine'], ['Original', '+retrofit', '+synthetic']),
language=pd.Categorical(df['language'], ['DE', 'ES', 'FR', 'IT', 'JA', 'RU', 'ZH', 'AVG'])
)
g = p9.ggplot(df, p9.aes(x='language', y='accuracy', fill='refine'))
g += p9.geom_bar(position='dodge', stat='identity', width=.8)
g += p9.coord_cartesian(ylim=ylim)
g += p9.scale_fill_manual(['#999999', '#EA5F94', '#FFB14E'])
g += p9.theme_void(base_size=FONT_SIZE, base_family='Arial')
g += p9.theme(
plot_background=p9.element_rect(fill='white'),
panel_grid_major_y=p9.element_line(),
axis_text_x=p9.element_text(margin={'t': 10}),
axis_text_y=p9.element_text(margin={'r': 8}),
legend_position=(.7, .9),
legend_direction='horizontal',
legend_title=p9.element_blank(),
legend_text=p9.element_text(size=FONT_SIZE),
legend_box_margin=0,
figure_size=(12, 3)
)
g.save(filename=output_file(output))
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
def theme_cognoma(fontsize_mult=1):
return (gg.theme_bw(base_size=14 * fontsize_mult) + gg.theme(
line=gg.element_line(color="#4d4d4d"),
rect=gg.element_rect(fill="white", color=None),
text=gg.element_text(color="black"),
axis_ticks=gg.element_line(color="#4d4d4d"),
legend_key=gg.element_rect(color=None),
panel_border=gg.element_rect(color="#4d4d4d"),
panel_grid=gg.element_line(color="#b3b3b3"),
panel_grid_major_x=gg.element_blank(),
panel_grid_minor=gg.element_blank(),
strip_background=gg.element_rect(fill="#FEF2E2", color="#4d4d4d"),
axis_text=gg.element_text(size=12 * fontsize_mult, color="#4d4d4d"),
axis_title_x=gg.element_text(size=13 * fontsize_mult, color="#4d4d4d"),
axis_title_y=gg.element_text(size=13 * fontsize_mult,
color="#4d4d4d")))
def create_length_plot(len_df, legend_position='right', legend_box='vertical'):
mean_len_df = len_df.groupby(['Task', 'Method']).mean().reset_index()
mean_len_df[' '] = 'Mean Length'
plt = (ggplot(len_df) + aes(x='x', fill='Method', y='..density..') +
geom_histogram(binwidth=2, position='identity', alpha=.6) +
geom_text(aes(x='x', y=.22, label='x', color='Method'),
mean_len_df,
inherit_aes=False,
format_string='{:.1f}',
show_legend=False) +
geom_segment(aes(x='x', xend='x', y=0, yend=.205, linetype=' '),
mean_len_df,
inherit_aes=False,
color='black') + scale_linetype_manual(['dashed']) +
facet_wrap('Task') + xlim(0, 20) + ylim(0, .23) +
xlab('Example Length') + ylab('Frequency') +
scale_color_manual(values=COLORS) +
scale_fill_manual(values=COLORS) + theme_fs() + theme(
aspect_ratio=1,
legend_title=element_blank(),
legend_position=legend_position,
legend_box=legend_box,
))
return plt
def plot_breakdown(cip_df: pd.DataFrame):
"""Stacked bar plot of increasing and decreasing stocks per sector in the specified df"""
cols_to_drop = [colname for colname in cip_df.columns if colname.startswith('bin_')]
df = cip_df.drop(columns=cols_to_drop)
df = pd.DataFrame(df.sum(axis='columns'), columns=['sum'])
df = df.merge(stocks_by_sector(), left_index=True, right_on='asx_code')
if len(df) == 0: # no stock in cip_df have a sector? ie. ETF?
