Spaces:
Sleeping
Sleeping
Upload 4 files
Browse files- .gitattributes +1 -0
- 20k_5_epochs.keras +3 -0
- app.py +183 -0
- model.py +71 -0
- process_input.py +67 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
20k_5_epochs.keras filter=lfs diff=lfs merge=lfs -text
|
20k_5_epochs.keras
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0565eca7a0095c40e516cd84b42354a964f0143f77c31c7329818a2853307f9
|
3 |
+
size 1691202
|
app.py
ADDED
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
"""
|
2 |
+
Ryan Tietjen
|
3 |
+
Sep 2024
|
4 |
+
Demo application for paper abstract fragmentaion demonstration
|
5 |
+
"""
|
6 |
+
import gradio as gr
|
7 |
+
import tensorflow as tf
|
8 |
+
from tensorflow import keras
|
9 |
+
from keras import layers
|
10 |
+
from timeit import default_timer as timer
|
11 |
+
from process_input import split_abstract
|
12 |
+
from process_input import split_abstract_original
|
13 |
+
from process_input import split_sentences_by_characters
|
14 |
+
import pandas as pd
|
15 |
+
import tensorflow_hub as hub
|
16 |
+
from model import EmbeddingLayer
|
17 |
+
from process_input import encode_labels
|
18 |
+
|
19 |
+
|
20 |
+
sample_list = []
|
21 |
+
example1 = f"""The aim of this study was to describe the electrocardiographic ( ECG ) evolutionary changes after an acute myocardial infarction ( AMI ) and to evaluate their correlation with left ventricular function and remodeling.
|
22 |
+
The QRS complex changes after AMI have been correlated with infarct size and left ventricular function.
|
23 |
+
By contrast , the significance of T wave changes is controversial.
|
24 |
+
We studied 536 patients enrolled in the GISSI-3-Echo substudy who underwent ECG and echocardiographic studies at 24 to 48 h ( S1 ) , at hospital discharge ( S2 ) , at six weeks ( S3 ) and six months ( S4 ) after AMI.
|
25 |
+
The number of Qwaves ( nQ ) and QRS quantitative score ( QRSs ) did not change over time.
|
26 |
+
From S2 to S4 , the number of negative T waves ( nT NEG ) decreased ( p < 0.0001 ) , wall motion abnormalities ( % WMA ) improved ( p < 0.001 ) , ventricular volumes increased ( p < 0.0001 ) while ejection fraction remained stable.
|
27 |
+
According to the T wave changes after hospital discharge , patients were divided into four groups : stable positive T waves ( group 1 , n = 35 ) , patients who showed a decrease > or = 1 in nT NEG ( group 2 , n = 361 ) , patients with no change in nT NEG ( group 3 , n = 64 ) and those with an increase > or = 1 in nT NEG ( group 4 , n = 76 ).
|
28 |
+
The QRSs and nQ remained stable in all groups.
|
29 |
+
Groups 3 and 4 showed less recovery in % WMA , more pronounced ventricular enlargement and progressive decline in ejection fraction than groups 1 and 2 ( interaction time x groups p < 0.0001 ).
|
30 |
+
The analysis of serial ECG can predict postinfarct left ventricular remodeling.
|
31 |
+
Normalization of negative T waves during the follow-up appears more strictly related to recovery of regional dysfunction than QRS changes.
|
32 |
+
Lack of resolution and late appearance of new negative T predict unfavorable remodeling with progressive deterioration of ventricular function."""
|
33 |
+
sample_list.append(example1)
|
34 |
+
|
35 |
+
def format_non_empty_lists(objective, background, methods, results, conclusion):
|
36 |
+
"""
|
37 |
+
This function checks each provided list and formats a string with the list name and its contents
|
38 |
+
only if the list is not empty.
|
39 |
+
|
40 |
+
Parameters:
|
41 |
+
- objective (list): List containing sentences classified as 'Objective'.
|
42 |
+
- background (list): List containing sentences classified as 'Background'.
|
43 |
+
- methods (list): List containing sentences classified as 'Methods'.
|
44 |
+
- results (list): List containing sentences classified as 'Results'.
|
45 |
+
- conclusion (list): List containing sentences classified as 'Conclusion'.
|
46 |
+
|
47 |
+
Returns:
|
48 |
+
- str: A formatted string that contains the non-empty list names and their contents.
