Demosthene-OR commited on
Commit
877d19f
·
1 Parent(s): 033655d
assets/value_props_logo.png CHANGED
requirements.txt CHANGED
@@ -34,3 +34,4 @@ gTTS==2.5.1
34
  https://files.pythonhosted.org/packages/cc/58/96aff0e5cb8b59c06232ea7e249ed902d04ec89f52636f5be06ceb0855fe/extra_streamlit_components-0.1.60-py3-none-any.whl
35
  streamlit-option-menu==0.3.12
36
  deep-translator==1.11.4
 
 
34
  https://files.pythonhosted.org/packages/cc/58/96aff0e5cb8b59c06232ea7e249ed902d04ec89f52636f5be06ceb0855fe/extra_streamlit_components-0.1.60-py3-none-any.whl
35
  streamlit-option-menu==0.3.12
36
  deep-translator==1.11.4
37
+ sentence_transformers==3.1.1
tabs/intro.py CHANGED
@@ -11,8 +11,8 @@ def run():
11
  # TODO: choose between one of these GIFs
12
  # st.image("https://dst-studio-template.s3.eu-west-3.amazonaws.com/1.gif")
13
  # st.image("https://dst-studio-template.s3.eu-west-3.amazonaws.com/2.gif")
14
- # st.image("https://dst-studio-template.s3.eu-west-3.amazonaws.com/3.gif")
15
- st.image("assets/tough-communication.gif",use_column_width=True)
16
 
17
 
18
  # if st.session_state.Cloud == 0:
@@ -28,7 +28,7 @@ def run():
28
  st.header("**"+tr("A propos")+"**")
29
  st.markdown(tr(
30
  """
31
- Cet espace a pour objectif de tester differentes briques nécéssaire pour l'outils "Value Props"
32
  """)
33
  , unsafe_allow_html=True)
34
 
@@ -36,7 +36,9 @@ def run():
36
  '''
37
  sent = \
38
  """
39
-
 
 
40
  """
41
  st.markdown(tr(sent), unsafe_allow_html=True)
42
  '''
 
11
  # TODO: choose between one of these GIFs
12
  # st.image("https://dst-studio-template.s3.eu-west-3.amazonaws.com/1.gif")
13
  # st.image("https://dst-studio-template.s3.eu-west-3.amazonaws.com/2.gif")
14
+ st.image("https://dst-studio-template.s3.eu-west-3.amazonaws.com/3.gif")
15
+ # st.image("assets/tough-communication.gif",use_column_width=True)
16
 
17
 
18
  # if st.session_state.Cloud == 0:
 
28
  st.header("**"+tr("A propos")+"**")
29
  st.markdown(tr(
30
  """
31
+ Cet espace a pour objectif de tester les differentes briques nécéssaires pour l'outils "Value Props"
32
  """)
33
  , unsafe_allow_html=True)
34
 
 
36
  '''
37
  sent = \
38
  """
39
+
40
+
41
+
42
  """
43
  st.markdown(tr(sent), unsafe_allow_html=True)
44
  '''
tabs/sentence_similarity_tab.py CHANGED
@@ -14,12 +14,25 @@ from gensim import corpora
14
  import networkx as nx
15
  from sklearn.manifold import TSNE
16
  from gensim.models import KeyedVectors
 
17
  from translate_app import tr
18
 
19
- title = "Data Vizualization"
20
- sidebar_name = "Data Vizualization"
21
  dataPath = st.session_state.DataPath
22
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  with contextlib.redirect_stdout(open(os.devnull, "w")):
24
  nltk.download('stopwords')
25
 
@@ -135,35 +148,7 @@ def dist_frequence_mots(df_count_word):
135
  st.pyplot(fig)
136
 
