def kde_plot(self, x, color, x_units="f", y_units="f", shade=False, line_width=0.25, bw=1.0, ax=None):
"""
Documentation:
---
Description:
Create kernel density curve for a feature.
---
Parameters:
x : array
Data for plotting.
color : str (some sort of color code)
Color of KDE lines.
x_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p' displays
percentages, d' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
y_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p' displays
percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
shade : boolean, default=True
Controls whether area under KDE curve is shaded.
line_width : float or int, default= 0.25
Controlsthickness of kde lines
bw : float, default=1.0
Scaling factor for the KDE curve. Smaller values create more detailed curves
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# create kernel density estimation line
g = sns.kdeplot(
data=x,
shade=shade,
color=color,
legend=None,
linewidth=self.chart_scale * line_width,
ax=ax
)
# format x and y ticklabels
ax.set_yticklabels(
ax.get_yticklabels() * 100 if "p" in y_units else ax.get_yticklabels(),
rotation=0,
fontsize=1.1 * self.chart_scale,
color=style.style_grey,
)
ax.set_xticklabels(
ax.get_xticklabels() * 100 if "p" in y_units else ax.get_xticklabels(),
rotation=0,
fontsize=1.1 * self.chart_scale,
color=style.style_grey,
)
# use label formatter utility function to customize chart labels
util.util_label_formatter(ax=ax, x_units=x_units, y_units=y_units)
def bar_h(self, y, counts, color=style.style_grey, label_rotate=45, x_units="f", alpha=0.8, ax=None):
"""
Documentation:
---
Description:
Create horizontal bar plot.
---
Parameters:
y : array
1-dimensional array of values to plot on y-axis representing distinct categories.
counts : array or string
1-dimensional array of value counts for categories.
color : str (some sort of color code), default=style.style_grey
Bar color.
label_rotate : float or int, default=45
Number of degrees to rotate the x-tick labels.
x_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 's' displays string. 'f' displays float. 'p' displays
percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
alpha : float, default=0.8
Controls transparency of bars. Accepts value between 0.0 and 1.0.
ax : axes object, default=None
Axis on which to place visual.
"""
if ax is None:
ax = self.ax
# plot horizontal bar plot
plt.barh(y=y, width=counts, color=color, tick_label=y, alpha=alpha)
# rotate x-tick labels
plt.xticks(rotation=label_rotate)
# customize x-ticklabels
ax.set_xticklabels(
ax.get_xticklabels() * 100 if "p" in x_units else ax.get_xticklabels(),
rotation=0,
fontsize=0.9 * self.chart_scale,
color=style.style_grey,
)
# use label formatter utility function to customize chart labels
util.util_label_formatter(ax=ax, x_units=x_units)
def reg_plot(self, x, y, data, dot_color=style.style_grey, dot_size=2.0, line_color=style.style_blue, line_width = 0.3,
x_jitter=None, x_units="f", y_units="f", x_rotate=None, alpha=0.3, ax=None):
"""
Documentation:
---
Description:
create scatter plot with regression line.
---
Parameters:
x : str
Name of independent variable in dataframe.
y : str
Name of numeric target variable.
data : Pandas DataFrame
Pandas DataFrame including both x and y columns.
dot_color : str
Color of scattered dots.
dot_size : float or int
Size of scattered dots.
line_color : str
Regression line color.
line_width : float or int
Regression line width.
x_jitter : float, default=None
optional paramter for randomly displacing dots along the x_axis to enable easier
visibility of individual dots.
x_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p' displays
percentages, d' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
y_units : str, default='f'
Determines unit of measurement for y-axis tick labels. 'f' displays float. 'p' displays
percentages, d' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
x_rotate : int, default=None
Rotates x_axis tick mark labels x degrees.
alpha : float, default=0.3
Controls transparency of objects. Accepts value between 0.0 and 1.0.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# create regression plot
g = sns.regplot(
x=x,
y=y,
data=data,
x_jitter=x_jitter,
scatter_kws={
"alpha": alpha,
"color": dot_color,
"s": dot_size * self.chart_scale,
},
line_kws={
"color": line_color,
"linewidth": self.chart_scale * line_width,
},
ax=ax,
).set(xlabel=None, ylabel=None)
# format x and y ticklabels
ax.set_yticklabels(
ax.get_yticklabels() * 100 if "p" in y_units else ax.get_yticklabels(),
rotation=0,
fontsize=1.1 * self.chart_scale,
color=style.style_grey,
)
ax.set_xticklabels(
ax.get_xticklabels() * 100 if "p" in y_units else ax.get_xticklabels(),
rotation=0,
fontsize=1.1 * self.chart_scale,
color=style.style_grey,
)
# use label formatter utility function to customize chart labels
util.util_label_formatter(
ax=ax, x_units=x_units, y_units=y_units, x_rotate=x_rotate
)
def dist_plot(self, x, color, x_units="f", y_units="f", fit=None, kde=False, x_rotate=None, alpha=0.8,
bbox=(1.2, 0.9), legend_labels=None, color_map="viridis", ax=None):
"""
Documentation:
---
Description:
Creates distribution plot for numeric variable. Optionally overlays a kernel density
estimation curve.
