Initial commit

.gitignore

@@ -0,0 +1,2 @@
+# Virtual environments
+venv

README.md

@@ -1,13 +1,13 @@
 ---
-title: Petarda
-emoji: 🌍
-colorFrom: gray
-colorTo: red
+title: Petarda Classification-neu
+emoji: 🤯🤯🤯🤯🤯
+colorFrom: yellow
+colorTo: blue
 sdk: gradio
 sdk_version: 5.9.1
 app_file: app.py
 pinned: false
-short_description: PErsonality Trait prediction - AI model Roberta - Demo App
+short_description: classificating Personality Traits using roberta - demo app
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,108 @@
+
+# 1. Import the required packages
+import torch
+import gradio as gr
+
+from typing import Dict
+from transformers import pipeline
+
+# 2. Define function to use our model on given text 
+def trait_classifier(text: str) -> Dict[str, float]:
+    # Set up text classification pipeline
+    agr_classifier = pipeline(task="text-classification", 
+                                        # Because our model is on Hugging Face already, we can pass in the model name directly
+                                        model="kar0lina/petarda_xlm-roberta-base_agr", # link to model on HF Hub
+                                        device="cuda" if torch.cuda.is_available() else "cpu",
+                                        top_k=None) # return all possible scores (not just top-1)
+    con_classifier = pipeline(task="text-classification", 
+                                        # Because our model is on Hugging Face already, we can pass in the model name directly
+                                        model="kar0lina/petarda_xlm-roberta-base_con", # link to model on HF Hub
+                                        device="cuda" if torch.cuda.is_available() else "cpu",
+                                        top_k=None) # return all possible scores (not just top-1)
+    ext_classifier = pipeline(task="text-classification", 
+                                        # Because our model is on Hugging Face already, we can pass in the model name directly
+                                        model="kar0lina/petarda_xlm-roberta-base_ext", # link to model on HF Hub
+                                        device="cuda" if torch.cuda.is_available() else "cpu",
+                                        top_k=None) # return all possible scores (not just top-1)
+    neu_classifier = pipeline(task="text-classification", 
+                                        # Because our model is on Hugging Face already, we can pass in the model name directly
+                                        model="kar0lina/petarda_xlm-roberta-base_neu", # link to model on HF Hub
+                                        device="cuda" if torch.cuda.is_available() else "cpu",
+                                        top_k=None) # return all possible scores (not just top-1)
+    ope_classifier = pipeline(task="text-classification", 
+                                        # Because our model is on Hugging Face already, we can pass in the model name directly
+                                        model="kar0lina/petarda_xlm-roberta-base_ope", # link to model on HF Hub
+                                        device="cuda" if torch.cuda.is_available() else "cpu",
+                                        top_k=None) # return all possible scores (not just top-1)
+
+    
+    # Get outputs from pipeline (as a list of dicts)
+    outputs_agr = agr_classifier(text)[0]
+    outputs_con = con_classifier(text)[0]
+    outputs_ext = ext_classifier(text)[0]
+    outputs_neu = neu_classifier(text)[0]
+    outputs_ope = ope_classifier(text)[0]
+    print("outputs_agr: ", outputs_agr)
+    print("outputs_con: ", outputs_con)
+    print("outputs_ext: ", outputs_ext)
+    print("outputs_neu: ", outputs_neu)
+    print("outputs_ope: ", outputs_ope)
+
+    # Format output for Gradio (e.g. {"label_1": probability_1, "label_2": probability_2})
+    output_dict = {}
+    #agr
+    if outputs_agr[0]['label'] == 'POSITIVE':
+        output_dict['Agreeablenes'] = outputs_agr[0]["score"]
+    else:
+        output_dict['Agreeablenes'] = outputs_agr[1]["score"]
+
+
+    #con
+    if outputs_con[0]['label'] == 'POSITIVE':
+        output_dict['Consiousness'] = outputs_con[0]["score"]
+    else:
+        output_dict['Consiousness'] = outputs_con[1]["score"]
+
+
+    #ext
+    if outputs_ext[0]['label'] == 'POSITIVE':
+        output_dict['Extraversion'] = outputs_ext[0]["score"]
+    else:
+        output_dict['Extraversion'] = outputs_ext[1]["score"]
+
+
+    #neu
+    if outputs_neu[0]['label'] == 'POSITIVE':
+        output_dict['Neuroticism'] = outputs_neu[0]["score"]
+    else:
+        output_dict['Neuroticism'] = outputs_neu[1]["score"]
+
+
+    #ope
+    if outputs_ope[0]['label'] == 'POSITIVE':
+        output_dict['Openness'] = outputs_ope[0]["score"]
+    else:
+        output_dict['Openness'] = outputs_ope[1]["score"]
+
+
+    # output_dict = {'neu': probability_1, 'ext': probability_2, 'ope': # probability_3}
+    return output_dict
+
+# 3. Create a Gradio interface with details about our app
+description = """
+A text classifier for PErsonality Trait prediction using Ai model Roberta - Demo App. 
+
+Fine-tuned from [xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base)"""
+
+demo = gr.Interface(fn=trait_classifier, 
+             inputs="text", 
+             outputs=gr.Label(num_top_classes=2), # show top 2 classes (that's all we have)
+             title="🤯 Petarda",
+             theme="gr.themes.Ocean((primary_hue='amber', secondary_hue='cyan')",
+             description=description,
+             examples=[["I have a real problem right now... I am struggling a lot :("],
+                       ["He's such a nice, gentle man and it was great"]])
+
+# 4. Launch the interface
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+torch
+transformers