Added same init across pages

app/pages/01_Topic_Explorer_📚.py

@@ -1,5 +1,6 @@
 from logging import getLogger
 from pathlib import Path
+import joblib
 
 import pandas as pd
 import plotly.express as px
@@ -9,14 +10,40 @@ import streamlit as st
 from top2vec import Top2Vec
 
 
+@st.cache(show_spinner=False)
 def initialize_state():
-    with st.spinner('Loading App...'):
+    with st.spinner("Loading app..."):
         if 'model' not in st.session_state:
             model = Top2Vec.load('models/model.pkl')
             model._check_model_status()
             model.hierarchical_topic_reduction(num_topics=20)
-            assert len(model.topic_words_reduced) == 20
+
             st.session_state.model = model
+            st.session_state.umap_model = joblib.load(proj_dir / 'models' / 'umap.sav')
+            logger.info("loading data...")
+
+            data = pd.read_csv(proj_dir/'data'/'data.csv')
+            data['topic_id'] = data['topic_id'].apply(lambda x: f'{x:02d}')
+            st.session_state.data = data
+
+            topics = pd.read_csv(proj_dir/'data'/'topics.csv')
+            topics['topic_id'] = topics['topic_id'].apply(lambda x: f'{x:02d}')
+
+            st.session_state.topics = topics
+
+        if 'data' not in st.session_state:
+            logger.info("loading data...")
+            data = pd.read_csv(proj_dir/'data'/'data.csv')
+            data['topic_id'] = data['topic_id'].apply(lambda x: f'{x:02d}')
+            st.session_state.data = data
+            st.session_state.selected_data = data
+            st.session_state.all_topics = list(data.topic_id.unique())
+
+        if 'topics' not in st.session_state:
+            logger.info("loading topics...")
+            topics = pd.read_csv(proj_dir/'data'/'topics.csv')
+            topics['topic_id'] = topics['topic_id'].apply(lambda x: f'{x:02d}')
+            st.session_state.topics = topics
 
 def main():
     st.write(""" 

app/pages/02_Document_Explorer_📖.py

@@ -1,6 +1,7 @@
 from distutils.fancy_getopt import wrap_text
 from logging import getLogger
 from pathlib import Path
+import joblib
 
 import pandas as pd
 import plotly.express as px
@@ -12,22 +13,40 @@ from streamlit_plotly_events import plotly_events
 from top2vec import Top2Vec
 
 
+@st.cache(show_spinner=False)
 def initialize_state():
-    if 'data' not in st.session_state:
-        logger.info("loading data...")
-        data = pd.read_csv(proj_dir/'data'/'data.csv')
-        data['topic_id'] = data['topic_id'].apply(lambda x: f'{x:02d}')
-        st.session_state.data = data
-        st.session_state.selected_data = data
-        st.session_state.all_topics = list(data.topic_id.unique())
-
-    if 'topics' not in st.session_state:
-        logger.info("loading topics...")
-        topics = pd.read_csv(proj_dir/'data'/'topics.csv')
-        topics['topic_id'] = topics['topic_id'].apply(lambda x: f'{x:02d}')
-        st.session_state.topics = topics
-
-        st.session_state.selected_points = []
+    with st.spinner("Loading app..."):
+        if 'model' not in st.session_state:
+            model = Top2Vec.load('models/model.pkl')
+            model._check_model_status()
+            model.hierarchical_topic_reduction(num_topics=20)
+
+            st.session_state.model = model
+            st.session_state.umap_model = joblib.load(proj_dir / 'models' / 'umap.sav')
+            logger.info("loading data...")
+
+            data = pd.read_csv(proj_dir/'data'/'data.csv')
+            data['topic_id'] = data['topic_id'].apply(lambda x: f'{x:02d}')
+            st.session_state.data = data
+
+            topics = pd.read_csv(proj_dir/'data'/'topics.csv')
+            topics['topic_id'] = topics['topic_id'].apply(lambda x: f'{x:02d}')
+
+            st.session_state.topics = topics
+
+        if 'data' not in st.session_state:
+            logger.info("loading data...")
+            data = pd.read_csv(proj_dir/'data'/'data.csv')
+            data['topic_id'] = data['topic_id'].apply(lambda x: f'{x:02d}')
+            st.session_state.data = data
+            st.session_state.selected_data = data
+            st.session_state.all_topics = list(data.topic_id.unique())
+
+        if 'topics' not in st.session_state:
+            logger.info("loading topics...")
+            topics = pd.read_csv(proj_dir/'data'/'topics.csv')
+            topics['topic_id'] = topics['topic_id'].apply(lambda x: f'{x:02d}')
+            st.session_state.topics = topics
 
 def reset():
     logger.info("Resetting...")

app/pages/03_Semantic_Search_🔍.py

@@ -17,6 +17,8 @@ def initialize_state():
         if 'model' not in st.session_state:
             model = Top2Vec.load('models/model.pkl')
             model._check_model_status()
+            model.hierarchical_topic_reduction(num_topics=20)
+
             st.session_state.model = model
             st.session_state.umap_model = joblib.load(proj_dir / 'models' / 'umap.sav')
             logger.info("loading data...")
@@ -30,6 +32,22 @@ def initialize_state():
 
             st.session_state.topics = topics
 
+        if 'data' not in st.session_state:
+            logger.info("loading data...")
+            data = pd.read_csv(proj_dir/'data'/'data.csv')
+            data['topic_id'] = data['topic_id'].apply(lambda x: f'{x:02d}')
+            st.session_state.data = data
+            st.session_state.selected_data = data
+            st.session_state.all_topics = list(data.topic_id.unique())
+
+        if 'topics' not in st.session_state:
+            logger.info("loading topics...")
+            topics = pd.read_csv(proj_dir/'data'/'topics.csv')
+            topics['topic_id'] = topics['topic_id'].apply(lambda x: f'{x:02d}')
+            st.session_state.topics = topics
+
+            st.session_state.selected_points = []
+
 def main():
 
     max_docs = st.sidebar.slider("# docs", 10, 100, value=50)