File size: 4,085 Bytes
63994d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7aaa1ae
63994d4
 
 
 
 
 
 
 
230629e
63994d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2ebc879
 
 
 
885f549
63994d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2ebc879
 
 
 
 
230629e
885f549
 
47d9b77
63994d4
 
 
 
 
 
 
 
 
 
 
 
 
 
230629e
 
 
 
 
 
 
 
 
 
 
63994d4
230629e
 
63994d4
 
230629e
 
 
 
 
 
 
 
 
 
 
 
 
63994d4
230629e
 
63994d4
230629e
63994d4
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
"""
Reference: https://huggingface.co/spaces/gwf-uwaterloo/acl-spectrum (By Ehsan Khamallo)
"""

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 = "hess_papers_details.json"

st.markdown(
    """
    <link href="https://cdn.jsdelivr.net/npm/bootstrap@4.6.1/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha256-DF7Zhf293AJxJNTmh5zhoYYIMs2oXitRfBjY+9L//AY=" crossorigin="anonymous">
    <link rel="preconnect" href="https://fonts.googleapis.com">
    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
    <link href="https://fonts.googleapis.com/css2?family=Permanent+Marker&display=swap" rel="stylesheet">
    <style>
    .title {
        font-family: 'Arial';
        font-size: 2.0rem;
    }
    </style>""",
    unsafe_allow_html=True,
)

st.sidebar.write(
    """<center><p class="title">
    Clustering on HESS Papers 🌎🌿
    </p></center>""",
    unsafe_allow_html=True,
)

st.sidebar.write(
    """<p class="text-justify">
    A clustered visualization of all papers submitted to the
    <a href=https://www.hydrology-and-earth-system-sciences.net/>Hydrology and Earth System Sciences</a> (HESS) conference.
    5318 papers are embedded using <a href="https://huggingface.co/allenai/specter2_base">spectre2</a> and reduced with
    t-SNE. Papers span from as early as 1997 to 2023.
    </p>""",
    unsafe_allow_html=True,
)

def to_string_authors(list_of_authors):
    if len(list_of_authors) > 5:
        return ", ".join(list_of_authors[:5]) + ", et al."
    elif len(list_of_authors) > 2:
        return ", ".join(list_of_authors[:-1]) + ", and " + list_of_authors[-1]
    else:
        return " and ".join(list_of_authors)


def load_df(data_file: os.PathLike):
    df = pd.read_json(data_file, orient="records")
    df["x"] = df["t-SNE1"]
    df["y"] = df["t-SNE2"]

    df["authors_trimmed"] = df["authors_trimmed"]

    # #sort dataframe by year
    # df['year'] = pd.to_datetime(df['year'])
    # df = df.sort_values('year', ascending=True)
    # df['year'] = df['year'].dt.strftime('%Y')
    #df['year'] = df['year'].astype(int)

    return df

@st.cache_data
def load_dataframe():
    return load_df(DATA_FILE)

DF = load_dataframe()
DF["opacity"] = 0.04
min_year, max_year = DF["year"].min(), DF["year"].max()

with st.sidebar:
    author_names = st.text_input("Author names (separated by comma)")

    title = st.text_input("Title")

    # Work on this
    # topics = st.multiselect(
    #     "Topics",
    #     ["Topics 1: "],
    #     ["Topics 2: "],
    # )

    start_year, end_year = st.select_slider(
        "Publication year",
        options=[str(y) for y in range(min_year, max_year + 1)],
        value=(str(min_year), str(max_year)),
    )

    start_year = int(start_year)
    end_year = int(end_year)
    df_mask = (DF["year"] >= start_year) & (DF["year"] <= end_year)

    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_mask = df_mask & author_mask

    if title:
        df_mask = df_mask & DF.title.apply(lambda x: title.lower() in x.lower())

    DF.loc[df_mask, "opacity"] = 1.0
    st.write(f"Number of points: {DF[df_mask].shape[0]}")

fig = px.scatter(
    DF,
    x="x",
    y="y",
    opacity=DF["opacity"],
    color=DF["cluster"],
    width=1000,
    height=800,
    custom_data=("title", "authors_trimmed", "year"),
    color_continuous_scale="haline",
)

fig.update_traces(
hovertemplate="<b>%{customdata[0]}</b><br>%{customdata[1]}<br>%{customdata[2]}<br><i>"
    )

fig.update_layout(
    showlegend=False,
    font=dict(
        family="Times New Roman",
        size=30,
    ),
    hoverlabel=dict(
        align="left",
        font_size=14,
        font_family="Rockwell",
        namelength=-1,
    ),
)

fig.update_xaxes(title="")
fig.update_yaxes(title="")

st.plotly_chart(fig, use_container_width=True)