Target,Age,Gender,Income,Occupation
0,25,0,2850,2
1,36,0,6585,0
1,22,1,1759,1
0,48,0,3446,1
...

data_config = clarify.DataConfig(
    s3_data_input_path=dataset_s3_uri,
    dataset_type='text/csv',
    headers=['Target', 'Age', 'Gender', 'Income', 'Occupation'],
    label='Target',
    s3_output_path=clarify_job_output_s3_uri,
)

bias_config = clarify.BiasConfig(
    label_values_or_threshold=[1],
    facet_name='Gender',
    facet_values_or_threshold=[0],
)

clarify_processor.run_pre_training_bias(
     data_config=data_config,
    data_bias_config=bias_config,
    methods="all",
)

0,0.028986845165491
1,0.825382471084594
...

model_config = clarify.ModelConfig(
    model_name=your_model,
    instance_type='ml.m4.xlarge',
    instance_count=1,
)

predicted_label_config = clarify.ModelPredictedLabelConfig(
    label=0,
)

clarify_processor.run_post_training_bias(
    data_config=data_config,
    data_bias_config=bias_config,
    model_config=model_config,
    model_predicted_label_config=predicted_label_config,
    methods="all",
)

clarify_processor.run_bias(
    data_config=data_config,
     bias_config=bias_config,
     model_config=model_config,
    model_predicted_label_config=predicted_label_config,
    pre_training_methods="all",
    post_training_methods="all",
)

probability_config = clarify.ModelPredictedLabelConfig(
    probability=1,
)

shap_config = clarify.SHAPConfig(
    num_clusters=1,
)

clarify_processor.run_explainability(
    data_config=data_config,
    model_config=model_config,
    model_scores=probability_config,
    explainability_config=shap_config,
)

pdp_config = clarify.PDPConfig(
    features=["Income"],
    grid_resolution=10,
)

clarify_processor.run_explainability(
    data_config=data_config,
    model_config=model_config,
    model_scores=probability_config,
    explainability_config=pdp_config,
)

shap_pdp_config = clarify.PDPConfig(
    top_k_features=2,
    grid_resolution=10,
)

clarify_processor.run_explainability(
    data_config=data_config,
    model_config=model_config,
    model_scores=probability_config,
    explainability_config=[shap_config, shap_pdp_config],
)

Untuk informasi selengkapnya, lihat Format permintaan JSONLINES.

{"Features":[25,0,2850,2],"Label":0}
{"Features":[36,0,6585,0],"Label":1}
{"Features":[22,1,1759,1],"Label":1}
{"Features":[48,0,3446,1],"Label":0}
...

data_config = clarify.DataConfig(
    s3_data_input_path=jsonl_dataset_s3_uri,
    dataset_type='application/jsonlines',
    headers=['Age', 'Gender', 'Income', 'Occupation', 'Target'],
    label='Label',
    features='Features',
    s3_output_path=clarify_job_output_s3_uri,
)

{"predicted_label":0,"probability":0.028986845165491}
{"predicted_label":1,"probability":0.825382471084594}
...

model_config = clarify.ModelConfig(
    model_name=your_model,
    instance_type='ml.m4.xlarge',
    instance_count=1,
    content_template='{"Features":$features}',
)

predicted_label_config = clarify.ModelPredictedLabelConfig(
    label='predicted_label',
)

probability_config = clarify.ModelPredictedLabelConfig(
    probability='probability',
)

0,2,"Flavor needs work"
1,3,"They taste good"
1,5,"The best"
0,1,"Taste is awful"
...

nlp_data_config = clarify.DataConfig(
    s3_data_input_path=nlp_dataset_s3_uri,
    dataset_type='text/csv',
    headers=['Target', 'Rating', 'Comments'],
    label='Target',
    s3_output_path=clarify_job_output_s3_uri,
)

0.491656005382537
0.569582343101501
...

nlp_model_config = clarify.ModelConfig(
    model_name=your_nlp_model_name,
    instance_type='ml.g4dn.xlarge',
    instance_count=1,
)

probability_config = clarify.ModelPredictedLabelConfig(
    probability=0,
)

text_config = clarify.TextConfig(
    language='english',
    granularity='token',
)
nlp_shap_config = clarify.SHAPConfig(
    baseline=[[4, '[MASK]']],
    num_samples=100,
    text_config=text_config,
)

4, '[MASK]'

2,"[MASK] needs work"

4,"Flavor [MASK] work"

