Spaces:
Sleeping
Sleeping
Enzo Reis de Oliveira
commited on
Commit
·
ddae879
1
Parent(s):
b383374
Fixing bug
Browse files- app.py +31 -22
- requirements.txt +1 -2
app.py
CHANGED
|
@@ -2,17 +2,20 @@ import os
|
|
| 2 |
import sys
|
| 3 |
import json
|
| 4 |
import tempfile
|
|
|
|
| 5 |
import pandas as pd
|
| 6 |
import gradio as gr
|
|
|
|
| 7 |
|
| 8 |
-
# 1)
|
| 9 |
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
|
| 10 |
INFERENCE_PATH = os.path.join(BASE_DIR, "smi-ted", "inference")
|
| 11 |
sys.path.insert(0, INFERENCE_PATH)
|
| 12 |
|
|
|
|
| 13 |
from smi_ted_light.load import load_smi_ted
|
| 14 |
|
| 15 |
-
#
|
| 16 |
MODEL_DIR = os.path.join(INFERENCE_PATH, "smi_ted_light")
|
| 17 |
model = load_smi_ted(
|
| 18 |
folder=MODEL_DIR,
|
|
@@ -20,7 +23,7 @@ model = load_smi_ted(
|
|
| 20 |
vocab_filename="bert_vocab_curated.txt",
|
| 21 |
)
|
| 22 |
|
| 23 |
-
#
|
| 24 |
def gerar_embedding_e_csv(smiles: str):
|
| 25 |
smiles = smiles.strip()
|
| 26 |
if not smiles:
|
|
@@ -28,46 +31,52 @@ def gerar_embedding_e_csv(smiles: str):
|
|
| 28 |
return json.dumps(erro), gr.update(visible=False)
|
| 29 |
|
| 30 |
try:
|
|
|
|
| 31 |
vetor = model.encode(smiles, return_torch=True)[0].tolist()
|
| 32 |
-
#
|
| 33 |
df = pd.DataFrame([vetor])
|
| 34 |
tmp = tempfile.NamedTemporaryFile(suffix=".csv", delete=False)
|
| 35 |
df.to_csv(tmp.name, index=False)
|
| 36 |
tmp.close()
|
| 37 |
-
#
|
| 38 |
return json.dumps(vetor), gr.update(value=tmp.name, visible=True)
|
| 39 |
except Exception as e:
|
| 40 |
erro = {"erro": str(e)}
|
| 41 |
return json.dumps(erro), gr.update(visible=False)
|
| 42 |
|
| 43 |
-
#
|
| 44 |
with gr.Blocks() as demo:
|
| 45 |
gr.Markdown(
|
| 46 |
"""
|
| 47 |
-
|
| 48 |
-
Cole uma sequência SMILES e
|
| 49 |
-
|
| 50 |
-
|
| 51 |
"""
|
| 52 |
)
|
| 53 |
|
| 54 |
with gr.Row():
|
| 55 |
-
|
| 56 |
-
|
|
|
|
| 57 |
with gr.Row():
|
| 58 |
-
|
| 59 |
-
label="Embedding (JSON)",
|
| 60 |
-
interactive=False,
|
| 61 |
-
lines=4,
|
| 62 |
-
placeholder=
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
)
|
| 64 |
-
out_file = gr.File(label="Download do CSV", visible=False)
|
| 65 |
|
| 66 |
-
|
|
|
|
| 67 |
fn=gerar_embedding_e_csv,
|
| 68 |
-
inputs=
|
| 69 |
-
outputs=[
|
| 70 |
)
|
| 71 |
|
| 72 |
if __name__ == "__main__":
|
| 73 |
-
demo.launch()
|
|
|
|
| 2 |
import sys
|
| 3 |
import json
|
| 4 |
import tempfile
|
| 5 |
+
|
| 6 |
import pandas as pd
|
| 7 |
import gradio as gr
|
| 8 |
+
from PIL import Image
|
| 9 |
|
| 10 |
+
# 1) Ajusta o path antes de importar o loader
|
| 11 |
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
|
| 12 |
INFERENCE_PATH = os.path.join(BASE_DIR, "smi-ted", "inference")
