Update app.py

app.py

@@ -1,9 +1,12 @@
 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')
 
@@ -13,9 +16,24 @@ classifier = pipeline("zero-shot-classification", model="Fralet/personality")
 # Define the candidate labels according to the Enneagram types
 default_labels = ["Peacemaker", "Loyalist", "Achiever", "Reformer", "Individualist", "Helper", "Challenger", "Investigator", "Enthusiast"]
 
-# Streamlit interface
+# 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.xls")  # Replace 'your_excel_file.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)
 
 # User-defined labels option
 user_labels = st.text_input("Enter custom labels separated by comma (optional)")
@@ -25,30 +43,15 @@ labels = user_labels.split(',') if user_labels else default_labels
 confidence_threshold = st.slider("Confidence Threshold", 0.0, 1.0, 0.5)
 
 if st.button("Predict Personality"):
-    # Text Preprocessing
-    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)
-
-    processed_text = preprocess_text(resume_text)
+    # Combine relevant text columns
+    question_columns = [f'Q{i}' for i in range(1, 37)]  # Adjust range if there are more or fewer question columns
+    data['combined_text'] = data[['CV/Resume'] + question_columns].agg(' '.join, axis=1)
+    data['processed_text'] = data['combined_text'].apply(preprocess_text)
     
-    # Make prediction
-    result = classifier(processed_text, labels)
+    # Make predictions
+    predictions = data['processed_text'].apply(lambda x: classifier(x, labels))
     
-    # Display the results
-    st.write("Predictions (above confidence threshold):")
-    displayed = False
-    for label, score in zip(result['labels'], result['scores']):
-        if score >= confidence_threshold:
-            st.write(f"{label}: {score*100:.2f}%")
-            displayed = True
-    if not displayed:
-        st.write("No predictions exceed the confidence threshold.")
+    # Extract and display predictions
+    data['predicted_labels'] = predictions.apply(lambda x: [label for label, score in zip(x['labels'], x['scores']) if score >= confidence_threshold])
+    st.dataframe(data[['True_label', 'Predicted', 'predicted_labels']])
+