File size: 8,223 Bytes
6362d22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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", 
    initial_sidebar_state="auto"
)

# CSS for styling
st.markdown("""

    <style>

        .main-title {

            font-size: 36px;

            color: #4A90E2;

            font-weight: bold;

            text-align: center;

        }

        .section {

            background-color: #f9f9f9;

            padding: 10px;

            border-radius: 10px;

            margin-top: 10px;

        }

        .section p, .section ul {

            color: #666666;

        }

    </style>

""", unsafe_allow_html=True)

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

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

    sentence_detector = SentenceDetector() \
        .setInputCols(["document"]) \
        .setOutputCol("sentence")

    tokenizer = Tokenizer() \
        .setInputCols(["sentence"]) \
        .setOutputCol("token")

    word_embeddings = WordEmbeddingsModel.pretrained("hebrew_cc_300d", "he") \
        .setInputCols(["sentence", "token"]) \
        .setOutputCol("embeddings")

    ner = NerDLModel.pretrained("hebrewner_cc_300d", "he") \
        .setInputCols(["sentence", "token", "embeddings"]) \
        .setOutputCol("ner")

    ner_converter = NerConverter().setInputCols(["sentence", "token", "ner"]).setOutputCol("ner_chunk")

    pipeline = Pipeline(stages=[documentAssembler, sentence_detector, tokenizer, word_embeddings, ner, ner_converter])
    return pipeline

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

def annotate(data):
    document, chunks, labels = data["Document"], data["NER Chunk"], data["NER Label"]
    annotated_words = []
    for chunk, label in zip(chunks, labels):
        parts = document.split(chunk, 1)
        if parts[0]:
            annotated_words.append(parts[0])
        annotated_words.append((chunk, label))
        document = parts[1]
    if document:
        annotated_words.append(document)
    annotated_text(*annotated_words)

# Set up the page layout
st.markdown('<div class="main-title">Recognize entities in Persian text</div>', unsafe_allow_html=True)
st.markdown("""

<div class="section">

    <p>Named Entity Recognition (NER) models identify and categorize important entities in a text. This page details a word embeddings-based NER model for Hebrew texts, using the <code>hebrew_cc_300d</code> word embeddings. The model is pretrained and available for use with Spark NLP.</p>

</div>

""", unsafe_allow_html=True)