return None
assert set(df.columns) == set(['sum', 'asx_code', 'sector_name'])
df['increasing'] = df.apply(lambda row: 'up' if row['sum'] >= 0.0 else 'down', axis=1)
sector_names = df['sector_name'].value_counts().index.tolist() # sort bars by value count (ascending)
sector_names_cat = pd.Categorical(df['sector_name'], categories=sector_names)
df = df.assign(sector_name_cat=sector_names_cat)
#print(df)
plot = (
p9.ggplot(df, p9.aes(x='factor(sector_name_cat)', fill='factor(increasing)'))
+ p9.geom_bar()
+ p9.labs(x="Sector", y="Number of stocks")
+ p9.theme(axis_text_y=p9.element_text(size=7),
subplots_adjust={"left": 0.2, 'right': 0.85},
legend_title=p9.element_blank()
)
+ p9.coord_flip()
)
return plot_as_inline_html_data(plot)
class THEME():
bgcolor = "#293241"
LOADER_COLOR = "#2a9d8f"
LOADER_TYPE = "dot"
colors_light = [
"#d88c9a", "#f2d0a9", "#f1e3d3", "#99c1b9", "#8e7dbe", "#50514f",
"#f25f5c", "#ffe066", "#247ba0", "#70c1b3", "#c97c5d", "#b36a5e"
]
colors_dark = [
"#e07a5f", "#3d405b", "#81b29a", "#2b2d42", "#f77f00", "#6d597a"
]
# mt = theme(panel_background=element_rect(fill=bgcolor)
# ,plot_background=element_rect(fill=bgcolor)
# , axis_text_x = element_text(color="black")
# , axis_text_y = element_text(color="black")
# , strip_margin_y=0.05
# , strip_margin_x=0.5)
mt = theme_bw() + theme(panel_border=element_blank())
cat_colors = scale_fill_manual(values=colors_light)
cat_colors_lines = scale_color_manual(values=colors_light)
gradient_colors = scale_fill_gradient("#ce4257", "#aad576")
FILL = 1
COLOR = 2
LONG_FIGURE = (10, 20)
def gen_fig():
X_title = 'Edit Iteration'
Y_title = 'Position in Question'
C_title = 'Type'
stuff = pickle.load(open(data_dir, 'rb'))
all_questions, all_buzzes = stuff[0], stuff[1]
for k, (questions, buzzes) in enumerate(zip(all_questions, all_buzzes)):
if len(buzzes) < 5:
continue
if all(x == 'NULL' for x in buzzes):
continue
print(k)
length_buzzing_positions = {X_title: [], Y_title: [], C_title: []}
for i, (q, b) in enumerate(zip(questions, buzzes)):
length = len(q.split())
length_buzzing_positions[X_title].append(i)
length_buzzing_positions[Y_title].append(length)
length_buzzing_positions[C_title].append('Question Length')
if b == 'NULL':
b = length
length_buzzing_positions[X_title].append(i)
length_buzzing_positions[Y_title].append(b)
length_buzzing_positions[C_title].append('Buzzing Position')
df = pd.DataFrame(length_buzzing_positions)
p = (ggplot(df) +
geom_path(aes(x=X_title, y=Y_title, color=C_title), size=2) +
theme(
legend_title=element_blank(),
legend_position='top',
))
p.save(os.path.join(fig_dir, '{}.pdf'.format(k)))
def __init__(self, *args, **kwargs):
"""See main class docstring."""
p9.theme_matplotlib.__init__(self, *args, **kwargs)
gray = '#D9D9D9' # gray used in themes.theme_matplotlib
self.add_theme(
p9.theme(
panel_border=p9.element_rect(color=gray, size=0.7),
axis_line=p9.element_blank(),
axis_ticks_length=0,
axis_ticks=p9.element_blank(),
panel_grid_major=p9.element_line(color=gray, size=0.7),
panel_grid_minor=p9.element_blank(),
panel_ontop=True, # plot panel on top of grid
),
inplace=True)
def __init__(self, args, display_title='Analysis'):
super().__init__(args, display_title)
fusion_pos_file = Mkref_fusion.parse_genomeDir(
args.fusion_genomeDir)['fusion_pos']
self.pos_dict = Count_fusion.read_pos_file(fusion_pos_file)
self.p9_theme = {
'axis_line_x': p9.element_line(size=2, colour="black"),
'axis_line_y': p9.element_line(size=2, colour="black"),
'panel_grid_major': p9.element_blank(),
'panel_grid_minor': p9.element_blank(),
'panel_border': p9.element_blank(),
'panel_background': p9.element_blank(),
'axis_text_x': p9.element_text(colour="black"),
'axis_text_y': p9.element_text(colour="black"),
}
def plot_distributions_bar_plot_grid(dataframe, figure_size=(14, 4)):
"""
We create a function to plot the bar plot.
