def hist_pseudotime(adata, fill='#595959', alpha=1, bins=30):
"""Plots a histogram of pseudotime
Parameters
--------------
adata: AnnData
The AnnData object being used for the analysis. Must be previously
evaluated by `tl.pseudotime`.
fill: str
Controls the color of the histogram bars. Must be a supported color
name or hex-code.
alpha: float
A float between 0 and 1. Controls the transparency of the bars.
Returns
-----------
A plotnine histogram of pseudotime.
"""
if fill in adata.obs.columns:
hist_plt = (ggplot(adata.obs, aes('pseudotime', fill=fill)) +
geom_histogram(alpha=alpha, bins=bins))
else:
hist_plt = (ggplot(adata.obs, aes('pseudotime')) +
geom_histogram(fill=fill, alpha=alpha, bins=bins))
hist_plt = (hist_plt + labs(x='Pseudotime', y='Count') + theme_std)
return hist_plt
def plot():
outdir = 'output/protobowl/'
pathlib.Path(outdir).mkdir(parents=True, exist_ok=True)
df, questions = load_protobowl()
df.result = df.result.apply(lambda x: x is True)
df['log_n_records'] = df.user_n_records.apply(np.log)
df_user_grouped = df.groupby('uid')
user_stat = df_user_grouped.agg(np.mean)
print('{} users'.format(len(user_stat)))
print('{} records'.format(len(df)))
print('{} questions'.format(len(set(df.qid))))
max_color = user_stat.log_n_records.max()
user_stat['alpha'] = pd.Series(
user_stat.log_n_records.apply(lambda x: x / max_color),
index=user_stat.index)
# 2D user plot
p0 = ggplot(user_stat) \
+ geom_point(aes(x='relative_position', y='result',
size='user_n_records', color='log_n_records', alpha='alpha'),
show_legend={'color': False, 'alpha': False, 'size': False}) \
+ scale_color_gradient(high='#e31a1c', low='#ffffcc') \
+ labs(x='Average buzzing position', y='Accuracy') \
+ theme(aspect_ratio=1)
p0.save(os.path.join(outdir, 'protobowl_users.pdf'))
# p0.draw()
print('p0 done')
# histogram of number of records
p1 = ggplot(user_stat, aes(x='log_n_records', y='..density..')) \
+ geom_histogram(color='#e6550d', fill='#fee6ce') \
+ geom_density() \
+ labs(x='Log number of records', y='Density') \
+ theme(aspect_ratio=0.3)
p1.save(os.path.join(outdir, 'protobowl_hist.pdf'))
# p1.draw()
print('p1 done')
# histogram of accuracy
p2 = ggplot(user_stat, aes(x='result', y='..density..')) \
+ geom_histogram(color='#31a354', fill='#e5f5e0') \
+ geom_density() \
+ labs(x='Accuracy', y='Density') \
+ theme(aspect_ratio=0.3)
p2.save(os.path.join(outdir, 'protobowl_acc.pdf'))
# p2.draw()
print('p2 done')
# histogram of buzzing position
p3 = ggplot(user_stat, aes(x='relative_position', y='..density..')) \
+ geom_histogram(color='#3182bd', fill='#deebf7') \
+ geom_density() \
+ labs(x='Average buzzing position', y='Density') \
+ theme(aspect_ratio=0.3)
p3.save(os.path.join(outdir, 'protobowl_pos.pdf'))
# p3.draw()
print('p3 done')
def plot():
outdir = 'output/protobowl/'
pathlib.Path(outdir).mkdir(parents=True, exist_ok=True)
df = load_protobowl()
df.result = df.result.apply(lambda x: x is True)
df['log_n_records'] = df.user_n_records.apply(np.log)
df_user_grouped = df.groupby('uid')
user_stat = df_user_grouped.agg(np.mean)
print('{} users'.format(len(user_stat)))
print('{} records'.format(len(df)))
max_color = user_stat.log_n_records.max()
user_stat['alpha'] = pd.Series(
user_stat.log_n_records.apply(lambda x: x / max_color), index=user_stat.index)
