Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,9 +1,8 @@
|
|
| 1 |
-
# app.py
|
| 2 |
# -*- coding: utf-8 -*-
|
| 3 |
-
import os
|
| 4 |
import re
|
| 5 |
import unicodedata
|
| 6 |
from pathlib import Path
|
|
|
|
| 7 |
|
| 8 |
import gradio as gr
|
| 9 |
import joblib
|
|
@@ -11,67 +10,51 @@ import pandas as pd
|
|
| 11 |
from scipy import sparse
|
| 12 |
from sklearn.metrics.pairwise import cosine_similarity
|
| 13 |
|
| 14 |
-
#
|
| 15 |
-
#
|
| 16 |
-
#
|
| 17 |
-
|
|
|
|
| 18 |
VEC_PATH = ART / "tfidf_vectorizer.joblib"
|
| 19 |
MAT_PATH = ART / "tfidf_matrix.npz"
|
| 20 |
IDX_PATH = ART / "doc_index.csv"
|
| 21 |
|
| 22 |
-
#
|
| 23 |
-
#
|
| 24 |
-
#
|
| 25 |
-
import nltk
|
| 26 |
-
from nltk.corpus import stopwords
|
| 27 |
-
|
| 28 |
-
def _ensure_nltk():
|
| 29 |
-
try:
|
| 30 |
-
nltk.data.find("corpora/stopwords")
|
| 31 |
-
except LookupError:
|
| 32 |
-
nltk.download("stopwords")
|
| 33 |
-
_ensure_nltk()
|
| 34 |
-
|
| 35 |
def strip_accents(s: str) -> str:
|
| 36 |
return "".join(c for c in unicodedata.normalize("NFKD", s) if not unicodedata.combining(c))
|
| 37 |
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
if not isinstance(s, str):
|
| 42 |
s = "" if s is None else str(s)
|
| 43 |
s = strip_accents(s.lower())
|
| 44 |
-
s = re.sub(r"[“”„‟‹›«»—–‐-‒–—―\-]", " ", s)
|
| 45 |
-
s = re.sub(r"[^\w\s]", " ", s)
|
| 46 |
s = re.sub(r"\s+", " ", s).strip()
|
| 47 |
toks = [t for t in s.split() if t not in STOPWORDS and not t.isdigit()]
|
| 48 |
return " ".join(toks)
|
| 49 |
|
| 50 |
-
# ==========================
|
| 51 |
-
# Reglas heurísticas (ejemplo OPS)
|
| 52 |
-
# ==========================
|
| 53 |
-
REGLAS = [
|
| 54 |
-
{
|
| 55 |
-
"keywords": ["ops", "orden de prestacion de servicios", "contrato ops"],
|
| 56 |
-
"respuesta": {
|
| 57 |
-
"CICP": ("2.1.2.02.02.008", "Servicios prestados a las empresas y servicios de producción"),
|
| 58 |
-
"CPC": ("8", "Servicios prestados a las empresas y servicios de producción"),
|
| 59 |
-
"UNSPSC":("80111600", "Servicios de personal temporal"),
|
| 60 |
-
},
|
| 61 |
-
"motivo": "Coincidencia con palabra clave OPS",
|
| 62 |
-
},
|
| 63 |
-
]
|
| 64 |
-
|
| 65 |
-
def aplicar_reglas(consulta: str):
|
| 66 |
-
texto = limpiar_texto(consulta)
|
| 67 |
-
for regla in REGLAS:
|
| 68 |
-
if any(k in texto for k in regla["keywords"]):
|
| 69 |
-
rows = []
|
| 70 |
-
for cat, (cod, nom) in regla["respuesta"].items():
|
| 71 |
-
rows.append({"Catálogo": cat, "Código": cod, "Nombre": nom, "Similaridad": 1.0, "Origen": "Regla"})
|
| 72 |
-
return pd.DataFrame(rows)
|
| 73 |
-
return None
|
| 74 |
-
|
| 75 |
def catalog_tag(source_file: str) -> str:
|
| 76 |
s = (source_file or "").lower()
|
| 77 |
if "cicp" in s: return "CICP"
|
|
@@ -79,7 +62,7 @@ def catalog_tag(source_file: str) -> str:
|
|
| 79 |
if "unspsc" in s: return "UNSPSC"
|
| 80 |
return "OTRO"
|
| 81 |
|
| 82 |
-
def parse_code_name(codes_raw: str, text_original: str):
|
| 83 |
codes_raw = str(codes_raw or "")
|
| 84 |
text_original = str(text_original or "")
|
| 85 |
m = re.search(r"CODIGO;NOMBRE:\s*([^;|]+)\s*;\s*([^|]+)", codes_raw, flags=re.I)
|
|
@@ -99,75 +82,112 @@ def parse_code_name(codes_raw: str, text_original: str):
|
|
| 99 |
if m2 and name is None: name = m2.group(1).strip()