---
Parameters:
x : array
Data for plotting.
color : str (some sort of color code)
Color of bars and KDE lines.
x_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p' displays
percentages, d' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
y_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p' displays
percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
fit : random variabe object, default=None
Allows for the addition of another curve. utilizing 'norm' overlays a normal distribution
over the distribution bar chart. Useful for seeing how well, or not, the distribution tracks
with a specified distrbution.
kde : boolean, default=False
Controls whether kernel density is plotted over distribution.
x_rotate : int, default=None
Rotates x_axis tick mark labels x degrees.
alpha : float, default=0.8
Controls transparency of objects. Accepts value between 0.0 and 1.0.
bbox : tuple of floats, default=(1.2, 0.9)
Coordinates for determining legend position.
legend_labels : list, default=None
Custom legend labels.
color_map : str specifying built-in matplotlib colormap, default="viridis"
Color map applied to plots.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# create distribution plot with an optional fit curve
g = sns.distplot(
a=x,
kde=kde,
color=color,
axlabel=False,
fit=fit,
kde_kws={"lw": 0.2 * self.chart_scale},
hist_kws={"alpha": alpha},
ax=ax,
)
# tick label font size
ax.tick_params(axis="both", colors=style.style_grey, labelsize=1.2 * self.chart_scale)
# format x and y ticklabels
ax.set_yticklabels(
ax.get_yticklabels() * 100 if "p" in y_units else ax.get_yticklabels(),
rotation=0,
fontsize=1.1 * self.chart_scale,
color=style.style_grey,
)
ax.set_xticklabels(
ax.get_xticklabels() * 100 if "p" in y_units else ax.get_xticklabels(),
rotation=0,
fontsize=1.1 * self.chart_scale,
color=style.style_grey,
)
# use label formatter utility function to customize chart labels
util.util_label_formatter(
ax=ax, x_units=x_units, y_units=y_units, x_rotate=x_rotate
)
## create custom legend
if legend_labels is None:
legend_labels = legend_labels
else:
legend_labels = np.array(legend_labels)
# generate colors
color_list = style.color_gen(color_map, num=len(legend_labels))
label_color = {}
for ix, i in enumerate(legend_labels):
label_color[i] = color_list[ix]
# create legend Patches
patches = [Patch(color=v, label=k, alpha=alpha) for k, v in label_color.items()]
# draw legend
leg = plt.legend(
handles=patches,
fontsize=1.0 * self.chart_scale,
loc="upper right",
markerscale=0.5 * self.chart_scale,
ncol=1,
bbox_to_anchor=bbox,
)
# label font color
for text in leg.get_texts():
plt.setp(text, color="grey")
def scatter_2d(self, x, y, df=None, x_units="f", x_ticks=None, y_units="f", y_ticks=None, plot_buffer=True,
size=5, axis_limits=True, color=style.style_grey, facecolor="w", alpha=0.8,
x_rotate=None, ax=None):
"""
Documentation:
---
Description:
Create 2-dimensional scatter plot.
---
Parameters:
x : array or string
Either 1-dimensional array of values or a column name in a Pandas DataFrame.
y : array or string
Either 1-dimensional array of values or a column name in a Pandas DataFrame.
df : Pandas DataFrame, default=None
Pandas DataFrame containing data to plot. Can be any size - plotted columns will be
chosen by columns names specified in x and y parameters.
x_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p' displays
percentages, d' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
x_ticks : array, default=None
Custom x-tick labels.
y_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p' displays
percentages, d' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
y_ticks : array, default=None
Custom y-tick labels.
plot_buffer : bool, default=True
Controls whether dynamic plot buffer function is executed.
size : int or float, default=5
Size of scattered dots.
axis_limits : bool, default=True
Controls whether dynamic axis limit setting function is executed.
color : str (color code of some sort), default=style.style_grey
Color of scattered dots
facecolor : str (color code of some sort), default='w'
Face color of scattered dots.
alpha : float, default=0.8
Controls transparency of objects. Accepts value between 0.0 and 1.0.
x_rotate : int, default=None
Rotates x-axis tick mark labels x degrees.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# if a Pandas DataFrame is passed to function, create x and y arrays using columns names passed into function
if df is not None:
x = df[x].values.reshape(-1, 1)
y = df[y].values.reshape(-1, 1)
# else reshape arrays
else:
x = x.reshape(-1, 1)
y = y.reshape(-1, 1)
# plot 2-dimensional scatter
plt.scatter(
x=x,
y=y * 100 if "p" in y_units else y,
color=color,
s=size * self.chart_scale,
alpha=alpha,
facecolor=facecolor,
linewidth=0.167 * self.chart_scale,
)
# optionally set axis lower / upper limits
if axis_limits:
x_min, x_max, y_min, y_max = util.util_set_axes(x=x, y=y)
plt.axis([x_min, x_max, y_min, y_max])
# optionally create smaller buffer around plot area to prevent cutting off elements
if plot_buffer:
util.util_plot_buffer(ax=ax, x=0.02, y=0.02)
# optionally creates custom x-tick labels
if x_ticks is not None:
ax.set_xticks(x_ticks)
# optionally creates custom y-tick labels
if y_ticks is not None:
ax.set_yticks(y_ticks)
# format x and y ticklabels
ax.set_yticklabels(
ax.get_yticklabels() * 100 if "p" in y_units else ax.get_yticklabels(),
rotation=0,
fontsize=1.0 * self.chart_scale,
color=style.style_grey,
)
ax.set_xticklabels(
ax.get_xticklabels() * 100 if "p" in y_units else ax.get_xticklabels(),
rotation=0,
fontsize=1.0 * self.chart_scale,
color=style.style_grey,
)
# use label formatter utility function to customize chart labels
util.util_label_formatter(ax=ax, x_units=x_units, y_units=y_units, x_rotate=x_rotate)
def scatter_2d_hue(self, x, y, target, label, df=None, x_units="f", x_ticks=None, y_units="f", y_ticks=None,
plot_buffer=True, size=10, axis_limits=True, color=style.style_grey, facecolor="w",
bbox=(1.2, 0.9), color_map="viridis", alpha=0.8, x_rotate=None, ax=None):
"""
Documentation:
---
Description:
Create 2-dimensional scatter plot with a third dimension represented as a color hue in the
scatter dots.
