squaredev-io · momegas · Feb 23, 2023 · Feb 8, 2023 · Feb 10, 2023 · Feb 11, 2023
diff --git a/.streamlit/config.toml b/.streamlit/config.toml
@@ -0,0 +1,6 @@
+[theme]
+base="dark"
+primaryColor="#21babe"
+backgroundColor="#1e2025"
+secondaryBackgroundColor="#252a33"
+
diff --git a/docs/mkdocs/docs/sdk-docs.md b/docs/mkdocs/docs/sdk-docs.md
@@ -4,15 +4,15 @@ This is the documentation for Whitebox's SDK. For an interactive experience, you
 
 ## Models
 
-**_create_model_**_(name, type, prediction, labels=None, description="")_
+**_create_model_**_(name, type, target_column, labels=None, description="")_
 
 Creates a model in the database. This model works as placeholder for all the actual model's metadata.
 
 | Parameter       | Type             | Description                                                               |
 | --------------- | ---------------- | ------------------------------------------------------------------------- |
 | **name**        | `str`            | The name of the model.                                                    |
 | **type**        | `str`            | The model's type. Possible values: `binary`, `multi_class`, `regression`. |
-| **prediction**  | `str`            | The prediction of the model.                                              |
+| **target_column**  | `str`            | The name of the target column (y).                             |
 | **labels**      | `Dict[str, int]` | The model's labels. Defaults to `None`.                                   |
 | **description** | `str`            | The model's description. Defaults to an empty string `""`.                |
 

