Spaces:
Sleeping
Sleeping
File size: 4,249 Bytes
4d6e8c2 13923c6 10a1b87 2b9adc7 13923c6 3fae6a6 13923c6 4d6e8c2 70f5f26 1c33274 70f5f26 1c33274 70f5f26 4d6e8c2 70f5f26 4d6e8c2 70f5f26 3a03067 115f829 3a03067 0fb4e95 3fae6a6 0fb4e95 3a03067 3fae6a6 0fb4e95 3a03067 31bc5e0 3a03067 13923c6 bcba639 13923c6 4d6e8c2 71bbef9 70f5f26 4d6e8c2 3034e17 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 |
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 os
import numpy as np
print(os.getcwd())
#
from sentence_transformers import SentenceTransformer
from xgboost import XGBClassifier
import pickle
import xgboost as xgb
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")
#--------------------------------------------------------------------------------------------
# Load a pre-trained Sentence-BERT model
print("loading model")
model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2', device='cpu')
# Generate sentence embeddings
sentence_embeddings = model.encode(test_dataset["quote"])
#load the models
with open("xgb_bin.pkl","rb") as f:
xgb_bin = pickle.load(f)
with open("xgb_multi.pkl","rb") as f:
xgb_multi = pickle.load(f)
# Load the binary model
#xgb_bin = xgb.Booster()
#xgb_bin.load_model("xgb_model_bin.bin")
# Load the binary model
#xgb_multi = xgb.Booster()
#xgb_multi.load_model("xgb_model_muli.bin")
X_train = sentence_embeddings.copy()
y_train = test_dataset["label"].copy()
#binary
y_train_binary = y_train.copy()
y_train_binary[y_train_binary != 0] = 1
#multi class
X_train_multi = X_train[y_train != 0]
y_train_multi = y_train[y_train != 0]
#predictions
y_pred_bin = xgb_bin.predict(X_train)
y_pred_multi = xgb_multi.predict(X_train_multi) + 1
y_pred_bin[y_pred_bin==1] = y_pred_multi
#predictions = xgb.predict(embeddings)
# Make random predictions (placeholder for actual model inference)
true_labels = test_dataset["label"]
#predictions = xgb.predict(embeddings)
#--------------------------------------------------------------------------------------------
# YOUR MODEL INFERENCE STOPS HERE
#--------------------------------------------------------------------------------------------
# Stop tracking emissions
emissions_data = tracker.stop_task()
# Calculate accuracy
accuracy = accuracy_score(true_labels, y_pred_bin)
# 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 |