update api for audio task

README.md

@@ -1,71 +1,9 @@
----
-title: Submission Template
-emoji: 🔥
-colorFrom: yellow
-colorTo: green
-sdk: docker
-pinned: false
----
+# Submission API 
 
+## Dev locally
+To develop locally:
+  - `docker build -t myname .`
+  - `docker run -d --name myname -p 7860:7860 myname`
+  - then access the api locally through: http://0.0.0.0:7860/
 
-# Random Baseline Model for Climate Disinformation Classification
 
-## Model Description
-
-This is a random baseline model for the Frugal AI Challenge 2024, specifically for the text classification task of identifying climate disinformation. The model serves as a performance floor, randomly assigning labels to text inputs without any learning.
-
-### Intended Use
-
-- **Primary intended uses**: Baseline comparison for climate disinformation classification models
-- **Primary intended users**: Researchers and developers participating in the Frugal AI Challenge
-- **Out-of-scope use cases**: Not intended for production use or real-world classification tasks
-
-## Training Data
-
-The model uses the QuotaClimat/frugalaichallenge-text-train dataset:
-- Size: ~6000 examples
-- Split: 80% train, 20% test
-- 8 categories of climate disinformation claims
-
-### Labels
-0. No relevant claim detected
-1. Global warming is not happening
-2. Not caused by humans
-3. Not bad or beneficial
-4. Solutions harmful/unnecessary
-5. Science is unreliable
-6. Proponents are biased
-7. Fossil fuels are needed
-
-## Performance
-
-### Metrics
-- **Accuracy**: ~12.5% (random chance with 8 classes)
-- **Environmental Impact**:
-  - Emissions tracked in gCO2eq
-  - Energy consumption tracked in Wh
-
-### Model Architecture
-The model implements a random choice between the 8 possible labels, serving as the simplest possible baseline.
-
-## Environmental Impact
-
-Environmental impact is tracked using CodeCarbon, measuring:
-- Carbon emissions during inference
-- Energy consumption during inference
-
-This tracking helps establish a baseline for the environmental impact of model deployment and inference.
-
-## Limitations
-- Makes completely random predictions
-- No learning or pattern recognition
-- No consideration of input text
-- Serves only as a baseline reference
-- Not suitable for any real-world applications
-
-## Ethical Considerations
-
-- Dataset contains sensitive topics related to climate disinformation
-- Model makes random predictions and should not be used for actual classification
-- Environmental impact is tracked to promote awareness of AI's carbon footprint
-```

app.py

@@ -1,6 +1,6 @@
 from fastapi import FastAPI
 from dotenv import load_dotenv
-from tasks import text, image, audio
+from tasks import audio
 
 # Load environment variables
 load_dotenv()
@@ -11,8 +11,6 @@ app = FastAPI(
 )
 
 # Include all routers
-app.include_router(text.router)
-app.include_router(image.router)
 app.include_router(audio.router)
 
 @app.get("/")
@@ -20,8 +18,6 @@ async def root():
     return {
         "message": "Welcome to the Frugal AI Challenge API",
         "endpoints": {
-            "text": "/text - Text classification task",
-            "image": "/image - Image classification task (coming soon)",
             "audio": "/audio - Audio classification task (coming soon)"
         }
     } 

notebooks/template-image.ipynb

@@ -1,416 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Image task notebook template\n",
-    "## Loading the necessary libraries"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from fastapi import APIRouter\n",
-    "from datetime import datetime\n",
-    "from datasets import load_dataset\n",
-    "from sklearn.metrics import accuracy_score, precision_score, recall_score\n",
-    "\n",
-    "import random\n",
-    "\n",
-    "import sys\n",
-    "sys.path.append('../')\n",
-    "\n",
-    "from tasks.utils.evaluation import ImageEvaluationRequest\n",
-    "from tasks.utils.emissions import tracker, clean_emissions_data, get_space_info\n",
-    "from tasks.image import parse_boxes,compute_iou,compute_max_iou"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Loading the datasets and splitting them"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4f62b23ca587477d9f37430e687bf951",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "README.md:   0%|          | 0.00/7.72k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "c:\\Users\\theo.alvesdacosta\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\file_download.py:139: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\theo.alvesdacosta\\.cache\\huggingface\\hub\\datasets--pyronear--pyro-sdis. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
-      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
-      "  warnings.warn(message)\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "70735dd748e343119b5a7cd966dcd0f0",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train-00000-of-00007.parquet:   0%|          | 0.00/433M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "903c3227c24649f1a0424e039d74d303",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train-00001-of-00007.parquet:   0%|          | 0.00/434M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "8795b7696f124715b9d52287d5cd4ee0",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train-00002-of-00007.parquet:   0%|          | 0.00/432M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4b6c1240bf024d61bf913584d13834f5",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train-00003-of-00007.parquet:   0%|          | 0.00/428M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "cd5f8172a31f4fd79d489db96ede9c21",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train-00004-of-00007.parquet:   0%|          | 0.00/431M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "416af82dba3a4ab7ad13190703c90757",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train-00005-of-00007.parquet:   0%|          | 0.00/429M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6819ad85508641a1a64bea34303446ac",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train-00006-of-00007.parquet:   0%|          | 0.00/431M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "90a7f85c802b4330b502c8bbd3cca7f9",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "val-00000-of-00001.parquet:   0%|          | 0.00/407M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "b93f2f19aafb43e2b8db0fd7bb3ebd34",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating train split:   0%|          | 0/29537 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c14c0f2cde184c959970dfccaa26b2d2",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating val split:   0%|          | 0/4099 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "request = ImageEvaluationRequest()\n",
