Explainability

Fetch slice query

Parse slice query data

POSThttps://preprod.dev.fiddler.ai/v3/slice-query/parse

Body

application/json

model_id*string (uuid)

query*string

Response

200400500501

Successfully parsed slice query

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataParseSliceQueryResponseBody (object)

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/slice-query/parse', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "model_id": "123e4567-e89b-12d3-a456-426614174000",
      "query": "text"
    }),
});
const data = await response.json();

Response

200400500501

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "environment_name": "text",
    "is_prod": false,
    "is_slice": false,
    "model_name": "text",
    "table_name": "text"
  }
}

Fetch slice query

Fetch slice query data

POSThttps://preprod.dev.fiddler.ai/v3/slice-query/fetch

Body

application/json

model_id*string (uuid)

query*string

sampleboolean

max_rowsinteger

columnsarray of string

Response

200400500

Slice query data fetch successful

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataFetchSliceQueryResponse (object)

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/slice-query/fetch', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "model_id": "123e4567-e89b-12d3-a456-426614174000",
      "query": "text"
    }),
});
const data = await response.json();

Response

200400500

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "metadata": {
      "is_slice": false,
      "columns": [
        "text"
      ],
      "dtypes": [
        "text"
      ],
      "env": {
        "id": "123e4567-e89b-12d3-a456-426614174000",
        "type": "PRE_PRODUCTION",
        "name": "text"
      },
      "model": {
        "id": "123e4567-e89b-12d3-a456-426614174000",
        "name": "text",
        "version": "text"
      }
    },
    "rows": [
      []
    ]
  }
}

Get feature impact

Get feature impact for the given environment or a slice query

POSThttps://preprod.dev.fiddler.ai/v3/analytics/feature-impact

Body

application/json

data_source*FeatureImpactDataSource (one of)

Feature Impact api data sources

FeatureImpactEnvDataSource (object)FeatureImpactSliceQueryDataSource (object)FeatureImpactFqlDataSource (object)

model_id*string (uuid)

Unique ID of model.

num_refsinteger

Number of reference points used in the explanations. Only for non text inputs

num_iterationsinteger

The maximum number of ablated model inferences per feature. Only for non text inputs

ci_levelnumber

The confidence interval level (between 0 and 1) to use for all confidence intervals computed. Only for non text inputs

min_supportinteger

Specify a minimum support to retrieve top words. Only for Text data (NLP models)

output_columnsarray of string

Only used for NLP (TEXT inputs) models. Output column names to compute feature impact on. If None, use all.

ref_env_idstring (uuid)

environment to use for the reference dataset.

Response

200400500501

Feature Impact ran successfully on the given data

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataFeatureImpactResponse (one of)

Feature Impact api response (text or tabular).

FeatureImpactTextResponse (object)FeatureImpactTabularResponse (object)UploadFeatureImpactTabularResponse (object)

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/analytics/feature-impact', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "data_source": {
        "source_type": "ENVIRONMENT",
        "env_type": "PRE_PRODUCTION"
      },
      "model_id": "123e4567-e89b-12d3-a456-426614174000"
    }),
});
const data = await response.json();

Response

200400500501

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "response_type": "FEATURE_IMPACT_TEXT",
    "model_task": "text",
    "model_input_type": "text",
    "output_name": "sentiment",
    "min_support": 15,
    "num_inputs": 200,
    "env_name": "bank_churn",
    "env_uuid": "bcb8e333-39d1-4ba5-a485-dec1591f7122",
    "created_at": "2023-12-12 18:21:07.616438+00:00"
  }
}

Get feature importance

Get feature importance for the given environment or a slice query

POSThttps://preprod.dev.fiddler.ai/v3/analytics/feature-importance

Body

application/json

data_source*FeatureImportanceDataSource (one of)

FeatureImportanceEnvDataSource (object)FeatureImportanceSliceQueryDataSource (object)FeatureImpactFqlDataSource (object)

model_id*string (uuid)

num_refsinteger

Number of reference points used in the explanations

num_iterationsinteger

The maximum number of ablated model inferences per feature

ci_levelnumber

The confidence interval level (between 0 and 1) to use for all confidence intervals computed

ref_env_idstring (uuid)

environment to use for the reference dataset.

Response

200400500501

Feature Importance ran successfully on the given data

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataFeatureImportanceResponse (object)

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/analytics/feature-importance', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "data_source": {
        "source_type": "ENVIRONMENT",
        "env_type": "PRE_PRODUCTION"
      },
      "model_id": "123e4567-e89b-12d3-a456-426614174000"
    }),
});
const data = await response.json();

Response

200400500501

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "model_task": "text",
    "model_input_type": "text",
    "total_input_samples": 10000,
    "valid_input_samples": 9000,
    "ci_level": 0.9,
    "feature_names": [
      "CreditScore",
      "Geography",
      "Age"
    ],
    "fixed_sample_ci": [
      0.04,
      0.002,
      0.1
    ],
    "loss": "pointwise_logloss",
    "mean_loss": 2.41122,
    "mean_loss_ci": 0.0434,
    "mean_loss_increase_importance": [
      -0.0581,
      -0.097,
      -0.0707
    ],
    "num_refs": 500,
    "random_sample_ci": [
      0.024,
      0.0204,
      0.0246
    ],
    "num_inputs": 250,
    "num_iterations": 200,
    "env_name": "bank_churn",
    "env_uuid": "bcb8e333-39d1-4ba5-a485-dec1591f7122",
    "created_at": "2023-12-12 18:21:07.616438+00:00"
  }
}