|
| 100 |
return (code or "").strip(), (name or "").strip()
|
| 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 |
with gr.Row():
|
| 155 |
-
|
| 156 |
-
|
| 157 |
btn = gr.Button("Buscar")
|
| 158 |
-
|
|
|
|
| 159 |
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
["contrato de personal temporal", 1],
|
| 164 |
-
["reactivos de laboratorio para cromatografía hplc", 1],
|
| 165 |
-
],
|
| 166 |
-
inputs=[consulta, topk],
|
| 167 |
-
label="Ejemplos",
|
| 168 |
-
)
|
| 169 |
|
| 170 |
-
btn.click(
|
| 171 |
|
| 172 |
if __name__ == "__main__":
|
|
|
|
| 173 |
demo.launch()
|
|
|
|
|
|
|
| 1 |
# -*- coding: utf-8 -*-
|
|
|
|
| 2 |
import re
|
| 3 |
import unicodedata
|
| 4 |
from pathlib import Path
|
| 5 |
+
from typing import Tuple
|
| 6 |
|
| 7 |
import gradio as gr
|
| 8 |
import joblib
|
|
|
|
| 10 |
from scipy import sparse
|
| 11 |
from sklearn.metrics.pairwise import cosine_similarity
|
| 12 |
|
| 13 |
+
# -----------------------------
|
| 14 |
+
# Rutas (funciona en HF Spaces)
|
| 15 |
+
# -----------------------------
|
| 16 |
+
ROOT = Path(__file__).parent
|
| 17 |
+
ART = ROOT / "artifacts"
|
| 18 |
VEC_PATH = ART / "tfidf_vectorizer.joblib"
|
| 19 |
MAT_PATH = ART / "tfidf_matrix.npz"
|
| 20 |
IDX_PATH = ART / "doc_index.csv"
|
| 21 |
|
| 22 |
+
# -----------------------------
|
| 23 |
+
# Limpieza (sin NLTK)
|
| 24 |
+
# -----------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
def strip_accents(s: str) -> str:
|
| 26 |
return "".join(c for c in unicodedata.normalize("NFKD", s) if not unicodedata.combining(c))
|
| 27 |
|
| 28 |
+
# stopwords españolas normalizadas (compacta; puedes ampliar)
|
| 29 |
+
STOPWORDS = {
|
| 30 |
+
"a","aca","ahi","ahí","al","algo","algunas","algunos","alla","allá","alli","allí","ante","antes",
|
| 31 |
+
"aquel","aquella","aquellas","aquellos","aqui","aquí","asi","así","aun","aunque","bajo","bien","cabe",
|
| 32 |
+
"cada","casi","cierta","ciertas","cierto","ciertos","como","con","contra","cual","cuales","cualquier",
|
| 33 |
+
"cualesquiera","cuyo","cuya","cuyas","cuyos","de","del","desde","donde","dos","el","ella","ellas",
|
| 34 |
+
"ellos","en","entre","era","erais","eramos","éramos","eran","eres","es","esa","esas","ese","eso",
|
| 35 |
+
"esos","esta","está","estaba","estaban","estamos","estan","están","estar","estas","este","esto",
|
| 36 |
+
"estos","etc","fue","fueron","ha","habia","había","habian","habían","haber","hay","hasta","la","las",
|
| 37 |
+
"le","les","lo","los","mas","más","me","mi","mis","mucha","muchas","mucho","muchos","muy","nada","ni",
|
| 38 |
+
"no","nos","nosotras","nosotros","nuestra","nuestras","nuestro","nuestros","o","otra","otras","otro",
|
| 39 |
+
"otros","para","pero","poco","por","porque","que","qué","quien","quién","quienes","quiénes","se","sea",
|
| 40 |
+
"sean","ser","si","sí","sido","sin","sobre","su","sus","tal","tambien","también","tampoco","tan",
|
| 41 |
+
"tanta","tantas","tanto","te","tenia","tenía","tenian","tenían","tendra","tendrá","tendran","tendrán",
|
| 42 |
+
"tenemos","tengo","ti","tiene","tienen","todo","todos","tu","tus","un","una","unas","uno","unos",
|
| 43 |
+
"usted","ustedes","y","ya"
|
| 44 |
+
}
|
| 45 |
+
# normalizar stopwords
|
| 46 |
+
STOPWORDS = {strip_accents(w.lower()) for w in STOPWORDS} | {"aun"}
