def plot_scatter_line(
t: Tuple[pd.Series, pd.Series, int, int, str, str, str, int, bool]
) -> NoReturn:
X, y, file_name, target, feature, number_knots, dates = t
model = ds.natural_cubic_spline(X=X, y=y, number_knots=number_knots)
if dates:
XX = X.astype(dtype='datetime64[ns]')
else:
XX = X
fig, ax = ds.plot_scatter_line_x_y1_y2(
X=XX,
y1=y,
y2=model.predict(X),
figsize=figsize,
labellegendy2=f'number knots = {number_knots}')
ax.legend(frameon=False, loc='best')
ax.set_title(label=f'{axis_title}\n'
f'file: {file_name} '
f'column: {target}')
ax.set_xlabel(xlabel=x_axis_label)
ax.set_ylabel(ylabel=y_axis_label)
ds.despine(ax=ax)
fig.savefig(
f'{graphics_directory}'
f'/spline_'
f'{file_name.strip(".csv")}_'
f'{target}_{feature}_'
f'{number_knots}.svg',
format='svg')
def plot_recent_activity(activity: Optional[pd.DataFrame] = None) -> None:
"""
Line plot of number commits versus date.
Parameters
----------
activity : pd.DataFrame
"""
figsize = (12, 6)
title = 'Daily commits'
y_label = 'Number of commits'
x_label = 'Date'
if activity is None:
activity = recent_activity()
commits = activity.reset_index().groupby('date').agg('sum')
commits['low'] = commits['commits'].where(commits['commits'].between(0, 0))
fig, ax = ds.plot_line_x_y(X=commits.index,
y=commits['commits'],
figsize=figsize)
ax.plot(commits['low'], marker='x', color='#cc3311')
ax.xaxis.set_major_formatter(mdates.DateFormatter('%m-%d'))
ax.set_ylabel(ylabel=y_label, fontweight='bold')
ax.set_xlabel(xlabel=x_label, fontweight='bold')
ax.set_title(label=title, fontweight='bold')
median_value = commits['commits'].median()
ax.axhline(y=median_value, color='#33bbee', label=int(median_value))
ax.legend(frameon=False)
ds.despine(ax)
fig.savefig(fname='commits_daily.svg', format='svg')
ds.html_figure(file_name="commits_daily.svg")
print(f'Commits by date\n{commits}\n')
print(f"Median commits: {median_value.astype(dtype='int')}\n")
print(f"Commits by ascending value\n{commits.sort_values(by='commits')}\n")
print(f"Median commits: {median_value.astype(dtype='int')}")
def plot_scatter_y(t: pd.Series) -> None:
y, feature = t
fig, ax = ds.plot_scatter_y(y=y, figsize=figsize)
ax.set_ylabel(ylabel=feature)
ax.set_title(label='Time Series')
ds.despine(ax)
fig.savefig(fname=f'time_series_{feature}.svg', format='svg')
ds.html_figure(file_name=f'time_series_{feature}.svg',
caption=f'time_series_{feature}.svg')
