From 4d7723345a5d4495f7f3adc26712d3020d52c5cb Mon Sep 17 00:00:00 2001
From: Olivier Sprangers <osprangers@gmail.com>
Date: Thu, 19 Dec 2024 11:06:07 +0100
Subject: [PATCH] update_readme_index_and_fix_ml_frameworks_example

---
 README.md                              |   9 +-
 nbs/examples/MLFrameworksExample.ipynb | 397 +------------------------
 nbs/index.ipynb                        |   7 +-
 3 files changed, 10 insertions(+), 403 deletions(-)

diff --git a/README.md b/README.md
index cfa4a00..db09914 100644
--- a/README.md
+++ b/README.md
@@ -81,7 +81,6 @@ from hierarchicalforecast.evaluation import evaluate
 from hierarchicalforecast.methods import BottomUp, TopDown, MiddleOut
 from utilsforecast.losses import mse
 
-
 # Load TourismSmall dataset
 Y_df, S, tags = HierarchicalData.load('./data', 'TourismSmall')
 Y_df['ds'] = pd.to_datetime(Y_df['ds'])
@@ -92,10 +91,9 @@ Y_test_df  = Y_df.groupby('unique_id').tail(4)
 Y_train_df = Y_df.drop(Y_test_df.index)
 
 # Compute base auto-ARIMA predictions
-fcst = StatsForecast(df=Y_train_df,
-                     models=[AutoARIMA(season_length=4), Naive()],
-                     freq='Q', n_jobs=-1)
-Y_hat_df = fcst.forecast(h=4)
+fcst = StatsForecast(models=[AutoARIMA(season_length=4), Naive()],
+                     freq='QE', n_jobs=-1)
+Y_hat_df = fcst.forecast(df=Y_train_df, h=4)
 
