Shift to url classifier

.gitignore

@@ -0,0 +1 @@
+env/

app.py

@@ -2,41 +2,46 @@ import gradio as gr
 from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
 
 
-class EmotionClassifier:
-    def __init__(self, model_name: str):
-        self.model = AutoModelForSequenceClassification.from_pretrained(model_name)
-        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+class UrlClassifier:
+    def __init__(self):
         self.pipeline = pipeline(
-            "text-classification",
-            model=self.model,
-            tokenizer=self.tokenizer,
-            return_all_scores=True,
+            "zero-shot-classification",
+            model="MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli"
         )
+        self.candidate_labels = ["Apps", "Arts and Entertainment", "Automotive Ownership", "Automotive Products", "Beauty Services", "Business and Industrial", "Clothing and Accessories", "Collectables and Antiques", "Consumer Electronics", "Edible Consumer Packaged Goods", "Education and Careers", "Family and Parenting", "Finance and Insurance", "Food and Beverage Services", "Furniture", "Gifts and Holiday Items", "Hardware Supplies", "Health and Medical Services", "Hobbies and Interests", "Home and Garden Services", "Legal Services", "Life Events", "Logistics and Delivery", "Non-Profits", "Office Equipment and Supplies", "Pet Services", "Pharmaceuticals", "Real Estate", "Recreation and Fitness Activities", "Software", "Sporting Goods", "Travel and Tourism", "Web Services"]
+
 
     def predict(self, input_text: str):
-        pred = self.pipeline(input_text)[0]
-        result = {
-            "Sadness 😭": pred[0]["score"],
-            "Joy 😂": pred[1]["score"],
-            "Love 😍": pred[2]["score"],
-            "Anger 😠": pred[3]["score"],
-            "Fear 😨": pred[4]["score"],
-            "Surprise 😲": pred[5]["score"],
-        }
+        pred = self.pipeline(input_text, self.candidate_labels)
+        # pred = self.pipeline(input_text)[0]
+        
+        sorted_preds = sorted(zip(pred['scores'], pred['labels']))
+        result = {}
+        for i in range(len(sorted_preds)):
+            result[sorted_preds[i][1]] = sorted_preds[i][0]
+        
+        # result = {
+        #     "Sadness 😭": pred[0]["score"],
+        #     "Joy 😂": pred[1]["score"],
+        #     "Love 😍": pred[2]["score"],
+        #     "Anger 😠": pred[3]["score"],
+        #     "Fear 😨": pred[4]["score"],
+        #     "Surprise 😲": pred[5]["score"],
+        # }
         return result
 
 
 def main():
-    model = EmotionClassifier("bhadresh-savani/bert-base-uncased-emotion")
+    model = UrlClassifier()
     iface = gr.Interface(
         fn=model.predict,
         inputs=gr.inputs.Textbox(
             lines=3,
-            placeholder="Type a phrase that has some emotion",
-            label="Input Text",
+            placeholder="Input a shopping website URL",
+            label="Input URL",
         ),
         outputs="label",
-        title="Emotion Classification",
+        title="Ecommerce URL Classification",
         examples=[
             "I get so down when I'm alone",
             "I believe that today everything will work out",

requirements.txt

@@ -1,74 +1,75 @@
-analytics-python==1.4.0
-backcall==0.2.0
-backoff==1.10.0
-bcrypt==3.2.0
-certifi==2021.10.8
-cffi==1.15.0
-charset-normalizer==2.0.8
-click==8.0.3
-cryptography==36.0.0
+aiofiles==23.2.1
+aiohttp==3.8.5
+aiosignal==1.3.1
+altair==5.1.0
+annotated-types==0.5.0
+anyio==3.7.1
+async-timeout==4.0.3
+attrs==23.1.0
+certifi==2023.7.22
+charset-normalizer==3.2.0
+click==8.1.7
+contourpy==1.1.0
 cycler==0.11.0
-debugpy==1.5.1
-decorator==5.1.0
-entrypoints==0.3
-ffmpy==0.3.0
-filelock==3.4.0
-Flask==2.0.2
-Flask-CacheBuster==1.0.0
-Flask-Cors==3.0.10
-Flask-Login==0.5.0
-fonttools==4.28.2
-gradio==2.4.6
-huggingface-hub==0.1.2
-idna==3.3
-ipykernel==6.5.1
-ipython==7.30.0
-itsdangerous==2.0.1
-jedi==0.18.1
-Jinja2==3.0.3
-joblib==1.1.0
-jupyter-client==7.1.0
-jupyter-core==4.9.1
-kiwisolver==1.3.2
-markdown2==2.4.1
-MarkupSafe==2.0.1
-matplotlib==3.5.0
-matplotlib-inline==0.1.3
-monotonic==1.6
-nest-asyncio==1.5.1
-numpy==1.21.4
-packaging==21.3
-pandas==1.3.4
-paramiko==2.8.1
-parso==0.8.2
-pexpect==4.8.0
-pickleshare==0.7.5
-Pillow==8.4.0
-prompt-toolkit==3.0.23
-ptyprocess==0.7.0
-pycparser==2.21
-pycryptodome==3.11.0
+datasets==2.14.4
+dill==0.3.7
+fastapi==0.103.0
+ffmpy==0.3.1
+filelock==3.12.3
+fonttools==4.42.1
+frozenlist==1.4.0
+fsspec==2023.6.0
+gradio==3.41.2
+gradio_client==0.5.0
+h11==0.14.0
+httpcore==0.17.3
+httpx==0.24.1
+huggingface-hub==0.16.4
+idna==3.4
+importlib-resources==6.0.1
+Jinja2==3.1.2
+jsonschema==4.19.0
+jsonschema-specifications==2023.7.1
+kiwisolver==1.4.5
+MarkupSafe==2.1.3
+matplotlib==3.7.2
+mpmath==1.3.0
+multidict==6.0.4
+multiprocess==0.70.15
+networkx==3.1
+numpy==1.25.2
+orjson==3.9.5
+packaging==23.1
+pandas==2.0.3
+Pillow==10.0.0
+pyarrow==13.0.0
+pydantic==2.3.0
+pydantic_core==2.6.3
 pydub==0.25.1
-Pygments==2.10.0
-PyNaCl==1.4.0
-pyparsing==3.0.6
+pyparsing==3.0.9
 python-dateutil==2.8.2
-pytz==2021.3
-PyYAML==6.0
-pyzmq==22.3.0
-regex==2021.11.10
-requests==2.26.0
-sacremoses==0.0.46
-setuptools-scm==6.3.2
+python-multipart==0.0.6
+pytz==2023.3
+PyYAML==6.0.1
+referencing==0.30.2
+regex==2023.8.8
+requests==2.31.0
+rpds-py==0.10.0
+safetensors==0.3.3
+semantic-version==2.10.0
 six==1.16.0
-tokenizers==0.10.3
-tomli==1.2.2
-torch==1.10.0
-tornado==6.1
-tqdm==4.62.3
-traitlets==5.1.1
-transformers==4.12.5
-typing-extensions==4.0.0
-urllib3==1.26.7
-wcwidth==0.2.5
-Werkzeug==2.0.2
+sniffio==1.3.0
+starlette==0.27.0
+sympy==1.12
+tokenizers==0.13.3
+toolz==0.12.0
+torch==2.0.1
+tqdm==4.66.1
+transformers==4.32.1
+typing_extensions==4.7.1
+tzdata==2023.3
+urllib3==2.0.4
+uvicorn==0.23.2
+websockets==11.0.3
+xxhash==3.3.0
+yarl==1.9.2