def plot_graph(df: pd.DataFrame, columnx: str, columny: str, columnz: str,
figsize: Tuple[int, int], dateformat: str, graphname: str,
graphtitle: str, xaxislabel: str, yaxislabel: str) -> NoReturn:
fig, ax = ds.plot_line_x_y(X=df[columnx], y=df[columnz], figsize=figsize)
if dateformat:
ax.xaxis.set_major_locator(DayLocator())
ax.xaxis.set_minor_locator(NullLocator())
ax.xaxis.set_major_formatter(DateFormatter(dateformat))
ax.xaxis.set_minor_formatter(NullFormatter())
ax.set_xlabel(xlabel=xaxislabel)
ax.set_ylabel(ylabel=yaxislabel)
ax.set_title(label=graphtitle)
ds.despine(ax=ax)
fig.savefig(fname=f'{graphname}.svg', format='svg')
def main():
start_time = time.time()
global figsize, date_time_parser
file_names, graph_file_names, abscissa_names, ordinate_names,\
ordinate_predicted_names, x_axis_label, y_axis_label, axis_title,\
figsize, column_names_sort, date_time_parser,\
date_formatter, alpha_value, function, output_url,\
header_title, header_id, parser = parameters()
original_stdout = ds.html_begin(output_url=output_url,
header_title=header_title,
header_id=header_id)
print('<pre style="white-space: pre-wrap;">')
for (file_name, abscissa_name, ordinate_name, ordinate_predicted_name,
date_time_parser, column_names_sort, date_formatter,
graph_file_name) in zip(file_names, abscissa_names, ordinate_names,
ordinate_predicted_names, date_time_parser,
column_names_sort, date_formatter,
graph_file_names):
if date_time_parser == 'None':
data = ds.read_file(file_name=file_name,
sort_columns=column_names_sort,
sort_columns_bool=True)
else:
data = ds.read_file(file_name=file_name,
parse_dates=[abscissa_name],
sort_columns=column_names_sort,
sort_columns_bool=True)
data[ordinate_predicted_name] = data[ordinate_name]\
.ewm(alpha=alpha_value).mean()
fig, ax = ds.plot_scatter_line_x_y1_y2(
X=data[abscissa_name],
y1=data[ordinate_name],
y2=data[ordinate_predicted_name],
figsize=figsize)
ax.set_title(label=axis_title, fontweight='bold')
ax.set_xlabel(xlabel=x_axis_label, fontweight='bold')
ax.set_ylabel(ylabel=y_axis_label, fontweight='bold')
ds.despine(ax=ax)
fig.savefig(fname=f'{graph_file_name}.svg', format='svg')
ds.html_figure(file_name=f'{graph_file_name}.svg')
ds.page_break()
stop_time = time.time()
ds.report_summary(start_time=start_time,
stop_time=stop_time,
read_file_names=file_names,
targets=ordinate_names,
features=abscissa_names)
print('</pre>')
