Create app.py

app.py

@@ -0,0 +1,82 @@
+import gradio as gr
+import pandas as pd
+import nltk
+from nltk.corpus import stopwords
+from umap import UMAP
+from hdbscan import HDBSCAN
+from sentence_transformers import SentenceTransformer
+from sklearn.feature_extraction.text import CountVectorizer
+from bertopic import BERTopic
+from bertopic.representation import MaximalMarginalRelevance
+from bertopic.vectorizers import ClassTfidfTransformer
+
+# Charger les stopwords
+try:
+    stop_words = stopwords.words('english')
+except LookupError:
+    nltk.download('stopwords')
+    stop_words = stopwords.words('english')
+
+# Stopwords personnalisés
+custom_stopwords = ["made", "sure"]
+stop_words.extend(custom_stopwords)
+
+# Pipeline BERTopic personnalisé
+def generate_topics(file):
+    docs = pd.read_csv(file.name)
+
+    embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
+    embeddings = embedding_model.encode(docs['text'].tolist(), show_progress_bar=True)
+
+    umap_model = UMAP(
+        n_neighbors=20,
+        n_components=5,
+        min_dist=0.0,
+        metric='cosine',
+        random_state=42
+    )
+
+    hdbscan_model = HDBSCAN(
+        min_cluster_size=60,
+        min_samples=1,
+        metric='euclidean',
+        cluster_selection_method='eom',
+        prediction_data=True
+    )
+
+    vectorizer_model = CountVectorizer(
+        stop_words=stop_words,
+        min_df=1,
+        ngram_range=(1, 3)
+    )
+
+    ctfidf_model = ClassTfidfTransformer()
+    representation_model = MaximalMarginalRelevance(diversity=0.7)
+
+    BERT_model = BERTopic(
+        embedding_model=embedding_model,
+        umap_model=umap_model,
+        hdbscan_model=hdbscan_model,
+        vectorizer_model=vectorizer_model,
+        ctfidf_model=ctfidf_model,
+        representation_model=representation_model,
+        verbose=True
+    )
+
+    topics, _ = BERT_model.fit_transform(docs['text'].tolist())
+    BERT_model.reduce_outliers(docs['text'].tolist(), topics)
+
+    fig = BERT_model.visualize_documents(docs['text'].tolist())
+    return fig
+
+# Interface Gradio
+demo = gr.Interface(
+    fn=generate_topics,
+    inputs=gr.File(label="Upload bbc-text.csv"),
+    outputs=gr.Plot(label="Topic Map"),
+    title="Topic Modeling avec BERTopic",
+    description="Téléversez un fichier CSV avec une colonne 'text' pour générer une visualisation thématique interactive."
+)
+
+if __name__ == "__main__":
+    demo.launch()