# 2D user plot
p0 = ggplot(user_stat) \
+ geom_point(aes(x='relative_position', y='result',
size='user_n_records', color='log_n_records', alpha='alpha'),
show_legend={'color': False, 'alpha': False, 'size': False}) \
+ scale_color_gradient(high='#e31a1c', low='#ffffcc') \
+ labs(x='Average buzzing position', y='Accuracy') \
+ theme(aspect_ratio=1)
p0.save(os.path.join(outdir, 'protobowl_users.pdf'))
# p0.draw()
print('p0 done')
# histogram of number of records
p1 = ggplot(user_stat, aes(x='log_n_records', y='..density..')) \
+ geom_histogram(color='#e6550d', fill='#fee6ce') \
+ geom_density() \
+ labs(x='Log number of records', y='Density') \
+ theme(aspect_ratio=0.3)
p1.save(os.path.join(outdir, 'protobowl_hist.pdf'))
# p1.draw()
print('p1 done')
# histogram of accuracy
p2 = ggplot(user_stat, aes(x='result', y='..density..')) \
+ geom_histogram(color='#31a354', fill='#e5f5e0') \
+ geom_density() \
+ labs(x='Accuracy', y='Density') \
+ theme(aspect_ratio=0.3)
p2.save(os.path.join(outdir, 'protobowl_acc.pdf'))
# p2.draw()
print('p2 done')
# histogram of buzzing position
p3 = ggplot(user_stat, aes(x='relative_position', y='..density..')) \
+ geom_histogram(color='#3182bd', fill='#deebf7') \
+ geom_density() \
+ labs(x='Average buzzing position', y='Density') \
+ theme(aspect_ratio=0.3)
p3.save(os.path.join(outdir, 'protobowl_pos.pdf'))
# p3.draw()
print('p3 done')
def plot_char_percent_vs_accuracy_histogram(self, category=False):
if category:
return (ggplot(self.char_plot_df) + facet_wrap('category_jmlr') +
aes(x='char_percent', fill='Outcome') +
geom_histogram(binwidth=.05))
else:
return (ggplot(self.char_plot_df) +
aes(x='char_percent', fill='Outcome') +
geom_histogram(binwidth=.05))
def plot_char_percent_vs_accuracy_histogram(self, category=False):
if category:
return (
ggplot(self.char_plot_df) + facet_wrap('category_jmlr')
+ aes(x='char_percent', fill='Outcome')
+ geom_histogram(binwidth=.05)
)
else:
return (
ggplot(self.char_plot_df)
+ aes(x='char_percent', fill='Outcome')
+ geom_histogram(binwidth=.05)
)
def plot_char_percent_vs_accuracy_histogram(self, category=False):
if category:
return (
ggplot(self.char_plot_df)
+ facet_wrap("category_jmlr")
+ aes(x="char_percent", fill="Outcome")
+ geom_histogram(binwidth=0.05)
)
else:
return (
ggplot(self.char_plot_df)
+ aes(x="char_percent", fill="Outcome")
+ geom_histogram(binwidth=0.05)
)
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 test_midpoint():
p = (ggplot(df, aes('x')) +
geom_histogram(aes(fill='factor(z)'), bins=n, alpha=0.25) +
geom_freqpoly(bins=n, size=4) +
geom_point(stat='bin', bins=n, size=4, stroke=0, color='red'))
assert p + _theme == 'midpoint'
def test_scale_transformed_breaks():
df = pd.DataFrame({'x': np.repeat(range(1, 5), range(1, 5))})
p = ggplot(df, aes('x')) + geom_histogram(breaks=[1, 2.5, 4])
out1 = layer_data(p)
out2 = layer_data(p + scale_x_sqrt())
np.testing.assert_allclose(out1.xmin, [1, 2.5])
np.testing.assert_allclose(out2.xmin, np.sqrt([1, 2.5]))
def plot_n_train_vs_accuracy(self):
return (
ggplot(self.combined_df)
+ facet_wrap("seen")
+ aes(x="n_train", fill="Outcome")
+ geom_histogram(binwidth=1)
)
def plot_frequency(n = 200):
"""
Draws the histogram of the distribution of n tweets by date.
