🕷️ Crawler Inspector

URL Lookup

Direct Parameter Lookup

Raw Queries and Responses

1. Shard Calculation

Query:

Response:

Calculated Shard: 169 (from laksa014)

2. Crawled Status Check

Query:

curl -X POST \
  'http://laksa169.int.ahrefs:8124/' \
  -H 'Content-Type: text/plain' \
  -H 'X-ClickHouse-Database: crawler3' \
  -H 'Authorization: Basic YXBpOg==' \
  -d 'SELECT getAhrefsURLFromUnparsed(src_unparsed) AS found_url, ifNull(toUnixTimestamp(download_stamp), 0) AS crawl_time, ifNull(toUnixTimestamp(props_url_first_seen), 0) AS first_indexed_time, download_http_code AS http_code, src_unparsed AS src_unparsed, src_root_hash AS src_root_hash, history_drop_reason AS history_drop_reason, meta_title AS meta_title, meta_descriptions AS meta_descriptions, attrs_boilerpipe_text AS attrs_boilerpipe_text, attrs_markdown AS attrs_markdown, attrs_readable_markdown AS attrs_readable_markdown, meta_canonical AS meta_canonical FROM crawler3.page_info_local FINAL PREWHERE (src_root_hash, src_unparsed) IN ((getAhrefsRootHashFromUnparsed(getAhrefsUnparsedNoserviceFromURL(\'https://catboost.ai/docs/en/concepts/loss-functions\')), getAhrefsUnparsedNoserviceFromURL(\'https://catboost.ai/docs/en/concepts/loss-functions\'))) FORMAT JSONEachRow'

Response:

