File size: 8,119 Bytes
5761cdf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ee54fd3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5761cdf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
import streamlit as st
from sentence_transformers import SentenceTransformer, util
from sklearn.decomposition import LatentDirichletAllocation
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.manifold import TSNE
from langdetect import detect, DetectorFactory
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

DetectorFactory.seed = 0

# Load models for embedding and similarity
multi_embedding_model = SentenceTransformer('distiluse-base-multilingual-cased-v1')

class WordEmbeddingAgent:
    def __init__(self, model):
        self.model = model

    def get_embeddings(self, words):
        return self.model.encode(words)

class SimilarityAgent:
    def __init__(self, model):
        self.model = model

    def compute_similarity(self, text1, text2):
        embedding1 = self.model.encode(text1, convert_to_tensor=True)
        embedding2 = self.model.encode(text2, convert_to_tensor=True)
        return util.pytorch_cos_sim(embedding1, embedding2).item()

class TopicModelingAgent:
    def __init__(self, n_components=10):
        self.lda_model = LatentDirichletAllocation(n_components=n_components, random_state=42)

    def fit_transform(self, texts, lang):
        stop_words = 'english' if lang == 'en' else 'spanish'
        vectorizer = CountVectorizer(max_df=0.9, min_df=2, stop_words=stop_words)
        dtm = vectorizer.fit_transform(texts)
        self.lda_model.fit(dtm)
        return self.lda_model.transform(dtm), vectorizer

    def get_topics(self, vectorizer, num_words=10):
        topics = {}
        for idx, topic in enumerate(self.lda_model.components_):
            topics[idx] = [vectorizer.get_feature_names_out()[i] for i in topic.argsort()[-num_words:]]
        return topics

def detect_language(text):
    try:
        return detect(text)
    except:
        return "unknown"

def tsne_visualization(embeddings, words):
    tsne = TSNE(n_components=2, random_state=42)
    embeddings_2d = tsne.fit_transform(embeddings)
    df = pd.DataFrame(embeddings_2d, columns=['x', 'y'])
    df['word'] = words
    return df

def main():
    st.title("Multilingual Text Analysis System")
    user_input = st.text_area("Enter your text here:")

    if st.button("Analyze"):
        if user_input:
            lang = detect_language(user_input)
            st.write(f"Detected language: {lang}")

            embedding_agent = WordEmbeddingAgent(multi_embedding_model)
            similarity_agent = SimilarityAgent(multi_embedding_model)
            topic_modeling_agent = TopicModelingAgent()

            # Tokenize the input text into words
            words = user_input.split()
            
            # Generate Embeddings
            embeddings = embedding_agent.get_embeddings(words)
            st.write("Word Embeddings Generated.")

            # t-SNE Visualization
            tsne_df = tsne_visualization(embeddings, words)
            fig, ax = plt.subplots()
            ax.scatter(tsne_df['x'], tsne_df['y'])

            for i, word in enumerate(tsne_df['word']):
                ax.annotate(word, (tsne_df['x'][i], tsne_df['y'][i]))

            st.pyplot(fig)

            # Topic Modeling
            texts = [user_input, "Another text to improve topic modeling."]
            topic_distr, vectorizer = topic_modeling_agent.fit_transform(texts, lang)
            topics = topic_modeling_agent.get_topics(vectorizer)
            st.write("Topics Extracted:")
            for topic, words in topics.items():
                st.write(f"Topic {topic}: {', '.join(words)}")

            # Sentence Similarity (example with another text)
            text2 = "Otro texto de ejemplo para comparación de similitud." if lang != 'en' else "Another example text for similarity comparison."
            similarity_score = similarity_agent.compute_similarity(user_input, text2)
            st.write(f"Similarity Score with example text: {similarity_score:.4f}")

        else:
            st.warning("Please enter some text to analyze.")

if __name__ == "__main__":
    main()
import streamlit as st
from sentence_transformers import SentenceTransformer, util
from sklearn.decomposition import LatentDirichletAllocation
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.manifold import TSNE
from langdetect import detect, DetectorFactory
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

DetectorFactory.seed = 0

# Load models for embedding and similarity
multi_embedding_model = SentenceTransformer('distiluse-base-multilingual-cased-v1')

class WordEmbeddingAgent:
    def __init__(self, model):
        self.model = model

    def get_embeddings(self, words):
        return self.model.encode(words)

class SimilarityAgent:
    def __init__(self, model):
        self.model = model

    def compute_similarity(self, text1, text2):
        embedding1 = self.model.encode(text1, convert_to_tensor=True)
        embedding2 = self.model.encode(text2, convert_to_tensor=True)
        return util.pytorch_cos_sim(embedding1, embedding2).item()

class TopicModelingAgent:
    def __init__(self, n_components=10):
        self.lda_model = LatentDirichletAllocation(n_components=n_components, random_state=42)

    def fit_transform(self, texts, lang):
        stop_words = 'english' if lang == 'en' else 'spanish'
        vectorizer = CountVectorizer(max_df=0.9, min_df=2, stop_words=stop_words)
        dtm = vectorizer.fit_transform(texts)
        self.lda_model.fit(dtm)
        return self.lda_model.transform(dtm), vectorizer

    def get_topics(self, vectorizer, num_words=10):
        topics = {}
        for idx, topic in enumerate(self.lda_model.components_):
            topics[idx] = [vectorizer.get_feature_names_out()[i] for i in topic.argsort()[-num_words:]]
        return topics

def detect_language(text):
    try:
        return detect(text)
    except:
        return "unknown"

def tsne_visualization(embeddings, words):
    tsne = TSNE(n_components=2, random_state=42)
    embeddings_2d = tsne.fit_transform(embeddings)
    df = pd.DataFrame(embeddings_2d, columns=['x', 'y'])
    df['word'] = words
    return df

def main():
    st.title("Multilingual Text Analysis System")
    user_input = st.text_area("Enter your text here:")

    if st.button("Analyze"):
        if user_input:
            lang = detect_language(user_input)
            st.write(f"Detected language: {lang}")

            embedding_agent = WordEmbeddingAgent(multi_embedding_model)
            similarity_agent = SimilarityAgent(multi_embedding_model)
            topic_modeling_agent = TopicModelingAgent()

            # Tokenize the input text into words
            words = user_input.split()
            
            # Generate Embeddings
            embeddings = embedding_agent.get_embeddings(words)
            st.write("Word Embeddings Generated.")

            # t-SNE Visualization
            tsne_df = tsne_visualization(embeddings, words)
            fig, ax = plt.subplots()
            ax.scatter(tsne_df['x'], tsne_df['y'])

            for i, word in enumerate(tsne_df['word']):
                ax.annotate(word, (tsne_df['x'][i], tsne_df['y'][i]))

            st.pyplot(fig)

            # Topic Modeling
            texts = [user_input, "Another text to improve topic modeling."]
            topic_distr, vectorizer = topic_modeling_agent.fit_transform(texts, lang)
            topics = topic_modeling_agent.get_topics(vectorizer)
            st.write("Topics Extracted:")
            for topic, words in topics.items():
                st.write(f"Topic {topic}: {', '.join(words)}")

            # Sentence Similarity (example with another text)
            text2 = "Otro texto de ejemplo para comparación de similitud." if lang != 'en' else "Another example text for similarity comparison."
            similarity_score = similarity_agent.compute_similarity(user_input, text2)
            st.write(f"Similarity Score with example text: {similarity_score:.4f}")

        else:
            st.warning("Please enter some text to analyze.")

if __name__ == "__main__":
    main()