|
| 13 |
sys.path.insert(0, INFERENCE_PATH)
|
| 14 |
|
| 15 |
+
# 2) Importa o loader do SMI-TED Light
|
| 16 |
from smi_ted_light.load import load_smi_ted
|
| 17 |
|
| 18 |
+
# 3) Carrega o modelo
|
| 19 |
MODEL_DIR = os.path.join(INFERENCE_PATH, "smi_ted_light")
|
| 20 |
model = load_smi_ted(
|
| 21 |
folder=MODEL_DIR,
|
|
|
|
| 23 |
vocab_filename="bert_vocab_curated.txt",
|
| 24 |
)
|
| 25 |
|
| 26 |
+
# 4) Função que gera o embedding e cria o CSV temporário
|
| 27 |
def gerar_embedding_e_csv(smiles: str):
|
| 28 |
smiles = smiles.strip()
|
| 29 |
if not smiles:
|
|
|
|
| 31 |
return json.dumps(erro), gr.update(visible=False)
|
| 32 |
|
| 33 |
try:
|
| 34 |
+
# Gera o vetor
|
| 35 |
vetor = model.encode(smiles, return_torch=True)[0].tolist()
|
| 36 |
+
# Grava CSV
|
| 37 |
df = pd.DataFrame([vetor])
|
| 38 |
tmp = tempfile.NamedTemporaryFile(suffix=".csv", delete=False)
|
| 39 |
df.to_csv(tmp.name, index=False)
|
| 40 |
tmp.close()
|
| 41 |
+
# Retorna JSON em string e ativa o link de download
|
| 42 |
return json.dumps(vetor), gr.update(value=tmp.name, visible=True)
|
| 43 |
except Exception as e:
|
| 44 |
erro = {"erro": str(e)}
|
| 45 |
return json.dumps(erro), gr.update(visible=False)
|
| 46 |
|
| 47 |
+
# 5) Monta a interface com Blocks
|
| 48 |
with gr.Blocks() as demo:
|
| 49 |
gr.Markdown(
|
| 50 |
"""
|
| 51 |
+
# SMI-TED Embedding Generator
|
| 52 |
+
Cole uma sequência SMILES e:
|
| 53 |
+
- Veja o vetor embedding (JSON)
|
| 54 |
+
- Baixe-o em CSV
|
| 55 |
"""
|
| 56 |
)
|
| 57 |
|
| 58 |
with gr.Row():
|
| 59 |
+
smiles_in = gr.Textbox(label="SMILES", placeholder="Ex.: CCO")
|
| 60 |
+
gerar_btn = gr.Button("Gerar Embedding")
|
| 61 |
+
|
| 62 |
with gr.Row():
|
| 63 |
+
embedding_out = gr.Textbox(
|
| 64 |
+
label="Embedding (JSON)",
|
| 65 |
+
interactive=False,
|
| 66 |
+
lines=4,
|
| 67 |
+
placeholder="O vetor aparecerá aqui…"
|
| 68 |
+
)
|
| 69 |
+
download_csv = gr.File(
|
| 70 |
+
label="Baixar CSV",
|
| 71 |
+
visible=False
|
| 72 |
)
|
|
|
|
| 73 |
|
| 74 |
+
# Conecta botão à função que tem dois outputs
|
| 75 |
+
gerar_btn.click(
|
| 76 |
fn=gerar_embedding_e_csv,
|
| 77 |
+
inputs=smiles_in,
|
| 78 |
+
outputs=[embedding_out, download_csv]
|
| 79 |
)
|
| 80 |
|
| 81 |
if __name__ == "__main__":
|
| 82 |
+
demo.launch(server_name="0.0.0.0")
|
requirements.txt
CHANGED
|
@@ -5,6 +5,5 @@ numpy==1.26.4
|
|
| 5 |
pandas==1.4.0
|
| 6 |
tqdm>=4.66.4
|
| 7 |
rdkit>=2024.3.5
|
| 8 |
-
gradio
|
| 9 |
-
gradio-client==0.2.0
|
| 10 |
huggingface-hub
|
|
|
|
| 5 |
pandas==1.4.0
|
| 6 |
tqdm>=4.66.4
|
| 7 |
rdkit>=2024.3.5
|
| 8 |
+
gradio>=4.33.1
|
|
|
|
| 9 |
huggingface-hub
|