|
49 |
+
"""
|
50 |
+
|
51 |
+
output = ""
|
52 |
+
lists = {
|
53 |
+
'Objective': objective,
|
54 |
+
'Background': background,
|
55 |
+
'Methods': methods,
|
56 |
+
'Results': results,
|
57 |
+
'Conclusion': conclusion
|
58 |
+
}
|
59 |
+
|
60 |
+
for name, content in lists.items():
|
61 |
+
if content: # Check if the list is not empty
|
62 |
+
output += f"{name}:\n" # Append the category name followed by a newline
|
63 |
+
for item in content:
|
64 |
+
output += f" - {item}\n" # Append each item in the list, formatted as a list
|
65 |
+
|
66 |
+
output += "\n" # Append a newline for better separation between categories
|
67 |
+
|
68 |
+
return output.strip()
|
69 |
+
|
70 |
+
def fragment_single_abstract(abstract):
|
71 |
+
"""
|
72 |
+
Processes a single abstract by fragmenting it into structured sections based on predefined categories
|
73 |
+
such as Objective, Methods, Results, Conclusions, and Background. The function utilizes a pre-trained Keras model
|
74 |
+
to predict the category of each sentence in the abstract.
|
75 |
+
|
76 |
+
The process involves several steps:
|
77 |
+
1. Splitting the abstract into sentences.
|
78 |
+
2. Encoding these sentences using a custom embedding layer.
|
79 |
+
3. Classifying each sentence into one of the predefined categories.
|
80 |
+
4. Grouping the sentences by their predicted categories.
|
81 |
+
|
82 |
+
Parameters:
|
83 |
+
abstract (str): The abstract text that needs to be processed and categorized.
|
84 |
+
|
85 |
+
Returns:
|
86 |
+
tuple: A tuple containing two elements:
|
87 |
+
- A dictionary with keys as the category names ('Objective', 'Background', 'Methods', 'Results', 'Conclusions')
|
88 |
+
and values as lists of sentences belonging to these categories. Only non-empty categories are returned.
|
89 |
+
- The time taken to process the abstract (in seconds).
|
90 |
+
|
91 |
+
Example:
|
92 |
+
```python
|
93 |
+
abstract_text = "This study aims to evaluate the effectiveness of..."
|
94 |
+
categorized_abstract, processing_time = fragment_single_abstract(abstract_text)
|
95 |
+
print("Categorized Abstract:", categorized_abstract)
|
96 |
+
print("Processing Time:", processing_time)
|
97 |
+
```
|
98 |
+
|
99 |
+
Note:
|
100 |
+
- This function assumes that a Keras model 'test.keras' and a custom embedding layer 'EmbeddingLayer'
|
101 |
+
are available and correctly configured to be loaded.
|
102 |
+
- The function uses pandas for data manipulation, TensorFlow for machine learning operations,
|
103 |
+
and TensorFlow's data API for batching and prefetching data for model predictions.
|
104 |
+
"""
|
105 |
+
start_time = timer()
|
106 |
+
|
107 |
+
original_abstract = split_abstract_original(abstract)
|
108 |
+
df_original = pd.DataFrame(original_abstract)
|
109 |
+
sentences_original = df_original["text"].tolist()
|
110 |
+
|
111 |
+
abstract_split = split_abstract(abstract)
|
112 |
+
df = pd.DataFrame(abstract_split)
|
113 |
+
sentences = df["text"].tolist()
|
114 |
+
labels = encode_labels(df["target"])
|
115 |
+
|
116 |
+
objective = []
|
117 |
+
background = []
|
118 |
+
methods = []
|
119 |
+
results = []
|
120 |
+
conclusion = []
|
121 |
+
|
122 |
+
embed_layer = EmbeddingLayer()
|
123 |
+
model = tf.keras.models.load_model("20k_5_epochs.keras", custom_objects={'EmbeddingLayer': embed_layer})
|
124 |
+
|
125 |
+
data_by_character = split_sentences_by_characters(sentences)
|
126 |
+
line_numbers = tf.one_hot(df["line_number"].to_numpy(), depth=15)
|
127 |
+
total_line_numbers = tf.one_hot(df["total_lines"].to_numpy(), depth=20)
|
128 |
+
|
129 |
+
sentences_dataset = tf.data.Dataset.from_tensor_slices((line_numbers, total_line_numbers, sentences, data_by_character))
|
130 |
+
labels_dataset = tf.data.Dataset.from_tensor_slices(labels)
|
131 |
+
dataset = tf.data.Dataset.zip((sentences_dataset, labels_dataset)).batch(32).prefetch(tf.data.AUTOTUNE)
|
132 |
+
|
133 |
+
predictions = tf.argmax(model.predict(dataset), axis=1)
|
134 |
+
|
135 |
+
for i, prediction in enumerate(predictions):
|
136 |
+
if prediction == 0:
|
137 |
+
objective.append(sentences_original[i])
|
138 |
+
elif prediction == 1:
|
139 |
+
methods.append(sentences_original[i])
|
140 |
+
elif prediction == 2:
|
141 |
+
results.append(sentences_original[i])
|
142 |
+
elif prediction == 3:
|
143 |
+
conclusion.append(sentences_original[i])
|
144 |
+
elif prediction == 4:
|
145 |
+
background.append(sentences_original[i])
|
146 |
+
|
147 |
+
end_time = timer()
|
148 |
+
|
149 |
+
return format_non_empty_lists(objective, background, methods, results, conclusion), end_time - start_time
|
150 |
+
|
151 |
+
|
152 |
+
|
153 |
+
title = "Paper Abstract Fragmentation With TensorFlow by Ryan Tietjen"
|
154 |
+
description = f"""
|
155 |
+
This app will take the abstract of a paper and break it down into five categories: objective, background, methods, results, and conclusion.
