| import os |
| import sys |
| from pathlib import Path |
|
|
| import joblib |
| import numpy as np |
| import pandas as pd |
| import streamlit as st |
| from huggingface_hub import hf_hub_download |
|
|
| ARTIFACT_REPO = "wasicse/mvppred-artifacts" |
| ARTIFACT_FILES = [ |
| "angle_bundle.joblib", |
| "bite_bundle.joblib", |
| "distance_capacity_bundle.joblib", |
| "endurance_bundle.joblib", |
| "jump_accel_bundle.joblib", |
| "jump_distance_bundle.joblib", |
| "jump_power_bundle.joblib", |
| "jump_vel_bundle.joblib", |
| "sprint_bundle.joblib", |
| ] |
|
|
| @st.cache_resource |
| def ensure_artifacts(): |
| outdir = Path("artifacts_inference") |
| outdir.mkdir(exist_ok=True) |
| for name in ARTIFACT_FILES: |
| target = outdir / name |
| if not target.exists(): |
| downloaded = hf_hub_download( |
| repo_id=ARTIFACT_REPO, |
| filename=name, |
| repo_type="model", |
| ) |
| target.write_bytes(Path(downloaded).read_bytes()) |
|
|
| ensure_artifacts() |
|
|
| ROOT = Path(__file__).resolve().parents[1] |
| if str(ROOT) not in sys.path: |
| sys.path.insert(0, str(ROOT)) |
|
|
| from infer import predict_with_confidence |
|
|
| BUNDLE_DIR = "artifacts_inference" |
| INTERVAL = "q90" |
|
|
| CONFIDENCE_EMOJI = {"High": "🟢 High", "Medium": "🟡 Medium", "Low": "🔴 Low"} |
|
|
| @st.cache_resource |
| def load_bundle(path: str): |
| return joblib.load(path) |
|
|
| st.set_page_config(page_title="Lizard Performance Predictor", layout="wide") |
| st.title("MVPpred: Lizard Performance Predictor") |
| st.caption("Enter morphological measurements (use -1 for missing) to predict lizard performance traits.") |
|
|
| if not os.path.isdir(BUNDLE_DIR): |
| st.error(f"Bundle directory not found: {BUNDLE_DIR}") |
| st.stop() |
|
|
| bundle_files = sorted([f for f in os.listdir(BUNDLE_DIR) if f.endswith("_bundle.joblib")]) |
| if not bundle_files: |
| st.error("No *_bundle.joblib files found in bundle directory.") |
| st.stop() |
|
|
| targets = [f.replace("_bundle.joblib", "") for f in bundle_files] |
| selected_targets = st.multiselect("Targets to predict", targets, default=targets) |
|
|
| st.divider() |
|
|
| default_sample = { |
| "sex_num": 0, |
| "mass": 4.7, |
| "svl": 62.09, |
| "hl": 18.55, |
| "hw": 10.22, |
| "hh": 6.24, |
| "femur": 12.44, |
| "tibia": 10.93, |
| "metat": 4.18, |
| "hindtoe": 9.54, |
| "humerus": 8.43, |
| "radius": 7.19, |
| "metac": 2.48, |
| "foretoe": 6.28, |
| "tail": 72.69, |
| } |
|
|
| st.subheader("Enter sample") |
|
|
| with st.form("manual_input_form"): |
| default_sex = "m" if int(default_sample["sex_num"]) == 0 else "f" |
| sex = st.selectbox("Sex", ["m", "f"], index=0 if default_sex == "m" else 1, |
| help="Biological sex of the lizard") |
|
|
| col1, col2, col3 = st.columns(3) |
|
|
| with col1: |
| mass = st.number_input("mass", value=float(default_sample["mass"]), help="Body mass (g)") |
| svl = st.number_input("svl", value=float(default_sample["svl"]), help="Snout-vent length (mm)") |
| hl = st.number_input("hl", value=float(default_sample["hl"]), help="Head length (mm)") |
| hw = st.number_input("hw", value=float(default_sample["hw"]), help="Head width (mm)") |
| hh = st.number_input("hh", value=float(default_sample["hh"]), help="Head height (mm)") |
|
|
| with col2: |
| femur = st.number_input("femur", value=float(default_sample["femur"]), help="Femur length (mm)") |
| tibia = st.number_input("tibia", value=float(default_sample["tibia"]), help="Tibia length (mm)") |
| metat = st.number_input("metat", value=float(default_sample["metat"]), help="Metatarsal length (mm)") |
