Updata app.py

app.py

@@ -1,10 +1,43 @@
 import gradio
+import pandas as pd
+import concurrent.futures
+
 from App.tfidfrecommender import TfidfRecommender
 
 import gradio as gr
 
-def image_classifier(inp):
-    return {'cat': 0.3, 'dog': 0.7}
+desc = pd.read_csv('App/data/descriptions.csv')
+
+rec = TfidfRecommender(desc, 'id', 'description' , "none")
+def initialize_and_tokenize(tokenizer):
+    rec.tokenization_method = tokenizer
+    rec.tokenize_text()
+
+names = []
+def recommend (movies) :
+    pool = concurrent.futures.ThreadPoolExecutor(max_workers=10)
+    futures = [pool.submit(rec.recommend_k_items, movie, 5) for movie in movies]
+    idss = [f.result() for f in futures]
+    ids = [id for ids in idss for id in ids]
+    ids = list(set(ids))
+    names = desc[desc['id'].isin(ids)]['title'].to_list()
 
-demo = gr.Interface(fn=image_classifier, inputs="image", outputs="label")
+
+with gr.Blocks() as demo:
+    gr.Markdown("Start typing below and then click **Run** to see the output.")
+    with gr.Row():
+        radio = gr.Radio(["bert", "scibert", "nltk" , "none"], value="none", 
+                         label="Tokenization and text preprocess")
+    btn = gr.Button("Tokenize and Preprocess")
+    btn.click(fn=initialize_and_tokenize, inputs=radio, outputs=[])
+
+    gr.Markdown("Choose 3 movies")
+    with gr.Row():
+        dropdown = gr.Dropdown(choices = list(desc['title']), multiselect=True, max_choices=3,
+                               label="Movies")
+    btn2 = gr.Button("Recommend")
+    btn2.click(fn=recommend, inputs=dropdown,outputs=[])
+    gr.Markdown("rec{}".format(len(names)))
 demo.launch()
+
+# demo = gr.Interface(fn=image_classifier, inputs="image", outputs="label")