SIENTIAPDE-1273

Enhance MLFlowRepository and Activities classes with new methods and metrics

- Added `check_artifact_exists` method to MLFlowRepository for verifying artifact presence in the MLflow Model Registry.
- Implemented `get_prediction_data` method in MLFlowRepository to retrieve prediction data from models.
- Updated Activities class to integrate ModelMetrics for improved metrics handling.
- Enhanced tests for artifact existence checks and prediction data retrieval, ensuring robust coverage for new functionalities.
- Updated various workflows to include `transform_table_name` in input data for better data handling.

tests.ipynb

@@ -487,6 +487,107 @@
     "except Exception as e:\n",
     "    print(e)\n"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "771ab4ee",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>a</th>\n",
+       "      <th>b</th>\n",
+       "      <th>target</th>\n",
+       "      <th>prediction</th>\n",
+       "      <th>timestamp</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>7</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2025-01-01</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>5</td>\n",
+       "      <td>8</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2025-01-02</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>6</td>\n",
+       "      <td>9</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2025-01-03</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   a  b  target  prediction   timestamp\n",
+       "0  1  4       7           1  2025-01-01\n",
+       "1  2  5       8           2  2025-01-02\n",
+       "2  3  6       9           3  2025-01-03"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from pandas import DataFrame, merge\n",
+    "\n",
+    "retrain_dataset = DataFrame({\n",
+    "    'a': {'2025-01-01': 1, '2025-01-02': 2, '2025-01-03': 3},\n",
+    "    'b': {'2025-01-01': 4, '2025-01-02': 5, '2025-01-03': 6},\n",
+    "    'c': {'2025-01-01': 7, '2025-01-02': 8, '2025-01-03': 9},\n",
+    "})\n",
+    "\n",
+    "prediction_data = DataFrame({\n",
+    "    'prediction': {'1': 1, '2': 2, '3': 3},\n",
+    "})\n",
+    "\n",
+    "prediction_data.index = retrain_dataset.index\n",
+    "\n",
+    "prediction_data = merge(\n",
+    "    retrain_dataset, prediction_data, left_index=True, right_index=True, how='left')\n",
+    "\n",
+    "prediction_data.rename(columns={'c': 'target'}, inplace=True)\n",
+    "\n",
+    "prediction_data['timestamp'] = prediction_data.index\n",
+    "\n",
+    "prediction_data.reset_index(drop=True, inplace=True)\n",
+    "\n",
+    "display(prediction_data)"
+   ]
   }
  ],
  "metadata": {