Spaces:
Running
Running
#modules/morphosyntax/morphosyntax_interface.py | |
import streamlit as st | |
import spacy_streamlit | |
from streamlit_float import * | |
from streamlit_antd_components import * | |
from streamlit.components.v1 import html | |
import base64 | |
# Importar desde morphosyntax_process.py | |
from .morphosyntax_process import ( | |
process_morphosyntactic_input, | |
format_analysis_results, | |
perform_advanced_morphosyntactic_analysis, # Añadir esta importación | |
get_repeated_words_colors, # Y estas también | |
highlight_repeated_words, | |
POS_COLORS, | |
POS_TRANSLATIONS | |
) | |
from ..utils.widget_utils import generate_unique_key | |
from ..database.morphosintax_mongo_db import store_student_morphosyntax_result | |
from ..database.chat_db import store_chat_history | |
from ..database.morphosintaxis_export import export_user_interactions | |
import logging | |
logger = logging.getLogger(__name__) | |
def display_morphosyntax_interface(lang_code, nlp_models, t): | |
""" | |
Interfaz para el análisis morfosintáctico | |
Args: | |
lang_code: Código del idioma actual | |
nlp_models: Modelos de spaCy cargados | |
t: Diccionario de traducciones | |
""" | |
# Obtener el diccionario de traducciones morfosintácticas | |
morpho_t = t.get('MORPHOSYNTACTIC', {}) | |
# Inicializar el estado de la entrada | |
input_key = f"morphosyntax_input_{lang_code}" | |
if input_key not in st.session_state: | |
st.session_state[input_key] = "" | |
# Campo de entrada de texto | |
sentence_input = st.text_area( | |
morpho_t.get('morpho_input_label', 'Enter text to analyze'), | |
height=150, | |
placeholder=morpho_t.get('morpho_input_placeholder', 'Enter your text here...'), | |
value=st.session_state[input_key], | |
key=f"text_area_{lang_code}", | |
on_change=lambda: setattr(st.session_state, input_key, st.session_state[f"text_area_{lang_code}"]) | |
) | |
# Botón de análisis | |
if st.button(morpho_t.get('analyze_button', 'Analyze text'), key=f"analyze_button_{lang_code}"): | |
current_input = st.session_state[input_key] | |
if current_input: | |
try: | |
# Procesar el texto | |
doc = nlp_models[lang_code](current_input) | |
# Realizar análisis morfosintáctico | |
advanced_analysis = perform_advanced_morphosyntactic_analysis( | |
current_input, | |
nlp_models[lang_code] | |
) | |
# Guardar resultado en el estado de la sesión | |
st.session_state.morphosyntax_result = { | |
'doc': doc, | |
'advanced_analysis': advanced_analysis | |
} | |
# Mostrar resultados | |
display_morphosyntax_results( | |
st.session_state.morphosyntax_result, | |
lang_code, | |
morpho_t # Pasar morpho_t en lugar de t | |
) | |
# Guardar en la base de datos | |
if store_morphosyntax_result( | |
st.session_state.username, | |
current_input, | |
get_repeated_words_colors(doc), | |
advanced_analysis['arc_diagram'], | |
advanced_analysis['pos_analysis'], | |
advanced_analysis['morphological_analysis'], | |
advanced_analysis['sentence_structure'] | |
): | |
st.success(morpho_t.get('success_message', 'Analysis saved successfully')) | |
else: | |
st.error(morpho_t.get('error_message', 'Error saving analysis')) | |
except Exception as e: | |
st.error(morpho_t.get('error_processing', f'Error processing text: {str(e)}')) | |
else: | |
st.warning(morpho_t.get('warning_message', 'Please enter a text to analyze')) | |