137
  def dist_longueur_phrase(sent_len,sent_len2, lang1, lang2 ):
138
- '''
139
- fig = px.histogram(sent_len, nbins=16, range_x=[3, 18],labels={'count': 'Count', 'variable': 'Nb de mots'},
140
- color_discrete_sequence=['rgb(200, 0, 0)'], # Couleur des barres de l'histogramme
141
- opacity=0.7)
142
- fig.update_traces(marker=dict(color='rgb(200, 0, 0)', line=dict(color='white', width=2)), showlegend=False,)
143
- fig.update_layout(
144
- title={'text': 'Distribution du nb de mots/phrase', 'y':1.0, 'x':0.5, 'xanchor': 'center', 'yanchor': 'top'},
145
- title_font=dict(size=28), # Ajuste la taille de la police du titre
146
- xaxis_title=None,
147
- xaxis=dict(
148
- title_font=dict(size=30), # Ajuste la taille de la police de l'axe X
149
- tickfont=dict(size=22),
150
- showgrid=True, gridcolor='white'
151
- ),
152
- yaxis_title='Count',
153
- yaxis=dict(
154
- title_font= dict(size=30, color='black'), # Ajuste la taille de la police de l'axe Y
155
- title_standoff=10, # Éloigne le label de l'axe X du graphique
156
- tickfont=dict(size=22),
157
- showgrid=True, gridcolor='white'
158
- ),
159
- margin=dict(l=20, r=20, t=40, b=20), # Ajustez les valeurs de 'r' pour déplacer les commandes à droite
160
- # legend=dict(x=1, y=1), # Position de la légende à droite en haut
161
- # width = 600
162
- height=600, # Définir la hauteur de la figure
163
- plot_bgcolor='rgba(220, 220, 220, 0.6)',
164
- )
165
- st.plotly_chart(fig, use_container_width=True)
166
- '''
167
  df = pd.DataFrame({lang1:sent_len,lang2:sent_len2})
168
  sns.set()
169
  fig = plt.figure() # figsize=(12, 6*row_nb)
@@ -175,15 +160,6 @@ def dist_longueur_phrase(sent_len,sent_len2, lang1, lang2 ):
175
  chart.set(title=tr('Distribution du nombre de mots sur '+str(len(sent_len))+' phrase(s)'));
176
  st.pyplot(fig)
177
 
178
- '''
179
- # fig = ff.create_distplot([sent_len], ['Nb de mots'],bin_size=1, colors=['rgb(200, 0, 0)'])
180
-
181
- distribution = pd.DataFrame({'Nb mots':sent_len, 'Nb phrases':[1]*len(sent_len)})
182
- fig = px.histogram(distribution, x='Nb mots', y='Nb phrases', marginal="box",range_x=[3, 18], nbins=16, hover_data=distribution.columns)
183
- fig.update_layout(height=600,title={'text': 'Distribution du nb de mots/phrase', 'y':1.0, 'x':0.5, 'xanchor': 'center', 'yanchor': 'top'})
184
- fig.update_traces(marker=dict(color='rgb(200, 0, 0)', line=dict(color='white', width=2)), showlegend=False,)
185
- st.plotly_chart(fig, use_container_width=True)
186
- '''
187
 
188
  def find_color(x,min_w,max_w):
189
  b_min = 0.0*(max_w-min_w)+min_w
@@ -401,4 +377,4 @@ def run():
401
  )
402
  st.write("")
403
  proximite()
404
-
 
14
  import networkx as nx
15
  from sklearn.manifold import TSNE
16
  from gensim.models import KeyedVectors
17
+ from sentence_transformers import SentenceTransformer
18
  from translate_app import tr
19
 
20
+ title = "Sentence Similarity"
21
+ sidebar_name = "Sentence Similarity"
22
  dataPath = st.session_state.DataPath
23
 
24
+
25
+ from sentence_transformers import SentenceTransformer
26
+ sentences = ["This is an example sentence", "Each sentence is converted"]
27
+
28
+ model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')
29
+ embeddings = model.encode(sentences)
30
+ st.write(embeddings)
31
+ st.write("")
32
+ st.write("")
33
+ st.write("")
34
+
35
+ '''
36
  with contextlib.redirect_stdout(open(os.devnull, "w")):
37
  nltk.download('stopwords')
38
 
 
148
  st.pyplot(fig)
149
 
150
  def dist_longueur_phrase(sent_len,sent_len2, lang1, lang2 ):
151
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
152
  df = pd.DataFrame({lang1:sent_len,lang2:sent_len2})
153
  sns.set()
154
  fig = plt.figure() # figsize=(12, 6*row_nb)
 
160
  chart.set(title=tr('Distribution du nombre de mots sur '+str(len(sent_len))+' phrase(s)'));
161
  st.pyplot(fig)
162
 
 
 
 
 
 
 
 
 
 
163
 
164
  def find_color(x,min_w,max_w):
165
  b_min = 0.0*(max_w-min_w)+min_w
 
377
  )
378
  st.write("")
379
  proximite()
380
+ '''