File size: 3,772 Bytes
4d6e8c2
fe4a4cb
 
 
3b09640
9e5baf4
10b182c
6683ba7
19550e4
 
fe4a4cb
124a5e5
d47a449
124a5e5
4d6e8c2
fe4a4cb
4d6e8c2
3b09640
 
 
4d6e8c2
 
9e5baf4
1c33274
d47a449
 
8002c04
6683ba7
fe4a4cb
10b182c
4d6e8c2
 
fe4a4cb
10b182c
70f5f26
fe4a4cb
70f5f26
4d6e8c2
fe4a4cb
4d6e8c2
fe4a4cb
 
10b182c
fe4a4cb
3b09640
49a96d5
5de0d5d
fe4a4cb
10b182c
 
 
fe4a4cb
10b182c
fe4a4cb
 
 
10b182c
 
fe4a4cb
 
10b182c
 
fe4a4cb
10b182c
9e5baf4
 
 
d47a449
10b182c
8002c04
6683ba7
8002c04
 
6683ba7
d47a449
9e5baf4
10b182c
fe4a4cb
10b182c
 
fe4a4cb
 
10b182c
fe4a4cb
 
10b182c
fe4a4cb
 
4d6e8c2
 
fe4a4cb
70f5f26
fe4a4cb
 
 
 
 
 
4d6e8c2
 
10b182c
 
fe4a4cb
10b182c
 
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
from fastapi import APIRouter
from datetime import datetime
from datasets import load_dataset
from sklearn.metrics import accuracy_score
import os
import joblib
from pathlib import Path
import pickle
import numpy as np
import scipy

from sklearn.preprocessing import StandardScaler
from .fourier import FourierPreprocessor

from .utils.evaluation import AudioEvaluationRequest
from .utils.emissions import tracker, clean_emissions_data, get_space_info

from dotenv import load_dotenv
load_dotenv()

router = APIRouter()

DESCRIPTION = "Random Forest"
ROUTE = "/audio"
# MODEL_PATH = Path(__file__).parent / "audio_models" / "RandomForestClassifier_withScaler.pkl"
MODEL_PATH = Path(__file__).parent / "audio_models" / "RandomForestClassifier_withScaler_rawData.pkl"
# MODEL_PATH = Path(__file__).parent / "audio_models" / "RandomForestClassifier_withScaler_cloudpickle.pkl"


@router.post(ROUTE, tags=["Audio Task"], description=DESCRIPTION)
async def evaluate_audio(request: AudioEvaluationRequest):
    """
    Evaluate audio classification for rainforest sound detection.

    Current Model: Random Baseline
    - Makes random predictions from the label space (0-1)
    - Used as a baseline for comparison
    """
    # Get space info
    username, space_url = get_space_info()

    # Define the label mapping
    LABEL_MAPPING = {"chainsaw": 0, "environment": 1}
    # Load and prepare the dataset
    # Because the dataset is gated, we need to use the HF_TOKEN environment variable to authenticate
    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 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"]

    # Extract audio samples from test_dataset
    x_test = [sample["audio"]["array"] for sample in test_dataset]
    x_test_preprocessed = FourierPreprocessor().transform(x_test)

    clf = joblib.load(MODEL_PATH)

    # with open(MODEL_PATH, 'rb') as f:
    #     clf = pickle.load(f)
    
    predictions = clf.predict(x_test_preprocessed)

    # --------------------------------------------------------------------------------------------
    # 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