Fix:model stuff

app.py

@@ -5,11 +5,16 @@ from spacy.tokens import Span
 import gradio as gr
 
 DEFAULT_MODEL = "en_core_web"
-DEFAULT_TEXT = "David Bowie moved to the US in 1974, initially staying in New York City before settling in Los Angeles."
+DEFAULT_TEXT = "Apple is looking at buying U.K. startup for $1 billion."
 DEFAULT_TOK_ATTR = ['idx', 'text', 'pos_', 'lemma_', 'shape_', 'dep_']
 DEFAULT_ENTS = ['CARDINAL', 'DATE', 'EVENT', 'FAC', 'GPE', 'LANGUAGE', 'LAW', 'LOC', 'MONEY',
                 'NORP', 'ORDINAL', 'ORG', 'PERCENT', 'PERSON', 'PRODUCT', 'QUANTITY', 'TIME', 'WORK_OF_ART']
 
+texts = {"en": DEFAULT_TEXT, "ca": "Apple està buscant comprar una startup del Regne Unit per mil milions de dòlars", "da": "Apple overvejer at købe et britisk startup for 1 milliard dollar.", "de": "Die ganze Stadt ist ein Startup: Shenzhen ist das Silicon Valley für Hardware-Firmen",
+         "el": "Η άνιση κατανομή του πλούτου και του εισοδήματος, η οποία έχει λάβει τρομερές διαστάσεις, δεν δείχνει τάσεις βελτίωσης.", "es": "Apple está buscando comprar una startup del Reino Unido por mil millones de dólares.", "fi": "Itseajavat autot siirtävät vakuutusvastuun autojen valmistajille", "fr": "Apple cherche à acheter une start-up anglaise pour 1 milliard de dollars", "it": "Apple vuole comprare una startup del Regno Unito per un miliardo di dollari",
+         "ja": "アップルがイギリスの新興企業を１０億ドルで購入を検討", "ko": "애플이 영국의 스타트업을 10억 달러에 인수하는 것을 알아보고 있다.", "lt": "Jaunikis pirmąją vestuvinę naktį iškeitė į areštinės gultą", "nb": "Apple vurderer å kjøpe britisk oppstartfirma for en milliard dollar.", "nl": "Apple overweegt om voor 1 miljard een U.K. startup te kopen",
+         "pl": "Poczuł przyjemną woń mocnej kawy.", "pt": "Apple está querendo comprar uma startup do Reino Unido por 100 milhões de dólares", "ro": "Apple plănuiește să cumpere o companie britanică pentru un miliard de dolari", "ru": "Apple рассматривает возможность покупки стартапа из Соединённого Королевства за $1 млрд", "sv": "Apple överväger att köpa brittisk startup för 1 miljard dollar.", "zh": "作为语言而言，为世界使用人数最多的语言，目前世界有五分之一人口做为母语。"}
+
 
 def get_all_models():
     with open("requirements.txt") as f:
@@ -69,84 +74,104 @@ def vectors(text, model):
 def span(text, span1, span2, label1, label2, model):
     nlp = spacy.load(model + "_sm")
     doc = nlp(text)
-    idx1_1 = 0
-    idx1_2 = 0
-    idx2_1 = 0
-    idx2_2 = 0
-
-    span1 = span1.split(" ")
-    span2 = span2.split(" ")
-
-    for i in range(len(list(doc))):
-        tok = list(doc)[i]
-        if span1[0] == tok.text:
-            idx1_1 = i
-        if span1[-1] == tok.text:
-            idx1_2 = i + 1
-        if span2[0] == tok.text:
-            idx2_1 = i
-        if span2[-1] == tok.text:
-            idx2_2 = i + 1
-
-    doc.spans["sc"] = [
-        Span(doc, idx1_1, idx1_2, label1),
-        Span(doc, idx2_1, idx2_2, label2),
-    ]
+    if span1:
+        idx1_1 = 0
+        idx1_2 = 0
+        idx2_1 = 0
+        idx2_2 = 0
+
+        span1 = span1.split(" ")
+        span2 = span2.split(" ")
+
+        for i in range(len(list(doc))):
+            tok = list(doc)[i]
+            if span1[0] == tok.text:
+                idx1_1 = i
+            if span1[-1] == tok.text:
+                idx1_2 = i + 1
+            if span2[0] == tok.text:
+                idx2_1 = i
+            if span2[-1] == tok.text:
+                idx2_2 = i + 1
+
+        doc.spans["sc"] = [
+            Span(doc, idx1_1, idx1_2, label1),
+            Span(doc, idx2_1, idx2_2, label2),
+        ]
+    else:
+        idx1_1 = 0
+        idx1_2 = round(len(list(doc)) / 2)
+        idx2_1 = 0
+        idx2_2 = 1
+
+        doc.spans["sc"] = [
+            Span(doc, idx1_1, idx1_2, label1),
+            Span(doc, idx2_1, idx2_2, label2),
+        ]
 