---
Parameters:
x : array or string
Either 1-dimensional array of values or a column name in a Pandas DataFrame.
y : array or string
Either 1-dimensional array of values or a column name in a Pandas DataFrame.
target : array or string
Either 1-dimensional array of values or a column name in a Pandas DataFrame.
label : list
Labels corresponding to color hue.
df : Pandas DataFrame, default=None
Pandas DataFrame containing data to plot. Can be any size - plotted columns will be
chosen by columns names specified in x and y parameters.
x_units : str, default='d'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p' displays
percentages, d' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
x_ticks : array, default=None
Custom x-tick labels.
y_units : str, default='d'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p' displays
percentages, d' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
y_ticks : array, default=None
Custom y-tick labels.
plot_buffer : bool, default=True
Controls whether dynamic plot buffer function is executed.
size : int or float, default=10
Size of scattered dots.
axis_limits : bool, default=True
Controls whether dynamic axis limit setting function is executed.
color : str (color code of some sort), default=style.style_grey
Color of scattered dots
facecolor : str (color code of some sort), default='w'
Face color of scattered dots
bbox : tuple of floats, default=(1.2, 0.9)
Coordinates for determining legend position.
color_map : str specifying built-in matplotlib colormap, default="viridis"
Color map applied to plots.
alpha : float, default=0.8
Controls transparency of objects. Accepts value between 0.0 and 1.0.
x_rotate : int, default=None
Rotates x-axis tick mark labels x degrees.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# if a Pandas DataFrame is passed to function, create x and y and target arrays using columns names
# passed into function. Also concatenates columns into single object
if df is not None:
x = df[[x, y, target]].values
x = df[x].values
y = df[y].values
target = df[target].values
# concatenate the x, y and target arrays
else:
x = np.c_[x, y, target]
# unique target values
target_ids = np.unique(x[:, 2])
# generate color list
color_list = style.color_gen(name=color_map, num=len(target_ids))
# loop through sets of target values, labels and colors to create 2_d scatter with hue
for target_id, target_name, color in zip(target_ids, label, color_list):
plt.scatter(
x=x[x[:, 2] == target_id][:, 0],
y=x[x[:, 2] == target_id][:, 1],
color=color,
label=target_name,
s=size * self.chart_scale,
alpha=alpha,
facecolor="w",
linewidth=0.234 * self.chart_scale,
)
# add legend to figure
if label is not None:
plt.legend(
loc="upper right",
bbox_to_anchor=bbox,
ncol=1,
frameon=True,
fontsize=1.1 * self.chart_scale,
)
# optionally set axis lower / upper limits
if axis_limits:
x_min, x_max, y_min, y_max = util.util_set_axes(x=x, y=y)
plt.axis([x_min, x_max, y_min, y_max])
# optionally create smaller buffer around plot area to prevent cutting off elements
if plot_buffer:
util.util_plot_buffer(ax=ax, x=0.02, y=0.02)
# optionally creates custom x-tick labels
if x_ticks is not None:
ax.set_xticks(x_ticks)
# optionally creates custom y-tick labels
if y_ticks is not None:
ax.set_yticks(y_ticks)
# format x and y ticklabels
ax.set_yticklabels(
ax.get_yticklabels() * 100 if "p" in y_units else ax.get_yticklabels(),
rotation=0,
fontsize=1.0 * self.chart_scale,
color=style.style_grey,
)
ax.set_xticklabels(
ax.get_xticklabels() * 100 if "p" in y_units else ax.get_xticklabels(),
rotation=0,
fontsize=1.0 * self.chart_scale,
color=style.style_grey,
)
# use label formatter utility function to customize chart labels
util.util_label_formatter(ax=ax, x_units=x_units, y_units=y_units, x_rotate=x_rotate)
def facet_cat_num_scatter(self,
df,
x,
y,
cat_row=None,
cat_col=None,
split=None,
bbox=None,
aspect=1,
alpha=0.8,
height=4,
legend_labels=None,
x_units="f",
y_units="f",
color_map="viridis"):
"""
Documentation:
---
Description:
Creates scatter plots of two numeric variables and allows for faceting by up to two
categorical variables along the column and/or row axes of the figure.
---
Parameters:
df : Pandas DataFrame
Pandas DataFrame containing data for plotting.
x : str
Numeric variable to plot along x-axis.
y : str
Numeric variable to plot along y-axis.
cat_row : str
Categorical variable faceted along the row axis.
cat_col : str
Categorical variable faceted along the column axis.
split : str
Categorical variable for faceting the num_col variable.
bbox : tuple of floats, default=None
Coordinates for determining legend position.
aspect : float, default=1
Higher values create wider plot, lower values create narrow plot, while
keeping height constant.
alpha : float, default=0.8
Controls transparency of objects. Accepts value between 0.0 and 1.0.
height : float, default=4
Height in inches of each facet.
legend_labels : list, default=None
Custom legend labels.
x_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p'
displays percentages, d' displays dollars. Repeat character (e.g 'ff' or 'ddd')
for additional decimal places.
y_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 'f' displays float. 'p'
displays percentages, d' displays dollars. Repeat character (e.g 'ff' or 'ddd')
for additional decimal places.
color_map : str specifying built-in matplotlib colormap, default="viridis"
Color map applied to plots.