Get model scores

Get model scores for the given environment or a slice query

POSThttps://preprod.dev.fiddler.ai/v3/analytics/scores

Body

application/json

data_source*ScoresDataSource (one of)

ScoresEnvDataSource (object)ScoresSqlSliceQueryDataSource (object)ScoresFqlDataSource (object)

model_id*string (uuid)

Model uuid

binary_thresholdnumber

Threshold for binary classification models

top_kinteger

Top K for ranking models

metricsarray of enum

Response

200400500501

Scoring ran successfully on the given data

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataScoresResponse (one of)

ScoresRegressionResponse (object)ScoresBinaryClassificationResponse (object)ScoresMultiClassClassificationResponse (object)ScoresRankingResponse (object)

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/analytics/scores', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "data_source": {
        "source_type": "ENVIRONMENT",
        "env_type": "PRE_PRODUCTION"
      },
      "model_id": "123e4567-e89b-12d3-a456-426614174000"
    }),
});
const data = await response.json();

Response

200400500501

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "model_task": "REGRESSION",
    "total_samples": 10000,
    "valid_samples": 9500,
    "r_squared": 0.6934094625050112,
    "root_mean_squared_error": 0.43712324037225403,
    "mean_absolute_error": 0.34032740270302,
    "predictions": [
      6.346766948699951,
      5.74676698811151
    ],
    "targets": [
      6,
      5
    ],
    "error_distribution": {
      "count": [
        2,
        6
      ],
      "bins": [
        0,
        1,
        2
      ]
    }
  }
}

Update precomputed feature impact

Compute and update cached feature impact on an environment

PUThttps://preprod.dev.fiddler.ai/v3/analytics/precompute-feature-impact

Body

application/json

model_id*string (uuid)

Unique identifier for model.

env_id*string (uuid)

Unique identifier for environment.

env_type*string

Type of environment. Either PRE_PRODUCTION or PRODUCTION.

num_refsinteger

Number of reference points used in the explanations

num_iterationsinteger

The maximum number of ablated model inferences per feature

ci_levelnumber

The confidence interval level (between 0 and 1) to use for all confidence intervals computed

min_supportinteger

Used for TEXT models to specify a minimum support (number of times a specific work was present in the sample data) to retrieve top words. Default to 15.

Response

200400404500501

Feature impact pre-computation update ran successfully on the given data

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataobject

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/analytics/precompute-feature-impact', {
    method: 'PUT',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "model_id": "123e4567-e89b-12d3-a456-426614174000",
      "env_id": "123e4567-e89b-12d3-a456-426614174000",
      "env_type": "text"
    }),
});
const data = await response.json();

Response

200400404500501

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "job": {
      "id": "123e4567-e89b-12d3-a456-426614174000",
      "name": "text"
    }
  }
}

Precompute feature impact

Compute and cache feature impact on an environment

POSThttps://preprod.dev.fiddler.ai/v3/analytics/precompute-feature-impact

Body

application/json

model_id*string (uuid)

Unique identifier for model.

env_id*string (uuid)

Unique identifier for environment.

env_type*string

Type of environment. Either PRE_PRODUCTION or PRODUCTION.

num_refsinteger

Number of reference points used in the explanations

num_iterationsinteger

The maximum number of ablated model inferences per feature

ci_levelnumber

The confidence interval level (between 0 and 1) to use for all confidence intervals computed

min_supportinteger

Used for TEXT models to specify a minimum support (number of times a specific work was present in the sample data) to retrieve top words. Default to 15.

Response

200400404500501

Feature impact pre-computation ran successfully on the given data

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataobject

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/analytics/precompute-feature-impact', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "model_id": "123e4567-e89b-12d3-a456-426614174000",
      "env_id": "123e4567-e89b-12d3-a456-426614174000",
      "env_type": "text"
    }),
});
const data = await response.json();

Response

200400404500501

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "job": {
      "id": "123e4567-e89b-12d3-a456-426614174000",
      "name": "text"
    }
  }
}

Get precomputed feature impact

Get precomputed feature impact for a model

POSThttps://preprod.dev.fiddler.ai/v3/analytics/feature-impact/precomputed

Body

application/json

model_id*string (uuid)

Unique identifier for the model.

Response

200400404500501

Precomputed Feature impact retrieval ran successfully on the given data

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataFeatureImpactResponse (one of)

Feature Impact api response (text or tabular).