-    "\n",
-    "# Load and prepare the dataset\n",
-    "dataset = load_dataset(request.dataset_name)\n",
-    "\n",
-    "# Split dataset\n",
-    "train_test = dataset[\"train\"].train_test_split(test_size=request.test_size, seed=request.test_seed)\n",
-    "test_dataset = train_test[\"test\"]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Random Baseline"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Start tracking emissions\n",
-    "tracker.start()\n",
-    "tracker.start_task(\"inference\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "#--------------------------------------------------------------------------------------------\n",
-    "# YOUR MODEL INFERENCE CODE HERE\n",
-    "# Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.\n",
-    "#--------------------------------------------------------------------------------------------   \n",
-    "\n",
-    "# Make random predictions (placeholder for actual model inference)\n",
-    "\n",
-    "predictions = []\n",
-    "true_labels = []\n",
-    "pred_boxes = []\n",
-    "true_boxes_list = []  # List of lists, each inner list contains boxes for one image\n",
-    "\n",
-    "for example in test_dataset:\n",
-    "    # Parse true annotation (YOLO format: class_id x_center y_center width height)\n",
-    "    annotation = example.get(\"annotations\", \"\").strip()\n",
-    "    has_smoke = len(annotation) > 0\n",
-    "    true_labels.append(int(has_smoke))\n",
-    "    \n",
-    "    # Make random classification prediction\n",
-    "    pred_has_smoke = random.random() > 0.5\n",
-    "    predictions.append(int(pred_has_smoke))\n",
-    "    \n",
-    "    # If there's a true box, parse it and make random box prediction\n",
-    "    if has_smoke:\n",
-    "        # Parse all true boxes from the annotation\n",
-    "        image_true_boxes = parse_boxes(annotation)\n",
-    "        true_boxes_list.append(image_true_boxes)\n",
-    "        \n",
-    "        # For baseline, make one random box prediction per image\n",
-    "        # In a real model, you might want to predict multiple boxes\n",
-    "        random_box = [\n",
-    "            random.random(),  # x_center\n",
-    "            random.random(),  # y_center\n",
-    "            random.random() * 0.5,  # width (max 0.5)\n",
-    "            random.random() * 0.5   # height (max 0.5)\n",
-    "        ]\n",
-    "        pred_boxes.append(random_box)\n",
-    "\n",
-    "\n",
-    "#--------------------------------------------------------------------------------------------\n",
-    "# YOUR MODEL INFERENCE STOPS HERE\n",
-    "#--------------------------------------------------------------------------------------------   "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Stop tracking emissions\n",
-    "emissions_data = tracker.stop_task()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "\n",
-    "# Calculate classification metrics\n",
-    "classification_accuracy = accuracy_score(true_labels, predictions)\n",
-    "classification_precision = precision_score(true_labels, predictions)\n",
-    "classification_recall = recall_score(true_labels, predictions)\n",
-    "\n",
-    "# Calculate mean IoU for object detection (only for images with smoke)\n",
-    "# For each image, we compute the max IoU between the predicted box and all true boxes\n",
-    "ious = []\n",
-    "for true_boxes, pred_box in zip(true_boxes_list, pred_boxes):\n",
-    "    max_iou = compute_max_iou(true_boxes, pred_box)\n",
-    "    ious.append(max_iou)\n",
-    "\n",
-    "mean_iou = float(np.mean(ious)) if ious else 0.0"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'submission_timestamp': '2025-01-22T15:57:37.288173',\n",
-       " 'classification_accuracy': 0.5001692620176033,\n",
-       " 'classification_precision': 0.8397129186602871,\n",
-       " 'classification_recall': 0.4972677595628415,\n",
-       " 'mean_iou': 0.002819781629108398,\n",
-       " 'energy_consumed_wh': 0.779355299496116,\n",
-       " 'emissions_gco2eq': 0.043674291628462855,\n",
-       " 'emissions_data': {'run_id': '4e750cd5-60f0-444c-baee-b5f7b31f784b',\n",
-       "  'duration': 51.72819679998793,\n",
-       "  'emissions': 4.3674291628462856e-05,\n",
-       "  'emissions_rate': 8.445163379568943e-07,\n",
-       "  'cpu_power': 42.5,\n",
-       "  'gpu_power': 0.0,\n",
-       "  'ram_power': 11.755242347717285,\n",
-       "  'cpu_energy': 0.0006104993474311617,\n",
-       "  'gpu_energy': 0,\n",
-       "  'ram_energy': 0.00016885595206495442,\n",
-       "  'energy_consumed': 0.0007793552994961161,\n",
-       "  'country_name': 'France',\n",
-       "  'country_iso_code': 'FRA',\n",
-       "  'region': 'île-de-france',\n",
-       "  'cloud_provider': '',\n",
-       "  'cloud_region': '',\n",
-       "  'os': 'Windows-11-10.0.22631-SP0',\n",
-       "  'python_version': '3.12.7',\n",
-       "  'codecarbon_version': '3.0.0_rc0',\n",
-       "  'cpu_count': 12,\n",
-       "  'cpu_model': '13th Gen Intel(R) Core(TM) i7-1365U',\n",
-       "  'gpu_count': None,\n",
-       "  'gpu_model': None,\n",
-       "  'ram_total_size': 31.347312927246094,\n",
-       "  'tracking_mode': 'machine',\n",
-       "  'on_cloud': 'N',\n",
-       "  'pue': 1.0},\n",
-       " 'dataset_config': {'dataset_name': 'pyronear/pyro-sdis',\n",
-       "  'test_size': 0.2,\n",
-       "  'test_seed': 42}}"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "\n",
-    "# Prepare results dictionary\n",
-    "results = {\n",
-    "    \"submission_timestamp\": datetime.now().isoformat(),\n",
-    "    \"classification_accuracy\": float(classification_accuracy),\n",
-    "    \"classification_precision\": float(classification_precision),\n",
-    "    \"classification_recall\": float(classification_recall),\n",
-    "    \"mean_iou\": mean_iou,\n",
-    "    \"energy_consumed_wh\": emissions_data.energy_consumed * 1000,\n",
-    "    \"emissions_gco2eq\": emissions_data.emissions * 1000,\n",
-    "    \"emissions_data\": clean_emissions_data(emissions_data),\n",
-    "    \"dataset_config\": {\n",
-    "        \"dataset_name\": request.dataset_name,\n",
-    "        \"test_size\": request.test_size,\n",
-    "        \"test_seed\": request.test_seed\n",
-    "    }\n",
-    "}\n",
-    "results"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "base",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