 # Reconcile the base predictions
 reconcilers = [
@@ -116,7 +114,6 @@ Assumes you have a test dataframe.
 df = Y_rec_df.merge(Y_test_df, on=['unique_id', 'ds'])
 evaluation = evaluate(df = df,
                       tags = tags,
-                      train_df = Y_train_df,
                       metrics = [mse],
                       benchmark = "Naive")
 ```
diff --git a/nbs/examples/MLFrameworksExample.ipynb b/nbs/examples/MLFrameworksExample.ipynb
index 15cea8b..e8fd1e7 100644
--- a/nbs/examples/MLFrameworksExample.ipynb
+++ b/nbs/examples/MLFrameworksExample.ipynb
@@ -51,6 +51,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import os\n",
+    "os.environ[\"NIXTLA_ID_AS_COL\"] = \"1\"\n",
+    "\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "\n",
@@ -254,399 +257,7 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:lightning_fabric.utilities.seed:Seed set to 1\n",
-      "INFO:pytorch_lightning.utilities.rank_zero:GPU available: False, used: False\n",
-      "INFO:pytorch_lightning.utilities.rank_zero:TPU available: False, using: 0 TPU cores\n",
-      "INFO:pytorch_lightning.utilities.rank_zero:HPU available: False, using: 0 HPUs\n",
-      "INFO:pytorch_lightning.callbacks.model_summary:\n",
-      "  | Name         | Type          | Params | Mode \n",
-      "-------------------------------------------------------\n",
-      "0 | loss         | GMM           | 99     | train\n",
-      "1 | padder_train | ConstantPad1d | 0      | train\n",
-      "2 | scaler       | TemporalNorm  | 0      | train\n",
-      "3 | blocks       | ModuleList    | 2.8 M  | train\n",
-      "-------------------------------------------------------\n",
-      "2.8 M     Trainable params\n",
-      "999       Non-trainable params\n",
-      "2.8 M     Total params\n",
-      "11.232    Total estimated model params size (MB)\n",
-      "31        Modules in train mode\n",
-      "0         Modules in eval mode\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0476c56f8fb54718a911fcbd68086e1b",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Sanity Checking: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a3e7d4acc4b44fb3b1e3461610ec29bc",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Training: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c7d0340c0e1240c0af60b0e3b69b2b82",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d09edd79b9a948c4a94b62c759a0c58d",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9f9feef9af3d413e9871a21861068600",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "104895d59d854083af7c19a0892d5577",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "fb17fbe721d04f40afb6fdab416e0c31",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "aaac30761f7d4db4b0226329bf32b30c",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7b846d802ad74313908784cfc802c7b0",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5ceb8bbae7d54031bf850ad432443f4f",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "8053a4744bf64d4caaedd75e29a7f94a",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "1ef89ec33119465f98a1b51000b6bb0d",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "41eefe004a65470f805f1483f7e7aff5",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "8221bd951fa64edab600ad4b5b59423b",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a2f1ac7b41a7422e91d8a394e1c35fb6",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5a5525b6589c44a5a9cd2f19197c30be",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6cfa77425cbc4f9e99c7022f4dd6ad08",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "999baad94fe8413ea93d5e7caacf2c78",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "58430441bf4b4b88a94825dbd5f3eca8",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d23389b4e57740568e7ddfd8fd0d0681",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "dfb22402d5a04334a9b060ddff7dc18f",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ab6cebaf6c6c4d09828680bf806f5863",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Validation: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:pytorch_lightning.utilities.rank_zero:`Trainer.fit` stopped: `max_steps=2000` reached.\n",
-      "INFO:pytorch_lightning.utilities.rank_zero:GPU available: False, used: False\n",
-      "INFO:pytorch_lightning.utilities.rank_zero:TPU available: False, using: 0 TPU cores\n",
-      "INFO:pytorch_lightning.utilities.rank_zero:HPU available: False, using: 0 HPUs\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "69d301c3a0034f88bf8cef4e36678228",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Predicting: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:pytorch_lightning.utilities.rank_zero:GPU available: False, used: False\n",
-      "INFO:pytorch_lightning.utilities.rank_zero:TPU available: False, using: 0 TPU cores\n",
-      "INFO:pytorch_lightning.utilities.rank_zero:HPU available: False, using: 0 HPUs\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "36f37528f1d94b288b72fa9086fb49b9",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Predicting: |          | 0/? [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "c:\\Users\\ospra\\miniconda3\\envs\\hierarchicalforecast-backup\\lib\\site-packages\\utilsforecast\\processing.py:130: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
-      "  df[names] = values\n",
-      "c:\\Users\\ospra\\miniconda3\\envs\\hierarchicalforecast-backup\\lib\\site-packages\\utilsforecast\\processing.py:130: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
-      "  df[names] = values\n",
-      "c:\\Users\\ospra\\miniconda3\\envs\\hierarchicalforecast-backup\\lib\\site-packages\\utilsforecast\\processing.py:130: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
-      "  df[names] = values\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "level = np.arange(0, 100, 2)\n",
     "qs = [[50-lv/2, 50+lv/2] for lv in level]\n",
diff --git a/nbs/index.ipynb b/nbs/index.ipynb
index 9c6b644..c6d1e8a 100644
--- a/nbs/index.ipynb
+++ b/nbs/index.ipynb
@@ -117,6 +117,7 @@
     "from hierarchicalforecast.core import HierarchicalReconciliation\n",
     "from hierarchicalforecast.evaluation import evaluate\n",
     "from hierarchicalforecast.methods import BottomUp, TopDown, MiddleOut\n",
+    "from utilsforecast.losses import mse\n",
     "\n",
     "# Load TourismSmall dataset\n",
     "Y_df, S, tags = HierarchicalData.load('./data', 'TourismSmall')\n",
@@ -153,11 +154,9 @@
     "### Evaluation\n",
     "\n",
     "```python\n",
-    "from utilsforecast.losses import mse\n",
-    "\n",
-    "eval_df = Y_rec_df.merge(Y_test_df, on=['unique_id', 'ds'], how='left')\n",
+    "df = Y_rec_df.merge(Y_test_df, on=['unique_id', 'ds'], how='left')\n",
     "\n",
-    "evaluate(df=eval_df, metrics=[mse],\n",
+    "evaluate(df=df, metrics=[mse],\n",
     "                   tags=tags, benchmark='Naive')\n",
     "```"
    ]