def correlation_matrix(data: pd.DataFrame, vmin: int = -1) -> str:
"""Plot image of a matrix correlation.
Args:
data: The matrix correlation to plot.
vmin: Minimum value of value range.
Returns:
The resulting correlation matrix encoded as a string.
"""
fig_cor, axes_cor = plt.subplots()
cmap = config["plot"]["correlation"]["cmap"].get(str)
if vmin == 0:
cmap = get_cmap_half(cmap)
labels = data.columns
matrix_image = axes_cor.imshow(data,
vmin=vmin,
vmax=1,
interpolation="nearest",
cmap=cmap)
plt.colorbar(matrix_image)
axes_cor.set_xticks(
np.arange(0, data.shape[0],
float(data.shape[0]) / len(labels)))
axes_cor.set_yticks(
np.arange(0, data.shape[1],
float(data.shape[1]) / len(labels)))
font_size = get_correlation_font_size(len(labels))
axes_cor.set_xticklabels(labels, rotation=90, fontsize=font_size)
axes_cor.set_yticklabels(labels, fontsize=font_size)
plt.subplots_adjust(bottom=0.2)
return plot_360_n0sc0pe(plt)
def scatter_series(series, x_label="Width", y_label="Height") -> str:
"""
Examples:
>>> scatter_series(file_sizes, "Width", "Height")
Args:
series:
x_label:
y_label:
Returns:
"""
plt.xlabel(x_label)
plt.ylabel(y_label)
color = config["html"]["style"]["primary_color"].get(str)
if len(series) > 1000:
cmap = sns.light_palette(color, as_cmap=True)
plt.hexbin(*zip(*series.tolist()), cmap=cmap)
else:
plt.scatter(*zip(*series.tolist()), color=color)
return plot_360_n0sc0pe(plt)
def missing_heatmap(data: pd.DataFrame) -> str:
"""Generate missing values heatmap plot.
Args:
data: Pandas DataFrame to generate missing values heatmap plot from.
Returns:
The resulting missing values heatmap plot encoded as a string.
"""
height = 4
if len(data.columns) > 10:
height += int((len(data.columns) - 10) / 5)
height = min(height, 10)
font_size = get_font_size(data)
if len(data.columns) > 40:
font_size /= 1.4
labels = config["plot"]["missing"]["force_labels"].get(bool)
missingno.heatmap(
data,
figsize=(10, height),
fontsize=font_size,
cmap=config["plot"]["missing"]["cmap"].get(str),
labels=labels,
)
if len(data.columns) > 40:
plt.subplots_adjust(left=0.1, right=0.9, top=0.9, bottom=0.3)
else:
plt.subplots_adjust(left=0.2, right=0.9, top=0.8, bottom=0.3)
return plot_360_n0sc0pe(plt)
def make_pie_chart(series):
lab = series.value_counts().keys().tolist()
val = series.value_counts().values.tolist()
fig, ax = plt.subplots()
ax.pie(val, labels=lab, autopct='%1.1f%%', shadow=True, startangle=90)
ax.axis(
'equal') # Equal aspect ratio ensures that pie is drawn as a circle.
return plot_360_n0sc0pe(plt)
def scatter_pairwise(series1, series2, x_label, y_label) -> str:
plt.xlabel(x_label)
plt.ylabel(y_label)
color = config["html"]["style"]["primary_color"].get(str)
if len(series1) > 1000:
cmap = sns.light_palette(color, as_cmap=True)
plt.hexbin(series1.tolist(), series2.tolist(), gridsize=15, cmap=cmap)
else:
plt.scatter(series1.tolist(), series2.tolist(), color=color)
return plot_360_n0sc0pe(plt)
def scatter_complex(series) -> str:
plt.ylabel("Imaginary")
plt.xlabel("Real")
color = config["html"]["style"]["primary_color"].get(str)
if len(series) > 1000:
cmap = sns.light_palette(color, as_cmap=True)
plt.hexbin(series.real, series.imag, cmap=cmap)
else:
plt.scatter(series.real, series.imag, color=color)
return plot_360_n0sc0pe(plt)
def missing_dendrogram(data: pd.DataFrame) -> str:
"""Generate a dendrogram plot for missing values.
Args:
data: Pandas DataFrame to generate missing values dendrogram plot from.
Returns:
The resulting missing values dendrogram plot encoded as a string.
"""
missingno.dendrogram(data, fontsize=get_font_size(data) * 2.0)
plt.subplots_adjust(left=0.1, right=0.9, top=0.7, bottom=0.2)
return plot_360_n0sc0pe(plt)
def histogram(series: pd.Series, series_description: dict,
bins: Union[int, np.ndarray]) -> str:
"""Plot an histogram of the data.
Args:
series_description:
series: The data to plot.
bins: number of bins (int for equal size, ndarray for variable size)
Returns:
The resulting histogram encoded as a string.
"""
plot = _plot_histogram(series, series_description, bins)
plot.xaxis.set_tick_params(rotation=45)
plot.figure.tight_layout()
return plot_360_n0sc0pe(plt)
def missing_matrix(data: pd.DataFrame) -> str:
"""Generate missing values matrix plot
Args:
data: Pandas DataFrame to generate missing values matrix from.
Returns:
The resulting missing values matrix encoded as a string.
"""
labels = config["plot"]["missing"]["force_labels"].get(bool)
missingno.matrix(
data,
figsize=(10, 4),
color=hex_to_rgb(config["html"]["style"]["primary_color"].get(str)),
fontsize=get_font_size(data) / 20 * 16,
sparkline=False,
labels=labels,
)
plt.subplots_adjust(left=0.1, right=0.9, top=0.7, bottom=0.2)
return plot_360_n0sc0pe(plt)
def missing_bar(data: pd.DataFrame) -> str:
"""Generate missing values bar plot.
Args:
data: Pandas DataFrame to generate missing values bar plot from.
Returns:
The resulting missing values bar plot encoded as a string.
"""
labels = config["plot"]["missing"]["force_labels"].get(bool)
missingno.bar(
data,
figsize=(10, 5),
color=hex_to_rgb(config["html"]["style"]["primary_color"].get(str)),
fontsize=get_font_size(data),
labels=labels,
)
for ax0 in plt.gcf().get_axes():
ax0.grid(False)
plt.subplots_adjust(left=0.1, right=0.9, top=0.8, bottom=0.3)
return plot_360_n0sc0pe(plt)
def mini_histogram(series: pd.Series, series_description: dict,
bins: Union[int, np.ndarray]) -> str:
"""Plot a small (mini) histogram of the data.
Args:
series_description:
series: The data to plot.
bins: number of bins (int for equal size, ndarray for variable size)
Returns:
The resulting mini histogram encoded as a string.
"""
plot = _plot_histogram(series, series_description, bins, figsize=(2, 1.5))
plot.axes.get_yaxis().set_visible(False)
plot.set_facecolor("w")
xticks = plot.xaxis.get_major_ticks()
for tick in xticks:
tick.label1.set_fontsize(8)
plot.xaxis.set_tick_params(rotation=45)
plot.figure.tight_layout()
return plot_360_n0sc0pe(plt)