notebooks/template-text.ipynb

@@ -1,1642 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Text task notebook template\n",
-    "## Loading the necessary libraries"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[codecarbon WARNING @ 19:48:07] Multiple instances of codecarbon are allowed to run at the same time.\n",
-      "[codecarbon INFO @ 19:48:07] [setup] RAM Tracking...\n",
-      "[codecarbon INFO @ 19:48:07] [setup] CPU Tracking...\n",
-      "[codecarbon WARNING @ 19:48:09] We saw that you have a 13th Gen Intel(R) Core(TM) i7-1365U but we don't know it. Please contact us.\n",
-      "[codecarbon WARNING @ 19:48:09] No CPU tracking mode found. Falling back on CPU constant mode. \n",
-      " Windows OS detected: Please install Intel Power Gadget to measure CPU\n",
-      "\n",
-      "[codecarbon WARNING @ 19:48:11] We saw that you have a 13th Gen Intel(R) Core(TM) i7-1365U but we don't know it. Please contact us.\n",
-      "[codecarbon INFO @ 19:48:11] CPU Model on constant consumption mode: 13th Gen Intel(R) Core(TM) i7-1365U\n",
-      "[codecarbon WARNING @ 19:48:11] No CPU tracking mode found. Falling back on CPU constant mode.\n",
-      "[codecarbon INFO @ 19:48:11] [setup] GPU Tracking...\n",
-      "[codecarbon INFO @ 19:48:11] No GPU found.\n",
-      "[codecarbon INFO @ 19:48:11] >>> Tracker's metadata:\n",
-      "[codecarbon INFO @ 19:48:11]   Platform system: Windows-11-10.0.22631-SP0\n",
-      "[codecarbon INFO @ 19:48:11]   Python version: 3.12.7\n",
-      "[codecarbon INFO @ 19:48:11]   CodeCarbon version: 3.0.0_rc0\n",
-      "[codecarbon INFO @ 19:48:11]   Available RAM : 31.347 GB\n",
-      "[codecarbon INFO @ 19:48:11]   CPU count: 12\n",
-      "[codecarbon INFO @ 19:48:11]   CPU model: 13th Gen Intel(R) Core(TM) i7-1365U\n",
-      "[codecarbon INFO @ 19:48:11]   GPU count: None\n",
-      "[codecarbon INFO @ 19:48:11]   GPU model: None\n",
-      "[codecarbon INFO @ 19:48:11] Saving emissions data to file c:\\git\\submission-template\\notebooks\\emissions.csv\n"
-     ]
-    }
-   ],
-   "source": [
-    "from fastapi import APIRouter\n",
-    "from datetime import datetime\n",
-    "from datasets import load_dataset\n",
-    "from sklearn.metrics import accuracy_score\n",
-    "import random\n",
-    "\n",
-    "import sys\n",
-    "sys.path.append('../tasks')\n",
-    "\n",
-    "from utils.evaluation import TextEvaluationRequest\n",
-    "from utils.emissions import tracker, clean_emissions_data, get_space_info\n",
-    "\n",
-    "\n",
-    "# Define the label mapping\n",
-    "LABEL_MAPPING = {\n",
-    "    \"0_not_relevant\": 0,\n",
-    "    \"1_not_happening\": 1,\n",
-    "    \"2_not_human\": 2,\n",
-    "    \"3_not_bad\": 3,\n",
-    "    \"4_solutions_harmful_unnecessary\": 4,\n",
-    "    \"5_science_unreliable\": 5,\n",
-    "    \"6_proponents_biased\": 6,\n",
-    "    \"7_fossil_fuels_needed\": 7\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Loading the datasets and splitting them"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "668da7bf85434e098b95c3ec447d78fe",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "README.md:   0%|          | 0.00/5.18k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "c:\\Users\\theo.alvesdacosta\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\file_download.py:139: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\theo.alvesdacosta\\.cache\\huggingface\\hub\\datasets--QuotaClimat--frugalaichallenge-text-train. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
-      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
-      "  warnings.warn(message)\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5b68d43359eb429395da8be7d4b15556",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "train.parquet:   0%|          | 0.00/1.21M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "140a304773914e9db8f698eabeb40298",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating train split:   0%|          | 0/6091 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6d04e8ab1906400e8e0029949dc523a5",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Map:   0%|          | 0/6091 [00:00<?, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "request = TextEvaluationRequest()\n",
-    "\n",
-    "# Load and prepare the dataset\n",
-    "dataset = load_dataset(request.dataset_name)\n",
-    "\n",
-    "# Convert string labels to integers\n",
-    "dataset = dataset.map(lambda x: {\"label\": LABEL_MAPPING[x[\"label\"]]})\n",
-    "\n",
-    "# Split dataset\n",
-    "train_test = dataset[\"train\"].train_test_split(test_size=request.test_size, seed=request.test_seed)\n",
-    "test_dataset = train_test[\"test\"]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Random Baseline"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Start tracking emissions\n",
-    "tracker.start()\n",
-    "tracker.start_task(\"inference\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[1,\n",
-       " 7,\n",
-       " 6,\n",
-       " 6,\n",
-       " 2,\n",
-       " 0,\n",
-       " 1,\n",
-       " 7,\n",
-       " 3,\n",
-       " 6,\n",
-       " 6,\n",
-       " 3,\n",
-       " 6,\n",
-       " 6,\n",
-       " 5,\n",
-       " 0,\n",
-       " 2,\n",
-       " 6,\n",
-       " 2,\n",
-       " 6,\n",
-       " 5,\n",
-       " 4,\n",
-       " 1,\n",
-       " 3,\n",
-       " 6,\n",
-       " 4,\n",
-       " 2,\n",
-       " 1,\n",
-       " 4,\n",
-       " 0,\n",
-       " 3,\n",
-       " 4,\n",
-       " 1,\n",
-       " 5,\n",
-       " 5,\n",
-       " 1,\n",
-       " 2,\n",
-       " 7,\n",
-       " 6,\n",
-       " 1,\n",
-       " 3,\n",
-       " 1,\n",
-       " 7,\n",
-       " 7,\n",
-       " 0,\n",
-       " 0,\n",
-       " 3,\n",
-       " 3,\n",
-       " 3,\n",
-       " 4,\n",
-       " 1,\n",
-       " 4,\n",
-       " 4,\n",
-       " 1,\n",
-       " 4,\n",
-       " 5,\n",
-       " 6,\n",
-       " 1,\n",
-       " 2,\n",
-       " 2,\n",
-       " 2,\n",
-       " 5,\n",
-       " 2,\n",
-       " 7,\n",
-       " 2,\n",
-       " 7,\n",
-       " 7,\n",
-       " 6,\n",
-       " 4,\n",
-       " 2,\n",
-       " 0,\n",
-       " 1,\n",
-       " 6,\n",
-       " 3,\n",
-       " 2,\n",
-       " 5,\n",
-       " 5,\n",
-       " 2,\n",
-       " 0,\n",
-       " 7,\n",
-       " 0,\n",
-       " 1,\n",
-       " 5,\n",
-       " 5,\n",
-       " 7,\n",
-       " 4,\n",
-       " 6,\n",
-       " 7,\n",
-       " 1,\n",
-       " 7,\n",
-       " 1,\n",
-       " 0,\n",
-       " 3,\n",
-       " 4,\n",
-       " 2,\n",
-       " 5,\n",
-       " 3,\n",
-       " 3,\n",
-       " 3,\n",
-       " 2,\n",
-       " 2,\n",
-       " 1,\n",
-       " 0,\n",
