src/collectors/python.d.plugin/pandas/pandas.conf
# netdata python.d.plugin configuration for pandas
#
# This file is in YaML format. Generally the format is:
#
# name: value
#
# There are 2 sections:
# - global variables
# - one or more JOBS
#
# JOBS allow you to collect values from multiple sources.
# Each source will have its own set of charts.
#
# JOB parameters have to be indented (using spaces only, example below).
# ----------------------------------------------------------------------
# Global Variables
# These variables set the defaults for all JOBs, however each JOB
# may define its own, overriding the defaults.
# update_every sets the default data collection frequency.
# If unset, the python.d.plugin default is used.
update_every: 5
# priority controls the order of charts at the netdata dashboard.
# Lower numbers move the charts towards the top of the page.
# If unset, the default for python.d.plugin is used.
# priority: 60000
# penalty indicates whether to apply penalty to update_every in case of failures.
# Penalty will increase every 5 failed updates in a row. Maximum penalty is 10 minutes.
# penalty: yes
# autodetection_retry sets the job re-check interval in seconds.
# The job is not deleted if check fails.
# Attempts to start the job are made once every autodetection_retry.
# This feature is disabled by default.
# autodetection_retry: 0
# ----------------------------------------------------------------------
# JOBS (data collection sources)
#
# The default JOBS share the same *name*. JOBS with the same name
# are mutually exclusive. Only one of them will be allowed running at
# any time. This allows autodetection to try several alternatives and
# pick the one that works.
#
# Any number of jobs is supported.
#
# All python.d.plugin JOBS (for all its modules) support a set of
# predefined parameters. These are:
#
# job_name:
# name: myname # the JOB's name as it will appear on the dashboard
# # dashboard (by default is the job_name)
# # JOBs sharing a name are mutually exclusive
# update_every: 1 # the JOB's data collection frequency
# priority: 60000 # the JOB's order on the dashboard
# penalty: yes # the JOB's penalty
# autodetection_retry: 0 # the JOB's re-check interval in seconds
#
# Additionally to the above, example also supports the following:
#
# chart_configs: [<dictionary>] # an array for chart config dictionaries.
#
# ----------------------------------------------------------------------
# AUTO-DETECTION JOBS
# Some example configurations, enable this collector, uncomment and example below and restart netdata to enable.
# example pulling some hourly temperature data, a chart for today forecast (mean,min,max) and another chart for current.
# temperature:
# name: "temperature"
# update_every: 5
# chart_configs:
# - name: "temperature_forecast_by_city"
# title: "Temperature By City - Today Forecast"
# family: "temperature.today"
# context: "pandas.temperature"
# type: "line"
# units: "Celsius"
# df_steps: >
# pd.DataFrame.from_dict(
# {city: requests.get(f'https://api.open-meteo.com/v1/forecast?latitude={lat}&longitude={lng}&hourly=temperature_2m').json()['hourly']['temperature_2m']
# for (city,lat,lng)
# in [
# ('dublin', 53.3441, -6.2675),
# ('athens', 37.9792, 23.7166),
# ('london', 51.5002, -0.1262),
# ('berlin', 52.5235, 13.4115),
# ('paris', 48.8567, 2.3510),
# ('madrid', 40.4167, -3.7033),
# ('new_york', 40.71, -74.01),
# ('los_angeles', 34.05, -118.24),
# ]
# }
# );
# df.describe(); # get aggregate stats for each city;
# df.transpose()[['mean', 'max', 'min']].reset_index(); # just take mean, min, max;
# df.rename(columns={'index':'city'}); # some column renaming;
# df.pivot(columns='city').mean().to_frame().reset_index(); # force to be one row per city;
# df.rename(columns={0:'degrees'}); # some column renaming;
# pd.concat([df, df['city']+'_'+df['level_0']], axis=1); # add new column combining city and summary measurement label;
# df.rename(columns={0:'measurement'}); # some column renaming;
# df[['measurement', 'degrees']].set_index('measurement'); # just take two columns we want;
# df.sort_index(); # sort by city name;
# df.transpose(); # transpose so its just one wide row;
# - name: "temperature_current_by_city"
# title: "Temperature By City - Current"
# family: "temperature.current"
# context: "pandas.temperature"
# type: "line"
# units: "Celsius"
# df_steps: >
# pd.DataFrame.from_dict(
# {city: requests.get(f'https://api.open-meteo.com/v1/forecast?latitude={lat}&longitude={lng}¤t_weather=true').json()['current_weather']