# Sidebar content
model = st.sidebar.selectbox(
    "Choose the pretrained model",
    ["hebrewner_cc_300d"],
    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/public/NER_HE.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
examples =  [
    """ื•ื”ืชื•ืฆืื” : ืกืคืจื• ื”ืคืš ืœืจื‘ ืžื›ืจ ืขื ืง ื•ื‘ืกื™ืก ืœื•ื•ื™ื›ื•ื—ื™ื ืชื™ืื•ืœื•ื’ื™ื™ื ื•ื“ื™ื•ื ื™ื ื ื–ืขืžื™ื , ื›ืžื• ื’ื ื”ืชืงืคื•ืช ื•ื”ืืฉืžื•ืช ื›ืœืคื™ ื‘ืจืื•ืŸ ืžื—ื•ื’ื™ ื”ื›ื ืกื™ื™ื” ื›ืคื™ ืฉืžืขื•ืœื ืœื ื”ืชืขื•ืจืจื• ื›ืชื•ืฆืื” ืžืกืคืจื™ื”ื ืฉืœ ื•ื•ืืœืืก ืื• ืœืื“ืœื•ื , ื•ืืฃ ื’ืจื ืœืกื•ืคืจ ืžืฆืœื™ื— ื‘ื–ื›ื•ืช ืขืฆืžื• , ื“ืŸ ื‘ื•ืจืกื˜ื™ืŸ , ืœืขืจื•ืš ืืช ื”ืกืคืจ " ื”ืกื•ื“ื•ืช ืฉืžืื—ื•ืจื™ ืฆื•ืคืŸ ื“ื” ื•ื™ื ืฆ'ื™ " , ืฉื‘ื• ื”ื•ื ื‘ื•ื“ืง ืื—ืช ืœืื—ืช ืืช ื”ืขื•ื‘ื“ื•ืช ื•ื”ื”ื ื—ื•ืช ืฉืขืœื™ื”ืŸ ืžืกืชืžืš ื‘ืจืื•ืŸ ืขืœ ื™ื“ื™ ืฉืคืข ืฉืœ ืžืืžืจื™ื , ื—ืœืงื ืžืงื•ืจื™ื™ื ื•ื—ืœืงื ืœืงื•ื—ื™ื ืžืกืคืจื™ื , ื›ืชื‘ื™ ืขืช ื•ืจืื™ื•ื ื•ืช ืขื ื—ื•ืงืจื™ื ืฉื•ื ื™ื .""",
    """ื‘ื’ืœืœ ืงื•ืฆืจ ื”ื™ืจื™ืขื” ืœื ื ืชืขืกืง ื›ืืŸ ื‘ื›ืœ ื”ื ื•ืฉืื™ื ื”ืžื’ื•ื•ื ื™ื ืฉื‘ื”ื ื“ืŸ ื”ืกืคืจ , ื›ืžื• ืœืžืฉืœ ื“ืžื•ืชื” ืฉืœ ืžืจื™ื ื”ืžื’ื“ืœื™ืช , ื”ื“ืขื•ืช ื”ืื–ื•ื˜ืจื™ื•ืช ืฉืœ ืœื™ืื•ื ืจื“ื• ื“ื” ื•ื™ื ืฆื™ ื•ื›ืŸ ื”ืœืื” , ืืœื ื ืชืžืงื“ ื‘ื ื•ืฉื ืื—ื“ - ื‘ืื’ื•ื“ืช ื”ืกืชืจ " ืžืกื“ืจ ืฆื™ื•ืŸ " - ืžืกื“ืจ ื—ืฉืื™ ื”ืงื™ื™ื ื›ื‘ื™ื›ื•ืœ ืžื–ื” ืืœืฃ ืฉื ื” , ื•ืชืคืงื™ื“ื• ืœื”ื’ืŸ ืขืœ ืฆืืฆืื™ ื”ืฉื•ืฉืœืช ื”ืž ึถืจื•ื‘ ึผื™ื ื’ื™ืช ื”ืงื“ื•ืžื” ืฉืœ ืฆืจืคืช , ืฉื”ื ืœืžืขืฉื” ืฆืืฆืื™ ื™ืฉื•ืข ื•ืžืจื™ื ื”ืžื’ื“ืœื™ืช , ื•ืœืคื™ื›ืš ื”ื , ืœื“ืขืช ื—ื‘ืจื™ ื”ืžืกื“ืจ , ื”ืฉื•ืฉืœืช ื”ืžืœื›ื•ืชื™ืช ื”ืœื’ื™ื˜ื™ืžื™ืช ืฉืœ ืฆืจืคืช , ืžื” ืฉืื•ืžืจ ื›ืžื•ื‘ืŸ ืฉืžืœื›ื™ ืฆืจืคืช ื”ื ืžืžื•ืฆื ื™ื”ื•ื“ื™ .""",
    """ื‘ 32 ื‘ืื•ืงื˜ื•ื‘ืจ ื”ืชืคืขืœื” ืžืžื ื• ื‘ืขืœืช ื˜ื•ืจ ื‘ืขื™ืชื•ืŸ " ื‘ื•ืกื˜ื•ืŸ ื’ืœื•ื‘ " ื‘ืžืœื™ื ื”ื™ืื•ืช ืœืžืขืจื™ืฆื” ื‘ืช 21 : " ื”ื•ื ืขืฉื” ื‘ื—ื•ื“ืฉื™ื ืื—ื“ื™ื ืœืžืขืŸ ืฆื—ื•ืช ื”ื“ื™ื‘ื•ืจ ืžื” ืฉืœืงื— ืœื—ื‘ืจื” ืฉื ื™ื ื›ื“ื™ ืœืขืฉื•ืช ืœืžืขืŸ ื˜ืœื•ื•ื™ื–ื™ื” ืฆื‘ืขื•ื ื™ืช ... ืื ื“ื™ื‘ื•ืจ ื”ื™ื” ืกืคื•ืจื˜ ืื•ืœื™ืžืคื™ , ื”ื•ื ื”ื™ื” ื–ื•ื›ื” ื‘ืžื“ืœื™ื™ืช ื”ื–ื”ื‘ ... ืกื™ืœื‘ืจ ื›ื” ื˜ื•ื‘ , ืขื“ ืฉื”ื•ื ื’ื•ืจื ืœืื ื’ืœื™ืช ืœื”ื™ืฉืžืข ื›ืžื• ืฆืจืคืชื™ืช ... ืื ื™ื™ื‘ื—ืจ , ืชื”ื™ื” ืœื›ื•ืœื ื• ื”ื”ื–ื“ืžื ื•ืช ืœืœืžื•ื“ ืžืžื ื• ืœื”ื™ื•ืช ืกื˜ื•ื“ื ื˜ื™ื ื‘ื›ื™ืชืชื• ื”ืขื ืงื™ืช , ื”ื ืงืจืืช ืžืกืฆื•ืกื˜ืก " .""",