ds.html_end(original_stdout=original_stdout, output_url=output_url)
def main():
invoicing = pd.read_csv(data_file_name, parse_dates=[date_column])
invoicing = calculate_cycle_time(df=invoicing,
date_column=date_column,
invoice_start_column=invoice_start_column,
invoice_send_column=invoice_send_column,
total_time_column=total_time_column)
fig, ax = ds.plot_line_x_y(X=invoicing[date_column],
y=invoicing[total_time_column])
ds.despine(ax)
fig.suptitle(t=fig_title)
ax.set_title(label=ax_title)
ax.set_ylabel(ylabel=ylabel)
ax.set_xlabel(xlabel=date_column)
fig.savefig(fname='invoice_cycle_time.svg', format='svg')
print('Mean squared error')
print(mse.round(3))
print()
print('Root mean squared error')
print(round(math.sqrt(mse), 3))
ds.page_break()
# Scatter plot of predicted versus measured
fig, ax = ds.plot_scatter_x_y(X=y_all, y=predicted, figsize=figsize)
ax.plot([y_all.min(), y_all.max()], [y_all.min(), y_all.max()],
marker=None,
linestyle='-',
color=colour2)
ax.set_ylabel(ylabel=label_predicted)
ax.set_xlabel(xlabel=label_measured)
ax.set_title(label=title)
ds.despine(ax)
fig.savefig(fname=f'{graph_name}_scatter.svg', format='svg')
ds.html_figure(file_name=f'{graph_name}_scatter.svg',
caption=f'{graph_name}_scatter.svg')
# Line plot of predicted versus measured
fig, ax = ds.plot_line_line_y1_y2(y1=y_all,
y2=predicted,
figsize=figsize,
labellegendy1=label_measured,
labellegendy2=label_predicted)
ax.legend(frameon=False)
ax.set_title(label=title)
ds.despine(ax)
fig.savefig(fname=f'{graph_name}_lines.svg', format='svg')
ds.html_figure(file_name=f'{graph_name}_lines.svg',
caption=f'{graph_name}_lines.svg')
def main():
data_pumps = {
'x':
[8.7, 11, 13.4, 14.9, 8.7, 8.9, 12.6, 10.7, 13.5, 16.4, 18.9, 16, 9],
'y':
[17.9, 18.5, 17.4, 17.8, 14.9, 12.8, 11.7, 7.4, 8, 9.3, 9.7, 5, 5.1]
}
data_deaths = {
'x': [
13.6, 9.9, 14.7, 15.2, 13.2, 13.8, 13.1, 11, 15.2, 11.1, 11.7,
12.3, 10.6, 14.6, 16.6, 9.5, 13.3, 15, 15.1, 10.9, 12.5, 11.8,
12.2, 13.9, 12.3, 11, 11, 13.5, 10.8, 12.2, 13.9, 12.5, 15.7, 12.9,
13, 13.7, 13.1, 13.4, 14.8, 13.2, 9.8, 12.5, 13.4, 14.4, 16, 10.9,
12.5, 15.8, 16.5, 11.2, 15.8, 11, 11.7, 11.5, 11.8, 13, 14.1, 14.8,
12.6, 14.6, 12.5, 14.5, 9.2, 17.9, 11.2, 9.5, 10.8, 16.1, 10.4,
13.7, 15.8, 12.2, 11.5, 15.4, 15.9, 10.2, 14, 16.5, 17.5, 13.8,
14.1, 14.7, 12.6, 11.7, 14.4, 15.2, 15.8, 13.9, 15.2, 13.2, 12.7,
15.1, 12.8, 13.6, 14, 15.4, 14.8, 10.3, 10.5, 9.9, 14.2, 13.6, 15,
