Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import pandas as pd | |
| from transformers import pipeline | |
| import re | |
| import nltk | |
| from nltk.corpus import stopwords | |
| from nltk.stem import WordNetLemmatizer | |
| # Download necessary NLTK resources | |
| nltk.download('stopwords') | |
| nltk.download('wordnet') | |
| # Initialize the zero-shot classification pipeline | |
| classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli") | |
| # Streamlit interface setup | |
| st.title("Resume-based Personality Prediction by Serikov Ayanbek") | |
| resume_text = st.text_area("Enter Resume Text Here", height=300) | |
| # Load data from Excel | |
| data = pd.read_excel("ResponseTest.xlsx") # Replace 'ResponseTest.xlsx' with your actual file name | |
| data_open = pd.read_excel("ResponseOpen.xlsx") # Replace 'ResponseTest.xlsx' with your actual file name | |
| # Preprocess text function | |
| def preprocess_text(text): | |
| text = re.sub(r'\W', ' ', str(text)) | |
| text = text.lower() | |
| text = re.sub(r'\s+[a-z]\s+', ' ', text) | |
| text = re.sub(r'^[a-z]\s+', ' ', text) | |
| text = re.sub(r'\s+', ' ', text) | |
| stop_words = set(stopwords.words('english')) | |
| lemmatizer = WordNetLemmatizer() | |
| tokens = text.split() | |
| tokens = [lemmatizer.lemmatize(word) for word in tokens if word not in stop_words] | |
| return ' '.join(tokens) | |
| # Combine relevant text columns for processing | |
| question_columns = [f'Q{i}' for i in range(1, 37)] # Adjust the range based on your data columns | |
| data['processed_text'] = data[['CV/Resume'] + question_columns].agg(lambda x: ', '.join(x), axis=1) | |
| #data['processed_text'] = data[['CV/Resume'] + question_columns].agg(lambda x: ', '.join(x), axis=1).apply(preprocess_text) | |
| #data_open['processed_text_open'] = data_open[['CV/Resume', 'Question']].agg(' '.join, axis=1).apply(preprocess_text) | |
| data_open['processed_text_open'] = data_open[['Demo_F', 'Question']].agg(' '.join, axis=1) | |
| data_open['processed_text_mopen'] = data_open[['Demo_M', 'Question']].agg(' '.join, axis=1) | |
| labels = ["Peacemaker", "Loyalist", "Achiever", "Reformer", "Individualist", "Helper", "Challenger", "Investigator", "Enthusiast"] | |
| # Prediction confidence threshold | |
| confidence_threshold = st.slider("Confidence Threshold", 0.0, 1.0, 0.5) | |
| if st.button("Predict Personality by Test"): | |
| # Function to apply predictions using dynamic labels from MAX1, MAX2, MAX3 and only return the highest scored label | |
| def get_predictions(row): | |
| custom_labels = [row['MAX1'], row['MAX2'], row['MAX3']] # Get labels from each row | |
| processed_text = row['processed_text'] | |
| result = classifier(processed_text, custom_labels) | |
| highest_score_label = result['labels'][0] # Assumes the labels are sorted by score, highest first | |
| return highest_score_label | |
| # Apply predictions across all rows | |
| data['Predicted'] = data.apply(get_predictions, axis=1) | |
| st.dataframe(data[['True_label','MAX1','MAX2','MAX3', 'Predicted']]) | |
| if st.button("Predict Personality by Open Question F"): | |
| def get_predictions(row): | |
| processed_text = row['processed_text_open'] | |
| result = classifier(processed_text, labels) | |
| highest_score_label = result['labels'][0] # Assumes the labels are sorted by score, highest first | |
| return highest_score_label | |
| # Apply predictions across all rows | |
| data_open['Predicted_F'] = data_open.apply(get_predictions, axis=1) | |
| st.dataframe(data_open[['True_label', 'Predicted_F']]) | |
| if st.button("Predict Personality by Open Question M"): | |
| def get_predictionsM(row): | |
| processed_text = row['processed_text_mopen'] | |
| result = classifier(processed_text, labels) | |
| highest_score_label = result['labels'][0] # Assumes the labels are sorted by score, highest first | |
| return highest_score_label | |
| # Apply predictions across all rows | |
| data_open['Predicted_M'] = data_open.apply(get_predictionsM, axis=1) | |
| st.dataframe(data_open[['True_label', 'Predicted_M']]) |