diff --git a/docs/mkdocs/docs/tutorial/sdk.md b/docs/mkdocs/docs/tutorial/sdk.md
@@ -73,7 +73,7 @@ wb.create_model(
         'additionalProp1': 0,
         'additionalProp2': 1
     },
-    prediction="target"
+    target_column="target"
 )
 ```
 

diff --git a/examples/notebooks/sdk-example.ipynb b/examples/notebooks/sdk-example.ipynb
@@ -74,7 +74,7 @@
     }
    ],
    "source": [
-    "wb.create_model(name=\"Model 1\", type=\"binary\", labels={'additionalProp1': 0, 'additionalProp2': 1}, prediction=\"y_prediction_multi\")"
+    "wb.create_model(name=\"Model 1\", type=\"binary\", labels={'additionalProp1': 0, 'additionalProp2': 1}, target_column=\"y_prediction_multi\")"
    ]
   },
   {
@@ -248,7 +248,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -262,12 +262,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.8"
+   "version": "3.8.6"
   },
   "orig_nbformat": 4,
   "vscode": {
    "interpreter": {
-    "hash": "32a5a47fe20cdfbd609287887f2e78a4d5f2f7afeda3da775d5794970f9a3f8e"
+    "hash": "6b8a8ae524dcca06b04542d2d49be160be0f11dd19d43d7b2673d555344c6092"
    }
   }
  },

diff --git a/requirements.txt b/requirements.txt
@@ -137,6 +137,7 @@ SQLAlchemy==1.4.41
 stack-data==0.5.1
 starlette==0.20.4
 statsmodels==0.13.2
+streamlit==1.18.1
 tenacity==8.1.0
 threadpoolctl==3.1.0
 tomli==2.0.1
@@ -156,4 +157,4 @@ wheel==0.37.1
 wrapt==1.14.1
 xgboost==1.6.2
 yarl==1.8.1
-zipp==3.10.0
+zipp==3.10.0
diff --git a/whitebox/.streamlit/config.toml b/whitebox/.streamlit/config.toml
@@ -0,0 +1,6 @@
+[theme]
+base="dark"
+primaryColor="#21babe"
+backgroundColor="#1e2025"
+secondaryBackgroundColor="#252a33"
+
diff --git a/whitebox/api/v1/dataset_rows.py b/whitebox/api/v1/dataset_rows.py
@@ -45,15 +45,15 @@ async def create_dataset_rows(
     model = crud.models.get(db=db, _id=dict(body[0])["model_id"])
     if model:
         for row in body:
-            if not model.prediction in row.processed:
+            if not model.target_column in row.processed:
                 return errors.bad_request(
-                    f'Column "{model.prediction}" was not found in some or any of the rows in provided training dataset. Please try again!'
+                    f'Column "{model.target_column}" was not found in some or any of the rows in provided training dataset. Please try again!'
                 )
 
-        predictions = list(set(vars(x)["processed"][model.prediction] for x in body))
+        predictions = list(set(vars(x)["processed"][model.target_column] for x in body))
         if len(predictions) <= 1:
             return errors.bad_request(
-                f'Training dataset\'s "{model.prediction}" columns must have at least 2 different values!'
+                f'Training dataset\'s "{model.target_column}" columns must have at least 2 different values!'
             )
 
         new_dataset_rows = crud.dataset_rows.create_many(db=db, obj_list=body)
@@ -66,21 +66,21 @@ async def create_dataset_rows(
             background_tasks.add_task(
                 create_binary_classification_training_model_pipeline,
                 processed_dataset_rows_pd,
-                model.prediction,
+                model.target_column,
                 model.id,
             )
         elif model.type == ModelType.multi_class:
             background_tasks.add_task(
                 create_multiclass_classification_training_model_pipeline,
                 processed_dataset_rows_pd,
-                model.prediction,
+                model.target_column,
                 model.id,
             )
         elif model.type == ModelType.regression:
             background_tasks.add_task(
                 create_regression_training_model_pipeline,
                 processed_dataset_rows_pd,
-                model.prediction,
+                model.target_column,
                 model.id,
             )
         return new_dataset_rows

diff --git a/whitebox/api/v1/inference_rows.py b/whitebox/api/v1/inference_rows.py
@@ -50,8 +50,18 @@ async def create_many_inference_rows(
 ) -> List[InferenceRow]:
     """Inserts a set of inference rows into the database."""
 
-    new_inference_rows = crud.inference_rows.create_many(db=db, obj_list=body)
-    return new_inference_rows
+    model = crud.models.get(db=db, _id=dict(body[0])["model_id"])
+    if model:
+        for row in body:
+            if not model.target_column in row.processed:
+                return errors.bad_request(
+                    f'Column "{model.target_column}" was not found in some or any of the rows in provided inference dataset. Please try again!'
+                )
+
+        new_inference_rows = crud.inference_rows.create_many(db=db, obj_list=body)
+        return new_inference_rows
+    else:
+        return errors.not_found(f"Model with id: {dict(body[0])['model_id']} not found")
 
 
 @inference_rows_router.get(
@@ -138,7 +148,7 @@ async def create_inference_row_xai_report(
 
     xai_report = create_xai_pipeline_per_inference_row(
         training_set=pd.DataFrame(dataset_rows_processed),
-        target=model.prediction,
+        target=model.target_column,
         inference_row=inference_row_series,
         type_of_task=model.type,
         model_id=model.id,

diff --git a/whitebox/cron_tasks/monitoring_metrics.py b/whitebox/cron_tasks/monitoring_metrics.py
@@ -51,10 +51,10 @@ async def run_calculate_drifting_metrics_pipeline(
 
     # We need to drop the target column from the data to calculate drifting metrics
     processed_inference_dropped_target_df = inference_processed_df.drop(
-        [model.prediction], axis=1
+        [model.target_column], axis=1
     )
     processed_training_dropped_target_df = training_processed_df.drop(
-        [model.prediction], axis=1
+        [model.target_column], axis=1
     )
 
     data_drift_report = run_data_drift_pipeline(
@@ -63,7 +63,7 @@ async def run_calculate_drifting_metrics_pipeline(
     concept_drift_report = run_concept_drift_pipeline(
         training_processed_df,
         inference_processed_df,
-        model.prediction,