# Mostrar resultados previos si existen | |
elif 'morphosyntax_result' in st.session_state and st.session_state.morphosyntax_result is not None: | |
display_morphosyntax_results( | |
st.session_state.morphosyntax_result, | |
lang_code, | |
morpho_t # Pasar morpho_t en lugar de t | |
) | |
else: | |
st.info(morpho_t.get('morpho_initial_message', 'Enter text to begin analysis')) | |
############################################################################################################ | |
def display_morphosyntax_results(result, lang_code, t): | |
""" | |
Muestra los resultados del análisis morfosintáctico. | |
Args: | |
result: Resultado del análisis | |
lang_code: Código del idioma | |
t: Diccionario de traducciones | |
""" | |
# Obtener el diccionario de traducciones morfosintácticas | |
morpho_t = t.get('MORPHOSYNTACTIC', {}) | |
if result is None: | |
st.warning(morpho_t.get('no_results', 'No results available')) | |
return | |
doc = result['doc'] | |
advanced_analysis = result['advanced_analysis'] | |
# Mostrar leyenda | |
st.markdown(f"##### {morpho_t.get('legend', 'Legend: Grammatical categories')}") | |
legend_html = "<div style='display: flex; flex-wrap: wrap;'>" | |
for pos, color in POS_COLORS.items(): | |
if pos in POS_TRANSLATIONS[lang_code]: | |
legend_html += f"<div style='margin-right: 10px;'><span style='background-color: {color}; padding: 2px 5px;'>{POS_TRANSLATIONS[lang_code][pos]}</span></div>" | |
legend_html += "</div>" | |
st.markdown(legend_html, unsafe_allow_html=True) | |
# Mostrar análisis de palabras repetidas | |
word_colors = get_repeated_words_colors(doc) | |
with st.expander(morpho_t.get('repeated_words', 'Repeated words'), expanded=True): | |
highlighted_text = highlight_repeated_words(doc, word_colors) | |
st.markdown(highlighted_text, unsafe_allow_html=True) | |
# Mostrar estructura de oraciones | |
with st.expander(morpho_t.get('sentence_structure', 'Sentence structure'), expanded=True): | |
for i, sent_analysis in enumerate(advanced_analysis['sentence_structure']): | |
sentence_str = ( | |
f"**{morpho_t.get('sentence', 'Sentence')} {i+1}** " # Aquí está el cambio | |
f"{morpho_t.get('root', 'Root')}: {sent_analysis['root']} ({sent_analysis['root_pos']}) -- " # Y aquí | |
f"{morpho_t.get('subjects', 'Subjects')}: {', '.join(sent_analysis['subjects'])} -- " # Y aquí | |
f"{morpho_t.get('objects', 'Objects')}: {', '.join(sent_analysis['objects'])} -- " # Y aquí | |
f"{morpho_t.get('verbs', 'Verbs')}: {', '.join(sent_analysis['verbs'])}" # Y aquí | |
) | |
st.markdown(sentence_str) | |
# Mostrar análisis de categorías gramaticales # Mostrar análisis morfológico | |
col1, col2 = st.columns(2) | |
with col1: | |
with st.expander(morpho_t.get('pos_analysis', 'Part of speech'), expanded=True): | |
pos_df = pd.DataFrame(advanced_analysis['pos_analysis']) | |
# Traducir las etiquetas POS a sus nombres en el idioma seleccionado | |
pos_df['pos'] = pos_df['pos'].map(lambda x: POS_TRANSLATIONS[lang_code].get(x, x)) | |
# Renombrar las columnas para mayor claridad | |
pos_df = pos_df.rename(columns={ | |
'pos': t['grammatical_category'], | |
'count': t['count'], | |
'percentage': t['percentage'], | |
'examples': t['examples'] | |
}) | |
# Mostrar el dataframe | |
st.dataframe(pos_df) | |
with col2: | |