|
156 |
+
The dataset used can be found in the [PubMed 200k RCT]("https://arxiv.org/abs/1710.06071") and in [this repo](https://github.com/Franck-Dernoncourt/pubmed-rct). The model architecture
|
157 |
+
was based off of ["Neural Networks for Joint Sentence Classification in Medical Paper Abstracts."](https://arxiv.org/pdf/1612.05251)
|
158 |
+
|
159 |
+
This project achieved a testing accuracy of 88.12% and a F1 score of 87.92%. For the whole project, please visit [my GitHub](https://github.com/RyanTietjen/Paper-Fragmentation).
|
160 |
+
|
161 |
+
How to use:
|
162 |
+
|
163 |
+
-Paste the given abstract into the box below.
|
164 |
+
|
165 |
+
-Make sure to separate each sentence by a new line (this helps avoid ambiguity).
|
166 |
+
|
167 |
+
-Click submit, and allow the model to run!
|
168 |
+
"""
|
169 |
+
|
170 |
+
demo = gr.Interface(
|
171 |
+
fn=fragment_single_abstract,
|
172 |
+
inputs=gr.Textbox(lines=10, placeholder="Enter abstract here..."),
|
173 |
+
outputs=[
|
174 |
+
gr.Textbox(label="Fragmented Abstract"),
|
175 |
+
gr.Number(label="Time to process (s)"),
|
176 |
+
],
|
177 |
+
examples=sample_list,
|
178 |
+
title=title,
|
179 |
+
description=description,
|
180 |
+
)
|
181 |
+
|
182 |
+
|
183 |
+
demo.launch(share=False)
|
model.py
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
"""
|
2 |
+
Ryan Tietjen
|
3 |
+
Sep 2024
|
4 |
+
Create best model for the demo
|
5 |
+
"""
|
6 |
+
import tensorflow as tf
|
7 |
+
from keras import layers
|
8 |
+
import tensorflow_hub as hub
|
9 |
+
|
10 |
+
class EmbeddingLayer(layers.Layer):
|
11 |
+
def __init__(self, **kwargs):
|
12 |
+
super().__init__(**kwargs)
|
13 |
+
# Hardcode the module URL directly within the layer
|
14 |
+
# self.module_url = "https://tfhub.dev/google/universal-sentence-encoder/4"
|
15 |
+
url = "https://tfhub.dev/google/universal-sentence-encoder/4"
|
16 |
+
self.embed_model = hub.KerasLayer(url, trainable=False, name="universal_sentence_encoder")
|
17 |
+
|
18 |
+
def call(self, inputs):
|
19 |
+
return self.embed_model(inputs)
|
20 |
+
|
21 |
+
def get_config(self):
|
22 |
+
config = super().get_config()
|
23 |
+
# The URL is now a fixed part of the layer, so it can be included in the config for completeness
|
24 |
+
# config.update({'module_url': self.module_url})
|
25 |
+
return config
|
26 |
+
|
27 |
+
def create_token_model(token_embed):
|
28 |
+
input_layer = layers.Input(shape=[], dtype=tf.string)
|
29 |
+
embedding_layer = EmbeddingLayer()
|
30 |
+
token_embeddings = embedding_layer(input_layer)
|
31 |
+
output_layer = layers.Dense(128, activation="relu")(token_embeddings)
|
32 |
+
model = tf.keras.Model(input_layer, output_layer)
|
33 |
+
return model
|
34 |
+
|
35 |
+
def create_character_vectorizer_model(char_embed, char_vectorizer):
|
36 |
+
input_layer = layers.Input(shape=(1,), dtype=tf.string)
|
37 |
+
char_vectors = char_vectorizer(input_layer) # vectorize text inputs
|
38 |
+
char_embedding = char_embed(char_vectors) # create embedding
|
39 |
+
output_layer = layers.Bidirectional(layers.LSTM(32))(char_embedding)
|
40 |
+
model = tf.keras.Model(input_layer, output_layer)
|
41 |
+
return model
|
42 |
+
|
43 |
+
def create_line_number_model(input_shape, name):
|
44 |
+
input_layer = layers.Input(shape=(input_shape,), dtype=tf.int32, name=name)
|
45 |
+
output_layer = layers.Dense(32, activation="relu")(input_layer)
|
46 |
+
model = tf.keras.Model(input_layer, output_layer)
|
47 |
+
return model
|
48 |
+
|
49 |
+
|
50 |
+