    """ืœื ืžื™ื ื” ื•ืœื ืžืงืฆืชื” ! ื”ืจื™ ืฉื ืกื™ืคืจืชื™ ืขืœ ื”ื”ื’ืขื” ื‘ืงืจื•ื ื•ืช ื”ื—ื ืง , ืขืœ ื”ืžืชื™ื ืฉื˜ื•ืื˜ืื• ืžื”ืงืจื•ื ื•ืช , ืขืœ " ืงื•ืžื ื“ื• ืงื ื“ื” " , ืขืœ ืื ืฉื™ ื”ืก"ืก ื•ื›ืœื‘ื™ื”ื ื”ืืžืชื ื™ื™ื , ืขืœ ืืœื•ืžื•ืช ื”ืื•ืจ ืžื ืงืจื•ืช ื”ืขื™ื ื™ื™ื ืฉืฉืœื—ื• ื”ื–ืจืงื•ืจื™ื , ืขืœ ื‘ื›ื™ ื™ืœื“ื™ื ืฉื ืงืจืขื• ืžื–ืจื•ืขื•ืช ืืžื•ืชื™ื”ื , ื•ืœืขืชื™ื ื ืฉืืจื• ื”ืืžื”ื•ืช ื”ืฆืขื™ืจื•ืช ื‘ื—ื™ื™ื , ื•ืืชื” ืžื•ืชื™ืจ ืจืง ืžืœื™ื ื‘ื•ื“ื“ื•ืช ืขืœ ื”"ืกืœืงืฆื™ื” " .""",
    """ืฉื•ื•ื™ื“ ื—ื•ืฉืฃ ืืช ืชืžื—ื•ืจื™ ื”ืžื•ืฆืจื™ื ื”ื™ืฆื™ื‘ื™ื ืฉืœ ื”ื—ื‘ืจื”: " ื”ืžื—ื™ืจื™ื ื ื•ืชืจื• ื–ื”ื™ื : 70 ื“ื•ืœืจ ืœืื‘ื˜ื—ืช ืขืกืง ืงื˜ืŸ , 300 ื“ื•ืœืจ ืœืื‘ื˜ื—ืช ืจืฉืช ื‘ืขืกืง ืงื˜ืŸ , ื‘ื™ืŸ 1,500 ืœ - 3,500 ื“ื•ืœืจ ืœืื‘ื˜ื—ืช ื—ื‘ืจื•ืช ื’ื“ื•ืœื•ืช ืขื ืืชืจ ืจืืฉื™ ื•ืขื“ 500 ืžื—ืฉื‘ื™ื , ื‘ืืžืฆืขื•ืช ืžื•ืฆืจื™ ื”ืฆ'ืง ืคื•ื™ื ื˜ ืืงืกืคืจืก , ื•ื‘ื™ืŸ 15,000 ืœ - 20,000 ื“ื•ืœืจ ืœืขืกืง ืขื 3 ืขื“ 4 ืืชืจื™ื , ื—ื‘ืจื•ืช ื’ื“ื•ืœื•ืช ืขื ืžื—ื–ื•ืจื™ ืžื›ื™ืจื•ืช ืžืฉืžืขื•ืชื™ื™ื ."""
]

selected_text = st.selectbox("Select an example", examples)
custom_input = st.text_input("Try it with your own Sentence!")

text_to_analyze = custom_input if custom_input else selected_text

st.subheader('Full example text')
HTML_WRAPPER = """<div class="scroll entities" style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem; white-space:pre-wrap">{}</div>"""
st.markdown(HTML_WRAPPER.format(text_to_analyze), unsafe_allow_html=True)

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

# Display matched sentence
st.subheader("Processed output:")

results = {
    'Document': output[0]['document'][0].result,
    'NER Chunk': [n.result for n in output[0]['ner_chunk']],
    "NER Label": [n.metadata['entity'] for n in output[0]['ner_chunk']]
}

annotate(results)

with st.expander("View DataFrame"):
    df = pd.DataFrame({'NER Chunk': results['NER Chunk'], 'NER Label': results['NER Label']})
    df.index += 1
    st.dataframe(df)