"""
# create FacetGrid object
g = sns.FacetGrid(
df,
col=cat_col,
row=cat_row,
hue=split,
palette=sns.color_palette(
style.color_gen(color_map, num=len(np.unique(df[split].values)))),
hue_order=df[split].sort_values().drop_duplicates().values.tolist()
if split is not None else None,
height=height,
aspect=aspect,
margin_titles=True,
)
# map scatter plot to FacetGrid object
g = g.map(plt.scatter, x, y, s=1.2 * self.chart_scale)
# format x any y ticklabels, x and y labels, and main title
for ax in g.axes.flat:
_ = ax.set_yticklabels(
ax.get_yticklabels() *
100 if "p" in y_units else ax.get_yticklabels(),
rotation=0,
fontsize=0.8 * self.chart_scale,
color=style.style_grey,
)
_ = ax.set_xticklabels(
ax.get_xticklabels(),
rotation=0,
fontsize=0.8 * self.chart_scale,
color=style.style_grey,
)
_ = ax.set_ylabel(
ax.get_ylabel(),
rotation=90,
fontsize=1.05 * self.chart_scale,
color=style.style_grey,
)
_ = ax.set_xlabel(
ax.get_xlabel(),
rotation=0,
fontsize=1.05 * self.chart_scale,
color=style.style_grey,
)
_ = ax.set_title(
ax.get_title(),
rotation=0,
fontsize=1.05 * self.chart_scale,
color=style.style_grey,
)
# custom tick label formatting
util.util_label_formatter(ax=ax, x_units=x_units, y_units=y_units)
if ax.texts:
# this contains the right ylabel text
txt = ax.texts[0]
ax.text(
txt.get_unitless_position()[0],
txt.get_unitless_position()[1],
txt.get_text(),
transform=ax.transAxes,
va="center",
fontsize=1.05 * self.chart_scale,
color=style.style_grey,
rotation=-90,
)
# remove the original text
ax.texts[0].remove()
## create custom legend
# create labels
if split is not None:
if legend_labels is None:
legend_labels = (df[df[split].notnull()][split].sort_values().
drop_duplicates().values.tolist())
else:
legend_labels = np.array(legend_labels)
# generate colors
color_list = style.color_gen(color_map, num=len(legend_labels))
label_color = {}
for ix, i in enumerate(legend_labels):
label_color[i] = color_list[ix]
# create legend Patches
patches = [
Patch(color=v, label=k, alpha=alpha)
for k, v in label_color.items()
]
# draw legend
leg = plt.legend(
handles=patches,
fontsize=1.0 * self.chart_scale,
loc="upper right",
markerscale=0.5 * self.chart_scale,
ncol=1,
bbox_to_anchor=bbox,
)
# label font color
for text in leg.get_texts():
plt.setp(text, color="grey")
def facet_two_cat_bar(self,
df,
x,
y,
split,
x_units=None,
y_units=None,
bbox=None,
alpha=0.8,
legend_labels=None,
filter_nan=True,
color_map="viridis",
ax=None):
"""
Documentation:
Description:
Creates a series of bar plots that count a variable along the y_axis and separate the counts
into bins based on two category variables.
---
Parameters:
df : Pandas DataFrame
Pandas DataFrame containing data for plotting.
x : str
Categorical variable to plot along x-axis.
y : str
Pandas DataFrame containing data for plotting.
ariable to be counted along y-axis.
split : str
Categorical variable for faceting the num_col variable.
x_units : str, default=None
Determines unit of measurement for x-axis tick labels. 's' displays string. 'f' displays
float. 'p' displays percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd')
for additional decimal places.
y_units : str, default=None
Determines unit of measurement for x-axis tick labels. 's' displays string. 'f' displays
float. 'p' displays percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd')
for additional decimal places.
bbox : tuple of floats, default=None
Coordinates for determining legend position.
alpha : float, default=0.8
Controls transparency of objects. Accepts value between 0.0 and 1.0.
legend_labels : list, default=None
Custom legend labels.
filter_nan : bool, default=True
Remove records that have a null value in the column specified by the 'x' parameter.
color_map : str specifying built-in matplotlib colormap, default="viridis"
Color map applied to plots.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# remove nans from x columns
if filter_nan:
df = df.dropna(subset=[x])
# create bar plot
g = sns.barplot(
x=x,
y=y,
hue=split,
data=df,
palette=sns.color_palette(
style.color_gen("viridis", num=len(np.unique(df[split].values)))),
order=df[x].sort_values().drop_duplicates().values.tolist(),
hue_order=df[split].sort_values().drop_duplicates().values.tolist()
if split is not None else None,
ax=ax,
ci=None,
)
# format x-tick labels
g.set_xticklabels(
g.get_xticklabels(),
rotation=0,
fontsize=1.05 * self.chart_scale,
color=style.style_grey,
)
# format y-tick labels
g.set_yticklabels(
g.get_yticklabels() * 100 if "p" in y_units else g.get_yticklabels(),
rotation=0,
fontsize=1.05 * self.chart_scale,
color=style.style_grey,
)
# format x-axis label
g.set_xlabel(
g.get_xlabel(),
rotation=0,
fontsize=1.35 * self.chart_scale,
color=style.style_grey,
)
# format y-axis label
g.set_ylabel(
g.get_ylabel(),
rotation=90,
fontsize=1.35 * self.chart_scale,
color=style.style_grey,
)
# format title
g.set_title(
g.get_title(),
rotation=0,
fontsize=1.5 * self.chart_scale,
color=style.style_grey,
)
## create custom legend
# create labels
if split is not None:
if legend_labels is None:
legend_labels = (df[df[split].notnull()][split].sort_values().
drop_duplicates().values.tolist())
else:
legend_labels = np.array(legend_labels)
# generate colors
color_list = style.color_gen(color_map, num=len(legend_labels))
label_color = {}
for ix, i in enumerate(legend_labels):
label_color[i] = color_list[ix]
# create legend Patches
patches = [
Patch(color=v, label=k, alpha=alpha)
for k, v in label_color.items()
]
# draw legend
leg = plt.legend(
handles=patches,
fontsize=1.25 * self.chart_scale,
loc="upper right",
markerscale=0.5 * self.chart_scale,
ncol=1,
bbox_to_anchor=bbox,
)
# label font color
for text in leg.get_texts():
plt.setp(text, color="grey")
# use label formatter utility function to customize chart labels
util.util_label_formatter(ax=ax, x_units=x_units, y_units=y_units)
def facet_cat(self,
df,
feature,
label_rotate=0,
x_units="s",
y_units="f",
bbox=(1.2, 0.9),
alpha=0.8,
legend_labels=None,
color_map="viridis",
ax=None):
"""
Documentation:
---
Description:
Creates a count plot for a categorical variable and facet the variable by another
categorical variable.
