awacke1 commited on
Commit
7eca486
0 Parent(s):

Duplicate from awacke1/Knowledge-graphs

Browse files
.gitattributes ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
5
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.model filter=lfs diff=lfs merge=lfs -text
12
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
13
+ *.onnx filter=lfs diff=lfs merge=lfs -text
14
+ *.ot filter=lfs diff=lfs merge=lfs -text
15
+ *.parquet filter=lfs diff=lfs merge=lfs -text
16
+ *.pb filter=lfs diff=lfs merge=lfs -text
17
+ *.pt filter=lfs diff=lfs merge=lfs -text
18
+ *.pth filter=lfs diff=lfs merge=lfs -text
19
+ *.rar filter=lfs diff=lfs merge=lfs -text
20
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
21
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
22
+ *.tflite filter=lfs diff=lfs merge=lfs -text
23
+ *.tgz filter=lfs diff=lfs merge=lfs -text
24
+ *.xz filter=lfs diff=lfs merge=lfs -text
25
+ *.zip filter=lfs diff=lfs merge=lfs -text
26
+ *.zstandard filter=lfs diff=lfs merge=lfs -text
27
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ venv
2
+ test.html
.vscode/launch.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ // Use IntelliSense to learn about possible attributes.
3
+ // Hover to view descriptions of existing attributes.
4
+ // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
5
+ "version": "0.2.0",
6
+ "configurations": [
7
+ {
8
+ "name": "Python: Current File",
9
+ "type": "python",
10
+ "request": "launch",
11
+ "program": "${file}",
12
+ "console": "integratedTerminal",
13
+ "justMyCode": false
14
+ }
15
+ ]
16
+ }
.vscode/settings.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "workbench.colorCustomizations": {
3
+ "activityBar.background": "#09323E",
4
+ "titleBar.activeBackground": "#0C4656",
5
+ "titleBar.activeForeground": "#F6FCFE"
6
+ }
7
+ }
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: RE:Belle
3
+ emoji: 🌐
4
+ colorFrom: red
5
+ colorTo: blue
6
+ sdk: streamlit
7
+ sdk_version: 1.2.0
8
+ app_file: app.py
9
+ pinned: false
10
+ duplicated_from: awacke1/Knowledge-graphs
11
+ ---
12
+
13
+ # Configuration
14
+
15
+ `title`: _string_
16
+ Display title for the Space
17
+
18
+ `emoji`: _string_
19
+ Space emoji (emoji-only character allowed)
20
+
21
+ `colorFrom`: _string_
22
+ Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
23
+
24
+ `colorTo`: _string_
25
+ Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
26
+
27
+ `sdk`: _string_
28
+ Can be either `gradio`, `streamlit`, or `static`
29
+
30
+ `sdk_version` : _string_
31
+ Only applicable for `streamlit` SDK.
32
+ See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
33
+
34
+ `app_file`: _string_
35
+ Path to your main application file (which contains either `gradio` or `streamlit` Python code, or `static` html code).
36
+ Path is relative to the root of the repository.
37
+
38
+ `pinned`: _boolean_
39
+ Whether the Space stays on top of your list.
