Duplicate from valurank/keyword_and_keyphrase_extraction

Co-authored-by: Omotoso Abdulmatin <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,26 @@
+MICROSOFT REFERENCE SOURCE LICENSE (MS-RSL)
+
+This license governs use of the accompanying software. If you use the software, you accept this license. If you do not accept the license, do not use the software.
+
+1. Definitions
+The terms "reproduce," "reproduction" and "distribution" have the same meaning here as under U.S. copyright law.
+
+"You" means the licensee of the software.
+
+"Your company" means the company you worked for when you downloaded the software.
+
+"Reference use" means use of the software within your company as a reference, in read only form, for the sole purposes of debugging your products, maintaining your products, or enhancing the interoperability of your products with the software, and specifically excludes the right to distribute the software outside of your company.
+
+"Licensed patents" means any Licensor patent claims which read directly on the software as distributed by the Licensor under this license.
+
+2. Grant of Rights
+(A) Copyright Grant- Subject to the terms of this license, the Licensor grants you a non-transferable, non-exclusive, worldwide, royalty-free copyright license to reproduce the software for reference use.
+
+(B) Patent Grant- Subject to the terms of this license, the Licensor grants you a non-transferable, non-exclusive, worldwide, royalty-free patent license under licensed patents for reference use.
+
+3. Limitations
+(A) No Trademark License- This license does not grant you any rights to use the Licensor's name, logo, or trademarks.
+
+(B) If you begin patent litigation against the Licensor over patents that you think may apply to the software (including a cross-claim or counterclaim in a lawsuit), your license to the software ends automatically.
+
+(C) The software is licensed "as-is." You bear the risk of using it. The Licensor gives no express warranties, guarantees or conditions. You may have additional consumer rights under your local laws which this license cannot change. To the extent permitted under your local laws, the Licensor excludes the implied warranties of merchantability, fitness for a particular purpose and non-infringement.

README.md

@@ -0,0 +1,14 @@
+---
+title: Keyword And Keyphrase Extraction
+emoji: 👀
+colorFrom: gray
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.0.17
+app_file: app.py
+pinned: false
+license: other
+duplicated_from: valurank/keyword_and_keyphrase_extraction
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,40 @@
+#importing the necessary libraries
+
+import pandas as pd
+import numpy as np
+import gradio as gr
+from sentence_transformers import SentenceTransformer
+from keybert import KeyBERT
+from keyphrase_vectorizers import KeyphraseCountVectorizer
+
+# Defining a function to read in the text file
+
+def read_in_text(url):
+  with open(url, 'r') as file:
+    article = file.read()
+    return article
+    
+#tmp_model = SentenceTransformer('valurank/MiniLM-L6-Keyword-Extraction')
+kw_extractor = KeyBERT('valurank/MiniLM-L6-Keyword-Extraction')
+
+def get_keybert_results_with_vectorizer(text, number_of_results=20):
+    try:
+        keywords = kw_extractor.extract_keywords(text, vectorizer=KeyphraseCountVectorizer(), stop_words=None, top_n=number_of_results)
+        keywords = [i for i in keywords if i[1] > 0.20]
+
+        keybert_diversity_phrases = []
+        for i, j in keywords:
+          keybert_diversity_phrases.append(i)
+
+        output_df = pd.DataFrame()
+        output_df['keyword'] = np.array(keybert_diversity_phrases)
+        return output_df.head(20)
+    except Exception:
+        return "Error"
+        
+demo = gr.Interface(get_keybert_results_with_vectorizer, inputs=gr.inputs.Textbox(),
+                    outputs=gr.outputs.Dataframe(),
+                    title = "Keyword Extraction")
+                    
+if __name__ == "__main__":
+    demo.launch(debug=True)

requirements.txt

@@ -0,0 +1,7 @@
+keybert
+sentence_transformers
+keyphrase_vectorizers
+pandas
+numpy
+transformers==4.10.2
+sentencepiece==0.1.96