{"found_url":"https:\/\/catboost.ai\/docs\/en\/concepts\/loss-functions","crawl_time":1775673692,"first_indexed_time":1731946335,"http_code":200,"src_unparsed":"ai,catboost!\/docs\/en\/concepts\/loss-functions s443","src_root_hash":"17435841955170310369","history_drop_reason":null,"meta_title":"Objectives and metrics | CatBoost","meta_descriptions":["This section contains basic information regarding the supported metrics for various machine learning problems. Regression. Multiregression. Classification."],"attrs_boilerpipe_text":"This section contains basic information regarding the supported metrics for various machine learning problems.\nRegression\nMultiregression\nClassification\nMulticlassification\nMultilabel classification\nRanking\nRefer to the \nVariables used in formulas\nsection for the description of commonly used variables in the listed metrics.\nMetrics can be calculated during the training or separately from the training for a specified model. The calculated values are written to files and can be plotted by \nvisualization tools\n(both during and after the training) for further analysis.\nUser-defined parameters\nSome metrics provide user-defined parameters. These parameters must be set together with the metric name when it is being specified.\nThe parameters for each metric are set in the following format:\n<Metric>[:<parameter 1>=<value>;..;<parameter N>=<value>]\nThe supported parameters vary from one metric to another and are listed alongside the corresponding descriptions.\nUsage examples\nQuantile:alpha=0.1\nList of most important parameters\nThe following table contains the description of parameters that are used in several metrics. The default values vary from one metric to another and are listed alongside the corresponding descriptions.\nParameter:\nuse_weights\nDescription\nUse object\/group weights to calculate metrics if the specified value is \ntrue\nand set all weights to\n1\nregardless of the input data if the specified value is\nfalse\n.\nNote\nThis parameter cannot be used with the optimized objective. If weights are present, they are necessarily used to calculate the optimized objective. This behaviour cannot be disabled.\nParameter:\ntop\nDescription\nThe number of top samples in a group that are used to calculate the ranking metric. Top samples are either the samples with the largest approx values or the ones with the lowest target values if approx values are the same.\nEnable, disable and configure metrics calculation\nThe calculation of metrics can be resource-intensive. It creates a bottleneck in some cases, for example, if many metrics are calculated during the training or the computation is performed on GPU.\nThe training can be sped up by disabling the calculation of some metrics for the training dataset. Use the\nhints=skip_train~true\nparameter to disable the calculation of the specified metrics.\nNote\nThe calculation of some metrics is disabled by default for the training dataset to speed up the training. Use the\nhints=skip_train~false\nparameter to enable the calculation.\nMetrics that are not calculated by default for the train dataset\nPFound\nYetiRank\nNDCG\nYetiRankPairwise\nAUC\nNormalizedGini\nFilteredDCG\nDCG\nUsage examples\nEnable the calculation of the AUC metric:\nAUC:hints=skip_train~false\nDisable the calculation of the Logloss metric:\nLogloss:hints=skip_train~true\nAnother way to speed up the training is to set up the frequency of iterations to calculate the values of metrics. Use one of the following parameters:\nCommand-line version parameters:\n--metric-period\nPython parameters:\nmetric_period\nR parameters:\nmetric_period\nFor example, use the following parameter in Python or R to calculate metrics once per 50 iterations:\nmetric_period=50","attrs_markdown":"[![Logo icon](https:\/\/yastatic.net\/s3\/locdoc\/daas-static\/catboost\/71b237a322eec6f2889af0dae2a9c549.svg)](https:\/\/catboost.ai\/ \"CatBoost\")\n\n- Installation\n  - [Overview](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/installation)\n  - Python package installation\n  - CatBoost for Apache Spark installation\n  - R package installation\n  - Command-line version binary\n  - Build from source\n- Key Features\n- Training parameters\n- Python package\n- CatBoost for Apache Spark\n- R package\n- Command-line version\n- Applying models\n- Objectives and metrics\n  - [Overview](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions)\n  - [Variables used in formulas](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-variables-used)\n  - [Regression](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-regression)\n  - [Multiregression](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-multiregression)\n  - [Classification](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-classification)\n  - [Multiclassification](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-multiclassification)\n  - [Multilabel Classification](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-multilabel-classification)\n  - [Ranking](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-ranking)\n- Model analysis\n- Data format description\n- [Parameter tuning](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/parameter-tuning)\n- [Speeding up the training](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/speed-up-training)\n- Data visualization\n- Algorithm details\n- [FAQ](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/faq)\n- Educational materials\n- [Development and contributions](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/development-and-contributions)\n- [Contacts](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/contacts)\n\nObjectives and metrics\n\n## In this article:\n- [User-defined parameters](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions#user-defined-parameters)\n- [Enable, disable and configure metrics calculation](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions#enable-disable-configure-metrics)\n\n1. Objectives and metrics\n2. Overview\n\n# Objectives and metrics\n- [User-defined parameters](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions#user-defined-parameters)\n- [Enable, disable and configure metrics calculation](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions#enable-disable-configure-metrics)\n\nThis section contains basic information regarding the supported metrics for various machine learning problems.\n\n- [Regression](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-regression)\n- [Multiregression](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-multiregression)\n- [Classification](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-classification)\n- [Multiclassification](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-multiclassification)\n- [Multilabel classification](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-multilabel-classification)\n- [Ranking](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-ranking)\n\nRefer to the [Variables used in formulas](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-variables-used) section for the description of commonly used variables in the listed metrics.\n\nMetrics can be calculated during the training or separately from the training for a specified model. The calculated values are written to files and can be plotted by [visualization tools](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/features\/visualization) (both during and after the training) for further analysis.\n\n## User-defined parameters\nSome metrics provide user-defined parameters. These parameters must be set together with the metric name when it is being specified.\n\nThe parameters for each metric are set in the following format:\n```\n<Metric>[:<parameter 1>=<value>;..;<parameter N>=<value>]\n```\nThe supported parameters vary from one metric to another and are listed alongside the corresponding descriptions.\n\n#### Usage examples\n```\nQuantile:alpha=0.1\n```\n#### List of most important parameters\nThe following table contains the description of parameters that are used in several metrics. The default values vary from one metric to another and are listed alongside the corresponding descriptions.\n\n**Parameter:** `use_weights`\n\n#### Description\nUse object\/group weights to calculate metrics if the specified value is \"true\" and set all weights to \"1\" regardless of the input data if the specified value is \"false\".\n\nNote\n\nThis parameter cannot be used with the optimized objective. If weights are present, they are necessarily used to calculate the optimized objective. This behaviour cannot be disabled.\n\n**Parameter:** `top`\n\n#### Description\nThe number of top samples in a group that are used to calculate the ranking metric. Top samples are either the samples with the largest approx values or the ones with the lowest target values if approx values are the same.\n\n## Enable, disable and configure metrics calculation\nThe calculation of metrics can be resource-intensive. It creates a bottleneck in some cases, for example, if many metrics are calculated during the training or the computation is performed on GPU.\n\nThe training can be sped up by disabling the calculation of some metrics for the training dataset. Use the `hints=skip_train~true` parameter to disable the calculation of the specified metrics.\n\nNote\n\nThe calculation of some metrics is disabled by default for the training dataset to speed up the training. Use the `hints=skip_train~false` parameter to enable the calculation.