"""
return (
# Define the plot.
p9.ggplot(dataframe, p9.aes(x='threshold', fill='value'))
# Add the bars.
+ p9.geom_bar(position='dodge') +
p9.geom_text(p9.aes(label='stat(count)'),
stat='count',
position=p9.position_dodge(0.9),
size=7,
va='bottom')
# Rename the x axis.
+ p9.scale_x_discrete(name='Threshold')
# Rename the y axis, give some space on top and bottom (mul_bottom, add_bottom, mul_top, add_top).
+ p9.scale_y_continuous(name='Count', expand=(0, 0, 0, 500))
# Replace the names in the legend and set the colors of the bars.
+ p9.scale_fill_manual(values={
0: '#009e73',
1: '#d55e00'
},
labels=lambda l: [{
0: 'Stable',
1: 'Unstable'
}[x] for x in l])
# Place the plots in a grid, renaming the labels.
+ p9.facet_grid('. ~ iterations',
labeller=p9.labeller(cols=lambda x: f'iters = {x}'))
# Define the theme for the plot.
+ p9.theme(
# Remove the y axis name.
axis_title_y=p9.element_blank(),
# Set the size of x and y tick labels font.
axis_text_x=p9.element_text(size=7),
axis_text_y=p9.element_text(size=7),
# Place the legend on top, without title, and reduce the margin.
legend_title=p9.element_blank(),
legend_position='top',
legend_box_margin=2,
# Set the size for the figure.
figure_size=figure_size,
))
def plot_restaurants_per_neighborhood(filepath, restaurant_data_file,
pittsburgh_shapefile):
mexican_restaurants = pd.read_csv(filepath + restaurant_data_file)
gdf = gpd.GeoDataFrame(
mexican_restaurants,
geometry=gpd.points_from_xy(mexican_restaurants.longitude,
mexican_restaurants.latitude),
)
restaurant_locations = gdf.filter(items=["geometry"])
# import Pittsburgh neighborhood shapefile
neighborhood_polygons = gpd.read_file(pittsburgh_shapefile).filter(
items=["hood", "hood_no", "geometry"])
# spatial join to figure out which neighborhood each restaurant is in
restaurants_in_polys = gpd.sjoin(restaurant_locations,
neighborhood_polygons,
how="inner",
op="intersects")
restaurants_counted = restaurants_in_polys.groupby(
"hood_no").count().reset_index()
restaurants_in_hoods = restaurants_counted.filter(
items=["hood_no", "hood"])
restaurants_in_hoods.rename(columns={"hood": "num_restaurants"},
inplace=True)
restaurants_per_shape = gpd.GeoDataFrame(
pd.merge(neighborhood_polygons, restaurants_in_hoods, how="left"))
restaurant_map = (p.ggplot(restaurants_per_shape) +
p.geom_map(p.aes(fill="num_restaurants")) +
p.scale_colour_gradient(low="white", high="black") +
p.theme(
panel_background=p.element_rect(fill="white"),
axis_text_x=p.element_blank(),
axis_text_y=p.element_blank(),
axis_ticks_major_x=p.element_blank(),
axis_ticks_major_y=p.element_blank(),
)) + p.scale_fill_gradient(
low="#efefef", high="#073763", name="# Restaurants")
restaurant_map.save("restaurant_map.png")
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 theme_cognoma(fontsize_mult=1):
import plotnine as gg
return (gg.theme_bw(base_size = 14 * fontsize_mult) +
gg.theme(
line = gg.element_line(color = "#4d4d4d"),
rect = gg.element_rect(fill = "white", color = None),
text = gg.element_text(color = "black"),
axis_ticks = gg.element_line(color = "#4d4d4d"),
legend_key = gg.element_rect(color = None),
panel_border = gg.element_rect(color = "#4d4d4d"),
panel_grid = gg.element_line(color = "#b3b3b3"),
panel_grid_major_x = gg.element_blank(),
panel_grid_minor = gg.element_blank(),
strip_background = gg.element_rect(fill = "#FEF2E2", color = "#4d4d4d"),
axis_text = gg.element_text(size = 12 * fontsize_mult, color="#4d4d4d"),
axis_title_x = gg.element_text(size = 13 * fontsize_mult, color="#4d4d4d"),