15.7, 9.2, 16.8, 13.3, 10.6, 8.3, 13.4, 14.5, 16.8, 14.7, 10.3,
13.2, 9.1, 15.2, 8.4, 15.3, 13.3, 13.2, 12.6, 13.9, 13.5, 15.2,
11.6, 9.4, 11.4, 11.2, 11.9, 15, 13.6, 14.1, 10.5, 10.3, 13.8,
13.4, 12.6, 15.7, 13.8, 13.2, 15.1, 13.2, 14.6, 14.4, 15, 13.1,
13.4, 11.8, 16, 10.6, 14.6, 9.3, 14.5, 10.5, 14, 10.6, 10.6, 15.7,
11.8, 11.8, 11.6, 15.8, 10.7, 13.4, 11.2, 15.5, 14, 13.4, 14.6,
15.3, 14.5, 11.4, 12.5, 13.8, 10.6, 10.5, 14.8, 14.2, 13.3, 10.4,
12.5, 15, 10.6, 13.1, 10.1, 11.2, 12.9, 12.2, 12.4, 11.9, 11.5,
11.7, 12.5, 14.8, 14, 12.5, 9.2, 10.4, 12.7, 9.1, 8.3, 15.3, 11.2,
11.8, 12.7, 11.8, 12.2, 12.7, 13.6, 8.8, 12.2, 16.2, 12.8, 13.6,
12.7, 15, 13.9, 13.6, 12.5, 9.9, 17.6, 11.1, 16.7, 9.7, 13.4, 13.1,
13.7, 11.7, 13.1, 13.1, 12.3, 14.9, 11.5, 12.9, 11, 15.8, 12.9,
12.3, 9.8, 12.7, 12.7, 16, 11, 14.1, 11, 14.5, 15.6, 9.6, 15.5,
14.4, 11.4, 13.7, 11.4, 16, 9.9, 10.8, 12.6, 9.3, 13.8, 13.8, 14.7,
15.3, 14.1, 13.8, 11, 12.4, 14.8, 15, 15.4, 12.8, 11.3, 10.5, 11,
13.4, 10.3, 9.6, 14.5, 11.5, 12.7, 15, 12.3, 12.9, 15.3, 15.8,
13.1, 12.9, 15.3, 13, 12.5, 15.8, 14, 13, 13.9, 10.9, 16, 15.1,
13.5, 11.6, 10.7, 16.8, 13.9, 13.7, 13.3, 15.7, 15.5, 11, 15.5,
11.7, 12.4, 11.1, 9.6, 8.3, 14, 13.2, 15.3, 15.5, 15.4, 16.1, 12.4,
12.2, 15.1, 14, 9.6, 16.3, 12.6, 10.5, 14, 15.5, 11, 13.3, 13.9,
13.3, 12.7, 15.4, 15.7, 13.8, 11.7, 16.1, 12.6, 15.4, 16.3, 12.5,
15.7, 11.5, 14.2, 16.3, 13.6, 12.6, 11.7, 8.8, 10.9, 11.6, 13,
13.7, 11.1, 14.6, 10.4, 13.1, 11.9, 13.3, 9.9, 12.7, 9.3, 11.6,
13.1, 11.4, 13.6, 11.8, 16.3, 8.7, 15.7, 12.2, 14.8, 13.5, 15.7,
11.9, 12.5, 14.4, 12.2, 15.3, 11.5, 9, 10.8, 14.9, 13.2, 13.4,
14.4, 12.2, 12, 13.6, 8.8, 13.4, 12.6, 15.6, 12.5, 12.4, 12.4,
13.4, 12, 9.9, 12.1, 14.4, 15.7, 13.8, 11.4, 13.8, 15.6, 15, 14.1,
13.2, 13.3, 10.9, 12.1, 14, 11.3, 13.4, 13.5, 14.8, 13, 12.4, 12.3,
13.1, 14.8, 9.8, 14.1, 12, 16.1, 12.7, 14.7, 8.8, 10.5, 12.2, 11.7,
8.3, 12.4, 16.7, 15.7, 16.1, 14.3, 9.7, 13.3, 16.1, 14.4, 13.4,
14.5, 14.6, 13.7, 16.2, 16.3, 12.8, 13.4, 11.2, 11.6, 14.7, 9.4,
9.5, 15.7, 14.3, 14.2, 11.5, 15, 13.1, 11, 11.9, 13.5, 14.1, 10.9,
14.2, 10.4, 15.6, 11.3, 13, 13.6, 11.1, 14.6, 15.2, 13.4, 16.1,
14.3, 16.4, 12.6, 13.3, 11, 10.1, 15.6, 14.2, 13.4, 10.8, 13.2,
13.8, 11.4, 12.9, 13.6, 13.3, 12.2, 14.4, 8.9, 15.5, 14.3, 10,
13.2, 10.5, 9.5, 10.4, 10.9, 13.3, 12.6, 13.1, 11.6, 13.6, 13.4,
13.7, 10.7, 12.2, 14, 14.8, 15.1, 16.2, 15.3, 12.5, 14.7, 12.5,