\n\nMetrics that are not calculated by default for the train dataset\n\n- PFound\n- YetiRank\n- NDCG\n- YetiRankPairwise\n- AUC\n- NormalizedGini\n- FilteredDCG\n- DCG\n\nUsage examples\n\nEnable the calculation of the AUC metric:\n```\nAUC:hints=skip_train~false\n```\nDisable the calculation of the Logloss metric:\n```\nLogloss:hints=skip_train~true\n```\n\nAnother way to speed up the training is to set up the frequency of iterations to calculate the values of metrics. Use one of the following parameters:\n\n**Command-line version parameters:** `--metric-period`\n\n**Python parameters:** `metric_period`\n\n**R parameters:** `metric_period`\n\nFor example, use the following parameter in Python or R to calculate metrics once per 50 iterations:\n```\nmetric_period=50\n```\n\n### Was the article helpful?\nYes\n\nNo\n\nPrevious\n\n[Python](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/python-reference_apply_catboost_model)\n\nNext\n\n[Variables used in formulas](https:\/\/catboost.ai\/docs\/en\/concepts\/en\/concepts\/loss-functions-variables-used)\n\n![](https:\/\/mc.yandex.ru\/watch\/60763294)","attrs_readable_markdown":"This section contains basic information regarding the supported metrics for various machine learning problems.\n\n- [Regression](https:\/\/catboost.ai\/docs\/en\/concepts\/loss-functions-regression)\n- [Multiregression](https:\/\/catboost.ai\/docs\/en\/concepts\/loss-functions-multiregression)\n- [Classification](https:\/\/catboost.ai\/docs\/en\/concepts\/loss-functions-classification)\n- [Multiclassification](https:\/\/catboost.ai\/docs\/en\/concepts\/loss-functions-multiclassification)\n- [Multilabel classification](https:\/\/catboost.ai\/docs\/en\/concepts\/loss-functions-multilabel-classification)\n- [Ranking](https:\/\/catboost.ai\/docs\/en\/concepts\/loss-functions-ranking)\n\nRefer to the [Variables used in formulas](https:\/\/catboost.ai\/docs\/en\/concepts\/loss-functions-variables-used) section for the description of commonly used variables in the listed metrics.\n\nMetrics can be calculated during the training or separately from the training for a specified model. The calculated values are written to files and can be plotted by [visualization tools](https:\/\/catboost.ai\/docs\/en\/features\/visualization) (both during and after the training) for further analysis.\n\n## User-defined parameters\nSome metrics provide user-defined parameters. These parameters must be set together with the metric name when it is being specified.\n\nThe parameters for each metric are set in the following format:\n```\n<Metric>[:<parameter 1>=<value>;..;<parameter N>=<value>]\n```\nThe supported parameters vary from one metric to another and are listed alongside the corresponding descriptions.\n\n#### Usage examples\n```\nQuantile:alpha=0.1\n```\n#### List of most important parameters\nThe following table contains the description of parameters that are used in several metrics. The default values vary from one metric to another and are listed alongside the corresponding descriptions.\n\n**Parameter:** `use_weights`\n\n#### Description\nUse object\/group weights to calculate metrics if the specified value is \"true\" and set all weights to \"1\" regardless of the input data if the specified value is \"false\".\n\nNote\n\nThis parameter cannot be used with the optimized objective. If weights are present, they are necessarily used to calculate the optimized objective. This behaviour cannot be disabled.\n\n**Parameter:** `top`\n\n#### Description\nThe number of top samples in a group that are used to calculate the ranking metric. Top samples are either the samples with the largest approx values or the ones with the lowest target values if approx values are the same.\n\n## Enable, disable and configure metrics calculation\nThe calculation of metrics can be resource-intensive. It creates a bottleneck in some cases, for example, if many metrics are calculated during the training or the computation is performed on GPU.\n\nThe training can be sped up by disabling the calculation of some metrics for the training dataset. Use the `hints=skip_train~true` parameter to disable the calculation of the specified metrics.\n\nNote\n\nThe calculation of some metrics is disabled by default for the training dataset to speed up the training. Use the `hints=skip_train~false` parameter to enable the calculation.\n\nMetrics that are not calculated by default for the train dataset\n\n- PFound\n- YetiRank\n- NDCG\n- YetiRankPairwise\n- AUC\n- NormalizedGini\n- FilteredDCG\n- DCG\n\nUsage examples\n\nEnable the calculation of the AUC metric:\n```\nAUC:hints=skip_train~false\n```\nDisable the calculation of the Logloss metric:\n```\nLogloss:hints=skip_train~true\n```\n\nAnother way to speed up the training is to set up the frequency of iterations to calculate the values of metrics. Use one of the following parameters:\n\n**Command-line version parameters:** `--metric-period`\n\n**Python parameters:** `metric_period`\n\n**R parameters:** `metric_period`\n\nFor example, use the following parameter in Python or R to calculate metrics once per 50 iterations:\n```\nmetric_period=50\n```","meta_canonical":null}