axis_title_y = gg.element_text(size = 13 * fontsize_mult, color="#4d4d4d")
))
def create_confidence_plot(conf_df):
plt = (
ggplot(conf_df)
+ aes(x='x', color='Method', fill='Method')
+ geom_density(alpha=.45)
+ facet_wrap('Task', nrow=4)
+ xlab('Confidence')
+ scale_color_manual(values=COLORS)
+ scale_fill_manual(values=COLORS)
+ theme_fs()
+ theme(
axis_text_y=element_blank(),
axis_ticks_major_y=element_blank(),
axis_title_y=element_blank(),
legend_title=element_blank(),
legend_position='top',
legend_box='horizontal',
)
)
return plt
def __init__(self, base_size=11, base_family='DejaVu Sans'):
theme_light.__init__(self, base_size, base_family)
self.add_theme(theme(
axis_ticks=element_line(color='#DDDDDD', size=0.5),
panel_border=element_rect(fill='None', color='#838383',
size=1),
strip_background=element_rect(
fill='#DDDDDD', color='#838383', size=1),
strip_text_x=element_text(color='black'),
strip_text_y=element_text(color='black', angle=-90),
legend_key=element_blank()
), inplace=True)
def getErrorPlot(self, msg="Error Occured"):
"""
Creates a plotnine plot with error message. To be used to display error essages across dashboards.
parameters:
- msg: the message to be displayed when error occurs
"""
df = DataFrame({"x": [10], "y": [2], "label": [msg]})
p = ggplot(df , aes(x="x" , y="y" , label="label")) + geom_text(color="Black") \
+ THEME.cat_colors_lines \
+ THEME.mt \
+ theme(figure_size=(20,4) ,axis_text=element_blank(), panel_grid_major=element_blank() , panel_grid_minor=element_blank())
return p
def __init__(self, base_size=11, base_family="DejaVu Sans"):
theme_light.__init__(self, base_size, base_family)
self.add_theme(
theme(
axis_ticks=element_line(color="#DDDDDD", size=0.5),
panel_border=element_rect(fill="None", color="#838383", size=1),
strip_background=element_rect(fill="#DDDDDD", color="#838383", size=1),
strip_text_x=element_text(color="black"),
strip_text_y=element_text(color="black", angle=-90),
legend_key=element_blank(),
),
inplace=True,
)
def ikuya_sys_plot():
nips_df = load_ikuya_nips()
with open('2019_tacl_trick/data/ikuya_cdf.json') as f:
df = pd.DataFrame(json.load(f))
df = pd.concat([df, nips_df])
df['model'] = df['model'].map(relabel)
model_dtype = CategoricalDtype(
['Regular Test', 'IR Adversarial', 'RNN Adversarial'],
ordered=True)
df['model'] = df['model'].astype(model_dtype)
p = (
ggplot(df) + aes(x='x', y='y', color='model', xmin='x', xmax='x') +
geom_point(size=1.0, shape='.') +
xlab('Percent of Question Revealed') + ylab('Accuracy') +
scale_y_continuous(breaks=np.linspace(0, 1, 6), limits=[0, 1]) +
theme(
legend_position=(.335, .7),
legend_background=element_blank(
), #element_rect(alpha=1, fill='#EEEFEE', color='white'),
#legend_key=element_rect(alpha=0),
legend_box_margin=0,
legend_title=element_blank()))
p.save('2019_tacl_trick/auto_fig/ikuya_cdf.pdf', width=3.5, height=2.5)
def plot_breakdown(ld: LazyDictionary) -> p9.ggplot:
"""Stacked bar plot of increasing and decreasing stocks per sector in the specified df"""
cip_df = ld["cip_df"]
cols_to_drop = [
colname for colname in cip_df.columns if colname.startswith("bin_")
]
df = cip_df.drop(columns=cols_to_drop)
df = pd.DataFrame(df.sum(axis="columns"), columns=["sum"])
ss = ld["stocks_by_sector"]
# ss should be:
# asx_code sector_name
# asx_code
# 14D 14D Industrials
# 1AD 1AD Health Care
# 1AG 1AG Industrials
# 1AL 1AL Consumer Discretionary........
# print(ss)
df = df.merge(ss, left_index=True, right_index=True)
if len(df) == 0: # no stock in cip_df have a sector? ie. ETF?