def tribrid_model(num_classes, token_embed, char_embed, text_vectorizer):
|
51 |
+
|
52 |
+
token_model = create_token_model(token_embed)
|
53 |
+
character_vectorizer_model = create_character_vectorizer_model(char_embed, text_vectorizer)
|
54 |
+
line_number_model = create_line_number_model(15, "line_number")
|
55 |
+
total_lines_model = create_line_number_model(20, "total_lines")
|
56 |
+
|
57 |
+
hybrid_model = layers.Concatenate(name="hybrid")([token_model.output,
|
58 |
+
character_vectorizer_model.output])
|
59 |
+
|
60 |
+
dense_layer = layers.Dense(256, activation="relu")(hybrid_model)
|
61 |
+
dense_layer = layers.Dropout(0.5)(dense_layer)
|
62 |
+
|
63 |
+
tribrid_model = layers.Concatenate(name="tribrid") ([line_number_model.output, total_lines_model.output, dense_layer])
|
64 |
+
output_layer = layers.Dense(num_classes, activation="softmax")(tribrid_model)
|
65 |
+
|
66 |
+
model = tf.keras.Model([line_number_model.input, total_lines_model.input, token_model.input, character_vectorizer_model.input], output_layer)
|
67 |
+
|
68 |
+
model.compile(loss=tf.keras.losses.CategoricalCrossentropy(label_smoothing=0.2),
|
69 |
+
optimizer=tf.keras.optimizers.Adam(),
|
70 |
+
metrics=["accuracy"])
|
71 |
+
return model
|
process_input.py
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
"""
|
2 |
+
Sep 2024
|
3 |
+
Ryan Tietjen
|
4 |
+
Contains helper functions to process user input for the demo
|
5 |
+
"""
|
6 |
+
import pandas as pd
|
7 |
+
|
8 |
+
def split_abstract(abstract):
|
9 |
+
results = []
|
10 |
+
|
11 |
+
lines = abstract.split("\n")
|
12 |
+
for i, line in enumerate(lines):
|
13 |
+
entry = {
|
14 |
+
"target": 0,
|
15 |
+
"text": line.lower(),
|
16 |
+
"line_number": i + 1,
|
17 |
+
"total_lines": len(lines)
|
18 |
+
}
|
19 |
+
results.append(entry)
|
20 |
+
return results
|
21 |
+
|
22 |
+
def split_abstract_original(abstract):
|
23 |
+
results = []
|
24 |
+
|
25 |
+
lines = abstract.split("\n")
|
26 |
+
for i, line in enumerate(lines):
|
27 |
+
entry = {
|
28 |
+
"target": 0,
|
29 |
+
"text": line,
|
30 |
+
"line_number": i + 1,
|
31 |
+
"total_lines": len(lines)
|
32 |
+
}
|
33 |
+
results.append(entry)
|
34 |
+
return results
|
35 |
+
|
36 |
+
def split_sentences_by_characters(corpus):
|
37 |
+
return [" ".join(sentence) for sentence in corpus]
|
38 |
+
|
39 |
+
def encode_labels(*datasets):
|
40 |
+
"""
|
41 |
+
Encode labels for multiple datasets using a unified label mapping.
|
42 |
+
|
43 |
+
Args:
|
44 |
+
*datasets: Arbitrary number of array-like structures containing labels.
|
45 |
+
|
46 |
+
Returns:
|
47 |
+
tuple: Encoded labels as numpy arrays for each dataset.
|
48 |
+
"""
|
49 |
+
# Collect all labels from all datasets into a single list
|
50 |
+
all_labels = pd.concat([pd.Series(data) for data in datasets])
|
51 |
+
|
52 |
+
# Get unique labels and sort them to ensure consistency
|
53 |
+
unique_labels = pd.unique(all_labels)
|
54 |
+
unique_labels.sort()
|
55 |
+
|
56 |
+
# Create mapping from labels to integers
|
57 |
+
label_to_index = {label: idx for idx, label in enumerate(unique_labels)}
|
58 |
+
|
59 |
+
# Function to encode a single dataset
|
60 |
+
def encode_single_dataset(dataset, mapping):
|
61 |
+
return pd.Series(dataset).map(mapping).to_numpy()
|
62 |
+
|
63 |
+
# Encode all datasets using the mapping
|
64 |
+
encoded_datasets = tuple(encode_single_dataset(dataset, label_to_index) for dataset in datasets)
|
65 |
+
|
66 |
+
# Return only the encoded datasets
|
67 |
+
return encoded_datasets
|