     html = displacy.render(doc, style="span")
     return html
 
 
+def get_text(model):
+    for i in range(len(models)):
+        model = model.split("_")[0]
+        new_text = texts[model]
+
+    return new_text
+
+
 demo = gr.Blocks()
 
 with demo:
-    text_input = gr.Textbox(value=DEFAULT_TEXT, interactive=True)
     model_input = gr.Dropdown(
         choices=models, value=DEFAULT_MODEL, interactive=True)
+    text_button = gr.Button("Get new text")
+    text_input = gr.Textbox(value=DEFAULT_TEXT, interactive=True)
+    button = gr.Button("Generate")
     with gr.Tabs():
         with gr.TabItem("Dependency"):
             col_punct = gr.Checkbox(label="Collapse Punctuation", value=True)
             col_phrase = gr.Checkbox(label="Collapse Phrases", value=True)
             compact = gr.Checkbox(label="Compact", value=True)
             depen_output = gr.HTML()
-            depen_button = gr.Button("Generate")
+
         with gr.TabItem("Entity"):
             entity_input = gr.CheckboxGroup(DEFAULT_ENTS, value=DEFAULT_ENTS)
             entity_output = gr.HTML()
-            entity_button = gr.Button("Generate")
         with gr.TabItem("Tokens"):
             with gr.Column():
                 tok_input = gr.CheckboxGroup(
                     DEFAULT_TOK_ATTR, value=DEFAULT_TOK_ATTR)
                 tok_output = gr.Dataframe(
                     headers=DEFAULT_TOK_ATTR, overflow_row_behaviour="paginate")
-            tok_button = gr.Button("Generate")
         with gr.TabItem("Similarity"):
-            sim_text1 = gr.Textbox(value="David Bowie", label="Chosen")
-            sim_text2 = gr.Textbox(value="the US", label="Chosen")
+            with gr.Row():
+                sim_text1 = gr.Textbox(value="David Bowie", label="Chosen")
+                sim_text2 = gr.Textbox(value="the US", label="Chosen")
             sim_output = gr.Textbox(value="0.09", label="Similarity Score")
-            sim_button = gr.Button("Generate")
         with gr.TabItem("Spans"):
-            with gr.Row():
-                span1 = gr.Textbox(value="David Bowie", label="Span 1")
-                label1 = gr.Textbox(value="Name",
-                                    label="Label for Span 1")
-            with gr.Row():
-                span2 = gr.Textbox(value="David", label="Span 2")
-                label2 = gr.Textbox(value="First",
-                                    label="Label for Span 2")
-            span_output = gr.HTML()
-            span_button = gr.Button("Generate")
-
-    depen_button.click(dependency, inputs=[
-                       text_input, col_punct, col_phrase, compact, model_input], outputs=depen_output)
-    entity_button.click(
+            with gr.Column():
+                with gr.Row():
+                    span1 = gr.Textbox(label="Span 1")
+                    label1 = gr.Textbox(value="Label 1",
+                                        label="Label for Span 1")
+                with gr.Row():
+                    span2 = gr.Textbox(label="Span 2")
+                    label2 = gr.Textbox(value="Label 2",
+                                        label="Label for Span 2")
+                with gr.Row():
+                    span_output = gr.HTML()
+    text_button.click(get_text, inputs=[model_input], outputs=text_input)
+    button.click(dependency, inputs=[
+        text_input, col_punct, col_phrase, compact, model_input], outputs=depen_output)
+    button.click(
         entity, inputs=[text_input, entity_input, model_input], outputs=entity_output)
-    tok_button.click(
+    button.click(
         token, inputs=[text_input, tok_input, model_input], outputs=tok_output)
-    sim_button.click(vectors, inputs=[text_input, model_input], outputs=[
-                     sim_output, sim_text1, sim_text2])
-    span_button.click(
+    button.click(vectors, inputs=[text_input, model_input], outputs=[
+        sim_output, sim_text1, sim_text2])
+    button.click(
         span, inputs=[text_input, span1, span2, label1, label2, model_input], outputs=span_output)
 
 demo.launch()

requirements.txt

@@ -2,45 +2,30 @@
 gradio==3.0.18
 spacy==3.3.1
 
-https://huggingface.co/spacy/ca_core_news_lg/resolve/main/ca_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/ca_core_news_md/resolve/main/ca_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/ca_core_news_sm/resolve/main/ca_core_news_sm-any-py3-none-any.whl
-https://huggingface.co/spacy/ca_core_news_trf/resolve/main/ca_core_news_trf-any-py3-none-any.whl
 
-https://huggingface.co/spacy/da_core_news_lg/resolve/main/da_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/da_core_news_md/resolve/main/da_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/da_core_news_sm/resolve/main/da_core_news_sm-any-py3-none-any.whl
-https://huggingface.co/spacy/da_core_news_trf/resolve/main/da_core_news_trf-any-py3-none-any.whl
 