Parameters
----------
n: int
An integer specifying how many tweets should be analysed.
Returns
-------
It saves the histogram as a .png file in the static folder.
"""
from plotnine import ggplot, aes, geom_histogram, scale_x_datetime, labs, theme_minimal, ggsave
from Mod_1_API import gather_tweets
from mizani.breaks import date_breaks
from mizani.formatters import date_format
import pandas
df = pandas.DataFrame(gather_tweets(n))
plot1 = (ggplot(df, aes(x = 'Date', fill = 'Author')) +
geom_histogram() +
scale_x_datetime(breaks=date_breaks('1 week')) +
labs(x = "Time in weeks", y = "Number of tweets by source") +
theme_minimal()
)
ggsave(plot = plot1, filename = "test.png", path = "static/")
def plot_ccs_stats(self, variable, *,
trim_frac=0.005, bins=25, histogram_stat='count',
maxcol=None, panelsize=1.75):
"""Plot histograms of CCS stats for all runs.
Parameters
----------
variable : {'length', 'passes', 'accuracy'}
Variable for which we plot stats. You will get an error
if :meth:`Summaries.has_stat` is not true for `variable`.
trim_frac : float
Trim this amount of the bottom and top fraction from the
data before plotting. Useful if outliers greatly extend scale.
bins : int
Number of histogram binds
histogram_stat : {'count', 'density'}
Plot the count of CCSs or their density normalized for each run.
maxcol : None or int
Max number of columns in faceted plot.
panelsize : float
Size of each plot panel.
Returns
-------
plotnine.ggplot.ggplot
A panel of histograms.
"""
df = (self.ccs_stats(variable)
.assign(lower=lambda x: x[variable].quantile(trim_frac),
upper=lambda x: x[variable].quantile(1 - trim_frac),
trim=lambda x: ((x[variable] > x['upper']) |
(x[variable] < x['lower']))
)
.query('not trim')
)
npanels = len(df['name'].unique())
if maxcol is None:
ncol = npanels
else:
ncol = min(maxcol, npanels)
nrow = math.ceil(npanels / ncol)
p = (p9.ggplot(df, p9.aes(variable, y=f"..{histogram_stat}..")) +
p9.geom_histogram(bins=bins) +
p9.facet_wrap('~ name', ncol=ncol) +
p9.theme(figure_size=(panelsize * ncol, panelsize * nrow),
axis_text_x=p9.element_text(angle=90,
vjust=1,
hjust=0.5)
) +
p9.ylab('number of CCSs')
)
return p
def plot_histogram(df_plot,
variable_column,
output_file='plot_distribution',
facet_column='none',
x_log10=False):
"""Plot plot_distribution to png.
Parameters
----------
df_plot : pandas.DataFrame
DataFrame with <variable_column> as a column.
variable_column : string
String of variable_column column to plot.
output_file : string
Basename of output file.
facet_column : string
Column to facet the plot by.
Returns
-------
NULL
"""
df_plot['x'] = df_plot[variable_column]
if x_log10:
if np.any(df_plot['x'].values < 0):
return 1
elif np.any(df_plot['x'].values == 0):
df_plot['x'] = np.log10(df_plot['x'].values + 1e-10)
variable_column = variable_column + ' (log10)'
else:
df_plot['x'] = np.log10(df_plot['x'].values)
variable_column = variable_column + ' (log10)'
gplt = plt9.ggplot(df_plot, plt9.aes(x='x'))
gplt = gplt + plt9.theme_bw()
gplt = gplt + plt9.geom_histogram(alpha=0.8)
gplt = gplt + plt9.scale_x_continuous(
# trans='log10',
# labels=comma_labels,
minor_breaks=0)
gplt = gplt + plt9.scale_y_continuous(
# trans='log10',
# labels=comma_labels,
minor_breaks=0)
gplt = gplt + plt9.labs(title='', x=variable_column)
gplt = gplt + plt9.theme(axis_text_x=plt9.element_text(angle=-45, hjust=0))
if facet_column != 'none':
gplt = gplt + plt9.facet_wrap('~ {}'.format(facet_column), ncol=5)
n_facets = df_plot[facet_column].nunique()
gplt.save('{}.png'.format(output_file),
dpi=300,
width=6 * (n_facets / 4),
height=4 * (n_facets / 4),
limitsize=False)
else:
gplt.save('{}.png'.format(output_file), dpi=300, width=4, height=4)
return 0
def test_deepcopy():
p = ggplot(aes('x'), data=df) + geom_histogram()
p2 = deepcopy(p)