-       " 4,\n",
-       " 5,\n",
-       " 7,\n",
-       " 0,\n",
-       " 3,\n",
-       " 1,\n",
-       " 4,\n",
-       " 6,\n",
-       " 0,\n",
-       " 7,\n",
-       " 1,\n",
-       " 1,\n",
-       " 2,\n",
-       " 2,\n",
-       " 4,\n",
-       " 0,\n",
-       " 4,\n",
-       " 3,\n",
-       " 4,\n",
-       " 4,\n",
-       " 2,\n",
-       " 2,\n",
-       " 3,\n",
-       " 3,\n",
-       " 7,\n",
-       " 4,\n",
-       " 7,\n",
-       " 6,\n",
-       " 4,\n",
-       " 5,\n",
-       " 4,\n",
-       " 3,\n",
-       " 6,\n",
-       " 0,\n",
-       " 4,\n",
-       " 0,\n",
-       " 1,\n",
-       " 3,\n",
-       " 6,\n",
-       " 7,\n",
-       " 3,\n",
-       " 3,\n",
-       " 0,\n",
-       " 1,\n",
-       " 2,\n",
-       " 4,\n",
-       " 4,\n",
-       " 3,\n",
-       " 1,\n",
-       " 2,\n",
-       " 4,\n",
-       " 3,\n",
-       " 0,\n",
-       " 5,\n",
-       " 3,\n",
-       " 6,\n",
-       " 3,\n",
-       " 6,\n",
-       " 1,\n",
-       " 3,\n",
-       " 4,\n",
-       " 5,\n",
-       " 4,\n",
-       " 0,\n",
-       " 7,\n",
-       " 3,\n",
-       " 6,\n",
-       " 7,\n",
-       " 4,\n",
-       " 4,\n",
-       " 5,\n",
-       " 3,\n",
-       " 1,\n",
-       " 7,\n",
-       " 4,\n",
-       " 1,\n",
-       " 0,\n",
-       " 3,\n",
-       " 0,\n",
-       " 5,\n",
-       " 3,\n",
-       " 6,\n",
-       " 3,\n",
-       " 0,\n",
-       " 7,\n",
-       " 2,\n",
-       " 0,\n",
-       " 4,\n",
-       " 1,\n",
-       " 2,\n",
-       " 6,\n",
-       " 3,\n",
-       " 4,\n",
-       " 4,\n",
-       " 5,\n",
-       " 1,\n",
-       " 5,\n",
-       " 4,\n",
-       " 0,\n",
-       " 1,\n",
-       " 7,\n",
-       " 3,\n",
-       " 6,\n",
-       " 0,\n",
-       " 7,\n",
-       " 4,\n",
-       " 6,\n",
-       " 3,\n",
-       " 0,\n",
-       " 0,\n",
-       " 4,\n",
-       " 6,\n",
-       " 6,\n",
-       " 4,\n",
-       " 0,\n",
-       " 5,\n",
-       " 7,\n",
-       " 5,\n",
-       " 1,\n",
-       " 3,\n",
-       " 6,\n",
-       " 2,\n",
-       " 3,\n",
-       " 2,\n",
-       " 4,\n",
-       " 5,\n",
-       " 1,\n",
-       " 5,\n",
-       " 0,\n",
-       " 3,\n",
-       " 3,\n",
-       " 0,\n",
-       " 0,\n",
-       " 6,\n",
-       " 6,\n",
-       " 2,\n",
-       " 0,\n",
-       " 7,\n",
-       " 4,\n",
-       " 5,\n",
-       " 7,\n",
-       " 1,\n",
-       " 0,\n",
-       " 4,\n",
-       " 5,\n",
-       " 1,\n",
-       " 7,\n",
-       " 0,\n",
-       " 7,\n",
-       " 2,\n",
-       " 6,\n",
-       " 1,\n",
-       " 3,\n",
-       " 5,\n",
-       " 5,\n",
-       " 6,\n",
-       " 5,\n",
-       " 4,\n",
-       " 3,\n",
-       " 7,\n",
-       " 4,\n",
-       " 3,\n",
-       " 5,\n",
-       " 5,\n",
-       " 7,\n",
-       " 2,\n",
-       " 6,\n",
-       " 1,\n",
-       " 5,\n",
-       " 0,\n",
-       " 3,\n",
-       " 4,\n",
-       " 2,\n",
-       " 3,\n",
-       " 7,\n",
-       " 0,\n",
-       " 1,\n",
-       " 7,\n",
-       " 6,\n",
-       " 7,\n",
-       " 7,\n",
-       " 5,\n",
-       " 6,\n",
-       " 3,\n",
-       " 2,\n",
-       " 3,\n",
-       " 0,\n",
-       " 4,\n",
-       " 3,\n",
-       " 5,\n",
-       " 6,\n",
-       " 0,\n",
-       " 0,\n",
-       " 6,\n",
-       " 6,\n",
-       " 1,\n",
-       " 4,\n",
-       " 0,\n",
-       " 4,\n",
-       " 2,\n",
-       " 7,\n",
-       " 5,\n",
-       " 7,\n",
-       " 6,\n",
-       " 3,\n",
-       " 5,\n",
-       " 6,\n",
-       " 0,\n",
-       " 4,\n",
-       " 5,\n",
-       " 6,\n",
-       " 1,\n",
-       " 2,\n",
-       " 1,\n",
-       " 5,\n",
-       " 3,\n",
-       " 0,\n",
-       " 3,\n",
-       " 7,\n",
-       " 1,\n",
-       " 0,\n",
-       " 7,\n",
-       " 0,\n",
-       " 1,\n",
-       " 0,\n",
-       " 4,\n",
-       " 1,\n",
-       " 1,\n",
-       " 0,\n",
-       " 7,\n",
-       " 1,\n",
-       " 0,\n",
-       " 7,\n",
-       " 6,\n",
-       " 2,\n",
-       " 3,\n",
-       " 7,\n",
-       " 4,\n",
-       " 3,\n",
-       " 4,\n",
-       " 3,\n",
-       " 3,\n",
-       " 2,\n",
-       " 5,\n",
-       " 1,\n",
-       " 5,\n",
-       " 1,\n",
-       " 7,\n",
-       " 3,\n",
-       " 2,\n",
-       " 6,\n",
-       " 4,\n",
-       " 4,\n",
-       " 1,\n",
-       " 2,\n",
-       " 6,\n",
-       " 7,\n",
-       " 2,\n",
-       " 7,\n",
-       " 1,\n",
-       " 3,\n",
-       " 5,\n",
-       " 2,\n",
-       " 6,\n",
-       " 4,\n",
-       " 6,\n",
-       " 7,\n",
-       " 0,\n",
-       " 5,\n",
-       " 1,\n",
-       " 6,\n",
-       " 5,\n",
-       " 3,\n",
-       " 6,\n",
-       " 5,\n",
-       " 4,\n",
-       " 7,\n",
-       " 6,\n",
-       " 5,\n",
-       " 4,\n",
-       " 3,\n",
-       " 0,\n",
-       " 0,\n",
-       " 1,\n",
-       " 7,\n",
-       " 7,\n",
-       " 6,\n",
-       " 1,\n",
-       " 4,\n",
-       " 5,\n",
-       " 6,\n",
-       " 1,\n",
-       " 5,\n",
-       " 1,\n",
-       " 2,\n",
-       " 6,\n",
-       " 2,\n",
-       " 6,\n",
-       " 0,\n",
-       " 2,\n",
-       " 1,\n",
-       " 5,\n",
-       " 5,\n",
-       " 1,\n",
-       " 7,\n",
-       " 0,\n",
-       " 5,\n",
-       " 5,\n",
-       " 1,\n",
-       " 7,\n",
-       " 7,\n",
-       " 2,\n",
-       " 1,\n",
-       " 0,\n",
-       " 1,\n",
-       " 0,\n",
-       " 5,\n",
-       " 4,\n",
-       " 2,\n",
-       " 7,\n",
-       " 4,\n",
-       " 3,\n",
-       " 6,\n",
-       " 7,\n",
-       " 5,\n",
-       " 1,\n",
-       " 0,\n",
-       " 7,\n",
-       " 2,\n",
-       " 1,\n",
-       " 2,\n",
-       " 3,\n",
-       " 1,\n",
-       " 0,\n",
-       " 3,\n",
-       " 2,\n",
-       " 6,\n",
-       " 0,\n",
-       " 5,\n",
-       " 4,\n",
-       " 7,\n",
-       " 1,\n",
-       " 1,\n",
-       " 0,\n",
-       " 7,\n",
-       " 0,\n",
-       " 6,\n",
-       " 7,\n",
-       " 6,\n",
-       " 1,\n",
-       " 5,\n",
-       " 5,\n",
-       " 7,\n",
-       " 6,\n",
-       " 1,\n",
-       " 7,\n",
-       " 6,\n",
-       " 5,\n",
-       " 4,\n",
-       " 1,\n",
-       " 4,\n",
-       " 7,\n",
-       " 5,\n",
-       " 4,\n",
-       " 0,\n",
-       " 0,\n",
-       " 7,\n",
-       " 0,\n",
-       " 0,\n",
-       " 3,\n",
-       " 6,\n",
-       " 2,\n",
-       " 5,\n",
-       " 3,\n",
-       " 0,\n",
-       " 3,\n",
-       " 6,\n",
-       " 5,\n",
-       " 7,\n",
-       " 2,\n",
-       " 6,\n",
-       " 7,\n",
-       " 5,\n",
-       " 2,\n",
-       " 3,\n",
-       " 6,\n",
-       " 7,\n",
-       " 7,\n",
-       " 7,\n",
-       " 6,\n",
-       " 1,\n",
-       " 7,\n",
-       " 4,\n",
-       " 2,\n",
-       " 7,\n",
-       " 5,\n",
