Update modules/studentact/current_situation_analysis.py
Browse files
modules/studentact/current_situation_analysis.py
CHANGED
@@ -12,101 +12,77 @@ import logging
|
|
12 |
|
13 |
logger = logging.getLogger(__name__)
|
14 |
|
|
|
15 |
def analyze_text_dimensions(doc):
|
16 |
"""
|
17 |
Analiza las dimensiones principales del texto.
|
18 |
-
|
19 |
-
Args:
|
20 |
-
doc: Documento procesado por spaCy
|
21 |
-
|
22 |
-
Returns:
|
23 |
-
dict: M茅tricas del an谩lisis
|
24 |
"""
|
25 |
try:
|
26 |
# An谩lisis de vocabulario
|
27 |
-
vocab_score = analyze_vocabulary_diversity(doc)
|
28 |
-
|
29 |
-
value=vocab_score,
|
30 |
-
optimal_connections=len(doc) * 0.4 # 40% del total de palabras como conexiones 贸ptimas
|
31 |
-
)
|
32 |
-
|
33 |
# An谩lisis de estructura
|
34 |
struct_score = analyze_structure(doc)
|
35 |
-
|
36 |
-
value=struct_score,
|
37 |
-
optimal_length=20 # Longitud 贸ptima promedio de oraci贸n
|
38 |
-
)
|
39 |
-
|
40 |
# An谩lisis de cohesi贸n
|
41 |
cohesion_score = analyze_cohesion(doc)
|
42 |
-
|
43 |
-
value=cohesion_score,
|
44 |
-
optimal_value=0.7 # 70% de cohesi贸n como valor 贸ptimo
|
45 |
-
)
|
46 |
-
|
47 |
# An谩lisis de claridad
|
48 |
-
clarity_score = analyze_clarity(doc)
|
49 |
-
clarity_normalized = normalize_score(
|
50 |
-
value=clarity_score,
|
51 |
-
optimal_value=0.8 # 80% de claridad como valor 贸ptimo
|
52 |
-
)
|
53 |
|
54 |
return {
|
55 |
'vocabulary': {
|
56 |
-
'
|
57 |
-
'
|
58 |
},
|
59 |
'structure': {
|
60 |
-
'
|
61 |
-
'
|
62 |
},
|
63 |
'cohesion': {
|
64 |
-
'
|
65 |
-
'
|
66 |
},
|
67 |
'clarity': {
|
68 |
-
'
|
69 |
-
'
|
70 |
}
|
71 |
}
|
72 |
|
73 |
except Exception as e:
|
74 |
logger.error(f"Error en analyze_text_dimensions: {str(e)}")
|
75 |
-
|
|
|
|
|
|
|
|
|
|
|
76 |
|
|
|
77 |
def analyze_clarity(doc):
|
78 |
"""
|
79 |
-
Analiza la claridad del texto considerando m煤ltiples factores
|
80 |
-
- Longitud y variaci贸n de oraciones
|
81 |
-
- Uso de conectores
|
82 |
-
- Complejidad estructural
|
83 |
-
- Claridad referencial
|
84 |
-
- Densidad l茅xica
|
85 |
"""
|
86 |
try:
|
87 |
# 1. An谩lisis de oraciones
|
88 |
sentences = list(doc.sents)
|
89 |
if not sentences:
|
90 |
-
return 0.0
|
91 |
|
92 |
# Longitud de oraciones
|
93 |
sentence_lengths = [len(sent) for sent in sentences]
|
94 |
avg_length = sum(sentence_lengths) / len(sentences)
|
95 |
length_variation = np.std(sentence_lengths) if len(sentences) > 1 else 0
|
96 |
|
97 |
-
#
|
98 |
-
length_score = normalize_score(
|
99 |
-
avg_length,
|
100 |
-
optimal_length=20, # Longitud 贸ptima
|
101 |
-
range_factor=1.5 # Factor de tolerancia
|
102 |
-
)
|
103 |
|
104 |
# 2. An谩lisis de conectores
|
105 |
connector_count = 0
|
106 |
connector_types = {
|
107 |
-
'CCONJ': 0.8,
|
108 |
-
'SCONJ': 1.0,
|
109 |
-
'ADV': 0.6
|
110 |
}
|
111 |
|
112 |
for token in doc:
|
@@ -121,52 +97,33 @@ def analyze_clarity(doc):
|
|
121 |
verbs = [token for token in sent if token.pos_ == 'VERB']
|
122 |
clause_count += len(verbs)
|
123 |
|
124 |
-
|
125 |
-
|
126 |
-
optimal_value=2.0, # Promedio 贸ptimo de cl谩usulas por oraci贸n
|
127 |
-
range_factor=1.5
|
128 |
-
)
|