-https://huggingface.co/spacy/de_core_news_lg/resolve/main/de_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/de_core_news_md/resolve/main/de_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/de_core_news_sm/resolve/main/de_core_news_sm-any-py3-none-any.whl
-https://huggingface.co/spacy/de_dep_news_trf/resolve/main/de_dep_news_trf-any-py3-none-any.whl
 
-https://huggingface.co/spacy/el_core_news_lg/resolve/main/el_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/el_core_news_md/resolve/main/el_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/el_core_news_sm/resolve/main/el_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/en_core_web_lg/resolve/main/en_core_web_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/en_core_web_md/resolve/main/en_core_web_md-any-py3-none-any.whl
 https://huggingface.co/spacy/en_core_web_sm/resolve/main/en_core_web_sm-any-py3-none-any.whl
-https://huggingface.co/spacy/en_core_web_trf/resolve/main/en_core_web_trf-any-py3-none-any.whl
 
-https://huggingface.co/spacy/es_core_news_lg/resolve/main/es_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/es_core_news_md/resolve/main/es_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/es_core_news_sm/resolve/main/es_core_news_sm-any-py3-none-any.whl
-https://huggingface.co/spacy/es_dep_news_trf/resolve/main/es_dep_news_trf-any-py3-none-any.whl
 
-https://huggingface.co/spacy/fi_core_news_lg/resolve/main/fi_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/fi_core_news_md/resolve/main/fi_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/fi_core_news_sm/resolve/main/fi_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/fr_core_news_lg/resolve/main/fr_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/fr_core_news_md/resolve/main/fr_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/fr_core_news_sm/resolve/main/fr_core_news_sm-any-py3-none-any.whl
-https://huggingface.co/spacy/fr_dep_news_trf/resolve/main/fr_dep_news_trf-any-py3-none-any.whl
 
-https://huggingface.co/spacy/it_core_news_lg/resolve/main/it_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/it_core_news_md/resolve/main/it_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/it_core_news_sm/resolve/main/it_core_news_sm-any-py3-none-any.whl
 
@@ -48,47 +33,32 @@ https://huggingface.co/spacy/ja_core_news_lg/resolve/main/ja_core_news_lg-any-py
 https://huggingface.co/spacy/ja_core_news_md/resolve/main/ja_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/ja_core_news_sm/resolve/main/ja_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/ko_core_news_lg/resolve/main/ko_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/ko_core_news_md/resolve/main/ko_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/ko_core_news_sm/resolve/main/ko_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/lt_core_news_lg/resolve/main/lt_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/lt_core_news_md/resolve/main/lt_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/lt_core_news_sm/resolve/main/lt_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/mk_core_news_lg/resolve/main/mk_core_news_lg-any-py3-none-any.whl
-https://huggingface.co/spacy/mk_core_news_md/resolve/main/mk_core_news_md-any-py3-none-any.whl
-https://huggingface.co/spacy/mk_core_news_sm/resolve/main/mk_core_news_sm-any-py3-none-any.whl
-
-https://huggingface.co/spacy/nb_core_news_lg/resolve/main/nb_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/nb_core_news_md/resolve/main/nb_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/nb_core_news_sm/resolve/main/nb_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/nl_core_news_lg/resolve/main/nl_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/nl_core_news_md/resolve/main/nl_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/nl_core_news_sm/resolve/main/nl_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/pl_core_news_lg/resolve/main/pl_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/pl_core_news_md/resolve/main/pl_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/pl_core_news_sm/resolve/main/pl_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/pt_core_news_lg/resolve/main/pt_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/pt_core_news_md/resolve/main/pt_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/pt_core_news_sm/resolve/main/pt_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/ro_core_news_lg/resolve/main/ro_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/ro_core_news_md/resolve/main/ro_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/ro_core_news_sm/resolve/main/ro_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/ru_core_news_lg/resolve/main/ru_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/ru_core_news_md/resolve/main/ru_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/ru_core_news_sm/resolve/main/ru_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/sv_core_news_lg/resolve/main/sv_core_news_lg-any-py3-none-any.whl
 https://huggingface.co/spacy/sv_core_news_md/resolve/main/sv_core_news_md-any-py3-none-any.whl
 https://huggingface.co/spacy/sv_core_news_sm/resolve/main/sv_core_news_sm-any-py3-none-any.whl
 
-https://huggingface.co/spacy/zh_core_web_lg/resolve/main/zh_core_web_lg-any-py3-none-any.whl 
 https://huggingface.co/spacy/zh_core_web_md/resolve/main/zh_core_web_md-any-py3-none-any.whl 
 https://huggingface.co/spacy/zh_core_web_sm/resolve/main/zh_core_web_sm-any-py3-none-any.whl 
-https://huggingface.co/spacy/zh_core_web_trf/resolve/main/zh_core_web_trf-any-py3-none-any.whl