def plot_cdf(self, graphing_library='matplotlib'):
"""
plot CDF for important sub-metrics
"""
graphed = False
for percentile_csv in self.percentiles_files:
csv_filename = os.path.basename(percentile_csv)
# The last element is .csv, don't need that in the name of the chart
column = self.csv_column_map[percentile_csv.replace(".percentiles.", ".")]
if not self.check_important_sub_metrics(column):
continue
column = naarad.utils.sanitize_string(column)
graph_title = '.'.join(csv_filename.split('.')[0:-1])
if self.sub_metric_description and column in self.sub_metric_description.keys():
graph_title += ' (' + self.sub_metric_description[column] + ')'
if self.sub_metric_unit and column in self.sub_metric_unit.keys():
plot_data = [PD(input_csv=percentile_csv, csv_column=1, series_name=graph_title, x_label='Percentiles',
y_label=column + ' (' + self.sub_metric_unit[column] + ')', precision=None, graph_height=600, graph_width=1200, graph_type='line')]
else:
plot_data = [PD(input_csv=percentile_csv, csv_column=1, series_name=graph_title, x_label='Percentiles', y_label=column, precision=None,
graph_height=600, graph_width=1200, graph_type='line')]
graphed, div_file = Metric.graphing_modules[graphing_library].graph_data_on_the_same_graph(plot_data, self.resource_directory,
self.resource_path, graph_title)
if graphed:
self.plot_files.append(div_file)
return True
def plot_timeseries(self, graphing_library='matplotlib'):
"""
plot timeseries for sub-metrics
"""
if self.groupby:
plot_data = {}
# plot time series data for submetrics
for out_csv in sorted(self.csv_files, reverse=True):
csv_filename = os.path.basename(out_csv)
transaction_name = ".".join(csv_filename.split('.')[1:-1])
if transaction_name in self.anomalies.keys():
highlight_regions = self.anomalies[transaction_name]
else:
highlight_regions = None
# The last element is .csv, don't need that in the name of the chart
column = csv_filename.split('.')[-2]
transaction_name = ' '.join(csv_filename.split('.')[1:-2])
plot = PD(input_csv=out_csv, csv_column=1, series_name=transaction_name + '.' + column,
y_label=column + ' (' + self.sub_metric_description[column] + ')', precision=None, graph_height=500, graph_width=1200, graph_type='line',
highlight_regions=highlight_regions)
if transaction_name in plot_data:
plot_data[transaction_name].append(plot)
else:
plot_data[transaction_name] = [plot]
for transaction in plot_data:
graphed, div_file = Metric.graphing_modules[graphing_library].graph_data(plot_data[transaction], self.resource_directory, self.resource_path,
self.label + '.' + transaction)
if graphed:
self.plot_files.append(div_file)
else:
graphed = False
for out_csv in self.csv_files:
csv_filename = os.path.basename(out_csv)
transaction_name = ".".join(csv_filename.split('.')[1:-1])
if transaction_name in self.anomalies.keys():
highlight_regions = self.anomalies[transaction_name]
else:
highlight_regions = None
# The last element is .csv, don't need that in the name of the chart
column = self.csv_column_map[out_csv]
column = naarad.utils.sanitize_string(column)
graph_title = '.'.join(csv_filename.split('.')[0:-1])
if self.sub_metric_description and column in self.sub_metric_description.keys():
graph_title += ' (' + self.sub_metric_description[column] + ')'
if self.sub_metric_unit and column in self.sub_metric_unit.keys():
plot_data = [PD(input_csv=out_csv, csv_column=1, series_name=graph_title, y_label=column + ' (' + self.sub_metric_unit[column] + ')',
precision=None, graph_height=600, graph_width=1200, graph_type='line', highlight_regions=highlight_regions)]
else:
plot_data = [PD(input_csv=out_csv, csv_column=1, series_name=graph_title, y_label=column, precision=None, graph_height=600, graph_width=1200,
graph_type='line', highlight_regions=highlight_regions)]
graphed, div_file = Metric.graphing_modules[graphing_library].graph_data(plot_data, self.resource_directory, self.resource_path, graph_title)
if graphed:
self.plot_files.append(div_file)
return True
def plot_timeseries(self, graphing_library='matplotlib'):
if graphing_library != 'matplotlib':
return Metric.plot_timeseries(self, graphing_library)
else:
logger.info(
'Using graphing_library {lib} for metric {name}'.format(
lib=graphing_library, name=self.label))
plot_data = {}
# plot time series data for submetrics
for out_csv in sorted(self.csv_files, reverse=True):
csv_filename = os.path.basename(out_csv)
# The last element is .csv, don't need that in the name of the chart
column = csv_filename.split('.')[-2]
transaction_name = ' '.join(csv_filename.split('.')[1:-2])
plot = PD(input_csv=out_csv,
csv_column=1,
series_name=transaction_name,
y_label=self.sub_metric_description[column] + ' (' +
self.sub_metric_units[column] + ')',
precision=None,
graph_height=500,
graph_width=1200,
graph_type='line')
if transaction_name in plot_data:
plot_data[transaction_name].append(plot)
else:
plot_data[transaction_name] = [plot]
for transaction in plot_data:
graphed, div_file = Metric.graphing_modules[
graphing_library].graph_data(
plot_data[transaction], self.resource_directory,
self.resource_path, self.label + '.' + transaction)
if graphed:
self.plot_files.append(div_file)
return True
def plot_diff(self, graphing_library = 'matplotlib'):
"""
Generate CDF diff plots of the submetrics
"""
diff_datasource = sorted(set(self.reports[0].datasource) & set(self.reports[1].datasource))
graphed = False
for submetric in diff_datasource:
baseline_csv = naarad.utils.get_default_csv(self.reports[0].local_location, (submetric+'.percentiles'))
current_csv = naarad.utils.get_default_csv(self.reports[1].local_location, (submetric+'.percentiles'))
if ((naarad.utils.is_valid_file(baseline_csv) & naarad.utils.is_valid_file(current_csv)) == False):
continue
baseline_plot = PD(input_csv=baseline_csv, csv_column=1, series_name=submetric, y_label=submetric, precision=None, graph_height=600, graph_width=1200, graph_type='line', plot_label='baseline', x_label='Percentiles')
current_plot = PD(input_csv=current_csv, csv_column=1, series_name=submetric, y_label=submetric, precision=None, graph_height=600, graph_width=1200, graph_type='line', plot_label='current', x_label='Percentiles')
graphed, div_file = Diff.graphing_modules[graphing_library].graph_data_on_the_same_graph([baseline_plot, current_plot], os.path.join(self.output_directory, self.resource_path), self.resource_path, (submetric+'.diff'))
if graphed:
self.plot_files.append(div_file)
return True