__pycache__/app.cpython-38.pyc ADDED
Binary file (5.05 kB). View file
 
__pycache__/rebel.cpython-38.pyc ADDED
Binary file (3.7 kB). View file
 
__pycache__/utils.cpython-38.pyc ADDED
Binary file (314 Bytes). View file
 
app.py ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from logging import disable
2
+ from pkg_resources import EggMetadata
3
+ import streamlit as st
4
+ import streamlit.components.v1 as components
5
+ import networkx as nx
6
+ import matplotlib.pyplot as plt
7
+ from pyvis.network import Network
8
+ from streamlit.state.session_state import SessionState
9
+ from streamlit.type_util import Key
10
+ import rebel
11
+ import wikipedia
12
+ from utils import clip_text
13
+ from datetime import datetime as dt
14
+ import os
15
+
16
+ MAX_TOPICS = 3
17
+
18
+ wiki_state_variables = {
19
+ 'has_run_wiki':False,
20
+ 'wiki_suggestions': [],
21
+ 'wiki_text' : [],
22
+ 'nodes':[],
23
+ "topics":[],
24
+ "html_wiki":""
25
+ }
26
+
27
+ free_text_state_variables = {
28
+ 'has_run_free':False,
29
+ "html_free":""
30
+
31
+ }
32
+
33
+ BUTTON_COLUMS = 4
34
+
35
+ def wiki_init_state_variables():
36
+ for k in free_text_state_variables.keys():
37
+ if k in st.session_state:
38
+ del st.session_state[k]
39
+
40
+ for k, v in wiki_state_variables.items():
41
+ if k not in st.session_state:
42
+ st.session_state[k] = v
43
+
44
+ def wiki_generate_graph():
45
+ st.session_state["GRAPH_FILENAME"] = str(dt.now().timestamp()*1000) + ".html"
46
+
47
+ if 'wiki_text' not in st.session_state:
48
+ return
49
+ if len(st.session_state['wiki_text']) == 0:
50
+ st.error("please enter a topic and select a wiki page first")
51
+ return
52
+ with st.spinner(text="Generating graph..."):
53
+ texts = st.session_state['wiki_text']
54
+ st.session_state['nodes'] = []
55
+ nodes = rebel.generate_knowledge_graph(texts, st.session_state["GRAPH_FILENAME"])
56
+ HtmlFile = open(st.session_state["GRAPH_FILENAME"], 'r', encoding='utf-8')
57
+ source_code = HtmlFile.read()
58
+ st.session_state["html_wiki"] = source_code
59
+ os.remove(st.session_state["GRAPH_FILENAME"])
60
+ for n in nodes:
61
+ n = n.lower()
62
+ if n not in st.session_state['topics']:
63
+ possible_topics = wikipedia.search(n, results = 2)
64
+ st.session_state['nodes'].extend(possible_topics)
65
+ st.session_state['nodes'] = list(set(st.session_state['nodes']))
66
+ st.session_state['has_run_wiki'] = True
67
+ st.success('Done!')
68
+
69
+ def wiki_show_suggestion():
70
+ st.session_state['wiki_suggestions'] = []
71
+ with st.spinner(text="fetching wiki topics..."):
72
+ if st.session_state['input_method'] == "wikipedia":
73
+ text = st.session_state.text
74
+ if (text is not None) and (text != ""):
75
+ subjects = text.split(",")[:MAX_TOPICS]
76
+ for subj in subjects:
77
+ st.session_state['wiki_suggestions'] += wikipedia.search(subj, results = 3)
78
+
79
+ def wiki_show_text(page_title):
80
+ with st.spinner(text="fetching wiki page..."):
81
+ try:
82
+ page = wikipedia.page(title=page_title, auto_suggest=False)
83
+ st.session_state['wiki_text'].append(clip_text(page.summary))
84
+ st.session_state['topics'].append(page_title.lower())
85
+ st.session_state['wiki_suggestions'].remove(page_title)
86
+
87
+ except wikipedia.DisambiguationError as e:
88
+ with st.spinner(text="Woops, ambigious term, recalculating options..."):
89
+ st.session_state['wiki_suggestions'].remove(page_title)
90
+ temp = st.session_state['wiki_suggestions'] + e.options[:3]
91
+ st.session_state['wiki_suggestions'] = list(set(temp))
92
+ except wikipedia.WikipediaException:
93
+ st.session_state['wiki_suggestions'].remove(page_title)
94
+
95
+ def wiki_add_text(term):
96
+ if len(st.session_state['wiki_text']) > MAX_TOPICS:
97
+ return
98
+ try:
99
+ page = wikipedia.page(title=term, auto_suggest=False)
100
+ extra_text = clip_text(page.summary)
101
+
102
+ st.session_state['wiki_text'].append(extra_text)
103
+ st.session_state['topics'].append(term.lower())
104
+ st.session_state['nodes'].remove(term)
105
+
106
+ except wikipedia.DisambiguationError as e:
107
+ print(e)
108
+ with st.spinner(text="Woops, ambigious term, recalculating options..."):
109
+ st.session_state['nodes'].remove(term)
110
+ temp = st.session_state['nodes'] + e.options[:3]
111
+ st.session_state['nodes'] = list(set(temp))
112
+ except wikipedia.WikipediaException as e:
113
+ print(e)
114
+ st.session_state['nodes'].remove(term)
115
+
116
+ def wiki_reset_session():
117
+ for k in wiki_state_variables:
118
+ del st.session_state[k]
119
+
120
+ def free_reset_session():
121
+ for k in free_text_state_variables:
122
+ del st.session_state[k]
123
+
124
+ def free_text_generate():
125
+ st.session_state["GRAPH_FILENAME"] = str(dt.now().timestamp()*1000) + ".html"
126
+ text = st.session_state['free_text'][0:100]
127
+ rebel.generate_knowledge_graph([text], st.session_state["GRAPH_FILENAME"])
128
+ HtmlFile = open(st.session_state["GRAPH_FILENAME"], 'r', encoding='utf-8')
129
+ source_code = HtmlFile.read()
130
+ st.session_state["html_free"] = source_code
131
+ os.remove(st.session_state["GRAPH_FILENAME"])
132
+ st.session_state['has_run_free'] = True
133
+
134
+ def free_text_layout():
135
+ st.text_area("Free text", key="free_text", height=5, value="Tardigrades, known colloquially as water bears or moss piglets, are a phylum of eight-legged segmented micro-animals.")
