def _violinplot(
self,
data: dataType,
names: namesType,
title: titleType = None,
ax: matplotlib.axes.SubplotBase = None,
) -> matplotlib.figure.Figure:
"""For making violinplots."""
if ax is None:
_, ax = plt.subplots()
else:
ax = ax
figure = ax.get_figure()
width = max(self.num_players / 3, 12)
height = width / 2
spacing = 4
positions = spacing * arange(1, self.num_players + 1, 1)
figure.set_size_inches(width, height)
ax.violinplot(
data,
positions=positions,
widths=spacing / 2,
showmedians=True,
showextrema=False,
)
ax.set_xticks(positions)
ax.set_xticklabels(names, rotation=90)
ax.set_xlim([0, spacing * (self.num_players + 1)])
ax.tick_params(axis="both", which="both", labelsize=8)
if title:
ax.set_title(title)
plt.tight_layout()
return figure
def _violinplot(
self,
data: dataType,
names: namesType,
title: titleType = None,
ax: matplotlib.axes.SubplotBase = None
) -> matplotlib.figure.Figure:
"""For making violinplots."""
if ax is None:
_, ax = plt.subplots()
else:
ax = ax
figure = ax.get_figure()
width = max(self.nplayers / 3, 12)
height = width / 2
spacing = 4
positions = spacing * arange(1, self.nplayers + 1, 1)
figure.set_size_inches(width, height)
ax.violinplot(data,
positions=positions,
widths=spacing / 2,
showmedians=True,
showextrema=False)
ax.set_xticks(positions)
ax.set_xticklabels(names, rotation=90)
ax.set_xlim([0, spacing * (self.nplayers + 1)])
ax.tick_params(axis='both', which='both', labelsize=8)
if title:
ax.set_title(title)
plt.tight_layout()
return figure
def stackplot(
self,
eco,
title: titleType = None,
logscale: bool = True,
ax: matplotlib.axes.SubplotBase = None,
) -> matplotlib.figure.Figure:
populations = eco.population_sizes
if ax is None:
_, ax = plt.subplots()
else:
ax = ax
figure = ax.get_figure()
turns = range(len(populations))
pops = [
[populations[iturn][ir] for iturn in turns]
for ir in self.result_set.ranking
]
ax.stackplot(turns, *pops)
ax.yaxis.tick_left()
ax.yaxis.set_label_position("right")
ax.yaxis.labelpad = 25.0
ax.set_ylim([0.0, 1.0])
ax.set_ylabel("Relative population size")
ax.set_xlabel("Turn")
if title is not None:
ax.set_title(title)
trans = transforms.blended_transform_factory(ax.transAxes, ax.transData)
ticks = []
for i, n in enumerate(self.result_set.ranked_names):
x = -0.01
y = (i + 0.5) * 1 / self.result_set.num_players
ax.annotate(
n,
xy=(x, y),
xycoords=trans,
clip_on=False,
va="center",
ha="right",
fontsize=5,
)
ticks.append(y)
ax.set_yticks(ticks)
ax.tick_params(direction="out")
ax.set_yticklabels([])
if logscale:
ax.set_xscale("log")
plt.tight_layout()
return figure
def stackplot(
self,
eco,
title: titleType = None,
logscale: bool = True,
ax: matplotlib.axes.SubplotBase = None,
) -> matplotlib.figure.Figure:
populations = eco.population_sizes
if ax is None:
_, ax = plt.subplots()
else:
ax = ax
figure = ax.get_figure()
turns = range(len(populations))
pops = [
[populations[iturn][ir] for iturn in turns]
for ir in self.result_set.ranking
]
ax.stackplot(turns, *pops)
ax.yaxis.tick_left()
ax.yaxis.set_label_position("right")
ax.yaxis.labelpad = 25.0
ax.set_ylim([0.0, 1.0])
ax.set_ylabel("Relative population size")
ax.set_xlabel("Turn")
if title is not None:
ax.set_title(title)
trans = transforms.blended_transform_factory(ax.transAxes, ax.transData)
ticks = []
for i, n in enumerate(self.result_set.ranked_names):
x = -0.01
y = (i + 0.5) * 1 / self.result_set.num_players
ax.annotate(
n,
xy=(x, y),
xycoords=trans,
clip_on=False,
va="center",
ha="right",
fontsize=5,
)
ticks.append(y)
ax.set_yticks(ticks)
ax.tick_params(direction="out")
ax.set_yticklabels([])
if logscale:
ax.set_xscale("log")
plt.tight_layout()
return figure
def plot_1_2(ax: matplotlib.axes.SubplotBase, diff_df: pd.DataFrame, row_id: int) -> None:
ax.bar(diff_df.columns, diff_df.loc[row_id], color="red")
ax.set_title("difference")
ax.set_xlabel("k")
ax.set_ylabel("diff")
diff_df_min = diff_df.min().min()
diff_df_max = diff_df.max().max()
if CVResultsAggregator.check_limit(diff_df_min) and CVResultsAggregator.check_limit(diff_df_max):
ax.set_ylim(diff_df_min - 1, diff_df_max + 1)
def _plot_roc(self, axis: mpl.axes.SubplotBase, y_true: np.ndarray,
y_pred: np.ndarray, label: str, color: str):
x, y, _ = roc_curve(y_true, y_pred)
axis.plot(x,
y,
color,
label="{label}, area={auc:.2f}".format(auc=auc(x, y),
label=label))
axis.plot([0, 1], [0, 1], 'k--')
axis.set_xlabel("False Positive Rate")
axis.set_ylabel("True Positive Rate")
axis.set_title("ROC curves - {label}".format(label=label))
def _plot_wordcloud(self, axis: mpl.axes.SubplotBase, wc: WordCloud,
words: List[str], label: str):
"""Plot a given wordcloud on given axis.