129 |
-
|
130 |
-
# 4. Claridad referencial
|
131 |
-
reference_score = analyze_reference_clarity(doc)
|
132 |
|
133 |
-
#
|
134 |
content_words = len([token for token in doc if token.pos_ in ['NOUN', 'VERB', 'ADJ', 'ADV']])
|
135 |
-
|
136 |
density_score = normalize_score(
|
137 |
-
content_words /
|
138 |
-
optimal_value=0.6
|
139 |
-
range_factor=1.5
|
140 |
)
|
141 |
|
142 |
-
#
|
143 |
-
weights = {
|
144 |
-
'length': 0.2,
|
145 |
-
'connectors': 0.2,
|
146 |
-
'complexity': 0.2,
|
147 |
-
'reference': 0.2,
|
148 |
-
'density': 0.2
|
149 |
-
}
|
150 |
-
|
151 |
-
# C谩lculo del score final ponderado
|
152 |
clarity_score = (
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
weights['density'] * density_score
|
158 |
)
|
159 |
|
160 |
-
# Informaci贸n detallada para diagn贸stico
|
161 |
details = {
|
162 |
'length_score': length_score,
|
163 |
'connector_score': connector_score,
|
164 |
'complexity_score': complexity_score,
|
165 |
-
'reference_score': reference_score,
|
166 |
'density_score': density_score,
|
167 |
'avg_sentence_length': avg_length,
|
168 |
'length_variation': length_variation,
|
169 |
-
'connectors_per_sentence': connector_count / len(sentences)
|
170 |
}
|
171 |
|
172 |
return clarity_score, details
|
|
|
12 |
|
13 |
logger = logging.getLogger(__name__)
|
14 |
|
15 |
+
###################################################################
|
16 |
def analyze_text_dimensions(doc):
|
17 |
"""
|
18 |
Analiza las dimensiones principales del texto.
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
"""
|
20 |
try:
|
21 |
# An谩lisis de vocabulario
|
22 |
+
vocab_score, vocab_details = analyze_vocabulary_diversity(doc)
|
23 |
+
|
|
|
|
|
|
|
|
|
24 |
# An谩lisis de estructura
|
25 |
struct_score = analyze_structure(doc)
|
26 |
+
|
|
|
|
|
|
|
|
|
27 |
# An谩lisis de cohesi贸n
|
28 |
cohesion_score = analyze_cohesion(doc)
|
29 |
+
|
|
|
|
|
|
|
|
|
30 |
# An谩lisis de claridad
|
31 |
+
clarity_score, clarity_details = analyze_clarity(doc)
|
|
|
|
|
|
|
|
|
32 |
|
33 |
return {
|
34 |
'vocabulary': {
|
35 |
+
'normalized_score': vocab_score,
|
36 |
+
'details': vocab_details
|
37 |
},
|
38 |
'structure': {
|
39 |
+
'normalized_score': struct_score,
|
40 |
+
'details': None # Por ahora no tiene detalles
|
41 |
},
|
42 |
'cohesion': {
|
43 |
+
'normalized_score': cohesion_score,
|
44 |
+
'details': None # Por ahora no tiene detalles
|
45 |
},
|
46 |
'clarity': {
|
47 |
+
'normalized_score': clarity_score,
|
48 |
+
'details': clarity_details
|
49 |
}
|
50 |
}
|
51 |
|
52 |
except Exception as e:
|
53 |
logger.error(f"Error en analyze_text_dimensions: {str(e)}")
|
54 |
+
return {
|
55 |
+
'vocabulary': {'normalized_score': 0.0, 'details': {}},
|
56 |
+
'structure': {'normalized_score': 0.0, 'details': {}},
|
57 |
+
'cohesion': {'normalized_score': 0.0, 'details': {}},
|
58 |
+
'clarity': {'normalized_score': 0.0, 'details': {}}
|
59 |
+
}
|
60 |
|
61 |
+
####################################################################
|
62 |
def analyze_clarity(doc):
|
63 |
"""
|
64 |
+
Analiza la claridad del texto considerando m煤ltiples factores.