-       " 4,\n",
-       " 1,\n",
-       " 2,\n",
-       " 3,\n",
-       " 7,\n",
-       " 0,\n",
-       " 2,\n",
-       " 7,\n",
-       " 6,\n",
-       " 1,\n",
-       " 4,\n",
-       " 0,\n",
-       " 6,\n",
-       " 3,\n",
-       " 1,\n",
-       " 0,\n",
-       " 3,\n",
-       " 4,\n",
-       " 7,\n",
-       " 7,\n",
-       " 4,\n",
-       " 2,\n",
-       " 1,\n",
-       " 0,\n",
-       " 5,\n",
-       " 1,\n",
-       " 7,\n",
-       " 4,\n",
-       " 6,\n",
-       " 7,\n",
-       " 7,\n",
-       " 3,\n",
-       " 4,\n",
-       " 3,\n",
-       " 5,\n",
-       " 4,\n",
-       " 4,\n",
-       " 5,\n",
-       " 0,\n",
-       " 1,\n",
-       " 3,\n",
-       " 7,\n",
-       " 5,\n",
-       " 4,\n",
-       " 7,\n",
-       " 3,\n",
-       " 3,\n",
-       " 3,\n",
-       " 5,\n",
-       " 3,\n",
-       " 3,\n",
-       " 4,\n",
-       " 0,\n",
-       " 1,\n",
-       " 7,\n",
-       " 4,\n",
-       " 7,\n",
-       " 7,\n",
-       " 5,\n",
-       " 0,\n",
-       " 0,\n",
-       " 5,\n",
-       " 2,\n",
-       " 6,\n",
-       " 2,\n",
-       " 6,\n",
-       " 7,\n",
-       " 6,\n",
-       " 5,\n",
-       " 7,\n",
-       " 5,\n",
-       " 7,\n",
-       " 1,\n",
-       " 6,\n",
-       " 6,\n",
-       " 0,\n",
-       " 4,\n",
-       " 7,\n",
-       " 3,\n",
-       " 0,\n",
-       " 0,\n",
-       " 2,\n",
-       " 5,\n",
-       " 2,\n",
-       " 3,\n",
-       " 7,\n",
-       " 1,\n",
-       " 0,\n",
-       " 3,\n",
-       " 0,\n",
-       " 0,\n",
-       " 3,\n",
-       " 3,\n",
-       " 7,\n",
-       " 3,\n",
-       " 0,\n",
-       " 1,\n",
-       " 1,\n",
-       " 6,\n",
-       " 0,\n",
-       " 0,\n",
-       " 5,\n",
-       " 0,\n",
-       " 3,\n",
-       " 4,\n",
-       " 6,\n",
-       " 7,\n",
-       " 4,\n",
-       " 0,\n",
-       " 4,\n",
-       " 4,\n",
-       " 5,\n",
-       " 4,\n",
-       " 4,\n",
-       " 3,\n",
-       " 6,\n",
-       " 5,\n",
-       " 2,\n",
-       " 0,\n",
-       " 6,\n",
-       " 0,\n",
-       " 6,\n",
-       " 4,\n",
-       " 3,\n",
-       " 5,\n",
-       " 7,\n",
-       " 7,\n",
-       " 5,\n",
-       " 5,\n",
-       " 1,\n",
-       " 5,\n",
-       " 2,\n",
-       " 7,\n",
-       " 7,\n",
-       " 6,\n",
-       " 6,\n",
-       " 7,\n",
-       " 6,\n",
-       " 5,\n",
-       " 2,\n",
-       " 4,\n",
-       " 0,\n",
-       " 4,\n",
-       " 4,\n",
-       " 7,\n",
-       " 5,\n",
-       " 2,\n",
-       " 7,\n",
-       " 0,\n",
-       " 6,\n",
-       " 0,\n",
-       " 2,\n",
-       " 6,\n",
-       " 6,\n",
-       " 2,\n",
-       " 3,\n",
-       " 0,\n",
-       " 5,\n",
-       " 0,\n",
-       " 5,\n",
-       " 7,\n",
-       " 2,\n",
-       " 7,\n",
-       " 4,\n",
-       " 7,\n",
-       " 4,\n",
-       " 0,\n",
-       " 7,\n",
-       " 1,\n",
-       " 4,\n",
-       " 5,\n",
-       " 0,\n",
-       " 5,\n",
-       " 5,\n",
-       " 2,\n",
-       " 0,\n",
-       " 2,\n",
-       " 5,\n",
-       " 5,\n",
-       " 6,\n",
-       " 3,\n",
-       " 4,\n",
-       " 1,\n",
-       " 7,\n",
-       " 7,\n",
-       " 2,\n",
-       " 3,\n",
-       " 2,\n",
-       " 5,\n",
-       " 0,\n",
-       " 7,\n",
-       " 2,\n",
-       " 3,\n",
-       " 7,\n",
-       " 2,\n",
-       " 4,\n",
-       " 0,\n",
-       " 5,\n",
-       " 7,\n",
-       " 3,\n",
-       " 6,\n",
-       " 7,\n",
-       " 6,\n",
-       " 4,\n",
-       " 3,\n",
-       " 6,\n",
-       " 5,\n",
-       " 4,\n",
-       " 0,\n",
-       " 3,\n",
-       " 4,\n",
-       " 3,\n",
-       " 5,\n",
-       " 2,\n",
-       " 4,\n",
-       " 0,\n",
-       " 3,\n",
-       " 6,\n",
-       " 1,\n",
-       " 3,\n",
-       " 1,\n",
-       " 4,\n",
-       " 3,\n",
-       " 3,\n",
-       " 3,\n",
-       " 0,\n",
-       " 7,\n",
-       " 6,\n",
-       " 2,\n",
-       " 4,\n",
-       " 6,\n",
-       " 5,\n",
-       " 4,\n",
-       " 1,\n",
-       " 7,\n",
-       " 6,\n",
-       " 1,\n",
-       " 4,\n",
-       " 3,\n",
-       " 0,\n",
-       " 7,\n",
-       " 3,\n",
-       " 1,\n",
-       " 2,\n",
-       " 1,\n",
-       " 6,\n",
-       " 4,\n",
-       " 7,\n",
-       " 1,\n",
-       " 7,\n",
-       " 1,\n",
-       " 5,\n",
-       " 1,\n",
-       " 6,\n",
-       " 3,\n",
-       " 0,\n",
-       " 2,\n",
-       " 6,\n",
-       " 7,\n",
-       " 7,\n",
-       " 0,\n",
-       " 1,\n",
-       " 4,\n",
-       " 0,\n",
-       " 4,\n",
-       " 5,\n",
-       " 3,\n",
-       " 6,\n",
-       " 2,\n",
-       " 3,\n",
-       " 4,\n",
-       " 1,\n",
-       " 6,\n",
-       " 2,\n",
-       " 4,\n",
-       " 4,\n",
-       " 6,\n",
-       " 4,\n",
-       " 5,\n",
-       " 7,\n",
-       " 1,\n",
-       " 7,\n",
-       " 7,\n",
-       " 4,\n",
-       " 7,\n",
-       " 4,\n",
-       " 3,\n",
-       " 3,\n",
-       " 6,\n",
-       " 1,\n",
-       " 2,\n",
-       " 0,\n",
-       " 0,\n",
-       " 0,\n",
-       " 2,\n",
-       " 5,\n",
-       " 6,\n",
-       " 5,\n",
-       " 7,\n",
-       " 5,\n",
-       " 7,\n",
-       " 1,\n",
-       " 1,\n",
-       " 2,\n",
-       " 1,\n",
-       " 6,\n",
-       " 5,\n",
-       " 7,\n",
-       " 0,\n",
-       " 0,\n",
-       " 5,\n",
-       " 5,\n",
-       " 0,\n",
-       " 3,\n",
-       " 7,\n",
-       " 5,\n",
-       " 2,\n",
-       " 5,\n",
-       " 4,\n",
-       " 2,\n",
-       " 3,\n",
-       " 6,\n",
-       " 2,\n",
-       " 3,\n",
-       " 6,\n",
-       " 0,\n",
-       " 0,\n",
-       " 2,\n",
-       " 6,\n",
-       " 0,\n",
-       " 1,\n",
-       " 3,\n",
-       " 3,\n",
-       " 6,\n",
-       " 4,\n",
-       " 6,\n",
-       " 4,\n",
-       " 6,\n",
-       " 0,\n",
-       " 0,\n",
-       " 2,\n",
-       " 3,\n",
-       " 6,\n",
-       " 2,\n",
-       " 2,\n",
-       " 6,\n",
-       " 6,\n",
-       " 2,\n",
-       " 4,\n",
-       " 3,\n",
-       " 3,\n",
-       " 6,\n",
-       " 7,\n",
-       " 7,\n",
-       " 1,\n",
-       " 1,\n",
-       " 7,\n",
-       " 7,\n",
-       " 6,\n",
-       " 1,\n",
-       " 7,\n",
-       " 0,\n",
-       " 0,\n",
-       " 2,\n",
-       " 4,\n",
-       " 2,\n",
-       " 2,\n",
-       " 3,\n",
-       " 0,\n",
-       " 1,\n",
-       " 4,\n",
-       " 0,\n",
-       " 4,\n",
-       " 6,\n",
-       " 5,\n",
-       " 3,\n",
-       " 2,\n",
-       " 3,\n",
-       " 2,\n",
-       " 3,\n",
-       " 6,\n",
-       " 2,\n",
-       " 1,\n",
-       " 4,\n",
-       " 7,\n",
-       " 6,\n",
-       " 4,\n",
-       " 5,\n",
-       " 6,\n",
-       " 7,\n",
-       " 7,\n",
-       " 2,\n",
-       " 0,\n",
-       " 5,\n",
-       " 5,\n",
-       " 0,\n",