# for (city,lat,lng)
# in [
# ('dublin', 53.3441, -6.2675),
# ('athens', 37.9792, 23.7166),
# ('london', 51.5002, -0.1262),
# ('berlin', 52.5235, 13.4115),
# ('paris', 48.8567, 2.3510),
# ('madrid', 40.4167, -3.7033),
# ('new_york', 40.71, -74.01),
# ('los_angeles', 34.05, -118.24),
# ]
# }
# );
# df.transpose();
# df[['temperature']];
# df.transpose();
# example showing a read_csv from a url and some light pandas data wrangling.
# pull data in csv format from london demo server and then ratio of user cpus over system cpu averaged over last 60 seconds.
# example_csv:
# name: "example_csv"
# update_every: 2
# chart_configs:
# - name: "london_system_cpu"
# title: "London System CPU - Ratios"
# family: "london_system_cpu"
# context: "pandas"
# type: "line"
# units: "n"
# df_steps: >
# pd.read_csv('https://london.my-netdata.io/api/v1/data?chart=system.cpu&format=csv&after=-60', storage_options={'User-Agent': 'netdata'});
# df.drop('time', axis=1);
# df.mean().to_frame().transpose();
# df.apply(lambda row: (row.user / row.system), axis = 1).to_frame();
# df.rename(columns={0:'average_user_system_ratio'});
# df*100;
# example showing a read_json from a url and some light pandas data wrangling.
# pull data in json format (using requests.get() if json data is too complex for pd.read_json() ) from london demo server and work out 'total_bandwidth'.
# example_json:
# name: "example_json"
# update_every: 2
# chart_configs:
# - name: "london_system_net"
# title: "London System Net - Total Bandwidth"
# family: "london_system_net"
# context: "pandas"
# type: "area"
# units: "kilobits/s"
# df_steps: >
# pd.DataFrame(requests.get('https://london.my-netdata.io/api/v1/data?chart=system.net&format=json&after=-1').json()['data'], columns=requests.get('https://london.my-netdata.io/api/v1/data?chart=system.net&format=json&after=-1').json()['labels']);
# df.drop('time', axis=1);
# abs(df);
# df.sum(axis=1).to_frame();
# df.rename(columns={0:'total_bandwidth'});
# example showing a read_xml from a url and some light pandas data wrangling.
# pull weather forecast data in xml format, use xpath to pull out temperature forecast.
# example_xml:
# name: "example_xml"
# update_every: 2
# line_sep: "|"
# chart_configs:
# - name: "temperature_forcast"
# title: "Temperature Forecast"
# family: "temp"
# context: "pandas.temp"
# type: "line"
# units: "celsius"
# df_steps: >
# pd.read_xml('http://metwdb-openaccess.ichec.ie/metno-wdb2ts/locationforecast?lat=54.7210798611;long=-8.7237392806', xpath='./product/time[1]/location/temperature', parser='etree')|
# df.rename(columns={'value': 'dublin'})|
# df[['dublin']]|
# example showing a read_sql from a postgres database using sqlalchemy.
# note: example assumes a running postgress db on localhost with a netdata users and password netdata.
# sql:
# name: "sql"
# update_every: 5
# chart_configs:
# - name: "sql"
# title: "SQL Example"
# family: "sql.example"
# context: "example"
# type: "line"
# units: "percent"
# df_steps: >
# pd.read_sql_query(
# sql='\
# select \
# random()*100 as metric_1, \
# random()*100 as metric_2 \
# ',
# con=create_engine('postgresql://localhost/postgres?user=netdata&password=netdata')
# );