assert p is not p2
# Not sure what we have to do for that...
assert p.data is p2.data
assert len(p.layers) == len(p2.layers)
assert p.layers[0].geom is not p2.layers[0].geom
assert len(p.mapping) == len(p2.mapping)
assert p.mapping is not p2.mapping
assert p.environment is p2.environment
def plot_pixel_values(im):
plotr = pd.DataFrame(
{'values': im.flatten()},
index=range(len(im.flatten()))
)
return (
p9.ggplot()
+ p9.geom_histogram(data=plotr, mapping=p9.aes('values'))
+ p9.theme_xkcd()
+ p9.labels.xlab('Pixel values')
)
def plot_hists(df, out=None, **kwargs):
r"""Construct histograms
Create a set of histograms. Often used to visualize the results of random
sampling for multiple outputs.
Usually called as a dispatch from plot_auto().
Args:
out (list of strings): Variables to plot
Returns:
Seaborn histogram plot
Examples:
>>> import grama as gr
>>> import matplotlib.pyplot as plt
>>> from grama.models import make_cantilever_beam
>>> md = make_cantilever_beam()
>>> ## Dispatch from autoplotter
>>> (
>>> md
>>> >> gr.ev_sample(n=100, df_det="nom")
>>> >> gr.pt_auto()
>>> )
>>> ## Re-create without metadata
>>> (
>>> md
>>> >> gr.ev_sample(n=100, df_det="nom")
>>> >> gr.pt_hists(out=md.out)
>>> )
"""
if out is None:
raise ValueError("Must provide input columns list as keyword out")
return (
df
>> tf_pivot_longer(
columns=out,
names_to="var",
values_to="value",
)
>> ggplot(aes("value"))
+ geom_histogram(bins=30)
+ facet_wrap("var", scales="free")
+ theme_minimal()
+ labs(
x="Output Value",
y="Count",
)
)
def plot_estimate_distribution(dist):
return (pn.ggplot(dist, pn.aes(x='estimates')) +
pn.geom_histogram(bins=25) + pn.geom_vline(
xintercept=sum(pile['denomination']),
color="#FF5500",
size=2,
) + pn.geom_vline(
xintercept=3363400,
color="#FF5500",
size=2,
linetype='dotted',
))
def density_plot( # type: ignore
self,
df: pd.DataFrame,
xmin=None,
xmax=None,
fill: str = "#fbb4ae",
bins: int = 50,
**kwargs,
):
return (ggplot(df, aes(df.columns[0])) +
geom_histogram(fill=fill, bins=bins) +
self._scale_x(xmin, xmax) + ergo_theme +
theme(axis_text_x=element_text(rotation=45, hjust=1)))
def comparison_plot( # type: ignore
self,
df: pd.DataFrame,
xmin=None,
xmax=None,
bins: int = 50,
**kwargs):
return (ggplot(df, aes(df.columns[1], fill=df.columns[0])) +
scale_fill_brewer(type="qual", palette="Pastel1") +
geom_histogram(position="identity", alpha=0.9, bins=bins) +
self._scale_x(xmin, xmax) + facet_wrap(df.columns[0], ncol=1) +
guides(fill=False) + ergo_theme +
theme(axis_text_x=element_text(rotation=45, hjust=1)))
def create(self, file_path: str) -> None:
(ggplot(self._data, aes("loc")) +
geom_histogram(bins=100, fill="#1e4f79") +
facet_grid(facets="category ~ .", scales='free_y') +
scale_x_continuous(trans=asinh_trans(), labels=asinh_labels) +
scale_y_continuous(labels=comma_format())