136
+ st.button("Generate", on_click=free_text_generate, key="free_text_generate")
137
+
138
+ def free_test_init_state_variables():
139
+ for k in wiki_state_variables.keys():
140
+ if k in st.session_state:
141
+ del st.session_state[k]
142
+
143
+ for k, v in free_text_state_variables.items():
144
+ if k not in st.session_state:
145
+ st.session_state[k] = v
146
+
147
+ st.title('RE:Belle')
148
+ st.markdown(
149
+ """
150
+ ### Building Beautiful Knowledge Graphs With REBEL
151
+ """)
152
+ st.selectbox(
153
+ 'input method',
154
+ ('wikipedia', 'free text'), key="input_method")
155
+
156
+
157
+ def show_wiki_hub_page():
158
+ st.sidebar.button("Reset", on_click=wiki_reset_session, key="reset_key")
159
+
160
+ st.sidebar.markdown(
161
+ """
162
+ ## How To Create a Graph:
163
+ - Enter wikipedia search terms, separated by comma's
164
+ - Choose one or more of the suggested topics (max 3)
165
+ - Click generate!
166
+ """
167
+ )
168
+ cols = st.columns([8, 1])
169
+ with cols[0]:
170
+ st.text_input("wikipedia search term", on_change=wiki_show_suggestion, key="text", value="graphs, are, awesome")
171
+ with cols[1]:
172
+ st.text('')
173
+ st.text('')
174
+ st.button("Search", on_click=wiki_show_suggestion, key="show_suggestion_key")
175
+
176
+ if len(st.session_state['wiki_suggestions']) != 0:
177
+ num_buttons = len(st.session_state['wiki_suggestions'])
178
+ num_cols = num_buttons if 0 < num_buttons < BUTTON_COLUMS else BUTTON_COLUMS
179
+ columns = st.columns([1] * num_cols )
180
+ for q in range(1 + num_buttons//num_cols):
181
+ for i, (c, s) in enumerate(zip(columns, st.session_state['wiki_suggestions'][q*num_cols: (q+1)*num_cols])):
182
+ with c:
183
+ st.button(s, on_click=wiki_show_text, args=(s,), key=str(i)+s+"wiki_suggestion")
184
+
185
+ if len(st.session_state['wiki_text']) != 0:
186
+ for i, t in enumerate(st.session_state['wiki_text']):
187
+ new_expander = st.expander(label=t[:30] + "...", expanded=(i==0))
188
+ with new_expander:
189
+ st.markdown(t)
190
+
191
+ if len(st.session_state['wiki_text']) > 0:
192
+ st.button("Generate", on_click=wiki_generate_graph, key="gen_graph")
193
+ st.sidebar.markdown(
194
+ """
195
+ ## How to expand the graph
196
+ - Click a button below the graph to expand that node
197
+ (Only nodes that have wiki pages will be expanded)
198
+ - Hit the Generate button again to expand your graph!
199
+ """
200
+ )
201
+
202
+ if st.session_state['has_run_wiki']:
203
+
204
+ components.html(st.session_state["html_wiki"], width=720, height=600)
205
+ num_buttons = len(st.session_state["nodes"])
206
+ num_cols = num_buttons if 0 < num_buttons < BUTTON_COLUMS else BUTTON_COLUMS
207
+ columns = st.columns([1] * num_cols + [1])
208
+
209
+ for q in range(1 + num_buttons//num_cols):
210
+ for i, (c, s) in enumerate(zip(columns, st.session_state["nodes"][q*num_cols: (q+1)*num_cols])):
211
+ with c:
212
+ st.button(s, on_click=wiki_add_text, args=(s,), key=str(i)+s)
213
+
214
+ def show_free_text_hub_page():
215
+ st.sidebar.button("Reset", on_click=free_reset_session, key="free_reset_key")
216
+ st.sidebar.markdown(
217
+ """
218
+ ## How To Create a Graph:
219
+ - Enter a text you'd like to see as a graph.
