Spaces:
Running
Running
File size: 3,393 Bytes
93db903 2ea702b bd8fe60 2ea702b bd8fe60 93db903 bd8fe60 2ea702b bd8fe60 93db903 bd8fe60 93db903 bd8fe60 93db903 bd8fe60 93db903 bd8fe60 93db903 2ea702b |
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 |
import os
import re
import numpy as np
import pandas as pd
import plotly.express as px
import streamlit as st
st.set_page_config(layout="wide")
DATA_FILE = "data/gwf_2017-2021_specter2_base.json"
THEMES = {"cluster": "fall", "year": "mint", "source": "phase"}
def to_string_authors(list_of_authors):
if len(list_of_authors) > 6:
return ", ".join(list_of_authors[:6]) + ", 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["point2d"].apply(lambda x: x[0])
df["y"] = df["point2d"].apply(lambda x: x[1])
df["year"] = df["year"].replace("", 0)
df["year"] = df["year"].astype(int)
df["authors_trimmed"] = df.authors.apply(
lambda row: to_string_authors(
[(x[x.index(",") + 1 :].strip() + " " + x.split(",")[0].strip()) if "," in x else x for x in row]
)
)
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()
DF["opacity"] = 0.04
min_year, max_year = DF[DF["year"] > 0]["year"].min(), DF[DF["year"] > 0]["year"].max()
with st.sidebar:
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)),
)
src = st.text_input("Source")
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_mask = (DF["year"] >= start_year) & (DF["year"] <= end_year)
if src:
df_mask = df_mask & DF.source.apply(lambda x: src.lower() in x.lower())
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]}")
color = st.selectbox("Color", ("cluster", "year", "source"))
fig = px.scatter(
DF,
x="x",
y="y",
opacity=DF["opacity"],
color=color,
width=1000,
height=800,
custom_data=("title", "authors_trimmed", "year", "source", "keywords"),
color_continuous_scale=THEMES[color],
)
fig.update_traces(
hovertemplate="<b>%{customdata[0]}</b><br>%{customdata[1]}<br>%{customdata[2]}<br><i>%{customdata[3]}</i><br><i font-size='8'>Keywords: %{customdata[4]}</i>"
)
fig.update_layout(
# margin=dict(l=10, r=10, t=10, b=10),
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)
|