|
|
|
|
|
|
|
|
|
|
|
65 |
"""
|
66 |
try:
|
67 |
# 1. An谩lisis de oraciones
|
68 |
sentences = list(doc.sents)
|
69 |
if not sentences:
|
70 |
+
return 0.0, {}
|
71 |
|
72 |
# Longitud de oraciones
|
73 |
sentence_lengths = [len(sent) for sent in sentences]
|
74 |
avg_length = sum(sentence_lengths) / len(sentences)
|
75 |
length_variation = np.std(sentence_lengths) if len(sentences) > 1 else 0
|
76 |
|
77 |
+
# Normalizar longitud
|
78 |
+
length_score = normalize_score(avg_length, optimal_length=20)
|
|
|
|
|
|
|
|
|
79 |
|
80 |
# 2. An谩lisis de conectores
|
81 |
connector_count = 0
|
82 |
connector_types = {
|
83 |
+
'CCONJ': 0.8,
|
84 |
+
'SCONJ': 1.0,
|
85 |
+
'ADV': 0.6
|
86 |
}
|
87 |
|
88 |
for token in doc:
|
|
|
97 |
verbs = [token for token in sent if token.pos_ == 'VERB']
|
98 |
clause_count += len(verbs)
|
99 |
|
100 |
+
complexity_raw = clause_count / len(sentences) if len(sentences) > 0 else 0
|
101 |
+
complexity_score = normalize_score(complexity_raw, optimal_value=2.0)
|
|
|
|
|
|
|
|
|
|
|
|
|
102 |
|
103 |
+
# 4. Densidad l茅xica
|
104 |
content_words = len([token for token in doc if token.pos_ in ['NOUN', 'VERB', 'ADJ', 'ADV']])
|
105 |
+
total_words = len([token for token in doc])
|
106 |
density_score = normalize_score(
|
107 |
+
content_words / total_words if total_words > 0 else 0,
|
108 |
+
optimal_value=0.6
|
|
|
109 |
)
|
110 |
|
111 |
+
# C谩lculo del score final
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
112 |
clarity_score = (
|
113 |
+
0.3 * length_score +
|
114 |
+
0.3 * connector_score +
|
115 |
+
0.2 * complexity_score +
|
116 |
+
0.2 * density_score
|
|
|
117 |
)
|
118 |
|
|
|
119 |
details = {
|
120 |
'length_score': length_score,
|
121 |
'connector_score': connector_score,
|
122 |
'complexity_score': complexity_score,
|
|
|
123 |
'density_score': density_score,
|
124 |
'avg_sentence_length': avg_length,
|
125 |
'length_variation': length_variation,
|
126 |
+
'connectors_per_sentence': connector_count / len(sentences) if len(sentences) > 0 else 0
|
127 |
}
|
128 |
|
129 |
return clarity_score, details
|