-       " 3,\n",
-       " 6,\n",
-       " 6,\n",
-       " 5,\n",
-       " 4,\n",
-       " 4,\n",
-       " 7,\n",
-       " 0,\n",
-       " 5,\n",
-       " 1,\n",
-       " 7,\n",
-       " 0,\n",
-       " 3,\n",
-       " 1,\n",
-       " 7,\n",
-       " 0,\n",
-       " 1,\n",
-       " 4,\n",
-       " 7,\n",
-       " 5,\n",
-       " 0,\n",
-       " 4,\n",
-       " 0,\n",
-       " 0,\n",
-       " 1,\n",
-       " 0,\n",
-       " 6,\n",
-       " 4,\n",
-       " 0,\n",
-       " 5,\n",
-       " 4,\n",
-       " 6,\n",
-       " 6,\n",
-       " 7,\n",
-       " 2,\n",
-       " 6,\n",
-       " 2,\n",
-       " 6,\n",
-       " 0,\n",
-       " 3,\n",
-       " 2,\n",
-       " 2,\n",
-       " 1,\n",
-       " 5,\n",
-       " 4,\n",
-       " 7,\n",
-       " 6,\n",
-       " 6,\n",
-       " 2,\n",
-       " 5,\n",
-       " 5,\n",
-       " 5,\n",
-       " 0,\n",
-       " 3,\n",
-       " 5,\n",
-       " 4,\n",
-       " 5,\n",
-       " 7,\n",
-       " 5,\n",
-       " 0,\n",
-       " 5,\n",
-       " 0,\n",
-       " 0,\n",
-       " 2,\n",
-       " 0,\n",
-       " 2,\n",
-       " 1,\n",
-       " 0,\n",
-       " 2,\n",
-       " 4,\n",
-       " 3,\n",
-       " 4,\n",
-       " 1,\n",
-       " 7,\n",
-       " 2,\n",
-       " 1,\n",
-       " 0,\n",
-       " 3,\n",
-       " 0,\n",
-       " 3,\n",
-       " 1,\n",
-       " 1,\n",
-       " 0,\n",
-       " 5,\n",
-       " 3,\n",
-       " 1,\n",
-       " 2,\n",
-       " 5,\n",
-       " 6,\n",
-       " 7,\n",
-       " 6,\n",
-       " 7,\n",
-       " 0,\n",
-       " 2,\n",
-       " 6,\n",
-       " 3,\n",
-       " 1,\n",
-       " 5,\n",
-       " 4,\n",
-       " 2,\n",
-       " 4,\n",
-       " 6,\n",
-       " 5,\n",
-       " 2,\n",
-       " 7,\n",
-       " ...]"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "\n",
-    "#--------------------------------------------------------------------------------------------\n",
-    "# YOUR MODEL INFERENCE CODE HERE\n",
-    "# Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.\n",
-    "#--------------------------------------------------------------------------------------------   \n",
-    "\n",
-    "# Make random predictions (placeholder for actual model inference)\n",
-    "true_labels = test_dataset[\"label\"]\n",
-    "predictions = [random.randint(0, 7) for _ in range(len(true_labels))]\n",
-    "\n",
-    "predictions\n",
-    "\n",
-    "#--------------------------------------------------------------------------------------------\n",
-    "# YOUR MODEL INFERENCE STOPS HERE\n",
-    "#--------------------------------------------------------------------------------------------   "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[codecarbon WARNING @ 19:53:32] Background scheduler didn't run for a long period (47s), results might be inaccurate\n",
-      "[codecarbon INFO @ 19:53:32] Energy consumed for RAM : 0.000156 kWh. RAM Power : 11.755242347717285 W\n",
-      "[codecarbon INFO @ 19:53:32] Delta energy consumed for CPU with constant : 0.000564 kWh, power : 42.5 W\n",
-      "[codecarbon INFO @ 19:53:32] Energy consumed for All CPU : 0.000564 kWh\n",
-      "[codecarbon INFO @ 19:53:32] 0.000720 kWh of electricity used since the beginning.\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "EmissionsData(timestamp='2025-01-21T19:53:32', project_name='codecarbon', run_id='908f2e7e-4bb2-4991-a0f6-56bf8d7eda21', experiment_id='5b0fa12a-3dd7-45bb-9766-cc326314d9f1', duration=47.736408500000834, emissions=4.032368007471064e-05, emissions_rate=8.444466886328872e-07, cpu_power=42.5, gpu_power=0.0, ram_power=11.755242347717285, cpu_energy=0.0005636615353475565, gpu_energy=0, ram_energy=0.00015590305493261682, energy_consumed=0.0007195645902801733, country_name='France', country_iso_code='FRA', region='île-de-france', cloud_provider='', cloud_region='', os='Windows-11-10.0.22631-SP0', python_version='3.12.7', codecarbon_version='3.0.0_rc0', cpu_count=12, cpu_model='13th Gen Intel(R) Core(TM) i7-1365U', gpu_count=None, gpu_model=None, longitude=2.3494, latitude=48.8558, ram_total_size=31.347312927246094, tracking_mode='machine', on_cloud='N', pue=1.0)"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Stop tracking emissions\n",
-    "emissions_data = tracker.stop_task()\n",
-    "emissions_data"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "0.10090237899917966"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Calculate accuracy\n",
-    "accuracy = accuracy_score(true_labels, predictions)\n",
-    "accuracy"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'submission_timestamp': '2025-01-21T19:53:46.639165',\n",
-       " 'accuracy': 0.10090237899917966,\n",
-       " 'energy_consumed_wh': 0.7195645902801733,\n",
-       " 'emissions_gco2eq': 0.040323680074710634,\n",
-       " 'emissions_data': {'run_id': '908f2e7e-4bb2-4991-a0f6-56bf8d7eda21',\n",
-       "  'duration': 47.736408500000834,\n",
-       "  'emissions': 4.032368007471064e-05,\n",
-       "  'emissions_rate': 8.444466886328872e-07,\n",
-       "  'cpu_power': 42.5,\n",
-       "  'gpu_power': 0.0,\n",
-       "  'ram_power': 11.755242347717285,\n",
-       "  'cpu_energy': 0.0005636615353475565,\n",
-       "  'gpu_energy': 0,\n",
-       "  'ram_energy': 0.00015590305493261682,\n",
-       "  'energy_consumed': 0.0007195645902801733,\n",
-       "  'country_name': 'France',\n",
-       "  'country_iso_code': 'FRA',\n",
-       "  'region': 'île-de-france',\n",
-       "  'cloud_provider': '',\n",
-       "  'cloud_region': '',\n",
-       "  'os': 'Windows-11-10.0.22631-SP0',\n",
-       "  'python_version': '3.12.7',\n",
-       "  'codecarbon_version': '3.0.0_rc0',\n",
-       "  'cpu_count': 12,\n",
-       "  'cpu_model': '13th Gen Intel(R) Core(TM) i7-1365U',\n",
-       "  'gpu_count': None,\n",
-       "  'gpu_model': None,\n",
-       "  'ram_total_size': 31.347312927246094,\n",
-       "  'tracking_mode': 'machine',\n",
-       "  'on_cloud': 'N',\n",
-       "  'pue': 1.0},\n",
-       " 'dataset_config': {'dataset_name': 'QuotaClimat/frugalaichallenge-text-train',\n",
-       "  'test_size': 0.2,\n",
-       "  'test_seed': 42}}"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Prepare results dictionary\n",
-    "results = {\n",
-    "    \"submission_timestamp\": datetime.now().isoformat(),\n",
-    "    \"accuracy\": float(accuracy),\n",
-    "    \"energy_consumed_wh\": emissions_data.energy_consumed * 1000,\n",
-    "    \"emissions_gco2eq\": emissions_data.emissions * 1000,\n",
-    "    \"emissions_data\": clean_emissions_data(emissions_data),\n",
-    "    \"dataset_config\": {\n",
-    "        \"dataset_name\": request.dataset_name,\n",
