PROJECT 100 · PYTHON SOURCE

Shell shape and specimen groups

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': 100, 'dataset': 'abalone', 'title': 'Shell shape and specimen groups', 'question': 'How do shell-shape ratios and observed rings differ among recorded specimen categories?', 'method': 'Positive-length ratios and category-level robust summaries.', 'action': 'Investigate biological sampling composition before pooling specimen categories in a measurement study.', 'limitations': 'Physical measurements use source scaling. Rings are the modeled target; the source describes an approximate age conversion. Site and animal group identifiers are unavailable, limiting biological generalization. '}

def analyze():
    df = load('abalone').copy()
    df=df[df.length>0].copy();df['diameter_ratio']=df.diameter/df.length;df['height_ratio']=df.height/df.length
    t=df.groupby('sex').agg(specimens=('row_id','size'),median_diameter_ratio=('diameter_ratio','median'),median_height_ratio=('height_ratio','median'),median_rings=('rings','median')).reset_index()
    out=result(t,'sex','median_diameter_ratio','Diameter / length','The source category I denotes infant specimens, not a third adult sex. Ratios use the source scaling consistently.')
    return out

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