Spaces:
Running
Running
File size: 4,495 Bytes
8516ffb 2f2aa71 8516ffb ede50ba 8516ffb 34db5c9 641920f 34db5c9 8516ffb 2f2aa71 540545b 2f2aa71 8516ffb |
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 |
#===import module===
import streamlit as st
import pandas as pd
import plotly.express as px
import numpy as np
import sys
#===config===
st.set_page_config(
page_title="Coconut",
page_icon="🥥",
layout="wide"
)
st.header("Data visualization")
hide_streamlit_style = """
<style>
#MainMenu {visibility: hidden;}
footer {visibility: hidden;}
</style>
"""
st.markdown(hide_streamlit_style, unsafe_allow_html=True)
st.subheader('Put your CSV file and choose a visualization')
#===clear cache===
def reset_all():
st.cache_data.clear()
#===check type===
@st.cache_data(ttl=3600)
def get_ext(extype):
extype = uploaded_file.name
return extype
@st.cache_data(ttl=3600)
def upload(extype):
papers = pd.read_csv(uploaded_file)
#lens.org
if 'Publication Year' in papers.columns:
papers.rename(columns={'Publication Year': 'Year', 'Citing Works Count': 'Cited by',
'Publication Type': 'Document Type', 'Source Title': 'Source title'}, inplace=True)
return papers
@st.cache_data(ttl=3600)
def conv_txt(extype):
col_dict = {'TI': 'Title',
'SO': 'Source title',
'DT': 'Document Type',
'DE': 'Author Keywords',
'ID': 'Keywords Plus',
'AB': 'Abstract',
'TC': 'Cited by',
'PY': 'Year',}
papers = pd.read_csv(uploaded_file, sep='\t', lineterminator='\r')
papers.rename(columns=col_dict, inplace=True)
return papers
#===Read data===
uploaded_file = st.file_uploader("Choose a file", type=['csv', 'txt'], on_change=reset_all)
if uploaded_file is not None:
extype = get_ext(uploaded_file)
if extype.endswith('.csv'):
papers = upload(extype)
elif extype.endswith('.txt'):
papers = conv_txt(extype)
@st.cache_data(ttl=3600)
def get_minmax(extype):
extype = extype
MIN = int(papers['Year'].min())
MAX = int(papers['Year'].max())
GAP = MAX - MIN
return papers, MIN, MAX, GAP
tab1, tab2 = st.tabs(["📈 Generate visualization", "📓 Recommended Reading"])
with tab1:
#===sunburst===
try:
papers, MIN, MAX, GAP = get_minmax(extype)
except KeyError:
st.error('Error: Please check again your columns.')
sys.exit(1)
if (GAP != 0):
YEAR = st.slider('Year', min_value=MIN, max_value=MAX, value=(MIN, MAX), on_change=reset_all)
else:
st.write('You only have data in ', (MAX))
YEAR = (MIN, MAX)
@st.cache_data(ttl=3600)
def listyear(extype):
global papers
years = list(range(YEAR[0],YEAR[1]+1))
papers = papers.loc[papers['Year'].isin(years)]
return years, papers
@st.cache_data(ttl=3600)
def vis_sunbrust(extype):
papers['Cited by'] = papers['Cited by'].fillna(0)
vis = pd.DataFrame()
vis[['doctype','source','citby','year']] = papers[['Document Type','Source title','Cited by','Year']]
viz=vis.groupby(['doctype', 'source', 'year'])['citby'].agg(['sum','count']).reset_index()
viz.rename(columns={'sum': 'cited by', 'count': 'total docs'}, inplace=True)
fig = px.sunburst(viz, path=['doctype', 'source', 'year'], values='total docs',
color='cited by',
color_continuous_scale='RdBu',
color_continuous_midpoint=np.average(viz['cited by'], weights=viz['total docs']))
fig.update_layout(height=800, width=1200)
return fig
years, papers = listyear(extype)
if {'Document Type','Source title','Cited by','Year'}.issubset(papers.columns):
fig = vis_sunbrust(extype)
st.plotly_chart(fig, height=800, width=1200) #use_container_width=True)
else:
st.error('We require these columns: Document Type, Source title, Cited by, Year', icon="🚨")
with tab2:
st.markdown('**numpy.average — NumPy v1.24 Manual. (n.d.). Numpy.Average — NumPy v1.24 Manual.** https://numpy.org/doc/stable/reference/generated/numpy.average.html')
st.markdown('**Sunburst. (n.d.). Sunburst Charts in Python.** https://plotly.com/python/sunburst-charts/') |