10.9, 15.7, 11.7, 9.5, 13.3, 13.6, 13.4, 13.5, 11.1, 12.9, 12.8,
15.3, 12.8, 9.2, 14.4, 15.6, 10.4, 13, 13.2, 11, 13.5, 9.6, 14.5,
12.5, 10.7, 13.3, 9.4, 13.4, 13.5, 13.5, 13.6, 14.3, 9.6, 14.1,
12.9, 15.4, 13.8, 11.4, 12.4, 12.7, 13.6, 14.1, 15.1, 15.3, 14.7,
13.4, 12.3, 14.3, 12.4, 12.1, 12.4, 15.1, 17.3, 12.4, 15
],
'y': [
11.1, 12.6, 10.2, 10, 13, 8.9, 10.6, 11.9, 11.7, 9.6, 13.6, 11.5,
11.9, 10.6, 14.3, 10.7, 10.7, 10.2, 10, 9.8, 12, 11.8, 10.4, 12.8,
11.9, 11.9, 9.8, 13.3, 11.7, 13.6, 14, 11.6, 12.7, 9.9, 10.2, 11.4,
11.1, 11.1, 9.4, 13.2, 12.5, 12, 10.2, 11.6, 14.2, 12, 13.4, 12.4,
14.3, 8.6, 12.2, 9.8, 13.6, 12.3, 15.1, 13.9, 13.1, 10, 11, 12.9,
11.2, 8.7, 10.8, 7.2, 14.7, 10.7, 9.9, 14.1, 10.6, 9, 13.9, 11.8,
10.7, 11.2, 12.2, 11.9, 12.8, 11.4, 11.2, 8.9, 10.6, 11.5, 13.4,
10.4, 12.6, 17, 13.9, 12.7, 11.6, 12.9, 11.3, 13.2, 11.6, 13.2,
13.1, 13.3, 14.9, 11.4, 11.6, 12.3, 9.2, 12.5, 9.8, 12.4, 12, 11.4,
10.3, 11.6, 7.2, 13, 8.7, 11.4, 11.9, 11.4, 11.2, 13.2, 10, 7.4,
9.8, 12.4, 9.7, 11.5, 11, 12.5, 17, 11.1, 10.8, 9.6, 14.8, 10.2,
10.2, 11.5, 13.6, 11.2, 9.5, 12.7, 12.4, 11, 13.9, 8.9, 12.3, 10.1,
10.5, 11.4, 10.3, 14.1, 10.6, 8.8, 9.5, 14.4, 10.9, 10.6, 12.2,
11.5, 12.3, 12.8, 11.6, 11.7, 6.1, 11.2, 10.3, 11.1, 14, 11.7,
13.3, 11.5, 12.8, 10.7, 12.5, 16.2, 13.4, 8.8, 9.9, 11.2, 11.2, 11,
11, 10.8, 12, 12, 11.8, 10.6, 12, 9.9, 11.1, 11.5, 11.4, 11.7, 10,
11.3, 10.2, 11.4, 13.6, 11.5, 12.3, 12.7, 13.4, 12.3, 11.3, 9.2,
6.3, 7.1, 13.6, 11.4, 11.2, 11.3, 11.2, 13.6, 11.3, 13.4, 15.1,
11.3, 14.3, 11.6, 13.4, 10.2, 11.9, 12.7, 9.1, 13, 12.4, 7.3, 11.1,
14.4, 11, 13, 10.6, 10.1, 11.1, 11.8, 11.8, 11.9, 12.8, 12.6, 11.6,
11.2, 14, 10.3, 11.5, 11.8, 11.3, 12.1, 9.2, 11.9, 9.3, 11.7, 8.7,
11.3, 11.8, 11.1, 12.2, 9.9, 11.3, 11, 9.1, 11.9, 9.7, 11.6, 10.7,
13.8, 13.8, 10, 10, 12.4, 10.1, 11.3, 10.5, 10, 13.6, 13.5, 14.3,
9.8, 11.8, 11.2, 9.5, 11.4, 11.8, 12.3, 11.4, 10.7, 12, 14.8, 10.8,
9.1, 9.6, 13.9, 11.7, 12.1, 11.8, 11.2, 13, 13.4, 14.4, 14.6, 9.7,
14, 10.1, 12.6, 12.3, 12, 11.6, 14.6, 11.1, 9.6, 12.4, 11.2, 11.2,
11.1, 9.6, 11.4, 11.5, 10.9, 7.2, 13.3, 13, 9.3, 11.2, 7.3, 14.3,
13.7, 11.8, 11.7, 12.9, 10.9, 14.3, 10.6, 12.9, 12.8, 11.3, 11.2,
12.9, 13.6, 9.6, 10.7, 11.2, 13.9, 11.1, 10.5, 14.3, 11, 11.3,
14.4, 12.1, 12.9, 12.6, 12.1, 10.1, 11.2, 10.4, 11.2, 10.9, 14.7,
11.1, 11.2, 11.3, 11.8, 12.3, 11.6, 12.3, 14.2, 10.3, 12.2, 12.8,
