PROJECT 087 · PYTHON SOURCE

Multiclass fault recognition

Study-specific code. Shared modules, dependency versions, and reproduction instructions are included in all project files.

from pathlib import Path
import sys
ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(ROOT))
import numpy as np
import pandas as pd
from scipy.stats import spearmanr
from sklearn.decomposition import PCA
from sklearn.ensemble import IsolationForest
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import confusion_matrix, precision_score, recall_score
from portfolio.data import load
from portfolio.constants import *
from portfolio.methods import result, sql, rates, associations, distribution, regression, classification, cluster
from portfolio.engine import execute

META = {'id': 87, 'dataset': 'steel', 'title': 'Multiclass fault recognition', 'question': 'Can inspection features distinguish the seven recorded fault classes?', 'method': 'Fixed multiclass classification with grouped identical inputs and macro-F1 evaluation.', 'action': 'Validate against new production batches and healthy examples before considering deployment.', 'limitations': 'Every source row is a recorded fault. The data cannot estimate a production defect rate or distinguish healthy plates. Batch and machine IDs are absent, so grouped exact-input holdouts do not prove factory transfer. '}

def analyze():
    df = load('steel').copy()
    t,p,e=classification(df,STEEL_FEATURES,'fault')
    out=result(t,'model','macro_f1','Macro F1','Seven one-hot target indicators were removed during preparation. Healthy plates are not represented.',extra={'predictions':p},evaluation=e)
    return out

if __name__ == "__main__":
    execute(Path(__file__).parent, META, analyze)