Pandas SDK Example

%pip install -q "arize<8.0.0"

from arize.pandas.logger import Client, Schema

API_KEY = 'ARIZE_API_KEY'
SPACE_ID = 'YOUR SPACE ID'
arize_client = Client(space_id=SPACE_ID, api_key=API_KEY)

schema = Schema(
    prediction_id_column_name="prediction_id", 
    timestamp_column_name="prediction_ts",
    prediction_label_column_name="prediction_label",
    actual_label_column_name="actual_label",
    feature_column_names=["state", "states"],
    tag_column_names=["gender"]
)

# feature & tag columns can be optionally defined with typing:
feature_columns = TypedColumns(
    inferred=["state"],
    to_str=["states"],
)

schema = Schema(
    prediction_id_column_name="prediction_id", 
    timestamp_column_name="prediction_ts",
    prediction_label_column_name="prediction_label",
    actual_label_column_name="actual_label",
    feature_column_names=feature_columns,
    tag_column_names=["gender"]
)

# Declare embedding feature columns
embedding_feature_column_names = {
    # Dictionary keys will be the name of the embedding feature in the app
    "embedding_display_name": EmbeddingColumnNames(
        vector_column_name="vector", # column containing embedding vector (required)
        data_column_name="text", # column containing raw text (optional NLP)
        link_to_data_column_name="image_link" # column containing image URL links (optional CV)
    )
}

schema = Schema(
    embedding_feature_column_names=embedding_feature_column_names,
    ...
)

# Generate the Shap Values and save as a Dataframe
explainer = shap.TreeExplainer(tree_model)
shap_values = explainer.shap_values(X_data)
shap_dataframe = pd.DataFrame(
        shap_values, columns=[f"{fn}_shap" for fn in data["state"]]
)
shap_cols = shap_dataframe.columns

schema = Schema(
    shap_values_column_names=dict(zip("state", shap_cols)),
    ...
)

#log predictions
schema = Schema(
    prediction_id_column_name="prediction_id", 
    prediction_label_column_name="prediction_label",
    ...
)
# then log actuals 
schema = Schema(
    prediction_id_column_name="prediction_id", #needs to be the same as above
    actual_label_column_name="actual_label",
    ...
)

response = arize_client.log(
    model_id='sample-model-1', 
    model_version='v1', #Specify your model version to easily track changes across the Arize platform (i.e. a retrained model) 
    batch_id=None,
    model_type=ModelTypes.BINARY_CLASSIFICATION,
    metrics_validation=[Metrics.CLASSIFICATION, Metrics.AUC_LOG_LOSS]
    environment=Environments.PRODUCTION,#pick from training, production,or validation data
    dataframe=example_dataframe,
    schema=schema
)

metrics_validation=[Metrics.CLASSIFICATION, Metrics.AUC_LOG_LOSS]

repr(Metrics.CLASSIFICATION)
> CLASSIFICATION metrics include: Accuracy, Recall, Precision, FPR, FNR, F1, Sensitivity, Specificity