Duplicate from gwf-uwaterloo/scicatter2d

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+data/anthology-2020-23_specter2_base.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Scicatter2d
+emoji: 📉
+colorFrom: purple
+colorTo: indigo
+sdk: streamlit
+sdk_version: 1.26.0
+app_file: app.py
+pinned: false
+duplicated_from: gwf-uwaterloo/scicatter2d
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,89 @@
+import os
+import re
+import pandas as pd
+import plotly.express as px
+import streamlit as st
+
+st.set_page_config(layout="wide")
+DATA_FILE = "data/anthology-2020-23_specter2_base.json"
+THEMES = {"cluster": "fall", "year": "mint", "source": "phase"}
+
+def load_df(data_file: os.PathLike):
+    df = pd.read_json(data_file, orient="records")
+    df["x"] = df["point2d"].apply(lambda x: x[0])
+    df["y"] = df["point2d"].apply(lambda x: x[1])
+    if "publication_type" in df.columns:
+        df["type"] = df["publication_type"]
+        df = df.drop(columns=["point2d", "publication_type"])
+    else:
+        df = df.drop(columns=["point2d"])
+    return df
+
+
+@st.cache_data
+def load_dataframe():
+    return load_df(DATA_FILE)
+
+
+DF = load_dataframe()
+
+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)")
+
+    title = st.text_input("Title")
+
+    start_year = int(start_year)
+    end_year = int(end_year)
+    df = DF[(DF["year"] >= start_year) & (DF["year"] <= end_year)]
+    if 0 < len(venues) < 4:
+        selected_venues = [v.lower() for v in venues]
+        df = df[df["source"].isin(selected_venues)]
+    elif not venues:
+        st.write(":red[Please select a venue]")
+
+    if author_names:
+        authors = [a.strip() for a in author_names.split(",")]
+        author_mask = df.authors.apply(
+            lambda row: all(any(re.match(rf".*{a}.*", x, re.IGNORECASE) for x in row) for a in authors)
+        )
+        df = df[author_mask]
+
+    if title:
+        df = df[df.title.apply(lambda x: title.lower() in x.lower())]
+
+    st.write(f"Number of points: {df.shape[0]}")
+
+    color = st.selectbox("Color", ("cluster", "year", "source"))
+
+
+fig = px.scatter(
+    df,
+    x="x",
+    y="y",
+    color=color,
+    width=1000,
+    height=800,
+    hover_data=["title", "authors", "year", "source", "type"],
+    color_continuous_scale=THEMES[color],
+)
+fig.update_layout(
+    # margin=dict(l=10, r=10, t=10, b=10),
+    showlegend=False,
+    font=dict(
+        family="Times New Roman",
+        size=30,
+    ),
+)
+fig.update_xaxes(title="")
+fig.update_yaxes(title="")
+
+st.plotly_chart(fig, use_container_width=True)

data/anthology-2020-23_specter2_base.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf528ba2e72c9865d3a332b5d319a573142a2f6813eb78cd071c0781b4e780b3
+size 11791691

requirements.txt

@@ -0,0 +1,2 @@
+plotly
+pandas