#+ scale_y_continuous(labels=lambda l: ["%.2f%%" % (v * 100 / len(self._data)) for v in l])
+ ggtitle("Class Sizes") + xlab("Lines of Code") +
ylab("Number of Classes") +
theme_classic(base_size=32, base_family="Helvetica") +
theme(text=element_text(size=32), subplots_adjust={"hspace": 0.1
})).save(file_path,
width=8,
height=18)
def create(self, file_path: str) -> None:
(ggplot(self._data, aes("value")) +
geom_histogram(bins=100, fill="#1e4f79") +
facet_wrap(facets="variable", scales="free", ncol=3) +
scale_x_continuous(trans=asinh_trans(), labels=asinh_labels) +
scale_y_continuous(labels=comma_format()) +
ggtitle("Distributions of QMOOD Quality Attributes") +
xlab("Quality Attribute Value") + ylab("Number of Projects") +
theme_classic(base_size=32, base_family="Helvetica") +
theme(text=element_text(size=32),
subplots_adjust={
"wspace": 0.35,
"hspace": 0.35
})).save(file_path, width=24, height=12)
def create(self, file_path: str) -> None:
(ggplot(self._data, aes("value")) +
geom_histogram(bins=100, fill="#1e4f79") +
facet_wrap(facets="variable", scales="free", ncol=3) + xlim(0, 1) +
scale_y_continuous(labels=comma_format()) +
ggtitle("Intensity of Design Pattern Use") +
xlab("Percentage of Classes Participating in Design Pattern") +
ylab("Number of Projects") +
theme_classic(base_size=32, base_family="Helvetica") +
theme(text=element_text(size=32),
axis_title_y=element_text(margin={"r": 40}),
subplots_adjust={
"wspace": 0.3,
"hspace": 0.5
})).save(file_path, width=24, height=24)
def plot_histogram_100_bins(histogram_df):
"""This function plots the data in histogram_df as a histogram with 100 bins
Inputs
------
histogram_df: pandas.DataFrame
The dataframe containing the data to be plotted
Returns
-------
plot: plotnine.ggplot
The histogram figure
"""
plot = ggplot(histogram_df, aes(x='effect_size')) + geom_histogram(bins=100)
return plot
def plot_dist_with_ci(dist):
return (pn.ggplot(dist, pn.aes(x='estimates')) +
pn.geom_histogram(bins=25) + pn.geom_vline(
xintercept=dist.quantile(0.025),
color="#FF5500",
size=2,
linetype='dotted',
) + pn.geom_vline(
xintercept=dist.quantile(0.975),
color="#FF5500",
size=2,
linetype='dotted',
) + pn.ggtitle("${0:,.0f} ({1:,.0f}, {2:,.0f})".format(
np.mean(dist.estimates),
dist.estimates.quantile(0.025),
dist.estimates.quantile(0.975),
)))
def plotMutsHistogram(self, value, *,
mutant_order=1, bins=30, wt_vline=True):
"""Plot distribution of phenotype for all mutants of a given order.
Parameters
----------
value : {'latentPhenotype', 'observedPhenotype', 'observedEnrichment'}
What value to plot.
mutant_order : int
Plot mutations of this order. Currently only works for 1
(single mutants).
bins : int
Number of bins in histogram.
wt_vline : bool
Draw a vertical line at the wildtype value.
Returns
-------
plotnine.ggplot.ggplot
Histogram of phenotype for all mutants.