| hindtoe = st.number_input("hindtoe", value=float(default_sample["hindtoe"]), help="Longest hind toe length (mm)") |
|
|
| with col3: |
| humerus = st.number_input("humerus", value=float(default_sample["humerus"]), help="Humerus length (mm)") |
| radius = st.number_input("radius", value=float(default_sample["radius"]), help="Radius length (mm)") |
| metac = st.number_input("metac", value=float(default_sample["metac"]), help="Metacarpal length (mm)") |
| foretoe = st.number_input("foretoe", value=float(default_sample["foretoe"]), help="Longest fore toe length (mm)") |
| tail = st.number_input("tail", value=float(default_sample["tail"]), help="Tail length (mm)") |
|
|
| run_btn = st.form_submit_button("Run predictions", use_container_width=True) |
|
|
| if run_btn: |
| if not selected_targets: |
| st.warning("Please select at least one target.") |
| st.stop() |
|
|
| input_row = { |
| "sex": 0 if sex == "m" else 1, |
| "mass": mass, |
| "svl": svl, |
| "hl": hl, |
| "hw": hw, |
| "hh": hh, |
| "femur": femur, |
| "tibia": tibia, |
| "metat": metat, |
| "hindtoe": hindtoe, |
| "humerus": humerus, |
| "radius": radius, |
| "metac": metac, |
| "foretoe": foretoe, |
| "tail": tail, |
| } |
| df = pd.DataFrame([input_row]) |
|
|
| progress = st.progress(0) |
| status = st.empty() |
|
|
| all_outputs = [] |
| n = len(selected_targets) |
|
|
| for i, t in enumerate(selected_targets, start=1): |
| status.write(f"Running {t} ({i}/{n}) …") |
| path = os.path.join(BUNDLE_DIR, f"{t}_bundle.joblib") |
| bundle = load_bundle(path) |
| out = predict_with_confidence(bundle, df, interval=INTERVAL) |
| out.insert(0, "target", t) |
| all_outputs.append(out.reset_index(drop=True)) |
| progress.progress(i / n) |
|
|
| progress.empty() |
| status.success("Predictions complete.") |
|
|
| result = pd.concat(all_outputs, axis=0, ignore_index=True) |
|
|
| |
| result["confidence_label"] = result["confidence_label"].map( |
| lambda x: CONFIDENCE_EMOJI.get(x, x) |
| ) |
|
|
| |
| display_result = result.drop(columns=["confidence_score"]).copy() |
| for col in ["prediction", "lower", "upper"]: |
| display_result[col] = display_result[col].round(3) |
|
|
| |
| if display_result["note"].str.strip().eq("").all(): |
| display_result = display_result.drop(columns=["note"]) |
|
|
| st.subheader("Predictions") |
| st.caption("Interval shown is the 90% conformal prediction interval.") |
|
|
| st.markdown( |
| """ |
| <style> |
| div[data-testid="stDataFrame"] th, div[data-testid="stDataFrame"] td { |
| text-align: center !important; |
| } |
| </style> |
| """, |
| unsafe_allow_html=True, |
| ) |
|
|
| col_cfg = { |
| "target": st.column_config.TextColumn("Target", width="small"), |
| "prediction": st.column_config.NumberColumn("Prediction", format="%.3f", width="small"), |
| "lower": st.column_config.NumberColumn("Lower (90%)", format="%.3f", width="small"), |
| "upper": st.column_config.NumberColumn("Upper (90%)", format="%.3f", width="small"), |
| "confidence_label": st.column_config.TextColumn("Confidence", width="small"), |
| } |
| if "note" in display_result.columns: |
| col_cfg["note"] = st.column_config.TextColumn("Note", width="medium") |
|
|
| st.dataframe(display_result, use_container_width=True, hide_index=True, column_config=col_cfg) |
|
|
| csv_out = result.to_csv(index=False).encode("utf-8") |
| st.download_button( |
| "Download results CSV", |
| csv_out, |
| file_name="predictions_with_confidence.csv", |
| mime="text/csv", |
| ) |
|
|
