Spaces:
Running
Running
Create 0 FileChecker.py
Browse files- pages/0 FileChecker.py +139 -0
pages/0 FileChecker.py
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
|
4 |
+
#===config===
|
5 |
+
st.set_page_config(
|
6 |
+
page_title="Coconut",
|
7 |
+
page_icon="π₯₯",
|
8 |
+
layout="wide",
|
9 |
+
initial_sidebar_state="collapsed"
|
10 |
+
)
|
11 |
+
|
12 |
+
hide_streamlit_style = """
|
13 |
+
<style>
|
14 |
+
#MainMenu
|
15 |
+
{visibility: hidden;}
|
16 |
+
footer {visibility: hidden;}
|
17 |
+
[data-testid="collapsedControl"] {display: none}
|
18 |
+
</style>
|
19 |
+
"""
|
20 |
+
st.markdown(hide_streamlit_style, unsafe_allow_html=True)
|
21 |
+
|
22 |
+
st.page_link("https://www.coconut-libtool.com/the-app", label="Go to app", icon="π₯₯")
|
23 |
+
|
24 |
+
def reset_data():
|
25 |
+
st.cache_data.clear()
|
26 |
+
|
27 |
+
#===check filetype===
|
28 |
+
@st.cache_data(ttl=3600)
|
29 |
+
def get_ext(extype):
|
30 |
+
extype = uploaded_file.name
|
31 |
+
return extype
|
32 |
+
|
33 |
+
#===upload===
|
34 |
+
@st.cache_data(ttl=3600)
|
35 |
+
def upload(extype):
|
36 |
+
keywords = pd.read_csv(uploaded_file)
|
37 |
+
return keywords
|
38 |
+
|
39 |
+
@st.cache_data(ttl=3600)
|
40 |
+
def conv_txt(extype):
|
41 |
+
col_dict = {'TI': 'Title',
|
42 |
+
'SO': 'Source title',
|
43 |
+
'DE': 'Author Keywords',
|
44 |
+
'DT': 'Document Type',
|
45 |
+
'AB': 'Abstract',
|
46 |
+
'TC': 'Cited by',
|
47 |
+
'PY': 'Year',
|
48 |
+
'ID': 'Keywords Plus'}
|
49 |
+
keywords = pd.read_csv(uploaded_file, sep='\t', lineterminator='\r')
|
50 |
+
keywords.rename(columns=col_dict, inplace=True)
|
51 |
+
return keywords
|
52 |
+
|
53 |
+
st.header('File Checker', anchor=False)
|
54 |
+
st.subheader('Put your file here...', anchor=False)
|
55 |
+
|
56 |
+
#===read data===
|
57 |
+
uploaded_file = st.file_uploader('', type=['csv','txt'], on_change=reset_data)
|
58 |
+
|
59 |
+
if uploaded_file is not None:
|
60 |
+
extype = get_ext(uploaded_file)
|
61 |
+
if extype.endswith('.csv'):
|
62 |
+
data = upload(extype)
|
63 |
+
|
64 |
+
elif extype.endswith('.txt'):
|
65 |
+
data = conv_txt(extype)
|
66 |
+
|
67 |
+
col1, col2, col3 = st.columns(3)
|
68 |
+
|
69 |
+
with col1:
|
70 |
+
#===check keywords===
|
71 |
+
keycheck = list(data.columns)
|
72 |
+
keycheck = [k for k in keycheck if 'Keyword' in k]
|
73 |
+
container1 = st.container(border=True)
|
74 |
+
|
75 |
+
if not keycheck:
|
76 |
+
container1.subheader('β Keyword Stem', divider='red', anchor=False)
|
77 |
+
container1.write("Unfortunately, you don't have a column containing keywords in your data. Please check again. If you want to use it in another column, please rename it to 'Keywords'.")
|
78 |
+
else:
|
79 |
+
container1.subheader('βοΈ Keyword Stem', divider='blue', anchor=False)
|
80 |
+
container1.write('Congratulations! You can use Keywords Stem')
|
81 |
+
|
82 |
+
#===Visualization===
|
83 |
+
if 'Publication Year' in data.columns:
|
84 |
+
data.rename(columns={'Publication Year': 'Year', 'Citing Works Count': 'Cited by',
|
85 |
+
'Publication Type': 'Document Type', 'Source Title': 'Source title'}, inplace=True)
|
86 |
+
|
87 |
+
col2check = ['Document Type','Source title','Cited by','Year']
|
88 |
+
miss_col = [column for column in col2check if column not in data.columns]
|
89 |
+
container2 = st.container(border=True)
|
90 |
+
|
91 |
+
if not miss_col:
|
92 |
+
container2.subheader('βοΈ Sunburst', divider='blue', anchor=False)
|
93 |
+
container2.write('Congratulations! You can use Sunburst')
|
94 |
+
else:
|
95 |
+
container2.subheader('β Sunburst', divider='red', anchor=False)
|
96 |
+
miss_col_str = ', '.join(miss_col)
|
97 |
+
container2.write(f"Unfortunately, you don't have: {miss_col_str}. Please check again.")
|
98 |
+
|
99 |
+
with col2:
|
100 |
+
#===check any obj===
|
101 |
+
coldf = sorted(data.select_dtypes(include=['object']).columns.tolist())
|
102 |
+
container3 = st.container(border=True)
|
103 |
+
|
104 |
+
if not coldf:
|
105 |
+
container3.subheader('β Topic Modeling', divider='red', anchor=False)
|
106 |
+
container3.write("Unfortunately, you don't have a column containing object in your data. Please check again.")
|
107 |
+
else:
|
108 |
+
container3.subheader('βοΈ Topic Modeling', divider='blue', anchor=False)
|
109 |
+
container3.write('Congratulations! You can use Topic Modeling')
|
110 |
+
|
111 |
+
#===Burst===
|
112 |
+
container4 = st.container(border=True)
|
113 |
+
if not coldf or 'Year' not in data.columns:
|
114 |
+
container4.subheader('β Burst Detection', divider='red', anchor=False)
|
115 |
+
container4.write("Unfortunately, you don't have a column containing object in your data or a 'Year' column. Please check again.")
|
116 |
+
else:
|
117 |
+
container4.subheader('βοΈ Burst Detection', divider='blue', anchor=False)
|
118 |
+
container4.write('Congratulations! You can use Burst Detection')
|
119 |
+
|
120 |
+
with col3:
|
121 |
+
#===bidirected===
|
122 |
+
container5 = st.container(border=True)
|
123 |
+
if not keycheck:
|
124 |
+
container5.subheader('β Bidirected Network', divider='red', anchor=False)
|
125 |
+
container5.write("Unfortunately, you don't have a column containing keywords in your data. Please check again. If you want to use it in another column, please rename it to 'Keywords'.")
|
126 |
+
else:
|
127 |
+
container5.subheader('βοΈ Bidirected Network', divider='blue', anchor=False)
|
128 |
+
container5.write('Congratulations! You can use Bidirected Network')
|
129 |
+
|
130 |
+
#===scattertext===
|
131 |
+
container6 = st.container(border=True)
|
132 |
+
if not coldf:
|
133 |
+
container6.subheader('β Scattertext', divider='red', anchor=False)
|
134 |
+
container6.write("Unfortunately, you don't have a column containing object in your data. Please check again.")
|
135 |
+
else:
|
136 |
+
container6.subheader('βοΈ Scattertext', divider='blue', anchor=False)
|
137 |
+
container6.write('Congratulations! You can use Scattertext')
|
138 |
+
|
139 |
+
|