Hugging Face's logo

Spaces:
spark-nlp
/
keyword-extraction
Sleeping

App Files Community
keyword-extraction
File size: 4,661 Bytes 
4947cdd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
149
150
151
152
153
154
155
156
 
import streamlit as st
import sparknlp
import os
import pandas as pd

from sparknlp.base import *
from sparknlp.annotator import *
from pyspark.ml import Pipeline
from sparknlp.pretrained import PretrainedPipeline
from annotated_text import annotated_text

# Page configuration
st.set_page_config(
    layout="wide", 
    page_title="Spark NLP Demos App", 
    initial_sidebar_state="auto"
)

# CSS for styling
st.markdown("""

    <style>

        .main-title {

            font-size: 36px;

            color: #4A90E2;

            font-weight: bold;

            text-align: center;

        }

        .section p, .section ul {

            color: #666666;

        }

        .stTable {

            margin-left: auto;

            margin-right: auto;

        }

    </style>

""", unsafe_allow_html=True)

@st.cache_resource
def init_spark():
    return sparknlp.start()

@st.cache_resource
def create_pipeline(model):
    document_assembler = DocumentAssembler() \
    .setInputCol('text') \
    .setOutputCol('document')

    sentence_detector = SentenceDetector() \
        .setInputCols(['document']) \
        .setOutputCol('sentences')

    tokenizer = Tokenizer() \
        .setInputCols(['sentences']) \
        .setOutputCol('tokens') \
        .setContextChars(['(', ')', '?', '!', '.', ','])

    keywords = YakeKeywordExtraction() \
        .setInputCols('tokens') \
        .setOutputCol('keywords') \
        .setMinNGrams(2) \
        .setMaxNGrams(5) \
        .setNKeywords(100) \
        .setStopWords(StopWordsCleaner().getStopWords())

    pipeline = Pipeline(stages=[
        document_assembler, 
        sentence_detector,
        tokenizer,
        keywords
    ])

    return pipeline

def fit_data(pipeline, data):
    empty_df = spark.createDataFrame([['']]).toDF('text')
    pipeline_model = pipeline.fit(empty_df)
    model = LightPipeline(pipeline_model)
    results = model.fullAnnotate(data)[0]

    return results
    
def highlight_keywords(data):
    document_text = data["document"][0].result
    keywords = data["keywords"]
    annotations = []
    last_index = 0

    for keyword in keywords:
        keyword_text = keyword.result
        start_index = document_text.find(keyword_text, last_index)
        if start_index != -1:
            if start_index > last_index:
                annotations.append(document_text[last_index:start_index])
            annotations.append((keyword_text, 'Key Word'))
            last_index = start_index + len(keyword_text)
    
    if last_index < len(document_text):
        annotations.append(document_text[last_index:])

    annotated_text(*annotations)

# Set up the page layout
st.markdown('<div class="main-title">Detect Key Phrases With Spark NLP</div>', unsafe_allow_html=True)

# Sidebar content
model = st.sidebar.selectbox(
    "Choose the pretrained model",
    ["yake_model"],
    help="For more info about the models visit: https://sparknlp.org/models"
)

# Reference notebook link in sidebar
link = """

<a href="https://colab.research.google.com/github/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/KEYPHRASE_EXTRACTION.ipynb">

    <img src="https://colab.research.google.com/assets/colab-badge.svg" style="zoom: 1.3" alt="Open In Colab"/>

</a>

"""
st.sidebar.markdown('Reference notebook:')
st.sidebar.markdown(link, unsafe_allow_html=True)

# Load examples
folder_path = f"inputs/{model}"
examples = [
    lines[1].strip() 
    for filename in os.listdir(folder_path) 
    if filename.endswith('.txt') 
    for lines in [open(os.path.join(folder_path, filename), 'r', encoding='utf-8').readlines()] 
    if len(lines) >= 2
]

selected_text = st.selectbox("Select a sample text", examples)
custom_input = st.text_input("Try it for yourself!")

if custom_input:
    selected_text = custom_input
elif selected_text:
    selected_text = selected_text

st.subheader('Selected Text')
st.write(selected_text)

# Initialize Spark and create pipeline
spark = init_spark()
pipeline = create_pipeline(model)
output = fit_data(pipeline, selected_text)

# Display output
st.subheader("Annotated Document:")
highlight_keywords(output)

keys_df = pd.DataFrame([(k.result, k.begin, k.end, k.metadata['score'], k.metadata['sentence']) for k in output['keywords']],
                       columns=['keywords', 'begin', 'end', 'score', 'sentence'])
keys_df['score'] = keys_df['score'].astype(float)
# ordered by relevance
with st.expander("View Data Table"):
    st.table(keys_df.sort_values(['sentence', 'score']))