220
+ - Click generate!
221
+ """
222
+ )
223
+
224
+ free_text_layout()
225
+
226
+ if st.session_state['has_run_free']:
227
+ components.html(st.session_state["html_free"], width=720, height=600)
228
+
229
+ if st.session_state['input_method'] == "wikipedia":
230
+ wiki_init_state_variables()
231
+ show_wiki_hub_page()
232
+ else:
233
+ free_test_init_state_variables()
234
+ show_free_text_hub_page()
235
+
236
+
237
+
238
+ st.sidebar.markdown(
239
+ """
240
+ ## What This Is And Why We Built it
241
+
242
+ This space shows how a transformer network can be used to convert *human* text into a computer-queryable format: a **knowledge graph**. Knowledge graphs are graphs where each node (or *vertex* if you're fancy) represent a concept/person/thing and each edge the link between those concepts. If you'd like to know more, you can read [this blogpost](https://www.ml6.eu/knowhow/knowledge-graphs-an-introduction-and-business-applications).
243
+
244
+ Knowledge graphs aren't just cool to look at, they are an extremely versatile way of storing data, and are used in machine learning to perform tasks like fraud detection. You can read more about the applications of knowledge graphs in ML in [this blogpost](https://blog.ml6.eu/how-are-knowledge-graphs-and-machine-learning-related-ff6f5c1760b5).
245
+
246
+ There is one problem though: building knowledge graphs from scratch is a time-consuming and tedious task, so it would be a lot easier if we could leverage machine learning to **create** them from existing texts. This demo shows how a model named **REBEL** has been trained to do just that: it reads summaries from Wikipedia (or any other text you input), and generates a graph containing the information it distills from the text.
247
+ """
248
+ )
249
+
250
+ st.sidebar.markdown(
251
+ """
252
+ *Credits for the REBEL model go out to Pere-Lluís Huguet Cabot and Roberto Navigli.
253
+ The code can be found [here](https://github.com/Babelscape/rebel),
254
+ and the original paper [here](https://github.com/Babelscape/rebel/blob/main/docs/EMNLP_2021_REBEL__Camera_Ready_.pdf)*
255
+ """
256
+ )
rebel.py ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from typing import List
2
+ from transformers import pipeline
3
+ from pyvis.network import Network
4
+ from functools import lru_cache
5
+ import spacy
6
+ from spacy import displacy
7
+
8
+
9
+ DEFAULT_LABEL_COLORS = {
10
+ "ORG": "#7aecec",
11
+ "PRODUCT": "#bfeeb7",
12
+ "GPE": "#feca74",
13
+ "LOC": "#ff9561",
14
+ "PERSON": "#aa9cfc",
15
+ "NORP": "#c887fb",
16
+ "FACILITY": "#9cc9cc",
17
+ "EVENT": "#ffeb80",
18
+ "LAW": "#ff8197",
19
+ "LANGUAGE": "#ff8197",
20
+ "WORK_OF_ART": "#f0d0ff",
21
+ "DATE": "#bfe1d9",
22
+ "TIME": "#bfe1d9",
23
+ "MONEY": "#e4e7d2",
24
+ "QUANTITY": "#e4e7d2",
25
+ "ORDINAL": "#e4e7d2",
26
+ "CARDINAL": "#e4e7d2",
27
+ "PERCENT": "#e4e7d2",
28
+ }
29
+
30
+ def generate_knowledge_graph(texts: List[str], filename: str):
31
+ nlp = spacy.load("en_core_web_sm")
32
+ doc = nlp("\n".join(texts).lower())
33
+ NERs = [ent.text for ent in doc.ents]
34
+ NER_types = [ent.label_ for ent in doc.ents]