10.6, 9.5, 12.3, 11, 11.5, 13.6, 14.4, 12.1, 12.2, 11.4, 14.1, 8.9,
12.9, 14.2, 12.8, 13.1, 14.1, 11.4, 10.8, 11.2, 8.8, 10.1, 11.9,
8.8, 12, 11.4, 14.6, 11.6, 12, 11, 12.8, 14.2, 12, 11.3, 11.4,
12.6, 11.4, 11.8, 13.6, 13.1, 12.9, 11.1, 10.9, 14.2, 11.3, 10.2,
13.1, 9.8, 13, 12, 10, 13.9, 10.8, 13, 12.5, 12, 11, 11.3, 14.8,
12.4, 13.2, 12.5, 10.6, 14.6, 14.2, 11.3, 10.1, 12.1, 12.3, 14.2,
13.6, 11.6, 13.2, 8.4, 7.2, 14.3, 10.5, 12.4, 12.9, 10, 10.4, 10.9,
9, 11.4, 13.9, 14.2, 14.4, 14.3, 11.9, 8.6, 12.2, 11.9, 10.8, 10.7,
11.6, 12.5, 13.4, 10.4, 10.4, 12.4, 12, 14.2, 8.9, 13.1, 16.5, 9.4,
11.2, 11.3, 11.5, 9.6, 13.1, 11.6, 11.4, 8.6, 10.4, 10.9, 10.4,
14.4, 15, 10.8, 12.1, 10.6, 12.6, 13.4, 12.5, 11.6, 10.6, 12.6, 11,
9.8, 11.1, 14.3, 11.4, 10.3, 12.1, 14.2, 10.4, 11.3, 14.3, 12.5,
10.6, 11.2, 14.6, 11, 11, 14.2, 10.5, 10.1, 13.1, 11.1, 12.5, 14.1,
13.3, 9.2, 10.1, 9.9, 11.4, 11.1, 11.4, 11.1, 14.7, 12.9, 12.6,
11.5, 14.8, 15.3, 10.3, 12.5, 11.1, 10.9, 16, 9.8, 11.3, 11.1, 12,
10.9, 11.2, 10.7, 11.9, 9.7, 11, 10.6, 10.6, 11.1, 12.5, 12.9, 11,
11.9, 11.1, 11, 9.1, 15.6, 10.6, 15.5, 13.8, 13.8, 12.7, 9.9, 11.4,
11.3, 11.5, 13.1, 10.1, 13.6, 10.2, 12.5, 11.9, 10.4, 11.6, 10.3,
11.5, 10.2, 11.6, 11.9, 12.5
]
}
x_axis_label = 'X distance from lower left datum of map (m)'
y_axis_label = 'Y distance from lower left datum of map (m)'
axis_title = 'Broad Street Cholera Outbreak of 1854'
file_graph = 'broad_street_cholera_outbreak.svg'
output_url = 'broad_street_cholera.html'
header_title = 'broad_street_cholera'
header_id = 'broad-street-cholera'
axis_subtitle = 'Soho, London, UK'
legend1 = 'Deaths'
legend2 = 'Pumps'
figsize = (8, 6)
ds.style_graph()
original_stdout = ds.html_begin(output_url=output_url,
header_title=header_title,
header_id=header_id)
deaths = pd.DataFrame(data=data_deaths)
pumps = pd.DataFrame(data=data_pumps)
fig, ax = ds.plot_scatter_scatter_x1_x2_y1_y2(X1=deaths['x'],
X2=pumps['x'],
y1=deaths['y'],
y2=pumps['y'],
figsize=figsize,
markersize1=3,
labellegendy2=legend2,
colour1=colour1,
colour2=colour2,
markersize2=3,
labellegendy1=legend1)
ax.set_title(label=axis_title + '\n' + axis_subtitle)
ax.set_ylabel(ylabel=y_axis_label)
ax.set_xlabel(xlabel=x_axis_label)
ax.legend(frameon=False)
ds.despine(ax=ax)
fig.savefig(fname=file_graph, format='svg')
ds.html_figure(file_name=file_graph)
ds.html_end(original_stdout=original_stdout, output_url=output_url)