Upload 4 files
Browse files- app.py +109 -0
- model-topics.pkl +3 -0
- requirements.txt +28 -0
- tfidf-topics.pkl +3 -0
app.py
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
import pickle
|
4 |
+
import requests
|
5 |
+
import base64
|
6 |
+
|
7 |
+
#===config===
|
8 |
+
st.set_page_config(
|
9 |
+
page_title="ETDs Tagging",
|
10 |
+
page_icon="",
|
11 |
+
layout="wide"
|
12 |
+
)
|
13 |
+
st.header("Tagging Categories")
|
14 |
+
st.subheader('Put your file here...')
|
15 |
+
|
16 |
+
#========unique id========
|
17 |
+
@st.cache_resource(ttl=3600)
|
18 |
+
def create_list():
|
19 |
+
l = [1, 2, 3]
|
20 |
+
return l
|
21 |
+
|
22 |
+
l = create_list()
|
23 |
+
first_list_value = l[0]
|
24 |
+
l[0] = first_list_value + 1
|
25 |
+
uID = str(l[0])
|
26 |
+
|
27 |
+
@st.cache_data(ttl=3600)
|
28 |
+
def get_ext(uploaded_file):
|
29 |
+
extype = uID+uploaded_file.name
|
30 |
+
return extype
|
31 |
+
|
32 |
+
|
33 |
+
@st.cache_resource(ttl=3600)
|
34 |
+
# def read_model(local_path):
|
35 |
+
# with open(local_path, "rb") as f:
|
36 |
+
# svm_classifier = pickle.load(f)
|
37 |
+
# return svm_classifier
|
38 |
+
|
39 |
+
|
40 |
+
# def read_tf(local_path):
|
41 |
+
# with open(local_path, "rb") as f:
|
42 |
+
# preprocessing = pickle.load(f)
|
43 |
+
# return preprocessing
|
44 |
+
|
45 |
+
|
46 |
+
def read_model(url):
|
47 |
+
response = requests.get(url)
|
48 |
+
open("temp.pkl", "wb").write(response.content)
|
49 |
+
with open("temp.pkl", "rb") as f:
|
50 |
+
svm_classifier = pickle.load(f)
|
51 |
+
return svm_classifier
|
52 |
+
|
53 |
+
|
54 |
+
def read_tf(url):
|
55 |
+
response = requests.get(url)
|
56 |
+
open("temp.pkl", "wb").write(response.content)
|
57 |
+
with open("temp.pkl", "rb") as f:
|
58 |
+
preprocessing = pickle.load(f)
|
59 |
+
return preprocessing
|
60 |
+
|
61 |
+
svm_classifier = read_model("https://github.com/manika-lamba/ml/raw/main/category/model2.pkl")
|
62 |
+
preprocessing = read_tf("https://github.com/manika-lamba/ml/raw/main/category/preprocessing.pkl")
|
63 |
+
|
64 |
+
# Function to predict the category for a given abstract
|
65 |
+
def predict_category(abstract):
|
66 |
+
# Preprocess the abstract
|
67 |
+
abstract_preprocessed = preprocessing.transform([abstract])
|
68 |
+
# Make prediction
|
69 |
+
prediction = svm_classifier.predict(abstract_preprocessed)
|
70 |
+
return prediction
|
71 |
+
|
72 |
+
# Create sidebar
|
73 |
+
#===upload file===
|
74 |
+
@st.cache_data(ttl=3600)
|
75 |
+
def upload(file):
|
76 |
+
papers = pd.read_csv(uploaded_file)
|
77 |
+
return papers
|
78 |
+
|
79 |
+
@st.cache_data(ttl=3600)
|
80 |
+
def conv_txt(extype):
|
81 |
+
papers = pd.read_csv(uploaded_file, sep='\t', lineterminator='\r')
|
82 |
+
papers.rename(columns=col_dict, inplace=True)
|
83 |
+
return papers
|
84 |
+
|
85 |
+
# Read Data
|
86 |
+
|
87 |
+
uploaded_file = st.file_uploader("Choose a file", type=['csv'])
|
88 |
+
st.sidebar.header("Download Results")
|
89 |
+
st.sidebar.text("Download the tagged results as a CSV file.")
|
90 |
+
|
91 |
+
if uploaded_file is not None:
|
92 |
+
df = pd.read_csv(uploaded_file, encoding='latin-1')
|
93 |
+
st.dataframe(df)
|
94 |
+
|
95 |
+
# Tag the "Abstract" column with the corresponding categories
|
96 |
+
df['category'] = df['Abstract'].apply(lambda x: predict_category(x)[0])
|
97 |
+
st.dataframe(df)
|
98 |
+
|
99 |
+
# Convert DataFrame to CSV and encode it properly
|
100 |
+
csv = df.to_csv(index=False).encode('utf-8')
|
101 |
+
b64 = base64.b64encode(csv).decode() # Decode the Base64 encoded bytes
|
102 |
+
|
103 |
+
st.sidebar.download_button(
|
104 |
+
label="Download CSV",
|
105 |
+
data=base64.b64decode(b64), # Decode Base64 to bytes
|
106 |
+
file_name="results.csv",
|
107 |
+
mime="text/csv",
|
108 |
+
key='download-csv'
|
109 |
+
)
|
model-topics.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d23020e255ce442b0a6e52932278b23cec8e798834aa3241fd2d376e20d743cf
|
3 |
+
size 1518
|
requirements.txt
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
pip
|
2 |
+
streamlit==1.10.0
|
3 |
+
scikit-learn
|
4 |
+
gensim
|
5 |
+
matplotlib
|
6 |
+
nltk
|
7 |
+
numpy
|
8 |
+
pandas
|
9 |
+
pickleshare
|
10 |
+
plotly-express
|
11 |
+
plotly
|
12 |
+
pyldavis
|
13 |
+
regex
|
14 |
+
seaborn
|
15 |
+
setuptools
|
16 |
+
streamlit
|
17 |
+
streamlit-agraph
|
18 |
+
umap-learn
|
19 |
+
wordcloud
|
20 |
+
mlxtend
|
21 |
+
bertopic
|
22 |
+
ipywidgets==7.6.6
|
23 |
+
bitermplus
|
24 |
+
tmplot
|
25 |
+
tomotopy
|
26 |
+
pipeline
|
27 |
+
spacy==3.5.0
|
28 |
+
https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.5.0/en_core_web_sm-3.5.0-py3-none-any.whl
|
tfidf-topics.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eeacc5c20b8f1ff2451d7395598645fc81dc1585ea5e7d3aa5251ec0620656c0
|
3 |
+
size 553208
|