Spaces:
Build error
Build error
File size: 5,178 Bytes
f82b177 201e5c6 f82b177 3a464f9 21d4acd 3a464f9 21d4acd f82b177 cdac6e2 f82b177 |
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 |
import streamlit as st
st.set_page_config(
layout="centered", # Can be "centered" or "wide". In the future also "dashboard", etc.
initial_sidebar_state="auto", # Can be "auto", "expanded", "collapsed"
page_title='Extractive Summarization', # String or None. Strings get appended with "• Streamlit".
page_icon='./favicon.png', # String, anything supported by st.image, or None.
)
import pandas as pd
import numpy as np
import os
import sys
sys.path.append(os.path.abspath('./'))
import streamlit_apps_config as config
from streamlit_ner_output import show_html2, jsl_display_annotations, get_color
import sparknlp
from sparknlp.base import *
from sparknlp.annotator import *
from pyspark.sql import functions as F
from sparknlp_display import NerVisualizer
from pyspark.ml import Pipeline
from pyspark.sql.types import StringType
spark= sparknlp.start()
## Marking down NER Style
st.markdown(config.STYLE_CONFIG, unsafe_allow_html=True)
root_path = config.project_path
########## To Remove the Main Menu Hamburger ########
hide_menu_style = """
<style>
#MainMenu {visibility: hidden;}
</style>
"""
st.markdown(hide_menu_style, unsafe_allow_html=True)
########## Side Bar ########
## loading logo(newer version with href)
import base64
@st.cache(allow_output_mutation=True)
def get_base64_of_bin_file(bin_file):
with open(bin_file, 'rb') as f:
data = f.read()
return base64.b64encode(data).decode()
@st.cache(allow_output_mutation=True)
def get_img_with_href(local_img_path, target_url):
img_format = os.path.splitext(local_img_path)[-1].replace('.', '')
bin_str = get_base64_of_bin_file(local_img_path)
html_code = f'''
<a href="{target_url}">
<img height="90%" width="90%" src="data:image/{img_format};base64,{bin_str}" />
</a>'''
return html_code
logo_html = get_img_with_href('./jsl-logo.png', 'https://www.johnsnowlabs.com/')
st.sidebar.markdown(logo_html, unsafe_allow_html=True)
#sidebar info
model_name= ["nerdl_fewnerd_100d"]
st.sidebar.title("Pretrained model to test")
selected_model = st.sidebar.selectbox("", model_name)
######## Main Page #########
app_title= "Detect up to 8 entity types in general domain texts"
app_description= "Named Entity Recognition model aimed to detect up to 8 entity types from general domain texts. This model was trained on the Few-NERD/inter public dataset using Spark NLP, and is available in Spark NLP Models hub (https://nlp.johnsnowlabs.com/models)"
st.title(app_title)
st.markdown("<h2>"+app_description+"</h2>" , unsafe_allow_html=True)
if selected_model == "nerdl_fewnerd_100d":
st.markdown("**`PERSON`** **,** **`ORGANIZATION`** **,** **`LOCATION`** **,** **`ART`** **,** **`BUILDING`** **,** **`PRODUCT`** **,** **`EVENT`** **,** **`OTHER`**", unsafe_allow_html=True)
st.subheader("")
#### Running model and creating pipeline
st.cache(allow_output_mutation=True)
def get_pipeline(text):
documentAssembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentenceDetector= SentenceDetector()\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
embeddings= WordEmbeddingsModel.pretrained("glove_100d")\
.setInputCols(["sentence", "token"])\
.setOutputCol("embeddings")
ner= NerDLModel.pretrained("nerdl_fewnerd_100d")\
.setInputCols(["document", "token", "embeddings"])\
.setOutputCol("ner")
ner_converter= NerConverter()\
.setInputCols(["sentence", "token", "ner"])\
.setOutputCol("ner_chunk")
pipeline = Pipeline(
stages = [
documentAssembler,
sentenceDetector,
tokenizer,
embeddings,
ner,
ner_converter
])
empty_df = spark.createDataFrame([[""]]).toDF("text")
pipeline_model = pipeline.fit(empty_df)
text_df= spark.createDataFrame(pd.DataFrame({"text": [text]}))
result= pipeline_model.transform(text_df).toPandas()
return result
text= st.text_input("Type here your text and press enter to run:", value="12 Corazones ('12 Hearts') is Spanish-language dating game show produced in the United States for the television network Telemundo since January 2005, based on its namesake Argentine TV show format. The show is filmed in Los Angeles and revolves around the twelve Zodiac signs that identify each contestant. In 2008, Ho filmed a cameo in the Steven Spielberg feature film The Cloverfield Paradox, as a news pundit.")
#placeholder for warning
placeholder= st.empty()
placeholder.info("processing...")
result= get_pipeline(text)
placeholder.empty()
#Displaying Ner Visualization
df= pd.DataFrame({"ner_chunk": result["ner_chunk"].iloc[0]})
labels_set = set()
for i in df['ner_chunk'].values:
labels_set.add(i[4]['entity'])
labels_set = list(labels_set)
labels = st.sidebar.multiselect(
"NER Labels", options=labels_set, default=list(labels_set)
)
show_html2(text, df, labels, "Text annotated with identified Named Entities")
|