File size: 3,950 Bytes
4d6e8c2 3d612f9 4d6e8c2 3d612f9 1c33274 70f5f26 3d612f9 1c33274 70f5f26 4d6e8c2 70f5f26 4d6e8c2 3d612f9 4d6e8c2 76fccaf 4d6e8c2 70f5f26 3d612f9 4d6e8c2 3d612f9 4d6e8c2 70f5f26 4d6e8c2 70f5f26 4d6e8c2 1c33274 4d6e8c2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
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
import tensorflow as tf
from huggingface_hub import hf_hub_download
from transformers import ElectraTokenizer
router = APIRouter()
DESCRIPTION = "Electra with balanced dataset"
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
}
# Download our pre-trained model from Hugging Face
model_path = hf_hub_download(repo_id="julianaconsuegra/electra-base-climate-disinformation", filename="tf_model.h5")
# Load the model
model = tf.keras.models.load_model(model_path)
# 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"]
test_dataset = dataset["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.
#--------------------------------------------------------------------------------------------
# Load ELECTRA tokenizer
tokenizer = ElectraTokenizer.from_pretrained("google/electra-base-discriminator")
# Tokenize test data with same parameters as training
inputs = tokenizer(
test_dataset["text"],
truncation=True,
padding="max_length",
return_tensors="tf"
)
# Run model prediction
logits = model.predict({
"input_ids": inputs["input_ids"],
"attention_mask": inputs["attention_mask"]
})
predictions = tf.argmax(logits, axis=1).numpy()
# Get ground truth labels
true_labels = test_dataset["label"]
#--------------------------------------------------------------------------------------------
# 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 |