Update app.py

app.py

@@ -22,19 +22,46 @@ nltk.download('punkt')
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 import pandas as pd
+
+
+@st.cache
+def load_data():
+    #df = pd.read_json('https://www.dropbox.com/s/82lwbaym3b1o6uq/passages.jsonl?raw=1', lines=True)
+    
+    url = "https://drive.google.com/uc?export=download&id=1nIBS9is8YCeiPBqA7MifVC5xeaKWH8uL"
+    output = "passages.jsonl"
+    gdown.download(url, output, quiet=False)
+
+    df = pd.read_json(output, lines=True)
+
+    df.reset_index(inplace=True, drop=True)
+    return df
+
+
 st.title('Sociology Paragraph Search')
 
 st.write('This project is a work-in-progress that searches the text of recently-published articles from a few sociology journals and retrieves the most relevant paragraphs.')
 
-st.markdown('''Notes:
+
+with st.spinner(text="Loading data..."):
+    df = load_data()
+    passages = df['text'].values
+    
+no_of_graphs=len(df)
+no_of_articles = len(df['cite'].value_count())
+
+
+notes = f'''Notes:
 * To get the best results, search like you are using Google. My best luck comes from phrases like "social movements and public opinion", "inequality in latin america", "race color skin tone measurement", "audit study experiment gender", "Crenshaw intersectionality", or "logistic regression or linear probability model". You can also use questions like "What is a topic model?" or "How did Weber define bureaucracy?"
-* The dataset currently includes articles published in the last five years in *Mobilization*, Social Forces, Social Problems, Sociology of Race and Ethnicity, Gender and Society, Socius, JHSB, Annual Review of Sociology, and the American Sociological Review, totaling more than 100,000 paragraphs from a few thousand articles.
+* The dataset currently includes articles published in the last five years in *Mobilization*, Social Forces, Social Problems, Sociology of Race and Ethnicity, Gender and Society, Socius, JHSB, Annual Review of Sociology, and the American Sociological Review, totaling {no_of_graphs} paragraphs from a {no_of_articles} articles.
 * The most relevant paragraph to your search is returned first, along with up to four other related paragraphs from that article.
 * The most relevant sentence within each paragraph, as determined by math, is bolded.
 * Behind the scenes, the semantic search uses [text embeddings](https://www.sbert.net) with a [retrieve & re-rank](https://colab.research.google.com/github/UKPLab/sentence-transformers/blob/master/examples/applications/retrieve_rerank/retrieve_rerank_simple_wikipedia.ipynb) process to find the best matches.
 * The first search can take up to 30 seconds as the files load. After that, it's quicker to respond.
 * Let [me](mailto:neal.caren@unc.edu) know what you think or it looks broken.
-''')
+'''
+
+st.markdown(notes)
 
 
 def sent_trans_load():
@@ -49,24 +76,9 @@ def sent_cross_load():
     return cross_encoder
 
 
-@st.cache
-def load_data():
-    #df = pd.read_json('https://www.dropbox.com/s/82lwbaym3b1o6uq/passages.jsonl?raw=1', lines=True)
-    
-    url = "https://drive.google.com/uc?export=download&id=1nIBS9is8YCeiPBqA7MifVC5xeaKWH8uL"
-    output = "passages.jsonl"
-    gdown.download(url, output, quiet=False)
-
-    df = pd.read_json(output, lines=True)
 
-    df.reset_index(inplace=True, drop=True)
-    return df
 
 
-with st.spinner(text="Loading data..."):
-    df = load_data()
-    passages = df['text'].values
-
 @st.cache
 def load_embeddings():
     #efs = [np.load(f'embeddings_{i}.pt.npy')  for i in range(0,5)]