return None
assert set(df.columns) == set(["sum", "asx_code", "sector_name"])
df["increasing"] = df.apply(lambda row: "up"
if row["sum"] >= 0.0 else "down",
axis=1)
sector_names = (df["sector_name"].value_counts().index.tolist()
) # sort bars by value count (ascending)
sector_names_cat = pd.Categorical(df["sector_name"],
categories=sector_names)
df = df.assign(sector_name_cat=sector_names_cat)
# print(df)
plot = (p9.ggplot(
df, p9.aes(x="factor(sector_name_cat)", fill="factor(increasing)")) +
p9.geom_bar() + p9.coord_flip())
return user_theme(
plot,
x_axis_label="Sector",
y_axis_label="Number of stocks",
subplots_adjust={
"left": 0.2,
"right": 0.85
},
legend_title=p9.element_blank(),
asxtrade_want_fill_d=True,
)
def create_length_plot(len_df, legend_position='right', legend_box='vertical'):
mean_len_df = len_df.groupby(['Task', 'Method']).mean().reset_index()
mean_len_df[' '] = 'Mean Length'
plt = (
ggplot(len_df)
+ aes(x='x', fill='Method', y='..density..')
+ geom_histogram(binwidth=2, position='identity', alpha=.6)
+ geom_text(
aes(x='x', y=.22, label='x', color='Method'),
mean_len_df,
inherit_aes=False,
format_string='{:.1f}',
show_legend=False
)
+ geom_segment(
aes(x='x', xend='x', y=0, yend=.205, linetype=' '),
mean_len_df,
inherit_aes=False, color='black'
)
+ scale_linetype_manual(['dashed'])
+ facet_wrap('Task')
+ xlim(0, 20) + ylim(0, .23)
+ xlab('Example Length') + ylab('Frequency')
+ scale_color_manual(values=COLORS)
+ scale_fill_manual(values=COLORS)
+ theme_fs()
+ theme(
aspect_ratio=1,
legend_title=element_blank(),
legend_position=legend_position,
legend_box=legend_box,
)
)
return plt
def theme_tufte(base_size=11, base_family='serif', lines=True, ticks=True):
"""
Theme inspired by Chapter 6 'Data-Ink Maximization and Graphical Design` of
Edward Tufte's 'The Visual Display of Quantitative Information`.
Parameters
----------
base_size : int, optional
Base font size. All text sizes are scaled versions of the base font
size. Default is 11.
base_family : str, optional
Base font family.
lines : bool, optional
Draw axis spines. Default is True.
ticks : bool, optional
Draw axis ticks. Default is True.
Returns
-------
Plotnine theme.
"""
ret = (p9.theme_bw(base_size=base_size, base_family=base_family) +
p9.theme(legend_background=p9.element_blank(),
legend_key=p9.element_blank(),
panel_background=p9.element_blank(),
strip_background=p9.element_blank(),
plot_background=p9.element_rect(fill='white'),
axis_line=p9.element_line(size=0.5),
axis_ticks=p9.element_line(size=0.5),
panel_grid=p9.element_blank()))
if not ticks:
ret = ret + p9.theme(axis_ticks=p9.element_blank())
if not lines:
ret = ret + p9.theme(axis_line=p9.element_blank())
return ret
def rel_plot(sbs, variant, jitter=0.01):
plotdata = sbs[sbs.variant == variant]
xcol = "base"
ycol = "ratio"
plotdata = plotdata.assign(x=plotdata[xcol], y=plotdata[ycol])
plotdata = plotdata.assign(sbs_index=plotdata.index.values)
session_text = (plotdata[["session_index", "base_session_index"]].apply(
tuple, axis=1).map(lambda tup: f"{tup[0]} vs. {tup[1]}"))
plotdata = plotdata.assign(session_text=session_text)
x = np.geomspace(0.02, 1, num=5)
y = 1 / x
diag_df = pd.DataFrame({"x": x, "y": y})
scatterplot = (
ggplot(plotdata) + geom_jitter(
aes(x="x", y="y", fill="dataset", color="dataset"),
width=jitter,
height=jitter,
alpha=0.6,
size=1.0,
)