---
Parameters:
df : Pandas DataFrame
Pandas DataFrame containing data for plotting.
feature : str
Name of column that contains the category values to be used for faceting/
label_rotate : float or int, default=0
Number of degrees to rotate the x-tick labels.
x_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 's' displays string. 'f' displays
float. 'p' displays percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd')
for additional decimal places.
y_units : str, default='s'
Determines unit of measurement for y-axis tick labels. 's' displays string. 'f' displays
float. 'p' displays percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd')
for additional decimal places.
bbox : tuple of floats, default=(1.2, 0.9)
Coordinates for determining legend position.
alpha : float, default=0.8
Controls transparency of objects. Accepts value between 0.0 and 1.0.
legend_labels : list, default=None
Custom legend labels.
color_map : str specifying built-in matplotlib colormap, default="viridis"
Color map applied to plots.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
ixs = np.arange(df.shape[0])
bar_width = 0.35
feature_dict = {}
for feature in df.columns[1:]:
feature_dict[feature] = df[feature].values.tolist()
# generate color list
if isinstance(color_map, str):
color_list = style.color_gen(name=color_map,
num=len(feature_dict.keys()))
elif isinstance(color_map, list):
color_list = color_map
for feature_ix, (k, v) in enumerate(feature_dict.items()):
plt.bar(
ixs + (bar_width * feature_ix),
feature_dict[k],
bar_width,
alpha=alpha,
color=color_list[feature_ix],
label=str(k),
)
# wrap long x-tick labels
plt.xticks(
ixs[:df.shape[0]] + bar_width / 2,
[
"\n".join(textwrap.wrap(str(i).replace("_", " "), 12))
for i in df.iloc[:, 0].values
],
)
plt.xticks(rotation=label_rotate)
## create custom legend
# create labels
if legend_labels is None:
legend_labels = np.arange(len(color_list))
else:
legend_labels = np.array(legend_labels)
# define colors
label_color = {}
for ix, i in enumerate(legend_labels):
label_color[i] = color_list[ix]
# create legend Patches
patches = [
Patch(color=v, label=k, alpha=alpha) for k, v in label_color.items()
]
# draw legend
leg = plt.legend(
handles=patches,
fontsize=0.95 * self.chart_scale,
loc="upper right",
markerscale=0.3 * self.chart_scale,
ncol=1,
bbox_to_anchor=bbox,
)
# label font color
for text in leg.get_texts():
plt.setp(text, color="grey")
### general formatting
# if data is float dtype, then format as a number
if df.iloc[:, 0].values.dtype == np.float:
x_units = "f"
# otherwise represent data as a string
else:
x_units = "s"
# use label formatter utility function to customize chart labels
util.util_label_formatter(ax=ax, x_units=x_units, y_units=y_units)
# tick label font size
ax.tick_params(axis="both",
colors=style.style_grey,
labelsize=1.2 * self.chart_scale)
# dynamically set x-axis label size
if 7 < len(feature_dict[feature]) <= 10:
ax.tick_params(axis="x",
colors=style.style_grey,
labelsize=0.9 * self.chart_scale)
elif 10 < len(feature_dict[feature]) <= 20:
ax.tick_params(axis="x",
colors=style.style_grey,
labelsize=0.75 * self.chart_scale)
elif len(feature_dict[feature]) > 20:
ax.tick_params(axis="x",
colors=style.style_grey,
labelsize=0.6 * self.chart_scale)
def box_plot_h(self, x, y, data, color=style.style_grey, x_units="f", bbox=(1.05, 1), color_map="viridis",
suppress_outliers=False, alpha=0.8, legend_labels=None, ax=None):
"""
Documentation:
---
Description:
create horizontal box plots. useful for evaluating a object target on the y_axis
vs. a number independent variable on the x_axis.
---
Parameters:
x : str
Name of categorical variable.
y : str
Name of numeric variable.
data : Pandas DataFrame
Pandas DataFrame including both x and y data.
color : str (some sort of color code), default=style.style_grey
Determines color of box plot figures. Ideally this object is a color palette,
which can be a default seaborn palette, a custom seaborn palette, or a custom
matplotlib cmap.
x_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 's' displays string. 'f' displays
float. 'p' displays percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd')
for additional decimal places.
bbox : tuple of floats, default=(1.05, 1.0)
Coordinates for determining legend position.
color_map : str specifying built-in matplotlib colormap, default="viridis"
Color map applied to plots.
suppress_outliers : boolean, default=False
Controls removal of outliers from box/whisker plots
alpha : float, default=0.8
Controls transparency of bars. Accepts value between 0.0 and 1.0.
legend_labels : list, default=None
Custom legend labels.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# create horizontal box plot
g = sns.boxplot(
x=x,
y=y,
hue=y,
data=data,
orient="h",
palette=sns.color_palette(
style.color_gen(color_map, num=len(np.unique(data[y].values)))
),
showfliers=suppress_outliers,
ax=ax,
).set(xlabel=None, ylabel=None)
# fade box plot figures by reducing alpha
plt.setp(ax.artists, alpha=alpha)
ax.yaxis.set_visible(False)
# tick label font size
ax.tick_params(axis="both", colors=style.style_grey, labelsize=1.2 * self.chart_scale)
# use label formatter utility function to customize chart labels
util.util_label_formatter(ax=ax, x_units=x_units)
## custom legend
# use legend labels if provided, otherwise use unique values in y column
if legend_labels is None:
legend_labels = np.unique(data[y].values)
else:
legend_labels = np.array(legend_labels)
# generate colors
color_list = style.color_gen(color_map, num=len(legend_labels))
label_color = {}
for ix, i in enumerate(legend_labels):
label_color[i] = color_list[ix]
# create legend Patches
patches = [Patch(color=v, label=k, alpha=alpha) for k, v in label_color.items()]
# draw legend
leg = plt.legend(
handles=patches,
fontsize=1.0 * self.chart_scale,
loc="upper right",
markerscale=0.5 * self.chart_scale,
ncol=1,
bbox_to_anchor=bbox,
)
# label font color
for text in leg.get_texts():
plt.setp(text, color="grey")
def box_plot_v(self, x, y, data, color, label_rotate=0, y_units="f", color_map="viridis", alpha=0.8,
suppress_outliers=False, ax=None):
"""
Documentation:
---
Description:
Create vertical box plots. Useful for evaluating a numeric variable on the y-axis
versus several different category segments on the x-axis.
