Spaces:
Sleeping
Sleeping
| """QC filters applied to the per-tuber morphometrics dataframe. | |
| Three steps: | |
| - Drop ADC plot images whose ROI cropping removed substantial tuber area. | |
| - Derive the PCA-based axis ratio from eccentricity. | |
| - Filter out tubers with axis_ratio_pca above the pooled 99.5th percentile. | |
| """ | |
| from __future__ import annotations | |
| import numpy as np | |
| import pandas as pd | |
| # ADC plot images dropped because the cropping step removed substantial | |
| # tuber area. Values are the raw "Plot" column (image_id[-8:]). | |
| ADC_QC_DROP_PLOTS: tuple[str, ...] = ( | |
| "5_ADC116", | |
| "5_ADC131", | |
| "5_ADC141", | |
| "5_ADC129", | |
| "5_ADC105", | |
| "5_ADC205", | |
| ) | |
| AR_PCA_FILTER_QUANTILE: float = 0.995 | |
| def drop_qc_plots( | |
| df: pd.DataFrame, | |
| drop_plots: tuple[str, ...] = ADC_QC_DROP_PLOTS, | |
| plot_col: str = "Plot", | |
| ) -> pd.DataFrame: | |
| """Drop plots listed in drop_plots from the per-tuber dataframe.""" | |
| return df[~df[plot_col].isin(drop_plots)].copy() | |
| def derive_axis_ratio_pca(df: pd.DataFrame) -> pd.DataFrame: | |
| """Add axis_ratio_pca = 1 / sqrt(1 - eccentricity^2).""" | |
| df = df.copy() | |
| ecc = np.clip(df["eccentricity"], 0, 0.999999) | |
| df["axis_ratio_pca"] = 1.0 / np.sqrt(1.0 - ecc**2) | |
| return df | |
| def filter_axis_ratio( | |
| df: pd.DataFrame, | |
| quantile: float = AR_PCA_FILTER_QUANTILE, | |
| ) -> pd.DataFrame: | |
| """Keep tubers with axis_ratio_pca at or below the pooled quantile threshold.""" | |
| upper = df["axis_ratio_pca"].quantile(quantile) | |
| return df[df["axis_ratio_pca"] <= upper].copy() | |