# shape=plotdata.dataset.map(lambda x : '.' if x in ['lvis','objectnet'] else 'o'),
# size=plotdata.dataset.map(lambda x : 1. if x in ['lvis','objectnet'] else 2.))
# + geom_text(aes(x='base', y='delta', label='category', color='dataset'), va='bottom',
# data=plotdata1[plotdata1.ratio < .6],
# position=position_jitter(.05, .05), show_legend=False)
+ geom_line(aes(x="x", y="y"), data=diag_df)
# + geom_text(aes(x='x', y='y', label='session_text'), va='top', data=plotdata[(plotdata.y < .4) | (plotdata.y > 3)])
+ ylab(ycol)
# + geom_area(aes(y2=1.1, y=.9), linetype='dashed', alpha=.7)
+ geom_hline(aes(yintercept=1.1), linetype="dashed", alpha=0.7) +
geom_hline(aes(yintercept=0.9), linetype="dashed", alpha=0.7) +
geom_vline(
aes(xintercept=0.1, ),
linetype="dashed",
alpha=0.7,
) + geom_vline(
aes(xintercept=0.3, ),
linetype="dashed",
alpha=0.7,
)
# + geom_abline()
# + geom_point(aes(x='recall', y='precision', color='variant'), size=1.)
# + facet_wrap(facets=['cat'], ncol=6, scales='free_x')
+ xlab(xcol)
# +scale_color_discrete()
+ theme(
figure_size=(8, 5),
legend_position="top",
subplots_adjust={"hspace": 0.5},
legend_title=element_blank(),
legend_box_margin=-1,
legend_margin=0.0,
axis_text=element_text(size=12, margin={
"t": 0.2,
"l": -0.3
}),
legend_text=element_text(size=11),
axis_title=element_text(size=12,
margin={
"r": -0.2,
"b": 0.0,
"l": 0,
"t": 0.0
}),
) + scale_x_log10(labels=make_labeler(brief_format),
breaks=[0.01, 0.1, 0.3, 1.0]) +
scale_y_log10(labels=make_labeler(brief_format),
breaks=[0.5, 0.9, 1.1, 2.0, 3.0, 6, 12]))
return scatterplot
def ologram_merge_stats(inputfiles=None,
pdf_width=None,
pdf_height=None,
output=None,
labels=None):
# -------------------------------------------------------------------------
# Check user provided labels
# -------------------------------------------------------------------------
if labels is not None:
labels = labels.split(",")
for elmt in labels:
if not re.search("^[A-Za-z0-9_]+$", elmt):
message(
"Only alphanumeric characters and '_' allowed for --more-bed-labels",
type="ERROR")
if len(labels) != len(inputfiles):
message("--labels: the number of labels should be"
" the same as the number of input files ", type="ERROR")
if len(labels) != len(set(labels)):
message("Redundant labels not allowed.", type="ERROR")
# -------------------------------------------------------------------------
# Loop over input files
# -------------------------------------------------------------------------
df_list = list()
df_label = list()
for pos, infile in enumerate(inputfiles):
message("Reading file : " + infile.name)
# Read the dataset into a temporay dataframe
df_tmp = pd.read_csv(infile, sep='\t', header=0, index_col=None)
# Change name of 'feature_type' column.
df_tmp = df_tmp.rename(index=str, columns={"feature_type": "Feature"})
# Assign the name of the dataset to a new column
if labels is None:
file_short_name = os.path.basename(os.path.normpath(os.path.dirname(infile.name)))
df_label += [file_short_name]
else:
file_short_name = labels[pos]
df_label += [labels[pos]]
df_tmp = df_tmp.assign(**{"dataset": [file_short_name] * df_tmp.shape[0]})
# Pval set to 0 or -1 are changed to 1e-320 and NaN respectively
df_tmp.loc[df_tmp['summed_bp_overlaps_pvalue'] == 0, 'summed_bp_overlaps_pvalue'] = 1e-320
df_tmp.loc[df_tmp['summed_bp_overlaps_pvalue'] == -1, 'summed_bp_overlaps_pvalue'] = np.nan
# Compute -log10(pval)
df_tmp = df_tmp.assign(**{"-log_10(pval)": -np.log10(df_tmp.summed_bp_overlaps_pvalue)})
# Which p-values are signifcant ?
# TODO: For now, draws all p-values. Add Benjamini-Hochberg correction, and distinguish between NaN and 0.
df_tmp = df_tmp.assign(**{"pval_signif": df_tmp.summed_bp_overlaps_pvalue > 0})
# Add the df to the list to be subsequently merged
df_list += [df_tmp]
if len(set(df_label)) < len(df_label):
message('Enclosing directories are ambiguous and cannot be used as labels. You may use "--labels".',
type="ERROR")
# -------------------------------------------------------------------------
# Concatenate dataframes (row bind)
# -------------------------------------------------------------------------
message("Merging dataframes.")