3. Robots.txt Check

Query:

Response:

4. Spam/Ban Check

Query:

Response:

5. Seen Status Check

ℹ️ Skipped - page is already crawled

📄

INDEXABLE

✅

CRAWLED

1 day ago

🤖

ROBOTS ALLOWED

Page Info Filters

Filter	Status	Condition	Details
HTTP status	PASS	`download_http_code = 200`	HTTP 200
Age cutoff	PASS	`download_stamp > now() - 6 MONTH`	0 months ago
History drop	PASS	`isNull(history_drop_reason)`	No drop reason
Spam/ban	PASS	`fh_dont_index != 1 AND ml_spam_score = 0`	ml_spam_score=0
Canonical	PASS	`meta_canonical IS NULL OR = '' OR = src_unparsed`	Not set

Page Details

Property	Value
URL	https://catboost.ai/docs/en/concepts/loss-functions
Last Crawled	2026-04-08 18:41:32 (1 day ago)
First Indexed	2024-11-18 16:12:15 (1 year ago)
HTTP Status Code	200
Meta Title	Objectives and metrics \| CatBoost
Meta Description	This section contains basic information regarding the supported metrics for various machine learning problems. Regression. Multiregression. Classification.
Meta Canonical	null
Boilerpipe Text	This section contains basic information regarding the supported metrics for various machine learning problems. Regression Multiregression Classification Multiclassification Multilabel classification Ranking Refer to the Variables used in formulas section for the description of commonly used variables in the listed metrics. Metrics can be calculated during the training or separately from the training for a specified model. The calculated values are written to files and can be plotted by visualization tools (both during and after the training) for further analysis. User-defined parameters Some metrics provide user-defined parameters. These parameters must be set together with the metric name when it is being specified. The parameters for each metric are set in the following format: <Metric>[:<parameter 1>=<value>;..;<parameter N>=<value>] The supported parameters vary from one metric to another and are listed alongside the corresponding descriptions. Usage examples Quantile:alpha=0.1 List of most important parameters The following table contains the description of parameters that are used in several metrics. The default values vary from one metric to another and are listed alongside the corresponding descriptions. Parameter: use_weights Description Use object/group weights to calculate metrics if the specified value is true and set all weights to 1 regardless of the input data if the specified value is false . Note This parameter cannot be used with the optimized objective. If weights are present, they are necessarily used to calculate the optimized objective. This behaviour cannot be disabled. Parameter: top Description The number of top samples in a group that are used to calculate the ranking metric. Top samples are either the samples with the largest approx values or the ones with the lowest target values if approx values are the same. Enable, disable and configure metrics calculation The calculation of metrics can be resource-intensive. It creates a bottleneck in some cases, for example, if many metrics are calculated during the training or the computation is performed on GPU. The training can be sped up by disabling the calculation of some metrics for the training dataset. Use the hints=skip_train~true parameter to disable the calculation of the specified metrics. Note The calculation of some metrics is disabled by default for the training dataset to speed up the training. Use the hints=skip_train~false parameter to enable the calculation. Metrics that are not calculated by default for the train dataset PFound YetiRank NDCG YetiRankPairwise AUC NormalizedGini FilteredDCG DCG Usage examples Enable the calculation of the AUC metric: AUC:hints=skip_train~false Disable the calculation of the Logloss metric: Logloss:hints=skip_train~true Another way to speed up the training is to set up the frequency of iterations to calculate the values of metrics. Use one of the following parameters: Command-line version parameters: --metric-period Python parameters: metric_period R parameters: metric_period For example, use the following parameter in Python or R to calculate metrics once per 50 iterations: metric_period=50
Markdown	[![Logo icon](https://yastatic.net/s3/locdoc/daas-static/catboost/71b237a322eec6f2889af0dae2a9c549.svg)](https://catboost.ai/ "CatBoost") - Installation - [Overview](https://catboost.ai/docs/en/concepts/en/concepts/installation) - Python package installation - CatBoost for Apache Spark installation - R package installation - Command-line version binary - Build from source - Key Features - Training parameters - Python package - CatBoost for Apache Spark - R package - Command-line version - Applying models - Objectives and metrics - [Overview](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions) - [Variables used in formulas](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-variables-used) - [Regression](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-regression) - [Multiregression](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-multiregression) - [Classification](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-classification) - [Multiclassification](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-multiclassification) - [Multilabel Classification](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-multilabel-classification) - [Ranking](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-ranking) - Model analysis - Data format description - [Parameter tuning](https://catboost.ai/docs/en/concepts/en/concepts/parameter-tuning) - [Speeding up the training](https://catboost.ai/docs/en/concepts/en/concepts/speed-up-training) - Data visualization - Algorithm details - [FAQ](https://catboost.ai/docs/en/concepts/en/concepts/faq) - Educational materials - [Development and contributions](https://catboost.ai/docs/en/concepts/en/concepts/development-and-contributions) - [Contacts](https://catboost.ai/docs/en/concepts/en/concepts/contacts) Objectives and metrics ## In this article: - [User-defined parameters](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions#user-defined-parameters) - [Enable, disable and configure metrics calculation](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions#enable-disable-configure-metrics) 1. Objectives and metrics 2. Overview # Objectives and metrics - [User-defined parameters](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions#user-defined-parameters) - [Enable, disable and configure metrics calculation](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions#enable-disable-configure-metrics) This section contains basic information regarding the supported metrics for various machine learning problems. - [Regression](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-regression) - [Multiregression](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-multiregression) - [Classification](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-classification) - [Multiclassification](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-multiclassification) - [Multilabel classification](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-multilabel-classification) - [Ranking](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-ranking) Refer to the [Variables used in formulas](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-variables-used) section