FeatureImpactTextResponse (object)FeatureImpactTabularResponse (object)UploadFeatureImpactTabularResponse (object)

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/analytics/feature-impact/precomputed', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "model_id": "123e4567-e89b-12d3-a456-426614174000"
    }),
});
const data = await response.json();

Response

200400404500501

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "response_type": "FEATURE_IMPACT_TEXT",
    "model_task": "text",
    "model_input_type": "text",
    "output_name": "sentiment",
    "min_support": 15,
    "num_inputs": 200,
    "env_name": "bank_churn",
    "env_uuid": "bcb8e333-39d1-4ba5-a485-dec1591f7122",
    "created_at": "2023-12-12 18:21:07.616438+00:00"
  }
}

Update precomputed feature importance

Compute and update cached feature importance on an environment

PUThttps://preprod.dev.fiddler.ai/v3/analytics/precompute-feature-importance

Body

application/json

model_id*string (uuid)

env_id*string (uuid)

env_type*string

num_refsinteger

Number of reference points used in the explanations

num_iterationsinteger

The maximum number of ablated model inferences per feature

ci_levelnumber

The confidence interval level (between 0 and 1) to use for all confidence intervals computed

Response

200400404500501

Feature importance pre-computation update ran successfully on the given data

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataobject

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/analytics/precompute-feature-importance', {
    method: 'PUT',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "model_id": "123e4567-e89b-12d3-a456-426614174000",
      "env_id": "123e4567-e89b-12d3-a456-426614174000",
      "env_type": "text"
    }),
});
const data = await response.json();

Response

200400404500501

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "job": {
      "id": "123e4567-e89b-12d3-a456-426614174000",
      "name": "text"
    }
  }
}

Precompute feature importance

Compute and cache feature importance on an environment

POSThttps://preprod.dev.fiddler.ai/v3/analytics/precompute-feature-importance

Body

application/json

model_id*string (uuid)

env_id*string (uuid)

env_type*string

num_refsinteger

Number of reference points used in the explanations

num_iterationsinteger

The maximum number of ablated model inferences per feature

ci_levelnumber

The confidence interval level (between 0 and 1) to use for all confidence intervals computed

Response

200400404500501

Feature importance pre-computation ran successfully on the given data

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataobject

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/analytics/precompute-feature-importance', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "model_id": "123e4567-e89b-12d3-a456-426614174000",
      "env_id": "123e4567-e89b-12d3-a456-426614174000",
      "env_type": "text"
    }),
});
const data = await response.json();

Response

200400404500501

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "job": {
      "id": "123e4567-e89b-12d3-a456-426614174000",
      "name": "text"
    }
  }
}

Get precomputed feature importance

Get precomputed feature importance for a model

POSThttps://preprod.dev.fiddler.ai/v3/analytics/feature-importance/precomputed

Body

application/json

model_id*string (uuid)

Unique identifier for model.

Response

200400404500501

Precomputed Feature importance retrieval ran successfully on the given data

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataFeatureImportanceResponse (object)

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/analytics/feature-importance/precomputed', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "model_id": "123e4567-e89b-12d3-a456-426614174000"
    }),
});
const data = await response.json();

Response

200400404500501

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "model_task": "text",
    "model_input_type": "text",
    "total_input_samples": 10000,
    "valid_input_samples": 9000,
    "ci_level": 0.9,
    "feature_names": [
      "CreditScore",
      "Geography",
      "Age"
    ],
    "fixed_sample_ci": [
      0.04,
      0.002,
      0.1
    ],
    "loss": "pointwise_logloss",
    "mean_loss": 2.41122,
    "mean_loss_ci": 0.0434,
    "mean_loss_increase_importance": [
      -0.0581,
      -0.097,
      -0.0707
    ],
    "num_refs": 500,
    "random_sample_ci": [
      0.024,
      0.0204,
      0.0246
    ],
    "num_inputs": 250,
    "num_iterations": 200,
    "env_name": "bank_churn",
    "env_uuid": "bcb8e333-39d1-4ba5-a485-dec1591f7122",
    "created_at": "2023-12-12 18:21:07.616438+00:00"
  }
}

Get predictions from a model

Get predictions from a model

POSThttps://preprod.dev.fiddler.ai/v3/predict

Body

application/json

model_id*string (uuid)

chunk_sizeinteger

data*array of object

Response

200400404500

Predictions ran successfully on the given data

Body

application/json

api_versionenum

API version.

3.0

kindenum

Type of response, indicating a normal response.

NORMAL

dataPredictResponse (object)

Request

JavaScriptCurlPython

const response = await fetch('https://preprod.dev.fiddler.ai/v3/predict', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "model_id": "123e4567-e89b-12d3-a456-426614174000",
      "data": [
        {
          "CreditScore": 619,
          "Geography": "France",
          "Gender": "Female",
          "Age": 42,
          "Tenure": 2,
          "Balance": 0,
          "NumOfProducts": 1,
          "HasCrCard": "Yes",
          "IsActiveMember": "Yes",
          "EstimatedSalary": 101348.88
        }
      ]
    }),
});
const data = await response.json();

Response

200400404500

{
  "api_version": "3.0",
  "kind": "NORMAL",
  "data": {
    "predictions": [
      {
        "probability_christian": 0.706
      }
    ]
  }
}