PROJECT 090 · PYTHON SOURCE

Inspection geometry integrity

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': 90, 'dataset': 'steel', 'title': 'Inspection geometry integrity', 'question': 'Do image measurements contain impossible bounds or nonpositive areas?', 'method': 'Explicit geometry validation rules with counts and denominators.', 'action': 'Review flagged records against original images before correcting measurements.', '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()
    rules={'Reversed X bounds':df.x_maximum<df.x_minimum,'Reversed Y bounds':df.y_maximum<df.y_minimum,'Nonpositive area':df.pixels_areas<=0,'Negative X perimeter':df.x_perimeter<0,'Reversed luminosity bounds':df.maximum_of_luminosity<df.minimum_of_luminosity,'Steel type flags not one-hot':(df.typeofsteel_a300+df.typeofsteel_a400)!=1}
    t=pd.DataFrame([{'rule':k,'flagged_rows':int(v.sum()),'checked_rows':len(df),'flagged_share':v.mean()} for k,v in rules.items()])
    out=result(t,'rule','flagged_rows','Rows flagged','These rules check internal consistency only; passing them does not certify source labels or image quality.')
    return out

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