PROJECT 086 · PYTHON SOURCE

Inspection luminosity profiles

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': 86, 'dataset': 'steel', 'title': 'Inspection luminosity profiles', 'question': 'Which fault classes have different observed image contrast and luminosity profiles?', 'method': 'Derived image contrast and class-level median sensor summaries.', 'action': 'Evaluate acquisition consistency and whether lighting conditions influence recognition.', '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()
    df['contrast']=df.maximum_of_luminosity-df.minimum_of_luminosity
    t=df.groupby('fault').agg(records=('row_id','size'),median_contrast=('contrast','median'),median_luminosity_index=('luminosity_index','median')).reset_index()
    out=result(t,'fault','median_contrast','Source luminosity range','Contrast depends on image acquisition and is not a causal explanation of manufacturing faults.')
    return out

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