35
+
36
+ triplets = []
37
+ for triplet in texts:
38
+ triplets.extend(generate_partial_graph(triplet))
39
+ heads = [ t["head"].lower() for t in triplets]
40
+ tails = [ t["tail"].lower() for t in triplets]
41
+
42
+ nodes = list(set(heads + tails))
43
+ net = Network(directed=True, width="700px", height="700px")
44
+
45
+ for n in nodes:
46
+ if n in NERs:
47
+ NER_type = NER_types[NERs.index(n)]
48
+ if NER_type in NER_types:
49
+ if NER_type in DEFAULT_LABEL_COLORS.keys():
50
+ color = DEFAULT_LABEL_COLORS[NER_type]
51
+ else:
52
+ color = "#666666"
53
+ net.add_node(n, title=NER_type, shape="circle", color=color)
54
+ else:
55
+ net.add_node(n, shape="circle")
56
+ else:
57
+ net.add_node(n, shape="circle")
58
+
59
+ unique_triplets = set()
60
+ stringify_trip = lambda x : x["tail"] + x["head"] + x["type"].lower()
61
+ for triplet in triplets:
62
+ if stringify_trip(triplet) not in unique_triplets:
63
+ net.add_edge(triplet["head"].lower(), triplet["tail"].lower(),
64
+ title=triplet["type"], label=triplet["type"])
65
+ unique_triplets.add(stringify_trip(triplet))
66
+
67
+ net.repulsion(
68
+ node_distance=200,
69
+ central_gravity=0.2,
70
+ spring_length=200,
71
+ spring_strength=0.05,
72
+ damping=0.09
73
+ )
74
+ net.set_edge_smooth('dynamic')
75
+ net.show(filename)
76
+ return nodes
77
+
78
+
79
+ @lru_cache(maxsize=16)
80
+ def generate_partial_graph(text: str):
81
+ triplet_extractor = pipeline('text2text-generation', model='Babelscape/rebel-large', tokenizer='Babelscape/rebel-large')
82
+ a = triplet_extractor(text, return_tensors=True, return_text=False)[0]["generated_token_ids"]["output_ids"]
83
+ extracted_text = triplet_extractor.tokenizer.batch_decode(a)
84
+ extracted_triplets = extract_triplets(extracted_text[0])
85
+ return extracted_triplets
86
+
87
+
88
+ def extract_triplets(text):
89
+ """
90
+ Function to parse the generated text and extract the triplets
91
+ """
92
+ triplets = []
93
+ relation, subject, relation, object_ = '', '', '', ''
94
+ text = text.strip()
95
+ current = 'x'
96
+ for token in text.replace("<s>", "").replace("<pad>", "").replace("</s>", "").split():
97
+ if token == "<triplet>":
98
+ current = 't'
99
+ if relation != '':
100
+ triplets.append({'head': subject.strip(), 'type': relation.strip(),'tail': object_.strip()})
101
+ relation = ''
102
+ subject = ''
103
+ elif token == "<subj>":
104
+ current = 's'
105
+ if relation != '':
106
+ triplets.append({'head': subject.strip(), 'type': relation.strip(),'tail': object_.strip()})
107
+ object_ = ''
108
+ elif token == "<obj>":
109
+ current = 'o'
110
+ relation = ''
111
+ else:
112
+ if current == 't':
113
+ subject += ' ' + token
114
+ elif current == 's':
115
+ object_ += ' ' + token
116
+ elif current == 'o':
117
+ relation += ' ' + token
118
+ if subject != '' and relation != '' and object_ != '':
119
+ triplets.append({'head': subject.strip(), 'type': relation.strip(),'tail': object_.strip()})
120
+
121
+ return triplets
122
+
requirements.txt ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ altair==4.2.0
2
