Spaces:
Runtime error
Runtime error
adding objective and fixing punctuations
Browse files
app.py
CHANGED
|
@@ -7,6 +7,7 @@ from nltk import word_tokenize
|
|
| 7 |
from nltk.util import ngrams
|
| 8 |
from unidecode import unidecode
|
| 9 |
nltk.download('punkt')
|
|
|
|
| 10 |
|
| 11 |
# leemos diccionario de entidades
|
| 12 |
diccionario = pd.read_excel('diccionario.xlsx')
|
|
@@ -18,14 +19,30 @@ entities_dict = {}
|
|
| 18 |
for i in all_dicts:
|
| 19 |
entities_dict.update(i)
|
| 20 |
|
| 21 |
-
def
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
diccionario = entities_dict.copy()
|
| 24 |
tokens = word_tokenize(text, language = 'spanish')
|
| 25 |
-
tokens_lower = [unidecode(token.lower()) for token in tokens] # tokens en minuscula
|
|
|
|
| 26 |
|
| 27 |
dict_tokens = {tokens_lower[i]: tokens[i] for i in range(len(tokens))}
|
| 28 |
-
dict_keys = {unidecode(key.lower()): key for key in diccionario.keys()}
|
|
|
|
| 29 |
|
| 30 |
# presencia de ngrams
|
| 31 |
ngram_range = 5 # rango de ngramas a evaluar
|
|
@@ -39,7 +56,7 @@ def predict(text):
|
|
| 39 |
grams_detected.update({nmin: intersection})
|
| 40 |
|
| 41 |
sep = '%$·'
|
| 42 |
-
tmp_text =
|
| 43 |
for i in range(5, 1, -1):
|
| 44 |
try:
|
| 45 |
# obtener todos los ngramas de nivel "i"
|
|
@@ -69,6 +86,10 @@ def predict(text):
|
|
| 69 |
labeled_tokens.append((token, None))
|
| 70 |
|
| 71 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
# SERNAC CLASSIFICATION
|
| 73 |
|
| 74 |
with open('sernac_model.pkl', 'rb') as model:
|
|
@@ -76,36 +97,70 @@ def predict(text):
|
|
| 76 |
|
| 77 |
labels = [label for label in clf.classes_]
|
| 78 |
|
| 79 |
-
|
|
|
|
| 80 |
|
| 81 |
-
|
| 82 |
|
| 83 |
-
|
| 84 |
-
# SERNAC CATEGORIES CLASSIFICATION
|
| 85 |
|
| 86 |
-
|
| 87 |
-
clf = pickle.load(model)
|
| 88 |
|
| 89 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
|
| 91 |
-
|
| 92 |
|
| 93 |
-
|
| 94 |
|
| 95 |
-
|
|
|
|
| 96 |
|
| 97 |
|
| 98 |
# DEMO
|
| 99 |
demo = gr.Interface(
|
| 100 |
predict,
|
| 101 |
-
inputs = gr.Textbox(placeholder = "Ingresa el
|
| 102 |
-
outputs = [gr.Highlightedtext(label = '
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
examples=[
|
| 104 |
-
['este septiembre iremos manejando a
|
| 105 |
-
['no puedo, tengo que irme desde san pedro hasta la reina y luego hasta san pedro de la paz'],
|
| 106 |
-
['Buenas tardes, hace unas semanas compre un suzuki swift a derco de santiago, llevaba 2 semanas y la caja de cambios se echó a perder. Tengo asegurado el auto con BCI, pero aun no obtengo respuesta. ']
|
|
|
|
|
|
|
| 107 |
],
|
| 108 |
-
title = '
|
| 109 |
)
|
| 110 |
|
| 111 |
demo.launch()
|
|
|
|
| 7 |
from nltk.util import ngrams
|
| 8 |
from unidecode import unidecode
|
| 9 |
nltk.download('punkt')
|
| 10 |
+
import re
|
| 11 |
|
| 12 |
# leemos diccionario de entidades
|
| 13 |
diccionario = pd.read_excel('diccionario.xlsx')
|
|
|
|
| 19 |
for i in all_dicts:
|
| 20 |
entities_dict.update(i)
|
| 21 |
|
| 22 |
+
def f_remove_accents(old: str):
|
| 23 |
+
|
| 24 |
+
'''
|
| 25 |
+
Función que limpia acentos de las letras.