-    "        \"test_size\": request.test_size,\n",
-    "        \"test_seed\": request.test_seed\n",
-    "    }\n",
-    "}\n",
-    "\n",
-    "results"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Development of the model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "90f50ab19698484489f36976745efad3",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "config.json:   0%|          | 0.00/1.15k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "c:\\Users\\theo.alvesdacosta\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\file_download.py:139: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\theo.alvesdacosta\\.cache\\huggingface\\hub\\models--facebook--bart-large-mnli. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
-      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
-      "  warnings.warn(message)\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6e3974d8ff284603821f7beca9bd353d",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "model.safetensors:   0%|          | 0.00/1.63G [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bc29cb379c644b00b1bdf61d5426d99d",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "tokenizer_config.json:   0%|          | 0.00/26.0 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "635503cf819747c9a83f22aa4f2f11db",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "vocab.json:   0%|          | 0.00/899k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3a5f53e451e8483ca7c33f42245abd13",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "merges.txt:   0%|          | 0.00/456k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "84f922d1b68a4a0faa5e920d004efca0",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "tokenizer.json:   0%|          | 0.00/1.36M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Device set to use cpu\n"
-     ]
-    }
-   ],
-   "source": [
-    "from transformers import pipeline\n",
-    "classifier = pipeline(\"zero-shot-classification\",\n",
-    "                      model=\"facebook/bart-large-mnli\")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "sequence_to_classify = \"one day I will see the world\"\n",
-    "\n",
-    "candidate_labels = [\n",
-    "    \"Not related to climate change disinformation\",\n",
-    "    \"Climate change is not real and not happening\",\n",
-    "    \"Climate change is not human-induced\",\n",
-    "    \"Climate change impacts are not that bad\",\n",
-    "    \"Climate change solutions are harmful and unnecessary\",\n",
-    "    \"Climate change science is unreliable\",\n",
-    "    \"Climate change proponents are biased\",\n",
-    "    \"Fossil fuels are needed to address climate change\"\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'sequence': 'one day I will see the world',\n",
-       " 'labels': ['Fossil fuels are needed to address climate change',\n",
-       "  'Climate change science is unreliable',\n",
-       "  'Not related to climate change disinformation',\n",
-       "  'Climate change proponents are biased',\n",
-       "  'Climate change impacts are not that bad',\n",
-       "  'Climate change solutions are harmful and unnecessary',\n",
-       "  'Climate change is not human-induced',\n",
-       "  'Climate change is not real and not happening'],\n",
-       " 'scores': [0.16242119669914246,\n",
-       "  0.15683825314044952,\n",
-       "  0.1564282774925232,\n",
-       "  0.14603719115257263,\n",
-       "  0.12794046103954315,\n",
-       "  0.10180754214525223,\n",
-       "  0.0936085507273674,\n",
-       "  0.0549185685813427]}"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "classifier(sequence_to_classify, candidate_labels)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[codecarbon WARNING @ 11:00:07] Already started tracking\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5d66a13f76a4411d95b62d4a73012495",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "0it [00:00, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "[codecarbon WARNING @ 11:05:57] Background scheduler didn't run for a long period (349s), results might be inaccurate\n",
-      "[codecarbon INFO @ 11:05:57] Energy consumed for RAM : 0.018069 kWh. RAM Power : 11.755242347717285 W\n",
-      "[codecarbon INFO @ 11:05:57] Delta energy consumed for CPU with constant : 0.004122 kWh, power : 42.5 W\n",
-      "[codecarbon INFO @ 11:05:57] Energy consumed for All CPU : 0.065327 kWh\n",
-      "[codecarbon INFO @ 11:05:57] 0.083395 kWh of electricity used since the beginning.\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "EmissionsData(timestamp='2025-01-22T11:05:57', project_name='codecarbon', run_id='908f2e7e-4bb2-4991-a0f6-56bf8d7eda21', experiment_id='5b0fa12a-3dd7-45bb-9766-cc326314d9f1', duration=349.19709450000664, emissions=0.0002949120266226386, emissions_rate=8.445461750018632e-07, cpu_power=42.5, gpu_power=0.0, ram_power=11.755242347717285, cpu_energy=0.004122396676597424, gpu_energy=0, ram_energy=0.0011402244733631148, energy_consumed=0.005262621149960539, country_name='France', country_iso_code='FRA', region='île-de-france', cloud_provider='', cloud_region='', os='Windows-11-10.0.22631-SP0', python_version='3.12.7', codecarbon_version='3.0.0_rc0', cpu_count=12, cpu_model='13th Gen Intel(R) Core(TM) i7-1365U', gpu_count=None, gpu_model=None, longitude=2.3494, latitude=48.8558, ram_total_size=31.347312927246094, tracking_mode='machine', on_cloud='N', pue=1.0)"
-      ]
-     },
-     "execution_count": 26,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Start tracking emissions\n",
-    "tracker.start()\n",
-    "tracker.start_task(\"inference\")\n",
-    "\n",
-    "from tqdm.auto import tqdm\n",
-    "predictions = []\n",
-    "\n",
-    "\n",
-    "\n",
-    "# Option 1: Simple loop approach\n",
-    "\n",
-    "for i, text in tqdm(enumerate(test_dataset[\"quote\"])):\n",
-    "\n",
-    "    result = classifier(text, candidate_labels)\n",
-    "\n",
-    "    # Get index of highest scoring label\n",
-    "\n",
-    "    pred_label = candidate_labels.index(result[\"labels\"][0])\n",
-    "\n",
-    "    predictions.append(pred_label)\n",
-    "    if i == 100:\n",
-    "        break\n",
-    "\n",
-    "\n",
-    "# Stop tracking emissions\n",
-    "emissions_data = tracker.stop_task()\n",
-    "emissions_data\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "0.4"
-      ]
-     },
-     "execution_count": 28,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Calculate accuracy\n",
-    "accuracy = accuracy_score(true_labels[:100], predictions[:100])\n",
-    "accuracy"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "base",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

