Occupancy-Estimation-ML/run_experiments.py at main · MaherDissem/Occupancy-Estimation-ML · GitHub

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
import pandas as pd

from models.naive_bayes import NaiveBayes
from models.svm import SVMclassifier
from models.knn_classifier import KNNClassifier
from models.decision_tree import DecisionTree
from models.random_forest import RandomForest
from main import experiment
from utils import log_experiment


split_ratio = 0.2
run_grid_search = True
run_pca = True
n_components = 3  # originally, the dataset has 13 features
seed = 42
csv_path = "data/processed/h358-2015.csv"
data = pd.read_csv(csv_path, index_col=0)


for model in [
    NaiveBayes(),
    # SVMclassifier(),
    KNNClassifier(),
    DecisionTree(),
    RandomForest(),
]:

    # run with PCA
    run_pca = True
    acc, prec, rec, f1_score, cm, roc, report = experiment(
        data, model, split_ratio, run_pca, run_grid_search, n_components, seed
    )
    log_experiment(
        model,
        run_pca,
        run_grid_search,
        split_ratio,
        n_components,
        seed,
        acc,
        prec,
        rec,
        f1_score,
        roc,
    )

    # run without PCA
    run_pca = False
    acc, prec, rec, f1_score, cm, roc, report = experiment(
        data, model, split_ratio, run_pca, run_grid_search, n_components, seed
    )
    log_experiment(
        model,
        run_pca,
        run_grid_search,
        split_ratio,
        n_components,
        seed,
        acc,
        prec,
        rec,
        f1_score,
        roc,
    )