"""
if mutant_order != 1:
raise ValueError('only implemented for `mutant_order` of 1')
if value not in {'latentPhenotype', 'observedPhenotype',
'observedEnrichment'}:
raise ValueError(f"invalid `value` of {value}")
func = getattr(self, value)
xlist = [func(m) for m in self.muteffects.keys()]
p = (p9.ggplot(pd.DataFrame({value: xlist}),
p9.aes(value)) +
p9.geom_histogram(bins=bins) +
p9.theme(figure_size=(3.5, 2.5)) +
p9.ylab(f"number of {mutant_order}-mutants")
)
if wt_vline:
p = p + p9.geom_vline(
xintercept=func(''),
color=CBPALETTE[1],
linetype='dashed')
return p
def plot_pred_hist(label_list, pred_list, names=None, n_bins=10):
"""
予測確率のヒストグラムを描く
:param: label_list: 正解ラベルリストの配列. [(y1, y2, ...), (y1, y2, ...)] のようにして与える, pred_list に対応させる
:param: pred_list: 予測確率リストの配列. label_list と同じ長さにすること
:param: names=None: モデルの名称. None または同じ長さにすること. 指定しない場合, ラベルの組が 2~3 ならば ['train', 'valid', 'test'] を与える. 3より多い場合は通し番号にする.
:param: n_bins: ヒストグラムのビン数
:return: plotnine オブジェクト
TODO: geom_vline の表示方法
"""
if names is None:
if len(label_list) == 2:
names = ('train', 'test')
elif len(label_list) == 3:
names = ('train', 'valid', 'test')
else:
names = list(range(len(label_list)))
else:
pass
name_order = {k: v for v, k in enumerate(names)}
name_order_rev = {str(k): v for v, k in name_order.items()}
d = pd.DataFrame(
{col: v for col, v in zip(('y', 'prediction'), [list(chain.from_iterable(x)) for x in ([label_list, pred_list])])}
).assign(
model=list(chain.from_iterable([[name] * len(l) for name, l in zip(names, label_list)]))
).melt(
id_vars='model'
).assign(
order=lambda x: x.model.replace(name_order)
).sort_values(['order', 'variable'])
# 補助線としての平均値を引くためのデータ
d_mean = d.drop(columns='order').groupby(['variable', 'model']).mean(
).reset_index().rename(columns={'value': 'mean'})
d = d.merge(d_mean, on=['variable', 'model'])
return ggplot(
d,
aes(x='value', y='..density..', group='variable', fill='variable')
) + geom_histogram(position='identity', alpha=.5, bins=10
) + geom_vline(
aes(xintercept='mean', group='variable', color='variable',
linetype='variable')
) + labs(x='prediction', fill='frequency', linetype='mean', color='mean'
) + facet_wrap(
'~order', scales='free_y', labeller=lambda x: name_order_rev[x]
) + theme_classic() + theme(figure_size=(6, 4))
def hist_residuals(self, figure_size=(8, 4), sample_frac=1.0):
"""Histogram of residuals
Parameters
----------
figure_size : tuple(int, int), optional default=(8, 4)
Plot size (width, height)
sample_frac : float, optional default=1.0
Fraction of data points to plot
Returns
-------
plot : ggplot object
"""
return (ggplot(self.df.sample(frac=sample_frac), aes(x="residual")) +
geom_histogram(fill="lightblue", colour="grey") +
geom_vline(xintercept=0, color="red", linetype="dashed") +
labs(title="Residuals", x="Residuals") +
theme(figure_size=figure_size))
def show_community_prediction(
self,
percent_kept: float = 0.95,
side_cut_from: str = "both",
num_samples: int = 1000,
bins: int = 50,
):
"""
Plot samples from the community prediction on this question
:param percent_kept: percentage of sample distrubtion to keep
:param side_cut_from: which side to cut tails from, either 'both','lower', or 'upper'
:param num_samples: number of samples from the community
:param bins: The number of bins in the histogram, the more bins, the more 'fine grained' the graph. Fewer bins results in more aggregation
:return: ggplot graphics object
"""
community_samples = pd.Series([
self.sample_normalized_community() for _ in range(0, num_samples)
])
(_xmin,
_xmax) = self.get_central_quantiles(community_samples,
percent_kept=percent_kept,
side_cut_from=side_cut_from)
_xmin, _xmax = self.denormalize_samples([_xmin, _xmax])
df = pd.DataFrame(
data={"samples": self.denormalize_samples(community_samples)})
title_name = (
f"Q: {self.name}" if self.name else "\n".join(
textwrap.wrap(self.data["title"], 60)) # type: ignore
)
return (ggplot(df, aes("samples")) +
geom_histogram(fill="#b3cde3", bins=bins) +
scale_x_datetime(limits=(_xmin, _xmax)) +
labs(x="Prediction", y="Counts", title=title_name) +
ergo_theme +
theme(axis_text_x=element_text(rotation=45, hjust=1)))
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 plotMutsHistogram(self,
value, *,
k=None,
mutant_order=1,
bins=30,
wt_vline=True,
):
"""Plot distribution of phenotype for all mutants of a given order.