with st.expander(t['morphological_analysis'], expanded=True): | |
morph_df = pd.DataFrame(advanced_analysis['morphological_analysis']) | |
# Definir el mapeo de columnas | |
column_mapping = { | |
'text': t['word'], | |
'lemma': t['lemma'], | |
'pos': t['grammatical_category'], | |
'dep': t['dependency'], | |
'morph': t['morphology'] | |
} | |
# Renombrar las columnas existentes | |
morph_df = morph_df.rename(columns={col: new_name for col, new_name in column_mapping.items() if col in morph_df.columns}) | |
# Traducir las categorías gramaticales | |
morph_df[t['grammatical_category']] = morph_df[t['grammatical_category']].map(lambda x: POS_TRANSLATIONS[lang_code].get(x, x)) | |
# Traducir las dependencias | |
dep_translations = { | |
'es': { | |
'ROOT': 'RAÍZ', 'nsubj': 'sujeto nominal', 'obj': 'objeto', 'iobj': 'objeto indirecto', | |
'csubj': 'sujeto clausal', 'ccomp': 'complemento clausal', 'xcomp': 'complemento clausal abierto', | |
'obl': 'oblicuo', 'vocative': 'vocativo', 'expl': 'expletivo', 'dislocated': 'dislocado', | |
'advcl': 'cláusula adverbial', 'advmod': 'modificador adverbial', 'discourse': 'discurso', | |
'aux': 'auxiliar', 'cop': 'cópula', 'mark': 'marcador', 'nmod': 'modificador nominal', | |
'appos': 'aposición', 'nummod': 'modificador numeral', 'acl': 'cláusula adjetiva', | |
'amod': 'modificador adjetival', 'det': 'determinante', 'clf': 'clasificador', | |
'case': 'caso', 'conj': 'conjunción', 'cc': 'coordinante', 'fixed': 'fijo', | |
'flat': 'plano', 'compound': 'compuesto', 'list': 'lista', 'parataxis': 'parataxis', | |
'orphan': 'huérfano', 'goeswith': 'va con', 'reparandum': 'reparación', 'punct': 'puntuación' | |
}, | |
'en': { | |
'ROOT': 'ROOT', 'nsubj': 'nominal subject', 'obj': 'object', | |
'iobj': 'indirect object', 'csubj': 'clausal subject', 'ccomp': 'clausal complement', 'xcomp': 'open clausal complement', | |
'obl': 'oblique', 'vocative': 'vocative', 'expl': 'expletive', 'dislocated': 'dislocated', 'advcl': 'adverbial clause modifier', | |
'advmod': 'adverbial modifier', 'discourse': 'discourse element', 'aux': 'auxiliary', 'cop': 'copula', 'mark': 'marker', | |
'nmod': 'nominal modifier', 'appos': 'appositional modifier', 'nummod': 'numeric modifier', 'acl': 'clausal modifier of noun', | |
'amod': 'adjectival modifier', 'det': 'determiner', 'clf': 'classifier', 'case': 'case marking', | |
'conj': 'conjunct', 'cc': 'coordinating conjunction', 'fixed': 'fixed multiword expression', | |
'flat': 'flat multiword expression', 'compound': 'compound', 'list': 'list', 'parataxis': 'parataxis', 'orphan': 'orphan', | |
'goeswith': 'goes with', 'reparandum': 'reparandum', 'punct': 'punctuation' | |
}, | |
'fr': { | |
'ROOT': 'RACINE', 'nsubj': 'sujet nominal', 'obj': 'objet', 'iobj': 'objet indirect', | |
'csubj': 'sujet phrastique', 'ccomp': 'complément phrastique', 'xcomp': 'complément phrastique ouvert', 'obl': 'oblique', | |
'vocative': 'vocatif', 'expl': 'explétif', 'dislocated': 'disloqué', 'advcl': 'clause adverbiale', 'advmod': 'modifieur adverbial', | |
'discourse': 'élément de discours', 'aux': 'auxiliaire', 'cop': 'copule', 'mark': 'marqueur', 'nmod': 'modifieur nominal', | |
'appos': 'apposition', 'nummod': 'modifieur numéral', 'acl': 'clause relative', 'amod': 'modifieur adjectival', 'det': 'déterminant', | |
