mental-health-posts-classifier / mental_health_model.py
farah1's picture
Create mental_health_model.py
cbefb30 verified
import openai
from rank_bm25 import BM25Okapi
class MentalHealthClassifier:
def __init__(self, train_data):
# Tokenize the training data for BM25
self.tokenized_train = [doc.split() for doc in train_data["text"]]
self.bm25 = BM25Okapi(self.tokenized_train)
self.train_data = train_data
def classify_text(self, api_key, input_text, k=20):
# Set the OpenAI API key
openai.api_key = api_key
if not openai.api_key:
return "Error: OpenAI API key is not set."
# Tokenize input text
tokenized_text = input_text.split()
# Get top-k similar examples using BM25
scores = self.bm25.get_scores(tokenized_text)
top_k_indices = sorted(range(len(scores)), key=lambda i: scores[i], reverse=True)[:k]
# Build examples for the prompt
examples = "\n".join(
f"Example {i+1}:\nText: {self.train_data.iloc[idx]['text']}\nClassification: "
f"Stress={self.train_data.iloc[idx]['Ground_Truth_Stress']}, "
f"Anxiety={self.train_data.iloc[idx]['Ground_Truth_Anxiety']}, "
f"Depression={self.train_data.iloc[idx]['Ground_Truth_Depression']}, "
f"Other={self.train_data.iloc[idx]['Ground_Truth_Other_binary']}\n"
for i, idx in enumerate(top_k_indices)
)
# Construct OpenAI prompt
prompt = f"""
You are a mental health specialist. Analyze the provided text and classify it into one or more of the following categories: Stress, Anxiety, Depression, or Other.
Respond with a single category that best matches the content: Stress, Anxiety, Depression, or Other.
Here is the text to classify:
"{input_text}"
### Examples:
{examples}
"""
try:
response = openai.ChatCompletion.create(
messages=[
{"role": "system", "content": "You are a mental health specialist."},
{"role": "user", "content": prompt},
],
model="gpt-4",
temperature=0,
)
content = response.choices[0].message.content.strip()
return content # Return the label directly
except Exception as e:
return f"Error: {e}"