|
| 26 |
+
old: texto a limpiar (str)
|
| 27 |
+
'''
|
| 28 |
+
|
| 29 |
+
new = re.sub(r'[àáâãäå]', 'a', old)
|
| 30 |
+
new = re.sub(r'[èéêë]', 'e', new)
|
| 31 |
+
new = re.sub(r'[ìíîï]', 'i', new)
|
| 32 |
+
new = re.sub(r'[òóôõö]', 'o', new)
|
| 33 |
+
new = re.sub(r'[ùúûü]', 'u', new)
|
| 34 |
+
return new
|
| 35 |
+
|
| 36 |
+
def predict(text: str, goal = ''):
|
| 37 |
|
| 38 |
diccionario = entities_dict.copy()
|
| 39 |
tokens = word_tokenize(text, language = 'spanish')
|
| 40 |
+
#tokens_lower = [unidecode(token.lower()) for token in tokens] # tokens en minuscula
|
| 41 |
+
tokens_lower = [f_remove_accents(token.lower()) for token in tokens] # tokens en minuscula
|
| 42 |
|
| 43 |
dict_tokens = {tokens_lower[i]: tokens[i] for i in range(len(tokens))}
|
| 44 |
+
#dict_keys = {unidecode(key.lower()): key for key in diccionario.keys()}
|
| 45 |
+
dict_keys = {f_remove_accents(key.lower()): key for key in diccionario.keys()}
|
| 46 |
|
| 47 |
# presencia de ngrams
|
| 48 |
ngram_range = 5 # rango de ngramas a evaluar
|
|
|
|
| 56 |
grams_detected.update({nmin: intersection})
|
| 57 |
|
| 58 |
sep = '%$·'
|
| 59 |
+
tmp_text = ' '.join(tokens_lower)
|
| 60 |
for i in range(5, 1, -1):
|
| 61 |
try:
|
| 62 |
# obtener todos los ngramas de nivel "i"
|
|
|
|
| 86 |
labeled_tokens.append((token, None))
|
| 87 |
|
| 88 |
|
| 89 |
+
# CLASSIFICATION
|
| 90 |
+
|
| 91 |
+
input = np.array([text, goal], ndmin = 2)
|
| 92 |
+
|
| 93 |
# SERNAC CLASSIFICATION
|
| 94 |
|
| 95 |
with open('sernac_model.pkl', 'rb') as model:
|
|
|
|
| 97 |
|
| 98 |
labels = [label for label in clf.classes_]
|
| 99 |
|
| 100 |
+
probas = clf.predict_proba(input)
|
| 101 |
+
sernac_probas = {labels[i]: float(probas[0][i]) for i in range(probas.shape[1])}
|
| 102 |
|
| 103 |
+
sernac_categories, other_categories = {}, {}
|
| 104 |
|
| 105 |
+
if clf.predict(input) == 'SERNAC':
|
|
|
|
| 106 |
|
| 107 |
+
# SERNAC CATEGORIES CLASSIFICATION
|
|
|
|
| 108 |
|
| 109 |
+
with open('sernac_categories_model.pkl', 'rb') as model:
|
| 110 |
+
clf = pickle.load(model)
|
| 111 |
+
|
| 112 |
+
labels = [label for label in clf.classes_]
|
| 113 |
+
|
| 114 |
+
probas = clf.predict_proba(input)
|
| 115 |
+
|
| 116 |
+
sernac_categories = {labels[i]: float(probas[0][i]) for i in range(probas.shape[1])}
|
| 117 |
+
|
| 118 |
+
else:
|
| 119 |
+
|
| 120 |
+
# OTHER CATEGORIES CLASSIFICATION
|
| 121 |
+
|
| 122 |
+
with open('other_categories_model.pkl', 'rb') as model:
|
| 123 |
+
clf = pickle.load(model)
|
| 124 |
+
|
| 125 |
+
labels = [label for label in clf.classes_]
|
| 126 |
+
|
| 127 |
+
probas = clf.predict_proba(input)
|
| 128 |
+
|
| 129 |
+
other_categories = {labels[i]: float(probas[0][i]) for i in range(probas.shape[1])}
|
| 130 |
+
|
| 131 |
+
objective_categories = {}
|
| 132 |
+
if goal != '':
|
| 133 |
+
|
| 134 |
+
with open('objective_model.pkl', 'rb') as model:
|
| 135 |
+
clf = pickle.load(model)
|
| 136 |
+
|
| 137 |
+
labels = [label for label in clf.classes_]
|
| 138 |
|
| 139 |
+
probas = clf.predict_proba(input)
|
| 140 |
|
| 141 |
+
objective_categories = {labels[i]: float(probas[0][i]) for i in range(probas.shape[1])}
|
| 142 |
|
| 143 |
+
# RETURN
|
| 144 |
+
return labeled_tokens, sernac_probas, sernac_categories, other_categories, objective_categories
|
| 145 |
|
| 146 |
|
| 147 |
# DEMO
|
| 148 |
demo = gr.Interface(
|
| 149 |
predict,
|
| 150 |
+
inputs = [gr.Textbox(placeholder = "Ingresa el reclamo acá", label = 'Reclamo'), gr.Textbox(placeholder = "Ingresa el objetivo acá (opcional)", label = 'Objetivo')],
|
| 151 |
+
outputs = [gr.Highlightedtext(label = 'Entidades detectadas'),
|
| 152 |
+
gr.outputs.Label(label = 'Clasificación SERNAC'),
|
| 153 |
+
gr.outputs.Label(label = 'Clasificación categorías SERNAC'),
|
| 154 |
+
gr.outputs.Label(label = 'Clasificación categorías No SERNAC'),
|
| 155 |
+
gr.outputs.Label(label = 'Clasificación objetivo')],
|
| 156 |
examples=[
|
| 157 |
+
['este septiembre iremos manejando a tEmUco en un tóyòtA para pasar las fiestas patrias', 'ir a temuco'],
|
| 158 |
+
['no puedo, tengo que irme desde san pedro hasta la reina y luego hasta san pedro de la paz', ''],
|
| 159 |
+
['Buenas tardes, hace unas semanas compre un suzuki swift a derco de santiago, llevaba 2 semanas y la caja de cambios se echó a perder. Tengo asegurado el auto con BCI, pero aun no obtengo respuesta.', 'exijo una explicación!'],
|
| 160 |
+
['Tengo un toyota urban cruiser 1.3 año 2010 el cual consume mucho aceite y nunca me han respondido si tiene alguna solución o garantía me gustaría que fueran más concretas las respuestas gracias', 'Obtener una solucion Que reparación hay que hacer o si tiene garantía?'],
|
| 161 |
+
['Mi auto del año presenta Falla de motor y sensores siendo que lo compre nuevo 0km y tiene recién 5400kms.. Es un Peugeot 2008 gti... El servicio es como las pelotas.. Me mandaron a un servicio técnico en Calama que estaba cerrado', '']
|
| 162 |
],
|
| 163 |
+
title = 'Demo ML'
|
| 164 |
)
|
| 165 |
|
| 166 |
demo.launch()
|