Update app.py

app.py

@@ -3,10 +3,7 @@ import pandas as pd
 import plotly.express as px
 import streamlit as st
 
-OPTS = {
-    "ACL 2022": "data/acl2022_spectre2-base.json",
-    "ACL 2023": "data/acl2023_spectre2-base.json",
-}
+DATA_FILE = "data/anthology-2020-23_specter2_base.json"
 
 
 def load_df(data_file: os.PathLike):
@@ -22,22 +19,39 @@ def load_df(data_file: os.PathLike):
 
 
 @st.cache_data
-def load_dataframes():
-    return {venue: load_df(df_file) for venue, df_file in OPTS.items()}
+def load_dataframe():
+    return load_df(DATA_FILE)
 
-DFS = load_dataframes()
+DF = load_dataframe()
 
-option = st.selectbox(
-    'Please select a venue',
-    ('ACL 2022', 'ACL 2023',)
-)
+with st.sidebar:
+    venues = st.multiselect(
+        "Venues",
+        ["ACL", "EMNLP", "NAACL", "TACL"],
+        ["ACL", "EMNLP", "NAACL", "TACL"],
+    )
+
+    start_year, end_year = st.select_slider("Publication year", options=("2020", "2021", "2022", "2023"), value=("2020", "2023"))
+    author_names = st.text_input('Author names (separated by comma)')
+
+    start_year = int(start_year)
+    end_year = int(end_year)
+    df = DF[(DF["year"] >= start_year) & (DF["year"] <= end_year)]
+    if len(venues) < 4:
+        selected_venues = [v.lower() for v in venues]
+        df = df[df["source"].isin(selected_venues)]
+
+    if author_names:
+        authors = [a.strip().lower() for a in author_names.split(",")]
+        author_mask = df.authors.apply(lambda x: all(a in x for a in authors))
+        df = df[author_mask]
 
+    st.write(f"Number of points: {df.shape[0]}")
 
-external_stylesheets = ["https://codepen.io/chriddyp/pen/bWLwgP.css"]
 
 
 fig = px.scatter(
-    DFS[option],
+    df,
     x="x",
     y="y",
     color="cluster",