Parameters
----------
value : {'latentPhenotype', 'observedPhenotype', 'observedEnrichment'}
What value to plot.
k : int or None
If value is `latentPhenotype, which phenotype (1 <= `k` <=
:attr:`MultiLatentSigmoidPhenotypeSimulator.n_latent_phenotypes`)
to plot.
mutant_order : int
Plot mutations of this order. Currently only works for 1
(single mutants).
bins : int
Number of bins in histogram.
wt_vline : bool
Draw a vertical line at the wildtype value.
Returns
-------
plotnine.ggplot.ggplot
Histogram of phenotype for all mutants.
"""
if mutant_order != 1:
raise ValueError('only implemented for `mutant_order` of 1')
if value == 'latentPhenotype':
if isinstance(k, int) and 1 <= k <= self.n_latent_phenotypes:
kwargs = {'k': k}
xlabel = f"latentPhenotype {k}"
else:
raise ValueError(f"invalid `k` of {k}")
else:
kwargs = {}
xlabel = value
if value not in {'latentPhenotype', 'observedPhenotype',
'observedEnrichment'}:
raise ValueError(f"invalid `value` of {value}")
func = getattr(self, value)
xlist = [func(m, **kwargs) for m in self._all_subs]
p = (p9.ggplot(pd.DataFrame({value: xlist}),
p9.aes(value)) +
p9.geom_histogram(bins=bins) +
p9.theme(figure_size=(3.5, 2.5)) +
p9.ylab(f"number of {mutant_order}-mutants") +
p9.xlab(xlabel)
)
if wt_vline:
p = p + p9.geom_vline(
xintercept=func('', **kwargs),
color=CBPALETTE[1],
linetype='dashed')
return p
def test_histogram_count():
p = (ggplot(df, aes('x')) +
geom_histogram(aes(fill='factor(z)'), bins=n))
assert p + _theme == 'histogram-count'
def plot_n_train_vs_accuracy(self):
return (
ggplot(self.combined_df) + facet_wrap('seen')
+ aes(x='n_train', fill='Outcome')
+ geom_histogram(binwidth=1)
)
#Do we need to normalize our numeric and integer cols? #SeniorCitizen was already in binary form. So no. from plotnine import ggplot, aes, geom_histogram, geom_boxplot (ggplot(dat, aes(x='MonthlyCharges')) + geom_histogram()).save(filename="MonthlyCharges_Hist.png", dpi=300) (ggplot(dat, aes(x='TotalCharges')) + geom_histogram()).save(filename="TotalCharges_Hist.png", dpi=300) #Neither follow a normal distribution. Log transformation could help, but these are odd. dat["LogTotalCharges"] = np.log(dat["TotalCharges"]+1) dat["LogMonthlyCharges"] = np.log(dat["MonthlyCharges"]+1) (ggplot(dat, aes(x='LogMonthlyCharges')) + geom_histogram()) (ggplot(dat, aes(x='LogTotalCharges')) + geom_histogram()) #Doesn't really help so leave this for now. dat = dat.drop(columns = ["LogTotalCharges", "LogMonthlyCharges"])
def show_prediction(
self,
samples,
percent_kept: float = 0.95,
side_cut_from: str = "both",
show_community: bool = False,
num_samples: int = 1000,
bins: int = 50,
):
"""Plot prediction on the true question scale from samples or a submission object. Optionally compare prediction against a sample from the distribution of community predictions
:param samples: samples from a distribution answering the prediction question (true scale) or a prediction object
:param percent_kept: percentage of sample distrubtion to keep
:param side_cut_from: which side to cut tails from, either 'both','lower', or 'upper'
:param show_community: boolean indicating whether comparison to community predictions should be made
:param num_samples: number of samples from the community