---
Parameters:
x : str
Name of categorical variable.
y : str
Name of numeric variable.
data : Pandas DataFrame
Pandas DataFrame including both x and y data.
color : str
Determines color of box plot figures. Ideally this object is a color palette,
which can be a default seaborn palette, a custom seaborn palette, or a custom
matplotlib cmap.
label_rotate : float or int, default=45
Number of degrees to rotate the x-tick labels.
y_units : str, default='f'
Determines unit of measurement for y-axis tick labels. 's' displays string. 'f'
displays float. 'p' displays percentages, 'd' displays dollars. Repeat character
(e.g 'ff' or 'ddd') for additional decimal places.
color_map : str specifying built-in matplotlib colormap, default="viridis"
Color map applied to plots.
alpha : float, default=0.8
Controls transparency of objects. Accepts value between 0.0 and 1.0.
suppress_outliers : boolean, default=False
Controls removal of outliers from box/whisker plots.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# create vertical box plot.
g = sns.boxplot(
x=x,
y=y,
data=data,
orient="v",
palette=sns.color_palette(
style.color_gen(color_map, num=len(np.unique(data[x].values)))
),
showfliers=suppress_outliers,
ax=ax,
).set(xlabel=None, ylabel=None)
# tick label font size
ax.tick_params(axis="both", colors=style.style_grey, labelsize=1.2 * self.chart_scale)
# resize x-axis labels as needed
unique = np.unique(data[x])
if len(unique) > 10 and len(unique) <= 20:
ax.tick_params(
axis="x", colors=style.style_grey, labelsize=1.0 * self.chart_scale
)
elif len(unique) > 20:
ax.tick_params(
axis="x", colors=style.style_grey, labelsize=0.9 * self.chart_scale
)
else:
ax.tick_params(
axis="x", colors=style.style_grey, labelsize=1.2 * self.chart_scale
)
# resize y-axis
ax.tick_params(axis="y", labelsize=1.2 * self.chart_scale)
# fade box plot figures by reducing alpha.
plt.setp(ax.artists, alpha=alpha)
# rotate x-tick labels
plt.xticks(rotation=label_rotate)
ax.yaxis.set_visible(True)
# use label formatter utility function to customize chart labels
util.util_label_formatter(ax=ax, y_units=y_units)
def stacked_bar_h(self, df, label_rotate=0, x_units="p", alpha=0.8, color_map="viridis", bbox=(1.2,0.9),
legend_labels=None, ax=None):
"""
Documentation:
---
Description:
create horizontal bar plot.
---
Parameters:
df : Pandas DataFrame
1-dimensional array of values to plot on y-axis representing distinct categories.
label_rotate : float or int, default=45
Number of degrees to rotate the x-tick labels.
x_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 's' displays string. 'f'
displays float. 'p' displays percentages, 'd' displays dollars. Repeat character
(e.g 'ff' or 'ddd') for additional decimal places.
alpha : float, default=0.8
Controls transparency of bars. Accepts value between 0.0 and 1.0.
color_map : str specifying built-in matplotlib colormap, default="viridis"
Color map applied to plots.
bbox : tuple of floats, default=(1.2, 0.9)
Coordinates for determining legend position.
legend_labels : list, default=None
Custom legend labels.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# define class label count and bar color list
y = np.arange(len(df.index))
color_list = style.color_gen(color_map, num=len(y))
# define category labels
category_levels = np.arange(len(df.columns))
# plot stacked bars
for class_label, color in zip(np.arange(len(y)), color_list):
# first category
if class_label == 0:
plt.barh(
y=category_levels,
width=df.loc[class_label],
color=color,
alpha=alpha,
)
# stack all additional categories on previous categories
else:
plt.barh(
y=category_levels,
width=df.loc[class_label],
left=df.drop([x for x in df.index if x >= class_label]).sum(axis=0),
color=color,
alpha=alpha,
)
# convert x-axis tick labels to percentages
ax.set_xticklabels(
ax.get_xticklabels() * 100 if "p" in x_units else ax.get_xticklabels(),
rotation=0,
color=style.style_grey,
)
## create custom legend
if legend_labels is None:
legend_labels = np.arange(len(color_list))
else:
legend_labels = np.array(legend_labels)
# define colors
label_color = {}
for ix, i in enumerate(legend_labels):
label_color[i] = color_list[ix]
# create legend Patches
patches = [Patch(color=v, label=k, alpha=alpha) for k, v in label_color.items()]
# draw legend
leg = plt.legend(
handles=patches,
fontsize=0.95 * self.chart_scale,
loc="upper right",
markerscale=0.3 * self.chart_scale,
ncol=1,
bbox_to_anchor=bbox,
)
# label font color
for text in leg.get_texts():
plt.setp(text, color="grey")
# use label formatter utility function to customize chart labels
util.util_label_formatter(ax=ax, x_units=x_units)
# overwrite y-axis labels with category labels
try:
columns = df.columns.map(np.int)
except ValueError:
columns = df.columns
# dynamically size y-labels
if 7 < len(category_levels) <= 10:
ax.tick_params(axis="y", colors=style.style_grey, labelsize=0.9 * self.chart_scale)
elif 10 < len(category_levels) <= 20:
ax.tick_params(axis="y", colors=style.style_grey, labelsize=0.75 * self.chart_scale)
elif len(category_levels) > 20:
ax.tick_params(axis="y", colors=style.style_grey, labelsize=0.6 * self.chart_scale)
ax.tick_params(axis="x", colors=style.style_grey, labelsize=1.2 * self.chart_scale)
# wrap long y-tick labels
plt.yticks(
category_levels,
[
"\n".join(textwrap.wrap(str(i).replace("_", " "), 12))
for i in columns
],
)
def bar_v(self, x, counts, color=style.style_grey, x_labels=None, x_tick_wrap=False, label_rotate=0,
y_units="f", alpha=0.8, ax=None):
"""
Documentation:
---
Description:
Create vertical bar plot.