df_merged = pd.concat(df_list, axis=0)
# -------------------------------------------------------------------------
# Plotting
# -------------------------------------------------------------------------
message("Plotting")
my_plot = ggplot(data=df_merged,
mapping=aes(y='Feature', x='dataset'))
my_plot += geom_tile(aes(fill = 'summed_bp_overlaps_log2_fold_change'))
my_plot += scale_fill_gradient2()
my_plot += labs(fill = "log2(fold change) for summed bp overlaps")
# Points for p-val. Must be after geom_tile()
my_plot += geom_point(data = df_merged.loc[df_merged['pval_signif']],
mapping = aes(x='dataset',y='Feature',color = '-log_10(pval)'), size=4, shape ='D', inherit_aes = False)
my_plot += scale_color_gradientn(colors = ["#160E00","#FFB025","#FFE7BD"])
my_plot += labs(color = "-log10(p-value)")
# Theming
my_plot += theme_bw()
my_plot += theme(panel_grid_major=element_blank(),
axis_text_x=element_text(rotation=90),
panel_border=element_blank(),
axis_ticks=element_blank())
# -------------------------------------------------------------------------
# Saving
# -------------------------------------------------------------------------
message("Saving")
nb_ft = len(list(df_merged['Feature'].unique()))
nb_datasets = len(list(df_merged['dataset'].unique()))
if pdf_width is None:
panel_width = 0.6
pdf_width = panel_width * nb_datasets
if pdf_width > 100:
pdf_width = 100
message("Setting --pdf-width to 100 (limit)")
if pdf_height is None:
panel_height = 0.6
pdf_height = panel_height * nb_ft
if pdf_height > 500:
pdf_height = 500
message("Setting --pdf-height to 500 (limit)")
message("Page width set to " + str(pdf_width))
message("Page height set to " + str(pdf_height))
figsize = (pdf_width, pdf_height)
# -------------------------------------------------------------------------
# Turn warning off. Both pandas and plotnine use warnings for deprecated
# functions. I need to turn they off although I'm not really satisfied with
# this solution...
# -------------------------------------------------------------------------
def fxn():
warnings.warn("deprecated", DeprecationWarning)
# -------------------------------------------------------------------------
# Saving
# -------------------------------------------------------------------------
with warnings.catch_warnings():
warnings.simplefilter("ignore")
fxn()
message("Saving diagram to file : " + output.name)
message("Be patient. This may be long for large datasets.")
# NOTE : We must manually specify figure size with save_as_pdf_pages
save_as_pdf_pages(filename=output.name,
plots=[my_plot + theme(figure_size=figsize)],
width=pdf_width,
height=pdf_height)
theme2 = theme_gray()
theme3 = theme1 + theme2
assert theme3 == theme2
def test_add_empty_theme_element():
# An empty theme element does not alter the theme
theme1 = theme_gray() + theme(axis_line_x=element_line(color='red'))
theme2 = theme1 + theme(axis_line_x=element_line())
assert theme1 == theme2
l1 = element_line(color='red', size=1, linewidth=1, linetype='solid')
l2 = element_line(color='blue', size=2, linewidth=2)
l3 = element_line(color='blue', size=2, linewidth=2, linetype='solid')
blank = element_blank()
def test_add_element_heirarchy():
# parent themeable modifies child themeable
theme1 = theme_gray() + theme(axis_line_x=l1) # child
theme2 = theme1 + theme(axis_line=l2) # parent
theme3 = theme1 + theme(axis_line_x=l3) # child, for comparison
assert theme2.themeables['axis_line_x'] == \
theme3.themeables['axis_line_x']
theme1 = theme_gray() + theme(axis_line_x=l1) # child
theme2 = theme1 + theme(line=l2) # grand-parent
theme3 = theme1 + theme(axis_line_x=l3) # child, for comparison
assert theme2.themeables['axis_line_x'] == \
theme3.themeables['axis_line_x']