tasks/image.py

@@ -1,176 +0,0 @@
-from fastapi import APIRouter
-from datetime import datetime
-from datasets import load_dataset
-import numpy as np
-from sklearn.metrics import accuracy_score, precision_score, recall_score
-import random
-import os
-
-from .utils.evaluation import ImageEvaluationRequest
-from .utils.emissions import tracker, clean_emissions_data, get_space_info
-
-from dotenv import load_dotenv
-load_dotenv()
-
-router = APIRouter()
-
-DESCRIPTION = "Random Baseline"
-ROUTE = "/image"
-
-def parse_boxes(annotation_string):
-    """Parse multiple boxes from a single annotation string.
-    Each box has 5 values: class_id, x_center, y_center, width, height"""
-    values = [float(x) for x in annotation_string.strip().split()]
-    boxes = []
-    # Each box has 5 values
-    for i in range(0, len(values), 5):
-        if i + 5 <= len(values):
-            # Skip class_id (first value) and take the next 4 values
-            box = values[i+1:i+5]
-            boxes.append(box)
-    return boxes
-
-def compute_iou(box1, box2):
-    """Compute Intersection over Union (IoU) between two YOLO format boxes."""
-    # Convert YOLO format (x_center, y_center, width, height) to corners
-    def yolo_to_corners(box):
-        x_center, y_center, width, height = box
-        x1 = x_center - width/2
-        y1 = y_center - height/2
-        x2 = x_center + width/2
-        y2 = y_center + height/2
-        return np.array([x1, y1, x2, y2])
-    
-    box1_corners = yolo_to_corners(box1)
-    box2_corners = yolo_to_corners(box2)
-    
-    # Calculate intersection
-    x1 = max(box1_corners[0], box2_corners[0])
-    y1 = max(box1_corners[1], box2_corners[1])
-    x2 = min(box1_corners[2], box2_corners[2])
-    y2 = min(box1_corners[3], box2_corners[3])
-    
-    intersection = max(0, x2 - x1) * max(0, y2 - y1)
-    
-    # Calculate union
-    box1_area = (box1_corners[2] - box1_corners[0]) * (box1_corners[3] - box1_corners[1])
-    box2_area = (box2_corners[2] - box2_corners[0]) * (box2_corners[3] - box2_corners[1])
-    union = box1_area + box2_area - intersection
-    
-    return intersection / (union + 1e-6)
-
-def compute_max_iou(true_boxes, pred_box):
-    """Compute maximum IoU between a predicted box and all true boxes"""
-    max_iou = 0
-    for true_box in true_boxes:
-        iou = compute_iou(true_box, pred_box)
-        max_iou = max(max_iou, iou)
-    return max_iou
-
-@router.post(ROUTE, tags=["Image Task"],
-             description=DESCRIPTION)
-async def evaluate_image(request: ImageEvaluationRequest):
-    """
-    Evaluate image classification and object detection for forest fire smoke.
-    
-    Current Model: Random Baseline
-    - Makes random predictions for both classification and bounding boxes
-    - Used as a baseline for comparison
-    
-    Metrics:
-    - Classification accuracy: Whether an image contains smoke or not
-    - Object Detection accuracy: IoU (Intersection over Union) for smoke bounding boxes
-    """
-    # Get space info
-    username, space_url = get_space_info()
-    
-    # Load and prepare the dataset
-    dataset = load_dataset(request.dataset_name, token=os.getenv("HF_TOKEN"))
-    
-    # Split dataset
-    train_test = dataset["train"].train_test_split(test_size=request.test_size, seed=request.test_seed)
-    test_dataset = train_test["test"]
-    
-    # Start tracking emissions
-    tracker.start()
-    tracker.start_task("inference")
-    
-    #--------------------------------------------------------------------------------------------
-    # YOUR MODEL INFERENCE CODE HERE
-    # Update the code below to replace the random baseline with your model inference
-    #--------------------------------------------------------------------------------------------   
-    
-    predictions = []
-    true_labels = []
-    pred_boxes = []
-    true_boxes_list = []  # List of lists, each inner list contains boxes for one image
-    
-    for example in test_dataset:
-        # Parse true annotation (YOLO format: class_id x_center y_center width height)
-        annotation = example.get("annotations", "").strip()
-        has_smoke = len(annotation) > 0
-        true_labels.append(int(has_smoke))
-        
-        # Make random classification prediction
-        pred_has_smoke = random.random() > 0.5
-        predictions.append(int(pred_has_smoke))
-        
-        # If there's a true box, parse it and make random box prediction
-        if has_smoke:
-            # Parse all true boxes from the annotation
-            image_true_boxes = parse_boxes(annotation)
-            true_boxes_list.append(image_true_boxes)
-            
-            # For baseline, make one random box prediction per image
-            # In a real model, you might want to predict multiple boxes
-            random_box = [
-                random.random(),  # x_center
-                random.random(),  # y_center
-                random.random() * 0.5,  # width (max 0.5)
-                random.random() * 0.5   # height (max 0.5)
-            ]
-            pred_boxes.append(random_box)
-    
-    #--------------------------------------------------------------------------------------------
-    # YOUR MODEL INFERENCE STOPS HERE
-    #--------------------------------------------------------------------------------------------   
-    
-    # Stop tracking emissions
-    emissions_data = tracker.stop_task()
-    
-    # Calculate classification metrics
-    classification_accuracy = accuracy_score(true_labels, predictions)
-    classification_precision = precision_score(true_labels, predictions)
-    classification_recall = recall_score(true_labels, predictions)
-    
-    # Calculate mean IoU for object detection (only for images with smoke)
-    # For each image, we compute the max IoU between the predicted box and all true boxes
-    ious = []
-    for true_boxes, pred_box in zip(true_boxes_list, pred_boxes):
-        max_iou = compute_max_iou(true_boxes, pred_box)
-        ious.append(max_iou)
-    
-    mean_iou = float(np.mean(ious)) if ious else 0.0
-    
-    # Prepare results dictionary
-    results = {
-        "username": username,
-        "space_url": space_url,
-        "submission_timestamp": datetime.now().isoformat(),
-        "model_description": DESCRIPTION,
-        "classification_accuracy": float(classification_accuracy),
-        "classification_precision": float(classification_precision),
-        "classification_recall": float(classification_recall),
-        "mean_iou": mean_iou,
-        "energy_consumed_wh": emissions_data.energy_consumed * 1000,
-        "emissions_gco2eq": emissions_data.emissions * 1000,
-        "emissions_data": clean_emissions_data(emissions_data),
-        "api_route": ROUTE,
-        "dataset_config": {
-            "dataset_name": request.dataset_name,
-            "test_size": request.test_size,
-            "test_seed": request.test_seed
-        }
-    }
-    
-    return results 

tasks/text.py

@@ -1,92 +0,0 @@
-from fastapi import APIRouter
-from datetime import datetime
-from datasets import load_dataset
-from sklearn.metrics import accuracy_score
-import random
-
-from .utils.evaluation import TextEvaluationRequest
-from .utils.emissions import tracker, clean_emissions_data, get_space_info
-
-router = APIRouter()
-
-DESCRIPTION = "Random Baseline"
-ROUTE = "/text"
-
-@router.post(ROUTE, tags=["Text Task"], 
-             description=DESCRIPTION)
-async def evaluate_text(request: TextEvaluationRequest):
-    """
-    Evaluate text classification for climate disinformation detection.
-    
-    Current Model: Random Baseline
-    - Makes random predictions from the label space (0-7)
-    - Used as a baseline for comparison
-    """
-    # Get space info
-    username, space_url = get_space_info()
-
-    # Define the label mapping
-    LABEL_MAPPING = {
-        "0_not_relevant": 0,
-        "1_not_happening": 1,
-        "2_not_human": 2,
-        "3_not_bad": 3,
-        "4_solutions_harmful_unnecessary": 4,
-        "5_science_unreliable": 5,
-        "6_proponents_biased": 6,
-        "7_fossil_fuels_needed": 7
-    }
-
-    # Load and prepare the dataset
-    dataset = load_dataset(request.dataset_name)
-
-    # Convert string labels to integers
-    dataset = dataset.map(lambda x: {"label": LABEL_MAPPING[x["label"]]})
-
-    # Split dataset
-    train_test = dataset["train"].train_test_split(test_size=request.test_size, seed=request.test_seed)
-    test_dataset = train_test["test"]
-    
-    # Start tracking emissions
-    tracker.start()
-    tracker.start_task("inference")
-
-    #--------------------------------------------------------------------------------------------
-    # YOUR MODEL INFERENCE CODE HERE
-    # Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.
-    #--------------------------------------------------------------------------------------------   
-    
-    # Make random predictions (placeholder for actual model inference)
-    true_labels = test_dataset["label"]
-    predictions = [random.randint(0, 7) for _ in range(len(true_labels))]
-
-    #--------------------------------------------------------------------------------------------
-    # YOUR MODEL INFERENCE STOPS HERE
-    #--------------------------------------------------------------------------------------------   
-
-    
-    # Stop tracking emissions
-    emissions_data = tracker.stop_task()
-    
-    # Calculate accuracy
-    accuracy = accuracy_score(true_labels, predictions)
-    
-    # Prepare results dictionary
-    results = {
-        "username": username,
-        "space_url": space_url,
-        "submission_timestamp": datetime.now().isoformat(),
-        "model_description": DESCRIPTION,
-        "accuracy": float(accuracy),
-        "energy_consumed_wh": emissions_data.energy_consumed * 1000,
-        "emissions_gco2eq": emissions_data.emissions * 1000,
-        "emissions_data": clean_emissions_data(emissions_data),
-        "api_route": ROUTE,
-        "dataset_config": {
-            "dataset_name": request.dataset_name,
-            "test_size": request.test_size,
-            "test_seed": request.test_seed
-        }
-    }
-    
-    return results