---
Parameters:
x : array
1-dimensional array of values to plot on x-axis representing distinct categories.
counts : array or string
1-dimensional array of value counts for categories.
color : str (some sort of color code), default=style.style_grey
Bar color.
x_labels : list, default=None
Custom x_axis text labels.
x_tick_wrap : bool, default=False
Wrap x_axis tick labels.
label_rotate : float or int, default=0
Number of degrees to rotate the x-tick labels.
y_units : str, default='f'
Determines unit of measurement for y-axis tick labels. 's' displays string. 'f' displays float. 'p' displays
percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd') for additional
decimal places.
alpha : float, default=0.8
Controls transparency of bars. Accepts value between 0.0 and 1.0.
ax : axes object, default=None
Axis on which to place visual.
"""
if ax is None:
ax = self.ax
# custom labels
labels = x_labels if x_labels is not None else x
# create vertical bar plot.
plt.bar(
x=x,
height=counts,
color=color,
tick_label=labels,
alpha=alpha,
)
# rotate x-tick labels
plt.xticks(rotation=label_rotate)
# dynamically resize x_axis labels
if len(x) > 10 and len(x) <= 20:
ax.tick_params(
axis="x", colors=style.style_grey, labelsize=1.0 * self.chart_scale
)
elif len(x) > 20:
ax.tick_params(
axis="x", colors=style.style_grey, labelsize=0.9 * self.chart_scale
)
else:
ax.tick_params(
axis="x", colors=style.style_grey, labelsize=1.2 * self.chart_scale
)
# wrap long x-tick labels
if x_tick_wrap and type(labels):
try:
x = ["\n".join(textwrap.wrap(i.replace("_", " "), 12)) for i in labels]
ax.set_xticklabels(x)
except AttributeError:
pass
# format y-ticklabels
ax.set_yticklabels(
ax.get_yticklabels() * 100 if "p" in y_units else ax.get_yticklabels(),
rotation=0,
fontsize=1.2 * self.chart_scale,
color=style.style_grey,
)
# use label formatter utility function to customize chart labels
util.util_label_formatter(ax=ax, y_units=y_units)
def line(self,
x,
y,
label=None,
df=None,
linecolor=style.style_grey,
linestyle=None,
bbox=(1.2, 0.9),
x_units="f",
x_ticks=None,
y_units="f",
y_ticks=None,
marker_on=False,
plot_buffer=False,
axis_limits=False,
ax=None):
"""
Documentation:
---
Description:
Create single line plot.
---
Parameters:
x : list, array or string
1-dimensional array of values to plot along x-axis
y : list, array or string
1-dimensional array of values to plot along y-axis
label : str : default=None
Legend label for line.
df : Pandas DataFrame, default=None
Pandas DataFrame containing data to plot. can be any size, as plotted columns will be chosen
by columns names specified in x and y parameters.
linecolor : str, default=style.style_grey
Line color.
linestyle : str, default=None
Line style.
bbox : tuple of floats, default=(1.2, 0.9)
Coordinates for determining legend position.
x_units : str, default='f'
Determines unit of measurement for x-axis tick labels. 's' displays string. 'f' displays float.
'p' displays percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd') for
additional decimal places.
x_ticks : array, default=None
Custom x-tick labels.
y_units : str, default='f'
Determines unit of measurement for y-axis tick labels. 's' displays string. 'f' displays float.
'p' displays percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd') for
additional decimal places.
y_ticks : array, default=None
Custom y_tick labels.
marker_on : bool, default=False
Controls whether to show line with markers for each data element.
plot_buffer : bool, default=False
Controls whether dynamic plot buffer function is executed to ensure visual elements are
not cut-off at the figure borders.