axis: mpl.axes.SubplotBase, the subplot on which to plot
wx: WordCloud, wordcloud object to use
words: List[str], list of words to plot
label:str, label for wordcloud
"""
wordcloud = wc.generate(" ".join(words))
axis.imshow(wordcloud, interpolation='bilinear')
axis.set_title("Word cloud - {label}".format(label=label))
plt.axis("off")
def _heatmap(self, axis: mpl.axes.SubplotBase, data: np.matrix,
labels: list, title: str, fmt: str):
""" Plot given matrix as heatmap.
axis: mpl.axes.SubplotBase, the subplot on which to plot
data:np.matrix, the matrix to be plotted.
labels:list, list of labels of matrix data.
title:str, title of given image.
fmt:str, string formatting of digids
"""
heatmap(data,
xticklabels=labels,
yticklabels=labels,
annot=True,
fmt=fmt,
cmap="YlGnBu",
cbar=False)
plt.yticks(rotation=0)
plt.xticks(rotation=0)
axis.set_title(title)
def plt_settings_axes(g: matplotlib.axes.SubplotBase,
count_df: dask.dataframe.core.DataFrame,
grouping_col: list, facet: str, hide_xtitle: bool,
log_y: bool) -> None:
"""
Helper function for plot settings, used in function plt_generic_1d.
Modifies parameter g for setting titles, axis, formats, etc.
:param g: matplotlib Axes which will be modified directly in the function.
:param count_df: pandas dataframe which is plotted.
:param grouping_col: column for x axis.
:param facet: parameter passed by function plt_generic_1d, giving information
on whether we are plotting and average or a count value (on y axis).
:param hide_xtitle: if set to True, doesn't display title for x axis
:param log_y: if set to True, plot in logarithmic scale (for y axis)
:return: nothing. changes are done directly by modifying parameter g.
"""
if facet not in ['freq', 'avg']:
raise ValueError(
'Parameter facet should be a string of value either "freq" or "avg"'
)
# SET X AXIS
# Labels
# no particular setup if number of labels is less than the first threshold
num_xlabels = len(count_df[grouping_col])
if num_xlabels < LABEL_THRESHOLD_ROTATION:
g.set_xticklabels(count_df[grouping_col])
# rotate by 90 degrees if number of labels is between first and second threshold
elif num_xlabels < LABEL_THRESHOLD_SELECT:
g.set_xticklabels(count_df[grouping_col], rotation=90)
# display only certain labels (and rotate by 45 degrees) if number of labels is higher
else:
number_of_steps = num_xlabels / 50
l = np.arange(0, num_xlabels, number_of_steps)
pos = (l / num_xlabels) * (max(g.get_xticks()) - min(g.get_xticks()))
g.set_xticks(pos)
g.set_xticklabels(count_df[grouping_col].iloc[l], rotation=45)
# Title
# option to remove the x axis title (when its obvious, e.g. for the years)
if hide_xtitle:
g.set_xlabel('')
else:
g.set_xlabel(grouping_col)
# SET Y AXIS
# log scale option
if log_y:
g.set_yscale("log")
if facet == 'freq':
g.set_ylabel('# content items (log scale)')
elif facet == 'avg':
g.set_ylabel('title length (log scale)')
else:
if facet == 'freq':
g.set_ylabel('# content items')
elif facet == 'avg':
g.set_ylabel('title length')
# Labels
ylabels = ['{:,.0f}'.format(y) for y in g.get_yticks()]
g.set_yticklabels(ylabels)
# Plot Title
if facet == 'freq':
g.set_title('Number of content items by %s' % grouping_col)
elif facet == 'avg':
g.set_title('Average title length of content items by %s' %
grouping_col)
def plot_2_1(ax: matplotlib.axes.SubplotBase, pval_df: pd.DataFrame, row_id: int) -> None:
ax.bar(pval_df.columns, -np.log10(pval_df.loc[row_id]), color="red")
ax.set_title("significance of difference")
ax.set_xlabel("k")
ax.set_ylabel("-log10(p-value)")
ax.set_ylim(0, 4)