|
| 47 |
+
|
| 48 |
+
def clean_text(s: str) -> str:
|
| 49 |
if not isinstance(s, str):
|
| 50 |
s = "" if s is None else str(s)
|
| 51 |
s = strip_accents(s.lower())
|
| 52 |
+
s = re.sub(r"[“”„‟‹›«»—–‐-‒–—―\-]", " ", s) # comillas/guiones unicode
|
| 53 |
+
s = re.sub(r"[^\w\s]", " ", s) # puntuación
|
| 54 |
s = re.sub(r"\s+", " ", s).strip()
|
| 55 |
toks = [t for t in s.split() if t not in STOPWORDS and not t.isdigit()]
|
| 56 |
return " ".join(toks)
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
def catalog_tag(source_file: str) -> str:
|
| 59 |
s = (source_file or "").lower()
|
| 60 |
if "cicp" in s: return "CICP"
|
|
|
|
| 62 |
if "unspsc" in s: return "UNSPSC"
|
| 63 |
return "OTRO"
|
| 64 |
|
| 65 |
+
def parse_code_name(codes_raw: str, text_original: str) -> Tuple[str, str]:
|
| 66 |
codes_raw = str(codes_raw or "")
|
| 67 |
text_original = str(text_original or "")
|
| 68 |
m = re.search(r"CODIGO;NOMBRE:\s*([^;|]+)\s*;\s*([^|]+)", codes_raw, flags=re.I)
|
|
|
|
| 82 |
if m2 and name is None: name = m2.group(1).strip()
|
| 83 |
return (code or "").strip(), (name or "").strip()
|
| 84 |
|
| 85 |
+
# -----------------------------
|
| 86 |
+
# Reglas duras (ejemplo OPS)
|
| 87 |
+
# -----------------------------
|
| 88 |
+
REGLAS = [
|
| 89 |
+
{
|
| 90 |
+
"keywords": ["ops", "orden de prestacion de servicios", "contrato ops"],
|
| 91 |
+
"respuesta": {
|
| 92 |
+
"CICP": ("2.1.2.02.02.008", "Servicios prestados a las empresas y servicios de producción"),
|
| 93 |
+
"CPC": ("8", "Servicios prestados a las empresas y servicios de producción"),
|
| 94 |
+
"UNSPSC":("80111600", "Servicios de personal temporal"),
|
| 95 |
+
},
|
| 96 |
+
"motivo": "Coincidencia con palabra clave OPS",
|
| 97 |
+
},
|
| 98 |
+
]
|
| 99 |
+
|
| 100 |
+
def aplicar_reglas(query: str):
|
| 101 |
+
q = clean_text(query)
|
| 102 |
+
for r in REGLAS:
|
| 103 |
+
if any(k in q for k in r["keywords"]):
|
| 104 |
+
df = pd.DataFrame(
|
| 105 |
+
[{"Catálogo": k, "Código": v[0], "Nombre": v[1], "Similaridad": 1.0} for k, v in r["respuesta"].items()]
|
| 106 |
+
)
|
| 107 |
+
return df, r["motivo"]
|
| 108 |
+
return None, None
|
| 109 |
+
|
| 110 |
+
# -----------------------------
|
| 111 |
+
# Carga perezosa de artefactos
|
| 112 |
+
# -----------------------------
|
| 113 |
+
VECTOR = None
|
| 114 |
+
MATRIX = None
|
| 115 |
+
INDEX = None
|
| 116 |
+
|
| 117 |
+
def ensure_loaded():
|
| 118 |
+
global VECTOR, MATRIX, INDEX
|
| 119 |
+
if VECTOR is None:
|
| 120 |
+
VECTOR = joblib.load(VEC_PATH)
|
| 121 |
+
if MATRIX is None:
|
| 122 |
+
MATRIX = sparse.load_npz(MAT_PATH)
|
| 123 |
+
if INDEX is None:
|
| 124 |
+
INDEX = pd.read_csv(IDX_PATH)
|
| 125 |
+
|
| 126 |
+
# -----------------------------
|
| 127 |
+
# Motor TF-IDF agrupado
|
| 128 |
+
# -----------------------------
|
| 129 |
+
def recomendar(query: str, k: int):
|
| 130 |
+
try:
|
| 131 |
+
# 1) Reglas
|
| 132 |
+
df_regla, motivo = aplicar_reglas(query)
|
| 133 |
+
if df_regla is not None:
|
| 134 |
+
return df_regla, f"⚙️ Regla activada: {motivo}"
|
| 135 |
+
|
| 136 |
+
# 2) Modelo
|
| 137 |
+
ensure_loaded()
|
| 138 |
+
q = clean_text(query)
|
| 139 |
+
if not q:
|
| 140 |
+
return pd.DataFrame(), "La consulta quedó vacía tras limpieza."