:param bins: The number of bins in the histogram, the more bins, the more 'fine grained' the graph. Fewer bins results in more aggregation
:return: ggplot graphics object
"""
if isinstance(samples, SubmissionMixtureParams):
prediction = samples
prediction_normed_samples = pd.Series([
logistic.sample_mixture(prediction)
for _ in range(0, num_samples)
])
else:
if isinstance(samples, list):
samples = pd.Series(samples)
if not type(samples) in [pd.Series, np.ndarray]:
raise ValueError(
"Samples should be a list, numpy arrray or pandas series")
num_samples = samples.shape[0]
prediction_normed_samples = self.normalize_samples(samples)
title_name = (
f"Q: {self.name}" if self.name else "\n".join(
textwrap.wrap(self.data["title"], 60)) # type: ignore
)
if show_community:
df = pd.DataFrame(
data={
"community": [ # type: ignore
self.sample_normalized_community()
for _ in range(0, num_samples)
],
"prediction":
prediction_normed_samples, # type: ignore
})
# import pdb
# pdb.set_trace()
# get domain for graph given the percentage of distribution kept
(_xmin,
_xmax) = self.get_central_quantiles(df,
percent_kept=percent_kept,
side_cut_from=side_cut_from)
_xmin, _xmax = self.denormalize_samples([_xmin, _xmax])
df["prediction"] = self.denormalize_samples(df["prediction"])
df["community"] = self.denormalize_samples(df["community"])
df = pd.melt(df, var_name="sources",
value_name="samples") # type: ignore
return (ggplot(df, aes("samples", fill="sources")) +
scale_fill_brewer(type="qual", palette="Pastel1") +
geom_histogram(position="identity", alpha=0.9) +
scale_x_datetime(limits=(_xmin, _xmax)) +
facet_wrap("sources", ncol=1) + labs(
x="Prediction",
y="Counts",
title=title_name,
) + guides(fill=False) + ergo_theme +
theme(axis_text_x=element_text(rotation=45, hjust=1)))
else:
(_xmin, _xmax) = self.get_central_quantiles(
prediction_normed_samples,
percent_kept=percent_kept,
side_cut_from=side_cut_from,
)
_xmin, _xmax = self.denormalize_samples([_xmin, _xmax])
df = pd.DataFrame(data={
"prediction":
self.denormalize_samples(prediction_normed_samples)
})
return (ggplot(df, aes("prediction")) +
geom_histogram(fill="#b3cde3", bins=bins)
# + coord_cartesian(xlim = (_xmin,_xmax))
+ scale_x_datetime(limits=(_xmin, _xmax)) +
labs(x="Prediction", y="Counts", title=title_name) +
ergo_theme +
theme(axis_text_x=element_text(rotation=45, hjust=1)))
user_stat.log_n_records.apply(lambda x: x / max_color), index=user_stat.index)
p0 = ggplot(user_stat) \
+ geom_point(aes(x='ratio', y='accuracy',
size='n_records', color='log_n_records', alpha='alpha'),
show_legend={'color': False, 'alpha': False, 'size': False}) \
+ scale_color_gradient(high='#e31a1c', low='#ffffcc') \
+ theme(aspect_ratio=1)
p0.save('protobowl_users.pdf')
# p0.draw()
print('p0 done')
p1 = ggplot(user_stat, aes(x='log_n_records', y='..density..')) \
+ geom_histogram(color='#e6550d', fill='#fee6ce') \
+ geom_density() \
+ theme(aspect_ratio=0.3)
p1.save('protobowl_hist.pdf')
# p1.draw()
print('p1 done')
p2 = ggplot(user_stat, aes(x='accuracy', y='..density..')) \
+ geom_histogram(color='#31a354', fill='#e5f5e0') \
+ geom_density(aes(x='accuracy')) \
+ theme(aspect_ratio=0.3)
p2.save('protobowl_acc.pdf')
# p2.draw()
print('p2 done')