for the description of commonly used variables in the listed metrics. Metrics can be calculated during the training or separately from the training for a specified model. The calculated values are written to files and can be plotted by [visualization tools](https://catboost.ai/docs/en/concepts/en/features/visualization) (both during and after the training) for further analysis. ## User-defined parameters Some metrics provide user-defined parameters. These parameters must be set together with the metric name when it is being specified. The parameters for each metric are set in the following format: ``` <Metric>[:<parameter 1>=<value>;..;<parameter N>=<value>] ``` The supported parameters vary from one metric to another and are listed alongside the corresponding descriptions. #### Usage examples ``` Quantile:alpha=0.1 ``` #### List of most important parameters The following table contains the description of parameters that are used in several metrics. The default values vary from one metric to another and are listed alongside the corresponding descriptions. Parameter: `use_weights` #### Description Use object/group weights to calculate metrics if the specified value is "true" and set all weights to "1" regardless of the input data if the specified value is "false". Note This parameter cannot be used with the optimized objective. If weights are present, they are necessarily used to calculate the optimized objective. This behaviour cannot be disabled. Parameter: `top` #### Description The number of top samples in a group that are used to calculate the ranking metric. Top samples are either the samples with the largest approx values or the ones with the lowest target values if approx values are the same. ## Enable, disable and configure metrics calculation The calculation of metrics can be resource-intensive. It creates a bottleneck in some cases, for example, if many metrics are calculated during the training or the computation is performed on GPU. The training can be sped up by disabling the calculation of some metrics for the training dataset. Use the `hints=skip_train~true` parameter to disable the calculation of the specified metrics. Note The calculation of some metrics is disabled by default for the training dataset to speed up the training. Use the `hints=skip_train~false` parameter to enable the calculation. Metrics that are not calculated by default for the train dataset - PFound - YetiRank - NDCG - YetiRankPairwise - AUC - NormalizedGini - FilteredDCG - DCG Usage examples Enable the calculation of the AUC metric: ``` AUC:hints=skip_train~false ``` Disable the calculation of the Logloss metric: ``` Logloss:hints=skip_train~true ``` Another way to speed up the training is to set up the frequency of iterations to calculate the values of metrics. Use one of the following parameters: Command-line version parameters: `--metric-period` Python parameters: `metric_period` R parameters: `metric_period` For example, use the following parameter in Python or R to calculate metrics once per 50 iterations: ``` metric_period=50 ``` ### Was the article helpful? Yes No Previous [Python](https://catboost.ai/docs/en/concepts/en/concepts/python-reference_apply_catboost_model) Next [Variables used in formulas](https://catboost.ai/docs/en/concepts/en/concepts/loss-functions-variables-used) ![](https://mc.yandex.ru/watch/60763294)
Readable Markdown	This section contains basic information regarding the supported metrics for various machine learning problems. - [Regression](https://catboost.ai/docs/en/concepts/loss-functions-regression) - [Multiregression](https://catboost.ai/docs/en/concepts/loss-functions-multiregression) - [Classification](https://catboost.ai/docs/en/concepts/loss-functions-classification) - [Multiclassification](https://catboost.ai/docs/en/concepts/loss-functions-multiclassification) - [Multilabel classification](https://catboost.ai/docs/en/concepts/loss-functions-multilabel-classification) - [Ranking](https://catboost.ai/docs/en/concepts/loss-functions-ranking) Refer to the [Variables used in formulas](https://catboost.ai/docs/en/concepts/loss-functions-variables-used) section for the description of commonly used variables in the listed metrics. Metrics can be calculated during the training or separately from the training for a specified model. The calculated values are written to files and can be plotted by [visualization tools](https://catboost.ai/docs/en/features/visualization) (both during and after the training) for further analysis. ## User-defined parameters Some metrics provide user-defined parameters. These parameters must be set together with the metric name when it is being specified. The parameters for each metric are set in the following format: ``` <Metric>[:<parameter 1>=<value>;..;<parameter N>=<value>] ``` The supported parameters vary from one metric to another and are listed alongside the corresponding descriptions. #### Usage examples ``` Quantile:alpha=0.1 ``` #### List of most important parameters The following table contains the description of parameters that are used in several metrics. The default values vary from one metric to another and are listed alongside the corresponding descriptions. Parameter: `use_weights` #### Description Use object/group weights to calculate metrics if the specified value is "true" and set all weights to "1" regardless of the input data if the specified value is "false". Note This parameter cannot be used with the optimized objective. If weights are present, they are necessarily used to calculate the optimized objective. This behaviour cannot be disabled. Parameter: `top` #### Description The number of top samples in a group that are used to calculate the ranking metric. Top samples are either the samples with the largest approx values or the ones with the lowest target values if approx values are the same. ## Enable, disable and configure metrics calculation The calculation of metrics can be resource-intensive. It creates a bottleneck in some cases, for example, if many metrics are calculated during the training or the computation is performed on GPU. The training can be sped up by disabling the calculation of some metrics for the training dataset. Use the `hints=skip_train~true` parameter to disable the calculation of the specified metrics. Note The calculation of some metrics is disabled by default for the training dataset to speed up the training. Use the `hints=skip_train~false` parameter to enable the calculation. Metrics that are not calculated by default for the train dataset - PFound - YetiRank - NDCG - YetiRankPairwise - AUC - NormalizedGini - FilteredDCG - DCG Usage examples Enable the calculation of the AUC metric: ``` AUC:hints=skip_train~false ``` Disable the calculation of the Logloss metric: ``` Logloss:hints=skip_train~true ``` Another way to speed up the training is to set up the frequency of iterations to calculate the values of metrics. Use one of the following parameters: Command-line version parameters: `--metric-period` Python parameters: `metric_period` R parameters: `metric_period` For example, use the following parameter in Python or R to calculate metrics once per 50 iterations: ``` metric_period=50 ```
Shard	169 (laksa)
Root Hash	17435841955170310369
Unparsed URL	ai,catboost!/docs/en/concepts/loss-functions s443