'clf': 'classificateur', 'case': 'marqueur de cas', 'conj': 'conjonction', 'cc': 'coordination', 'fixed': 'expression figée', | |
'flat': 'construction plate', 'compound': 'composé', 'list': 'liste', 'parataxis': 'parataxe', 'orphan': 'orphelin', | |
'goeswith': 'va avec', 'reparandum': 'réparation', 'punct': 'ponctuation' | |
} | |
} | |
morph_df[t['dependency']] = morph_df[t['dependency']].map(lambda x: dep_translations[lang_code].get(x, x)) | |
# Traducir la morfología | |
def translate_morph(morph_string, lang_code): | |
morph_translations = { | |
'es': { | |
'Gender': 'Género', 'Number': 'Número', 'Case': 'Caso', 'Definite': 'Definido', | |
'PronType': 'Tipo de Pronombre', 'Person': 'Persona', 'Mood': 'Modo', | |
'Tense': 'Tiempo', 'VerbForm': 'Forma Verbal', 'Voice': 'Voz', | |
'Fem': 'Femenino', 'Masc': 'Masculino', 'Sing': 'Singular', 'Plur': 'Plural', | |
'Ind': 'Indicativo', 'Sub': 'Subjuntivo', 'Imp': 'Imperativo', 'Inf': 'Infinitivo', | |
'Part': 'Participio', 'Ger': 'Gerundio', 'Pres': 'Presente', 'Past': 'Pasado', | |
'Fut': 'Futuro', 'Perf': 'Perfecto', 'Imp': 'Imperfecto' | |
}, | |
'en': { | |
'Gender': 'Gender', 'Number': 'Number', 'Case': 'Case', 'Definite': 'Definite', 'PronType': 'Pronoun Type', 'Person': 'Person', | |
'Mood': 'Mood', 'Tense': 'Tense', 'VerbForm': 'Verb Form', 'Voice': 'Voice', | |
'Fem': 'Feminine', 'Masc': 'Masculine', 'Sing': 'Singular', 'Plur': 'Plural', 'Ind': 'Indicative', | |
'Sub': 'Subjunctive', 'Imp': 'Imperative', 'Inf': 'Infinitive', 'Part': 'Participle', | |
'Ger': 'Gerund', 'Pres': 'Present', 'Past': 'Past', 'Fut': 'Future', 'Perf': 'Perfect', 'Imp': 'Imperfect' | |
}, | |
'fr': { | |
'Gender': 'Genre', 'Number': 'Nombre', 'Case': 'Cas', 'Definite': 'Défini', 'PronType': 'Type de Pronom', | |
'Person': 'Personne', 'Mood': 'Mode', 'Tense': 'Temps', 'VerbForm': 'Forme Verbale', 'Voice': 'Voix', | |
'Fem': 'Féminin', 'Masc': 'Masculin', 'Sing': 'Singulier', 'Plur': 'Pluriel', 'Ind': 'Indicatif', | |
'Sub': 'Subjonctif', 'Imp': 'Impératif', 'Inf': 'Infinitif', 'Part': 'Participe', | |
'Ger': 'Gérondif', 'Pres': 'Présent', 'Past': 'Passé', 'Fut': 'Futur', 'Perf': 'Parfait', 'Imp': 'Imparfait' | |
} | |
} | |
for key, value in morph_translations[lang_code].items(): | |
morph_string = morph_string.replace(key, value) | |
return morph_string | |
morph_df[t['morphology']] = morph_df[t['morphology']].apply(lambda x: translate_morph(x, lang_code)) | |
# Seleccionar y ordenar las columnas a mostrar | |
columns_to_display = [t['word'], t['lemma'], t['grammatical_category'], t['dependency'], t['morphology']] | |
columns_to_display = [col for col in columns_to_display if col in morph_df.columns] | |
# Mostrar el DataFrame | |
st.dataframe(morph_df[columns_to_display]) | |
# Mostrar diagramas de arco (código existente) | |
with st.expander(t['arc_diagram'], expanded=True): | |
sentences = list(doc.sents) | |
arc_diagrams = [] | |
for i, sent in enumerate(sentences): | |
st.subheader(f"{t['sentence']} {i+1}") | |
html = displacy.render(sent, style="dep", options={"distance": 100}) | |
html = html.replace('height="375"', 'height="200"') | |
html = re.sub(r'<svg[^>]*>', lambda m: m.group(0).replace('height="450"', 'height="300"'), html) | |
html = re.sub(r'<g [^>]*transform="translate\((\d+),(\d+)\)"', lambda m: f'<g transform="translate({m.group(1)},50)"', html) | |
