create app

README.md

@@ -1,12 +1,14 @@
 ---
-title: Call2Vec
+title: Call2vec
 emoji: 🌖
-colorFrom: pink
-colorTo: yellow
+colorFrom: blue
+colorTo: indigo
 sdk: gradio
 sdk_version: 3.0.24
 app_file: app.py
-pinned: false
+models: call2vec
+pinned: true
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+

app.py

@@ -0,0 +1,86 @@
+import gradio as gr
+import numpy as np
+import pandas as pd
+from datetime import datetime
+import os
+import re
+
+from huggingface_hub import hf_hub_url, cached_download
+from gensim.models.fasttext import load_facebook_model
+
+ACCESS_KEY = os.environ.get('ACCESS_KEY')
+
+# download model from huggingface hub
+url = hf_hub_url(repo_id="simonschoe/call2vec", filename="model.bin")
+cached_download(url)
+
+# load model via gensim
+model = load_facebook_model(cached_download(url))
+
+def process(_input, topn):
+
+    # split by delimiting characters
+    _input = re.split('[,;\n]', _input)
+
+    # convert input to lower, replace whitespaces by underscores
+    _input = [s.strip().lower().replace(' ', '_') for s in _input if s]
+
+    if _input[0] != ACCESS_KEY:
+        with open('log.txt', 'a') as f:
+            f.write(str(datetime.now()) + '+++' + '___'.join(_input) + '\n')
+
+    # apply model
+    if len(_input)>1:
+        # compute average seed embedding
+        avg_input = np.stack([model.wv[w] for w in _input], axis=0).mean(axis=0)
+        # find similarities
+        nearest_neighbors = model.wv.most_similar(positive=avg_input, topn=topn)
+        frequencies = [model.wv.get_vecattr(nn[0], 'count') for nn in nearest_neighbors]
+    else:
+        # find similarities
+        nearest_neighbors = model.wv.most_similar(positive=_input[0], topn=topn)
+        frequencies = [model.wv.get_vecattr(nn[0], 'count') for nn in nearest_neighbors]
+
+    result = pd.DataFrame([(a[0],a[1],b) for a,b in zip(nearest_neighbors, frequencies)], columns=['Token', 'Cosine Similarity', 'Frequency'])
+    if _input[0] == ACCESS_KEY:
+        with open('log.txt', 'r') as f:
+            prompts = f.readlines()
+            prompts = [p.strip().split('+++') for p in prompts]
+        result = pd.DataFrame(prompts, columns=['Time', 'Prompt'])
+    result.to_csv('result.csv')
+    return result, 'result.csv', '\n'.join(_input)
+
+def save(df):
+    df.to_csv('result.csv')
+    return 'result.csv'
+
+demo = gr.Blocks()
+
+with demo:
+    gr.Markdown("# Call2Vec")
+    gr.Markdown("## Earnings call transformation project")
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("""
+                #### Project Description
+                Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.""")
+            gr.Markdown(
+                """#### App usage:
+                Add your input prompts to the text field on the right. To use multiple input prompts at once separate
+                them by comma, semicolon or a new line
+                ##### Examples
+                - Climate change
+                - Financial risk, energy dependency, climate neutrality
+                """
+            )
+        with gr.Column():
+            text_input = gr.Textbox(lines=1)
+            with gr.Row():
+                n_output = gr.Slider(minimum=5, maximum=50, step=1)
+                compute_button = gr.Button("Compute")
+            df_output = gr.Dataframe(interactive=False)
+            file_out = gr.File(interactive=False)
+
+    compute_button.click(process, inputs=[text_input, n_output], outputs=[df_output, file_out, text_input])
+
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gensim==4.2.0
+huggingface_hub==0.8.1
+numpy==1.23.0
+pandas==1.4.3