4,"Flavor needs [MASK]"

clarify_processor.run_explainability(
    data_config=nlp_data_config,
    model_config=nlp_model_config,
    model_scores=probability_config,
    explainability_config=nlp_shap_config,
)

cv_data_config = clarify.DataConfig(
    s3_data_input_path=cv_dataset_s3_uri,
    dataset_type="application/x-image",
    s3_output_path=clarify_job_output_s3_uri,
)

Untuk informasi selengkapnya, lihat Klasifikasi Gambar - MXNet.

ic_model_config = clarify.ModelConfig(
    model_name=your_cv_ic_model,
    instance_type="ml.p2.xlarge",
    instance_count=1,
    content_type="image/jpeg",
    accept_type="application/json",
)

ic_prediction_config = clarify.ModelPredictedLabelConfig(
    label_headers=['bird', 'cat', 'dog'],
)

ic_image_config = clarify.ImageConfig(
    model_type="IMAGE_CLASSIFICATION",
    num_segments=20,
    segment_compactness=5,
)

ic_shap_config = clarify.SHAPConfig(
    num_samples=100,
    image_config=ic_image_config,
)

clarify_processor.run_explainability(
    data_config=cv_data_config,
    model_config=ic_model_config,
    model_scores=ic_prediction_config,
    explainability_config=ic_shap_config,
)

od_model_config = clarify.ModelConfig(
    model_name=your_cv_ic_model,
    instance_type="ml.p2.xlarge",
    instance_count=1,
    content_type="image/jpeg",
    accept_type="application/json",
)

ic_prediction_config = clarify.ModelPredictedLabelConfig(
    label_headers=['bird', 'cat', 'dog'],
)

od_image_config = clarify.ImageConfig(
    model_type="OBJECT_DETECTION",
    num_segments=20,
    segment_compactness=5,
    max_objects=5,
    iou_threshold=0.5,
    context=1.0,
)
od_shap_config = clarify.SHAPConfig(
    num_samples=100,
    image_config=image_config,
)

clarify_processor.run_explainability(
    data_config=cv_data_config,
    model_config=od_model_config,
    model_scores=od_prediction_config,
    explainability_config=od_shap_config,
)

[
    {
        "item_id": "item1",
        "timestamp": "2019-09-11",
        "target_value": 47650.3,
        "dynamic_feature_1": 0.4576,
        "dynamic_feature_2": 0.2164,
        "dynamic_feature_3": 0.1906,
        "static_feature_1": 3,
        "static_feature_2": 4
    },
    {
        "item_id": "item1",
        "timestamp": "2019-09-12",
        "target_value": 47380.3,
        "dynamic_feature_1": 0.4839,
        "dynamic_feature_2": 0.2274,
        "dynamic_feature_3": 0.1889,
        "static_feature_1": 3,
        "static_feature_2": 4
    },
    {
        "item_id": "item2",
        "timestamp": "2020-04-23",
        "target_value": 35601.4,
        "dynamic_feature_1": 0.5264,
        "dynamic_feature_2": 0.3838,
        "dynamic_feature_3": 0.4604,
        "static_feature_1": 1,
        "static_feature_2": 2
    },
]

time_series_data_config = clarify.TimeSeriesDataConfig(
    target_time_series='[].target_value',
    item_id='[].item_id',
    timestamp='[].timestamp',
    related_time_series=['[].dynamic_feature_1', '[].dynamic_feature_2', '[].dynamic_feature_3'],
    static_covariates=['[].static_feature_1', '[].static_feature_2'],
    dataset_format='timestamp_records',
)

asymmetric_shapley_value_config = AsymmetricShapleyValueConfig(
    direction="chronological",
    granularity="fine-grained",
    num_samples=10,
    baseline={
        "related_time_series": "zero", 
        "static_covariates": {
            "item1": [0, 0], "item2": [0, 0]
        }, 
        "target_time_series": "zero"
    },
)

model_config = clarify.ModelConfig(
    model_name=your_model,
    instance_type='ml.m4.xlarge',
    instance_count=1,
    record_template='{"start": $start_time, "target": $target_time_series, "dynamic_feat": $related_time_series, "cat": $static_covariates}',
    content_template='{"instances": $records}',,
    time_series_model_config=TimeSeriesModelConfig(
        forecast={'forecast': 'predictions[*].mean[:2]'}
    )
)

{
    "predictions": [
        {"mean": [13.4, 3.6, 1.0]}, 
        {"mean": [23.0, 4.7, 3.0]}, 
        {"mean": [3.4, 5.6, 2.0]}
    ]
}

[[13.4, 3.6], [23.0, 4.7], [3.4, 5.6]]