+        model.target_column,
     )
 
     new_drifting_metric = entities.DriftingMetric(
@@ -115,7 +115,7 @@ async def run_calculate_performance_metrics_pipeline(
     if model.type == ModelType.binary:
         binary_classification_metrics_report = (
             create_binary_classification_evaluation_metrics_pipeline(
-                cleaned_actuals_df, inference_processed_df[model.prediction], labels
+                cleaned_actuals_df, inference_processed_df[model.target_column], labels
             )
         )
 
@@ -130,7 +130,7 @@ async def run_calculate_performance_metrics_pipeline(
     elif model.type == ModelType.multi_class:
         multiclass_classification_metrics_report = (
             create_multiple_classification_evaluation_metrics_pipeline(
-                cleaned_actuals_df, inference_processed_df[model.prediction], labels
+                cleaned_actuals_df, inference_processed_df[model.target_column], labels
             )
         )
 
@@ -144,7 +144,7 @@ async def run_calculate_performance_metrics_pipeline(
 
     elif model.type == ModelType.regression:
         regression_metrics_report = create_regression_evaluation_metrics_pipeline(
-            cleaned_actuals_df, inference_processed_df[model.prediction]
+            cleaned_actuals_df, inference_processed_df[model.target_column]
         )
 
         new_performance_metric = entities.RegressionMetrics(

diff --git a/whitebox/entities/Model.py b/whitebox/entities/Model.py
@@ -13,7 +13,7 @@ class Model(Base):
     description = Column(String)
     type = Column("type", Enum(ModelType))
     labels = Column(JSON, nullable=True)
-    prediction = Column(String)
+    target_column = Column(String)
     created_at = Column(DateTime)
     updated_at = Column(DateTime)
 

diff --git a/whitebox/schemas/model.py b/whitebox/schemas/model.py
@@ -14,7 +14,7 @@ class ModelBase(BaseModel):
     name: str
     description: str
     type: ModelType
-    prediction: str
+    target_column: str
     labels: Optional[Dict[str, int]]
 
 

diff --git a/whitebox/sdk/whitebox.py b/whitebox/sdk/whitebox.py
@@ -1,11 +1,12 @@
 from enum import Enum
 import numpy as np
 import pandas as pd
-from whitebox.schemas.model import ModelCreateDto, ModelType
-from typing import Dict, Optional
+from whitebox.schemas.model import ModelCreateDto, ModelType, ModelUpdateDto
+from typing import Dict, Optional, Union
 import requests
 import logging
 from fastapi import status
+from fastapi.encoders import jsonable_encoder
 
 from whitebox.schemas.modelMonitor import (
     AlertSeverity,
@@ -39,7 +40,7 @@ def create_model(
         self,
         name: str,
         type: ModelType,
-        prediction: str,
+        target_column: str,
         labels: Dict[str, int] = None,
         description: str = "",
     ) -> dict:
@@ -51,11 +52,12 @@ def create_model(
             description=description,
             type=type,
             labels=labels,
-            prediction=prediction,
+            target_column=target_column,
         )
+
         result = requests.post(
             url=f"{self.host}/{self.api_version}/models",
-            json=new_model.dict(),
+            json=jsonable_encoder(new_model),
             headers={"api-key": self.api_key},
         )
 
@@ -75,6 +77,35 @@ def get_model(self, model_id: str) -> dict:
 
         return result.json()
 
+    def get_models(self) -> Union[dict, None]:
+        """
+        Returns all the models. If no models exist, returns None.
+        """
+        result = requests.get(
+            url=f"{self.host}/{self.api_version}/models",
+            headers={"api-key": self.api_key},
+        )
+        if result.status_code == status.HTTP_404_NOT_FOUND:
+            return None
+
+        return result.json()
+
+    def update_model(self, model_id: str, body: ModelUpdateDto):
+        """
+        Updates a model by its id. If any error occurs, returns False.
+        """
+        result = requests.put(
+            url=f"{self.host}/{self.api_version}/models/{model_id}",
+            json=body,
+            headers={"api-key": self.api_key},
+        )
+        logger.info(result.json())
+
+        if result.status_code == status.HTTP_200_OK:
+            return True
+
+        return False
+
     def delete_model(self, model_id: str):
         """
         Deletes a model by its id. If any error occurs, returns False.
@@ -169,6 +200,20 @@ def log_inferences(
 
         return False
 
+    def get_inferences(self, model_id: str):
+        """
+        Given a specific model id, this endpoint fetches all the inferences.
+        If some of the required data isn't found, returns None.
+        """
+        result = requests.get(
+            url=f"{self.host}/{self.api_version}/inference-rows?model_id={model_id}",
+            headers={"api-key": self.api_key},
+        )
+        if result.status_code == status.HTTP_404_NOT_FOUND:
+            return None
+
+        return result.json()
+
     def get_xai_row(self, inference_row_id: str):
         """
         Given a specific inference row id, this endpoint produces an explainability report for this inference.
@@ -191,8 +236,8 @@ def create_model_monitor(
         metric: MonitorMetrics,
         severity: AlertSeverity,
         email: str,
-        feature: Optional[str],
         lower_threshold: Optional[float],
+        feature: Optional[Union[str, None]] = None,
     ) -> dict:
         """
         Creates a monitor for a model.
@@ -218,6 +263,18 @@ def create_model_monitor(
         logger.info(result.json())
         return result.json()
 
+    def get_monitors(self, model_id: str) -> dict:
+        """
+        Returns all monitors for a model.
+        """
+        result = requests.get(
+            url=f"{self.host}/{self.api_version}/model-monitors?modelId={model_id}",
+            headers={"api-key": self.api_key},
+        )
+
+        logger.info(result.json())
+        return result.json()
+
     def get_alerts(self, model_id: str = "") -> dict:
         """
         Returns all alerts for a model.