|
| 141 |
+
|
| 142 |
+
xq = VECTOR.transform([q])
|
| 143 |
+
sims = cosine_similarity(xq, MATRIX).flatten()
|
| 144 |
+
|
| 145 |
+
df = INDEX.copy()
|
| 146 |
+
df["Similaridad"] = sims
|
| 147 |
+
df["Catálogo"] = df["source_file"].apply(catalog_tag)
|
| 148 |
+
|
| 149 |
+
# top-k por catálogo
|
| 150 |
+
out = []
|
| 151 |
+
for cat in ["CICP", "CPC", "UNSPSC"]:
|
| 152 |
+
sub = (
|
| 153 |
+
df[df["Catálogo"] == cat]
|
| 154 |
+
.sort_values("Similaridad", ascending=False)
|
| 155 |
+
.head(int(k))
|
| 156 |
+
.copy()
|
| 157 |
+
)
|
| 158 |
+
if sub.empty:
|
| 159 |
+
continue
|
| 160 |
+
parsed = sub.apply(lambda r: parse_code_name(r.get("codes_raw",""), r.get("text_original","")), axis=1)
|
| 161 |
+
sub["Código"] = [c for c, _ in parsed]
|
| 162 |
+
sub["Nombre"] = [n for _, n in parsed]
|
| 163 |
+
out.append(sub[["Catálogo", "Código", "Nombre", "Similaridad"]])
|
| 164 |
+
|
| 165 |
+
if not out:
|
| 166 |
+
return pd.DataFrame(), "Sin candidatos."
|
| 167 |
+
res = pd.concat(out, ignore_index=True)
|
| 168 |
+
return res, "OK"
|
| 169 |
+
except Exception as e:
|
| 170 |
+
# mostrará el error en la interfaz
|
| 171 |
+
return pd.DataFrame(), f"Error: {type(e).__name__}: {e}"
|
| 172 |
+
|
| 173 |
+
# -----------------------------
|
| 174 |
+
# Interfaz Gradio
|
| 175 |
+
# -----------------------------
|
| 176 |
+
with gr.Blocks(title="Recomendador por texto (CICP / CPC / UNSPSC)") as demo:
|
| 177 |
+
gr.Markdown("# Recomendador por texto (CICP / CPC / UNSPSC)\n\n_TF-IDF + reglas_")
|
| 178 |
with gr.Row():
|
| 179 |
+
query = gr.Textbox(label="Descripción técnica", placeholder="reactivos de laboratorio para cromatografía hplc", lines=3)
|
| 180 |
+
k = gr.Slider(1, 5, value=1, step=1, label="Top por catálogo")
|
| 181 |
btn = gr.Button("Buscar")
|
| 182 |
+
out = gr.Dataframe(headers=["Catálogo","Código","Nombre","Similaridad"], label="Resultados", wrap=True)
|
| 183 |
+
status = gr.Markdown()
|
| 184 |
|
| 185 |
+
def _on_click(q, topk):
|
| 186 |
+
df, msg = recomendar(q, topk)
|
| 187 |
+
return df, (f"**Estado:** {msg}" if msg else "")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 188 |
|
| 189 |
+
btn.click(_on_click, inputs=[query, k], outputs=[out, status])
|
| 190 |
|
| 191 |
if __name__ == "__main__":
|
| 192 |
+
# Para pruebas locales
|
| 193 |
demo.launch()
|