axis_limits : bool, default=False
Controls whether dynamic axis limit setting function is executed.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# if a Pandas DataFrame is passed to function, create x and y arrays using columns names passed into function
if df is not None:
if isinstance(df.index, pd.core.indexes.base.Index):
x = df.index.values
else:
x = df[x].values
y = df[y].values
else:
# convert input list to array
x = np.array(x) if isinstance(x, list) else x
y = np.array(y) if isinstance(y, list) else y
# reshape arrays if necessar
x = x.reshape(-1, 1) if len(x.shape) == 1 else x
y = y.reshape(-1, 1) if len(y.shape) == 1 else y
# add line to plot
plt.plot(
x,
y * 100 if "p" in y_units else y,
color=linecolor,
linestyle=linestyle,
linewidth=0.247 * self.chart_scale,
label=label,
marker="." if marker_on else None,
markersize=17 if marker_on else None,
markerfacecolor="w" if marker_on else None,
markeredgewidth=2.2 if marker_on else None,
)
# add legend to figure
if label is not None:
plt.legend(
loc="upper right",
bbox_to_anchor=bbox,
ncol=1,
frameon=True,
fontsize=1.1 * self.chart_scale,
)
# optionally set axis lower / upper limits
if axis_limits:
x_min, x_max, y_min, y_max = util.util_set_axes(x=x, y=y)
plt.axis([x_min, x_max, y_min, y_max])
# optionally create smaller buffer around plot area to prevent cutting off elements
if plot_buffer:
util.util_plot_buffer(ax=ax, x=0.02, y=0.02)
# optionally creates custom x-tick labels
if x_ticks is not None:
ax.set_xticks(x_ticks)
# optionally creates custom y-tick labels
if y_ticks is not None:
ax.set_yticks(y_ticks)
# format x and y ticklabels
ax.set_yticklabels(
ax.get_yticklabels() * 100 if "p" in y_units else ax.get_yticklabels(),
rotation=0,
fontsize=1.0 * self.chart_scale,
color=style.style_grey,
)
ax.set_xticklabels(
ax.get_xticklabels() * 100 if "p" in y_units else ax.get_xticklabels(),
rotation=0,
fontsize=1.0 * self.chart_scale,
color=style.style_grey,
)
# axis tick label formatting
util.util_label_formatter(ax=ax, x_units=x_units, y_units=y_units)
def multi_line(self,
x,
y,
label=None,
df=None,
linecolor=None,
linestyle=None,
bbox=(1.2, 0.9),
x_units="f",
x_ticks=None,
y_units="f",
y_ticks=None,
marker_on=False,
plot_buffer=False,
axis_limits=False,
color_map="viridis",
ax=None):
"""
Documentation:
Description:
Create single plot with multiple lines. Capable of adjusting which axis will have the same
data for each line and which will have different data for each line.
---
Parameters:
x : array or string
Either 1-dimensional array of values, a multidimensional array of values, a list of columns
in a Pandas DataFrame, or a column name in a Pandas DataFrame.
y : array or string
Either 1-dimensional array of values, a multidimensional array of values, a list of columns
in a Pandas DataFrame, or a column name in a Pandas DataFrame.
label : list of strings : default=None
Custom legend label for each line.
df : Pandas DataFrame, default=None
Pandas DataFrame containing data to plot. Can be any size, as plotted columns will be chosen
by columns names specified in x and y parameters.
linecolor : str, default=None
Line colors. If None, utilizes color_map
linestyle : str, default=None
Line style.
bbox : tuple, default=(1.2, 0.9)
Coordinates for determining legend position.
x_units : str, default='d'
Determines unit of measurement for x-axis tick labels. 's' displays string. 'f' displays float.
'p' displays percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd') for
additional decimal places.
x_ticks : array, default=None
Custom x-tick labels.
y_units : str, default='d'
Determines unit of measurement for x-axis tick labels. 's' displays string. 'f' displays float.
'p' displays percentages, 'd' displays dollars. Repeat character (e.g 'ff' or 'ddd') for
additional decimal places.
y_ticks : array, default=None
Custom y-tick labels.
marker_on : bool, default=False
Controls whether to show line with markers for each data element.
plot_buffer : bool, default=False
Controls whether dynamic plot buffer function is executed to ensure visual elements are
not cut-off at the figure borders.
axis_limits : bool, default=False
Controls whether dynamic axis limit setting function is executed.
color_map : str specifying built-in matplotlib colormap, default="viridis"
Color map applied to plots.
ax : axes object, default=None
Axis object for the visualization.
"""
if ax is None:
ax = self.ax
# if a Pandas DataFrame is passed to function, create x and y arrays using columns names passed into function
if df is not None:
if isinstance(df.index, pd.core.indexes.base.Index):
x = df.index.values
else:
x = df[x].values
y = df[y].values
else:
# convert input list to array
x = np.array(x) if isinstance(x, list) else x
y = np.array(y) if isinstance(y, list) else y
x = x.reshape(-1, 1) if len(x.shape) == 1 else x
y = y.reshape(-1, 1) if len(y.shape) == 1 else y
# generate color list
color_list = style.color_gen(name=color_map, num=y.shape[1])
# add multiple lines to plot
for ix in np.arange(y.shape[1]):
y_col = y[:, ix]
plt.plot(
x,
y_col * 100 if "p" in y_units else y_col,
color=linecolor if linecolor is not None else color_list[ix],
linestyle=linestyle
if linestyle is not None else style.style_line_style[0],
linewidth=0.247 * self.chart_scale,
label=label[ix] if label is not None else None,
marker="." if marker_on else None,
markersize=17 if marker_on else None,
markerfacecolor="w" if marker_on else None,
markeredgewidth=2.2 if marker_on else None,
)
# add legend to figure
if label is not None:
plt.legend(
loc="upper right",
bbox_to_anchor=bbox,
ncol=1,
frameon=True,
fontsize=1.1 * self.chart_scale,
)
# optionally set axis lower / upper limits
if axis_limits:
x_min, x_max, y_min, y_max = util.util_set_axes(x=x, y=y)
plt.axis([x_min, x_max, y_min, y_max])
# optionally create smaller buffer around plot area to prevent cutting off elements
if plot_buffer:
util.util_plot_buffer(ax=ax, x=0.02, y=0.02)
# optionally creates custom x-tick labels
if x_ticks is not None:
ax.set_xticks(x_ticks)
# optionally creates custom y-tick labels
if y_ticks is not None:
ax.set_yticks(y_ticks)
# format x and y ticklabels
ax.set_yticklabels(
ax.get_yticklabels() * 100 if "p" in y_units else ax.get_yticklabels(),
rotation=0,
fontsize=1.1 * self.chart_scale,
color=style.style_grey,
)
ax.set_xticklabels(
ax.get_xticklabels() * 100 if "p" in y_units else ax.get_xticklabels(),
rotation=0,
fontsize=1.1 * self.chart_scale,
color=style.style_grey,
)
# axis tick label formatting
util.util_label_formatter(ax=ax, x_units=x_units, y_units=y_units)