File size: 5,334 Bytes
e0f0969 1851abd e0f0969 d62d426 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 |
import os # For filesystem operations
import shutil # For directory cleanup
import zipfile # For extracting model archives
import pathlib # For path manipulations
import pandas # For tabular data handling
import gradio # For interactive UI
import huggingface_hub # For downloading model assets
import autogluon.tabular # For loading and running AutoGluon predictors
# Settings (Selected the following model: Tabular Flowers dataset predictor model )
MODEL_REPO_ID = "its-zion-18/flowers-tabular-autolguon-predictor"
ZIP_FILENAME = "autogluon_predictor_dir.zip"
CACHE_DIR = pathlib.Path("hf_assets")
EXTRACT_DIR = CACHE_DIR / "predictor_native"
# Feature column names and target column names which match original dataset
FEATURE_COLS = [
"flower_diameter_cm",
"petal_length_cm",
"petal_width_cm",
"petal_count",
"stem_height_cm",
"color",
]
TARGET_COL = "color"
# Encoding for outcome questions
OUTCOME_LABELS = {
0: "Pink",
1: "Red",
2: "White",
3: "Orange",
4: "Yellow",
5: "Purple",
}
# Download & load the native predictor
def _prepare_predictor_dir() -> str:
CACHE_DIR.mkdir(parents=True, exist_ok=True)
local_zip = huggingface_hub.hf_hub_download(
repo_id=MODEL_REPO_ID,
filename=ZIP_FILENAME,
repo_type="model",
local_dir=str(CACHE_DIR),
local_dir_use_symlinks=False,
)
if EXTRACT_DIR.exists():
shutil.rmtree(EXTRACT_DIR)
EXTRACT_DIR.mkdir(parents=True, exist_ok=True)
with zipfile.ZipFile(local_zip, "r") as zf:
zf.extractall(str(EXTRACT_DIR))
contents = list(EXTRACT_DIR.iterdir())
predictor_root = contents[0] if (len(contents) == 1 and contents[0].is_dir()) else EXTRACT_DIR
return str(predictor_root)
PREDICTOR_DIR = _prepare_predictor_dir()
PREDICTOR = autogluon.tabular.TabularPredictor.load(PREDICTOR_DIR, require_py_version_match=False)
# A mapping utility to make it easier to encode the variables
def _human_label(c):
try:
ci = int(c)
if ci in OUTCOME_LABELS:
return OUTCOME_LABELS[ci]
except Exception:
pass
if c in OUTCOME_LABELS:
return OUTCOME_LABELS[c]
return str(c)
# This functions takes all of our features, encoding removed due to lack of likert questions for original data.
def do_predict(flower_diameter_cm, petal_length_cm, petal_width_cm, petal_count, stem_height_cm):
row = {
FEATURE_COLS[0]: float(flower_diameter_cm),
FEATURE_COLS[1]: float(petal_length_cm),
FEATURE_COLS[2]: float(petal_width_cm),
FEATURE_COLS[3]: int(petal_count),
FEATURE_COLS[4]: float(stem_height_cm),
}
X = pandas.DataFrame([row], columns=FEATURE_COLS)
pred_series = PREDICTOR.predict(X)
raw_pred = pred_series.iloc[0]
try:
proba = PREDICTOR.predict_proba(X)
if isinstance(proba, pandas.Series):
proba = proba.to_frame().T
except Exception:
proba = None
pred_label = _human_label(raw_pred)
proba_dict = None
if proba is not None:
row0 = proba.iloc[0]
tmp = {}
for cls, val in row0.items():
key = _human_label(cls)
tmp[key] = float(val) + float(tmp.get(key, 0.0))
proba_dict = dict(sorted(tmp.items(), key=lambda kv: kv[1], reverse=True))
df_out = pandas.DataFrame([{
"Predicted outcome": pred_label,
"Confidence (%)": round((proba_dict.get(pred_label, 1.0) if proba_dict else 1.0) * 100, 2),
}])
md = f"**Prediction:** {pred_label}"
if proba_dict:
md += f" \n**Confidence:** {round(proba_dict.get(pred_label, 0.0) * 100, 2)}%"
return proba_dict
# Representative examples
EXAMPLES = [
[3.4, 1.3, 1, 7, 68.7],
[5.7, 3.2, 0.9, 5, 21.2],
[6.9, 3.8, 0.6, 17, 64.2],
[5.6, 1, 1.5, 7, 73.4],
[7.7, 1.5, 1.8, 13, 73.8],
]
# Gradio UI
with gradio.Blocks() as demo:
# Provide an introduction
gradio.Markdown("# What color would your flower be?")
gradio.Markdown("""
This is a simple app that demonstrates builds on the datasets and models
we've been making in class to answer what color flowers you may come across
given the dimensions of the petals.
To use the interface, make selections using the interface elements shown below.
""")
with gradio.Row():
flower_diameter_cm = gradio.Slider(0, 10, step=0.1, value=5.0, label=FEATURE_COLS[0])
petal_length_cm = gradio.Slider(0, 5, step=0.1, value=2.5, label=FEATURE_COLS[1])
petal_width_cm = gradio.Slider(0, 2, step=0.1, value=1.0, label=FEATURE_COLS[2])
with gradio.Row():
petal_count = gradio.Slider(0, 30, step=0.5, value=15.0, label=FEATURE_COLS[3])
stem_height_cm = gradio.Slider(0, 80, step=0.5, value=40.0, label=FEATURE_COLS[4])
proba_pretty = gradio.Label(num_top_classes=5, label="Class probabilities")
inputs = [flower_diameter_cm, petal_length_cm, petal_width_cm, petal_count, stem_height_cm]
for comp in inputs:
comp.change(fn=do_predict, inputs=inputs, outputs=[proba_pretty])
gradio.Examples(
examples=EXAMPLES,
inputs=inputs,
label="Representative examples",
examples_per_page=5,
cache_examples=False,
)
if __name__ == "__main__":
demo.launch()
|