plugin_name: python.d.plugin
modules:
  - meta:
      plugin_name: python.d.plugin
      module_name: pandas
      monitored_instance:
        name: Pandas
        link: https://pandas.pydata.org/
        categories:
          - data-collection.generic-data-collection
        icon_filename: pandas.png
      related_resources:
        integrations:
          list: []
      info_provided_to_referring_integrations:
        description: ""
      keywords:
        - pandas
        - python
      most_popular: false
    overview:
      data_collection:
        metrics_description: |
          [Pandas](https://pandas.pydata.org/) is a de-facto standard in reading and processing most types of structured data in Python.
          If you have metrics appearing in a CSV, JSON, XML, HTML, or [other supported format](https://pandas.pydata.org/docs/user_guide/io.html),
          either locally or via some HTTP endpoint, you can easily ingest and present those metrics in Netdata, by leveraging the Pandas collector.
          
          This collector can be used to collect pretty much anything that can be read by Pandas, and then processed by Pandas.
        method_description: |
          The collector uses [pandas](https://pandas.pydata.org/) to pull data and do pandas-based preprocessing, before feeding to Netdata.
      supported_platforms:
        include: []
        exclude: []
      multi_instance: true
      additional_permissions:
        description: ""
      default_behavior:
        auto_detection:
          description: ""
        limits:
          description: ""
        performance_impact:
          description: ""
    setup:
      prerequisites:
        list:
          - title: Python Requirements
            description: |
              This collector depends on some Python (Python 3 only) packages that can usually be installed via `pip` or `pip3`.
              
              ```bash
              sudo pip install pandas requests
              ```
              
              Note: If you would like to use [`pandas.read_sql`](https://pandas.pydata.org/docs/reference/api/pandas.read_sql.html) to query a database, you will need to install the below packages as well.
              
              ```bash
              sudo pip install 'sqlalchemy<2.0' psycopg2-binary
              ```
      configuration:
        file:
          name: python.d/pandas.conf
          description: ""
        options:
          description: |
            There are 2 sections:
            
            * Global variables
            * One or more JOBS that can define multiple different instances to monitor.
            
            The following options can be defined globally: priority, penalty, autodetection_retry, update_every, but can also be defined per JOB to override the global values.
            
            Additionally, the following collapsed table contains all the options that can be configured inside a JOB definition.
            
            Every configuration JOB starts with a `job_name` value which will appear in the dashboard, unless a `name` parameter is specified.
          folding:
            title: Config options
            enabled: true
          list:
            - name: chart_configs
              description: an array of chart configuration dictionaries
              default_value: "[]"
              required: true
            - name: chart_configs.name
              description: name of the chart to be displayed in the dashboard.
              default_value: None
              required: true
            - name: chart_configs.title
              description: title of the chart to be displayed in the dashboard.
              default_value: None
              required: true
            - name: chart_configs.family
              description: "[family](https://github.com/netdata/netdata/blob/master/docs/cloud/visualize/interact-new-charts.md#families) of the chart to be displayed in the dashboard."
              default_value: None
              required: true
            - name: chart_configs.context
              description: "[context](https://github.com/netdata/netdata/blob/master/docs/cloud/visualize/interact-new-charts.md#contexts) of the chart to be displayed in the dashboard."
              default_value: None
              required: true
            - name: chart_configs.type
              description: the type of the chart to be displayed in the dashboard.
              default_value: None
              required: true
            - name: chart_configs.units
              description: the units of the chart to be displayed in the dashboard.
              default_value: None
              required: true
            - name: chart_configs.df_steps
              description: a series of pandas operations (one per line) that each returns a dataframe.
              default_value: None
              required: true
            - name: update_every
              description: Sets the default data collection frequency.
              default_value: 5
              required: false
            - name: priority
              description: Controls the order of charts at the netdata dashboard.
              default_value: 60000
              required: false
            - name: autodetection_retry
              description: Sets the job re-check interval in seconds.
              default_value: 0
              required: false
            - name: penalty
              description: Indicates whether to apply penalty to update_every in case of failures.
              default_value: yes
              required: false
            - name: name
              description: Job name. This value will overwrite the `job_name` value. 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.
              default_value: ""
              required: false
        examples:
          folding:
            enabled: true
            title: Config
          list:
            - name: Temperature API Example
              folding:
                enabled: true
              description: example pulling some hourly temperature data, a chart for today forecast (mean,min,max) and another chart for current.
              config: |
                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}&current_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();
            - name: API CSV Example
              folding:
                enabled: true
              description: example showing a read_csv from a url and some light pandas data wrangling.
              config: |
                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;
            - name: API JSON Example
              folding:
                enabled: true
              description: example showing a read_json from a url and some light pandas data wrangling.
              config: |
                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'});
            - name: XML Example
              folding:
                enabled: true
              description: example showing a read_xml from a url and some light pandas data wrangling.
              config: |
                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']]|
            - name: SQL Example
              folding:
                enabled: true
              description: example showing a read_sql from a postgres database using sqlalchemy.
              config: |
                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')
                            );
    troubleshooting:
      problems:
        list: []
    alerts: []
    metrics:
      folding:
        title: Metrics
        enabled: false
      description: |
        This collector is expecting one row in the final pandas DataFrame. It is that first row that will be taken
        as the most recent values for each dimension on each chart using (`df.to_dict(orient='records')[0]`).
        See [pd.to_dict()](https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.to_dict.html)."
      availability: []
      scopes:
        - name: global
          description: |
            These metrics refer to the entire monitored application.
          labels: []
          metrics: []