Add files via upload

added code from hugging face to github

Dockerfile

@@ -0,0 +1,25 @@
+FROM python:3.9
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    software-properties-common \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set the working directory
+WORKDIR /code
+
+RUN mkdir /.cache && chmod 777 /.cache
+
+# Copy the requirements file
+COPY ./requirements.txt /code/requirements.txt
+COPY ./weights-roberta-base.h5 /code/weights-roberta-base.h5
+
+# Install Python dependencies
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Copy the application code
+COPY . /code/
+
+# Set the command to run the FastAPI application
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -0,0 +1,10 @@
+---
+title: Personality Assesment
+emoji: 🏢
+colorFrom: blue
+colorTo: indigo
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,15 @@
+import gradio as gr
+from model_utils import predict_personality
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict_personality,
+    inputs=gr.Textbox(lines=5, label="Enter text for personality prediction"),
+    outputs=gr.Label(num_top_classes=5, label="Personality Traits"),
+    title="Personality Prediction with RoBERTa",
+    description="Enter some text to predict personality traits using a fine-tuned RoBERTa model."
+)
+
+# Launch the interface
+if __name__ == "__main__":
+    iface.launch()

main.py

@@ -0,0 +1,61 @@
+# API/main.py
+
+# main.py (in the root directory)
+
+import sys
+import os
+from model_utils import predict_personality
+from fastapi import FastAPI
+
+app = FastAPI()
+
+@app.get("/")
+async def root():
+    return {"message": "Personality Assessment API is running"}
+
+@app.get("/predict")
+async def predict_personality_get(text: str):
+    try:
+        predictions = predict_personality(text)
+        return {"predictions": predictions}
+    except NameError:
+        return {"error": "predict_personality function not available"}
+
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)
+
+
+
+
+""" from fastapi import FastAPI, Request
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+app = FastAPI()
+
+# Load the model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("Minej/bert-base-personality")
+model = AutoModelForSequenceClassification.from_pretrained("Minej/bert-base-personality")
+
+# Define the personality trait labels
+labels = ["Extroversion", "Neuroticism", "Agreeableness", "Conscientiousness", "Openness"]
+
+# Function to predict personality traits
+def predict_personality(text):
+    inputs = tokenizer(text, return_tensors="pt")
+    outputs = model(**inputs)[0]
+    probabilities = torch.softmax(outputs, dim=1)
+    predictions = [{"trait": label, "score": float(prob)} for label, prob in zip(labels, probabilities[0])]
+    return predictions
+
+# Root path handler
+@app.get("/")
+async def root():
+    return {"message": "Personality Assessment API is running"}
+
+@app.get("/predict")
+async def predict_personality_get(text: str):
+    predictions = predict_personality(text)
+    return {"predictions": predictions} """

model_utils.py

@@ -0,0 +1,42 @@
+# model_utils.py
+
+import os
+import tensorflow as tf
+from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
+
+# Define the personality trait labels
+traits = ['cAGR', 'cCON', 'cEXT', 'cOPN', 'cNEU']
+
+def load_model_and_weights():
+    model_name = "roberta-base"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = TFAutoModelForSequenceClassification.from_pretrained(
+        model_name,
+        num_labels=len(traits),
+        problem_type="multi_label_classification"
+    )
+
+    # Load custom weights
+    weights_path = os.path.join(os.getcwd(), 'weights-roberta-base.h5')
+    if os.path.exists(weights_path):
+        try:
+            model.load_weights(weights_path)
+            print("Custom weights loaded successfully.")
+        except Exception as e:
+            print(f"Error loading weights: {str(e)}")
+            print("Using default weights.")
+    else:
+        print(f"Warning: Custom weights file not found at {weights_path}")
+        print("Using default weights.")
+
+    return tokenizer, model
+
+# Load the model and tokenizer
+tokenizer, model = load_model_and_weights()
+
+def predict_personality(text):
+    inputs = tokenizer(text, return_tensors="tf", truncation=True, padding=True, max_length=512)
+    outputs = model(inputs)
+    probabilities = tf.nn.sigmoid(outputs.logits)[0]  # Using sigmoid for multi-label
+    predictions = [{"trait": trait, "score": float(prob)} for trait, prob in zip(traits, probabilities)]
+    return predictions

requirements.txt

@@ -0,0 +1,11 @@
+fastapi==0.92.0
+uvicorn==0.20.0
+transformers==4.27.4
+torch==1.13.1
+gradio==3.23.0
+numpy==1.21.0
+pandas==1.3.0
+scikit-learn==0.24.2
+wget
+requests
+tensorflow