+ argon2-cffi==21.3.0
3
+ argon2-cffi-bindings==21.2.0
4
+ astor==0.8.1
5
+ attrs==21.4.0
6
+ backcall==0.2.0
7
+ backports.zoneinfo==0.2.1
8
+ base58==2.1.1
9
+ beautifulsoup4==4.10.0
10
+ bleach==4.1.0
11
+ blinker==1.4
12
+ blis==0.7.5
13
+ cachetools==5.0.0
14
+ catalogue==2.0.6
15
+ certifi==2021.10.8
16
+ cffi==1.15.0
17
+ charset-normalizer==2.0.10
18
+ click==7.1.2
19
+ cycler==0.11.0
20
+ cymem==2.0.6
21
+ debugpy==1.5.1
22
+ decorator==5.1.1
23
+ defusedxml==0.7.1
24
+ entrypoints==0.3
25
+ filelock==3.4.2
26
+ fonttools==4.28.5
27
+ gitdb==4.0.9
28
+ GitPython==3.1.26
29
+ got==0.0.1
30
+ huggingface-hub==0.2.1
31
+ idna==3.3
32
+ importlib-resources==5.4.0
33
+ ipykernel==6.6.1
34
+ ipython==7.31.0
35
+ ipython-genutils==0.2.0
36
+ ipywidgets==7.6.5
37
+ jedi==0.18.1
38
+ Jinja2==3.0.3
39
+ joblib==1.1.0
40
+ jsonpickle==2.0.0
41
+ jsonschema==4.3.3
42
+ jupyter-client==7.1.0
43
+ jupyter-core==4.9.1
44
+ jupyterlab-pygments==0.1.2
45
+ jupyterlab-widgets==1.0.2
46
+ kiwisolver==1.3.2
47
+ langcodes==3.3.0
48
+ MarkupSafe==2.0.1
49
+ matplotlib==3.5.1
50
+ matplotlib-inline==0.1.3
51
+ mistune==0.8.4
52
+ murmurhash==1.0.6
53
+ nbclient==0.5.9
54
+ nbconvert==6.4.0
55
+ nbformat==5.1.3
56
+ nest-asyncio==1.5.4
57
+ networkx==2.6.3
58
+ notebook==6.4.6
59
+ numpy==1.22.0
60
+ packaging==21.3
61
+ pandas==1.3.5
62
+ pandocfilters==1.5.0
63
+ parso==0.8.3
64
+ pathy==0.6.1
65
+ pexpect==4.8.0
66
+ pickleshare==0.7.5
67
+ Pillow==9.0.0
68
+ preshed==3.0.6
69
+ prometheus-client==0.12.0
70
+ prompt-toolkit==3.0.24
71
+ protobuf==3.19.3
72
+ ptyprocess==0.7.0
73
+ pyarrow==6.0.1
74
+ pycparser==2.21
75
+ pydantic==1.8.2
76
+ pydeck==0.7.1
77
+ Pygments==2.11.2
78
+ Pympler==1.0.1
79
+ pyparsing==3.0.6
80
+ pyrsistent==0.18.0
81
+ python-dateutil==2.8.2
82
+ pytz==2021.3
83
+ pytz-deprecation-shim==0.1.0.post0
84
+ pyvis==0.1.9
85
+ PyYAML==6.0
86
+ pyzmq==22.3.0
87
+ regex==2021.11.10
88
+ requests==2.27.1
89
+ sacremoses==0.0.47
90
+ Send2Trash==1.8.0
91
+ six==1.16.0
92
+ smart-open==5.2.1
93
+ smmap==5.0.0
94
+ soupsieve==2.3.1
95
+ spacy==3.2.1
96
+ spacy-legacy==3.0.8
97
+ spacy-loggers==1.0.1
98
+ srsly==2.4.2
99
+ streamlit==1.3.1
100
+ terminado==0.12.1
101
+ testpath==0.5.0
102
+ thinc==8.0.13
103
+ tokenizers==0.10.3
104
+ toml==0.10.2
105
+ toolz==0.11.2
106
+ torch==1.10.1
107
+ tornado==6.1
108
+ tqdm==4.62.3
109
+ traitlets==5.1.1
110
+ transformers==4.15.0
111
+ typer==0.4.0
112
+ typing-extensions==4.0.1
113
+ tzdata==2021.5
114
+ tzlocal==4.1
115
+ urllib3==1.26.8
116
+ validators==0.18.2
117
+ wasabi==0.9.0
118
+ watchdog==2.1.6
119
+ wcwidth==0.2.5
120
+ webencodings==0.5.1
121
+ widgetsnbextension==3.5.2
122
+ wikipedia==1.4.0
123
+ zipp==3.7.0
124
+ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.2.0/en_core_web_sm-3.2.0.tar.gz#egg=en_core_web_sm
utils.py ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+
2
+ def clip_text(t, lenght = 4):
3
+ t_sub = t.replace("...", "dotdotdot")
4
+ t_clipped = ".".join(t_sub.split(".")[:lenght]) + "."
5
+ t_reverted = t_clipped.replace("dotdotdot", "...")
6
+ return t_reverted