tasks/text.py

from fastapi import APIRouter
from datetime import datetime
from datasets import load_dataset
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
import pandas as pd
import numpy as np
from .utils.evaluation import TextEvaluationRequest
from .utils.emissions import tracker, clean_emissions_data, get_space_info
import os
import re
import pandas as pd
import tensorflow as tf
from sklearn import preprocessing, decomposition, model_selection, metrics, pipeline



router = APIRouter()

DESCRIPTION = " XGBOOST classification"
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: Bidirectional LSTM with Attention layer classification
    - Current Model: Bidirectional LSTM with Attention layer classification classification 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)
    
    train_dataset = train_test["train"]
    test_dataset = train_test["test"]
    
    from sklearn.feature_extraction.text import TfidfVectorizer
    from sklearn.model_selection import train_test_split
    from sklearn import metrics
    from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
    from sklearn.tree import DecisionTreeClassifier
    from datetime import datetime
    from sklearn.feature_extraction.text import CountVectorizer
    
    tfidf_vect = TfidfVectorizer(stop_words = 'english')
    
    tfidf_train = tfidf_vect.fit_transform(train_dataset['quote'])
    tfidf_train = tfidf_vect.transform(train_dataset['quote'])
    tfidf_test = tfidf_vect.fit_transform(test_dataset['quote'])
    tfidf_test = tfidf_vect.transform(test_dataset['quote'])
    true_labels = test_dataset["label"]
    y_train = train_dataset["label"]
    y_test = test_dataset["label"]

    
            
    # Model
    import xgboost as xgb

    #Parameters: {'colsample_bytree': 0.7039283369765, 'gamma': 0.3317686860083553, 'learning_rate': 0.08341079006092542, 'max_depth': 5, 'n_estimators': 140, 'subsample': 0.6594650911012452}
    #Parameters: {'colsample_bytree': 0.7039283369765, 'gamma': 0.3317686860083553, 'learning_rate': 0.08341079006092542, 'max_depth': 5, 'n_estimators': 140, 'subsample': 0.6594650911012452}
    #Parameters: {'colsample_bytree': 0.7498850106268238, 'gamma': 0.3690168082131852, 'learning_rate': 0.054839600377537934, 'max_depth': 5, 'n_estimators': 125, 'subsample': 0.6272998821416366}
    
    #xgb_model = xgb.XGBRegressor(max_depth=5, objective='multi:softprob', 
    #                             n_estimators=125, num_class=8, colsample_bytree=0.7498850106268238,gamma=0.3690168082131852,
    #                             learning_rate=0.054839600377537934, subsample=0.6272998821416366)
    #xgb_model.fit(tfidf_train, y_train)
    #y_pred = xgb_model.predict(tfidf_train)

    # Start tracking emissions
    tracker.start()
    tracker.start_task("inference")
    
    xgb_model = xgb.XGBRegressor(max_depth=6, objective='multi:softprob', 
                             n_estimators=500, num_class=8, colsample_bytree=0.75,gamma=0.35,
                             learning_rate=0.06, subsample=0.63)
    xgb_model.fit(tfidf_test, y_test)
    predictions = np.argmax(xgb_model.predict(tfidf_test), axis=1)
   
    # 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