st.write(html, unsafe_allow_html=True) | |
arc_diagrams.append(html) | |
# Botón de exportación | |
if st.button(morpho_t.get('export_button', 'Export Analysis')): | |
pdf_buffer = export_user_interactions(st.session_state.username, 'morphosyntax') | |
st.download_button( | |
label=morpho_t.get('download_pdf', 'Download PDF'), | |
data=pdf_buffer, | |
file_name="morphosyntax_analysis.pdf", | |
mime="application/pdf" | |
) | |
''' | |
if user_input: | |
# Añadir el mensaje del usuario al historial | |
st.session_state.morphosyntax_chat_history.append({"role": "user", "content": user_input}) | |
# Procesar el input del usuario nuevo al 26-9-2024 | |
response, visualizations, result = process_morphosyntactic_input(user_input, lang_code, nlp_models, t) | |
# Mostrar indicador de carga | |
with st.spinner(t.get('processing', 'Processing...')): | |
try: | |
# Procesar el input del usuario | |
response, visualizations, result = process_morphosyntactic_input(user_input, lang_code, nlp_models, t) | |
# Añadir la respuesta al historial | |
message = { | |
"role": "assistant", | |
"content": response | |
} | |
if visualizations: | |
message["visualizations"] = visualizations | |
st.session_state.morphosyntax_chat_history.append(message) | |
# Mostrar la respuesta más reciente | |
with st.chat_message("assistant"): | |
st.write(response) | |
if visualizations: | |
for i, viz in enumerate(visualizations): | |
st.markdown(f"**Oración {i+1} del párrafo analizado**") | |
st.components.v1.html( | |
f""" | |
<div style="width: 100%; overflow-x: auto; white-space: nowrap;"> | |
<div style="min-width: 1200px;"> | |
{viz} | |
</div> | |
</div> | |
""", | |
height=350, | |
scrolling=True | |
) | |
if i < len(visualizations) - 1: | |
st.markdown("---") # Separador entre diagramas | |
# Si es un análisis, guardarlo en la base de datos | |
if user_input.startswith('/analisis_morfosintactico') and result: | |
store_morphosyntax_result( | |
st.session_state.username, | |
user_input.split('[', 1)[1].rsplit(']', 1)[0], # texto analizado | |
result.get('repeated_words', {}), | |
visualizations, | |
result.get('pos_analysis', []), | |
result.get('morphological_analysis', []), | |
result.get('sentence_structure', []) | |
) | |
except Exception as e: | |
st.error(f"{t['error_processing']}: {str(e)}") | |
# Forzar la actualización de la interfaz | |
st.rerun() | |
# Botón para limpiar el historial del chat | |
if st.button(t['clear_chat'], key=generate_unique_key('morphosyntax', 'clear_chat')): | |
st.session_state.morphosyntax_chat_history = [] | |
st.rerun() | |
''' | |
''' | |
############ MODULO PARA DEPURACIÓN Y PRUEBAS ##################################################### | |
def display_morphosyntax_interface(lang_code, nlp_models, t): | |
st.subheader(t['morpho_title']) | |
text_input = st.text_area( | |
t['warning_message'], | |
height=150, | |
key=generate_unique_key("morphosyntax", "text_area") | |
) | |
if st.button( | |
t['results_title'], | |
key=generate_unique_key("morphosyntax", "analyze_button") | |
): | |
if text_input: | |
# Aquí iría tu lógica de análisis morfosintáctico | |
# Por ahora, solo mostraremos un mensaje de placeholder | |
st.info(t['analysis_placeholder']) | |
else: | |
st.warning(t['no_text_warning']) | |
### | |
################################################# | |
''' | |