Update app.py

app.py

@@ -1,10 +1,9 @@
 import streamlit as st
-from sentence_transformers import SentenceTransformer, InputExample, losses
+from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
 from keyphrasetransformer import KeyPhraseTransformer
-from datasets import load_dataset
-from torch.utils.data import DataLoader
-import torch
+from wordcloud import WordCloud
+import matplotlib.pyplot as plt
 
 kp = KeyPhraseTransformer()
 
@@ -19,101 +18,49 @@ def calculate_similarity(model, text1, text2):
     return cosine_similarity(embedding1, embedding2)[0][0]
 
 def generate_wordcloud(text, title):
-    # Your existing code for generating word clouds
-    pass
-
-class CustomCollate:
-    def __init__(self):
-        pass
-
-    def __call__(self, batch):
-        return batch
+    wordcloud = WordCloud(width=800, height=400, background_color='white').generate(text)
+    plt.figure(figsize=(10, 5))
+    plt.imshow(wordcloud, interpolation='bilinear')
+    plt.axis('off')
+    plt.title(title)
+    st.pyplot(plt)
 
 st.title("Resume Match Calculator")
 
 model = load_model()
-
-# Load your labeled dataset using the datasets library
-dataset = load_dataset("Unknown92/Resume_dataset")  # Replace with your actual dataset name
-
-# Access the training set
-train_data = dataset['train']
-
-# Create InputExamples from the 'Resume' column
-train_examples = []
-
-# For agility, let's use only a portion of the data
-n_examples = len(train_data) // 2
-
-for i in range(n_examples):
-    example = train_data[i]
-    resume_text = example['Resume']
-    train_examples.append(InputExample(texts=[resume_text]))
-
-# Now train_examples contains InputExample instances with 'Resume' as text
-# You can use train_examples for training your sentence embedding model
-
-# Create a DataLoader for training examples with custom collate function
-batch_size = 16
-train_dataloader = DataLoader(train_examples, shuffle=True, batch_size=batch_size, collate_fn=CustomCollate())
-
-# Create a TripletLoss instance for training
-train_loss = losses.TripletLoss(model=model)
-
-# Training loop with manual loss and accuracy calculation
-optimizer = torch.optim.AdamW(model.parameters(), lr=2e-5)
-epochs = 10  # Adjust the number of epochs as needed
-
-for epoch in range(epochs):
-    model.train()
-    total_loss = 0
-    total_batches = 0
-
-    for batch in train_dataloader:
-        optimizer.zero_grad()
-        embeddings = model.encode(batch[0]['texts'])
-        loss_value = train_loss.compute_loss(embeddings, torch.zeros_like(embeddings))
-        loss_value.backward()
-        optimizer.step()
-
-        total_loss += loss_value.item()
-        total_batches += 1
-
-    average_loss = total_loss / total_batches
-
-    # Print loss for the epoch
-    print(f"Epoch {epoch + 1}, Average Loss: {average_loss}")
-
 # Set the font size for the "Paste the Job Description" text
 st.markdown("<style>#fc1{font-size: 20px !important;}</style>", unsafe_allow_html=True)
 
 jd = st.text_area("Paste the Job Description:", height=100)
 resume = st.text_area("Paste Your the Resume:", height=100)
 
+
 if st.button("Calculate Match Score"):
     if jd and resume:
         score = calculate_similarity(model, jd, resume)
-        jp = kp.get_key_phrases(jd)
-        rp = kp.get_key_phrases(resume)
-
+        jp=kp.get_key_phrases(jd)
+        rp=kp.get_key_phrases(resume)
+         
         # Find missing keywords in rp with respect to jp
+        
         missing_keywords = set(jp) - set(rp)
 
-        # Generate word clouds for JD and Resume
+          # Generate word clouds for JD and Resume
         generate_wordcloud(' '.join(jp), 'Word Cloud for JD Keywords')
         generate_wordcloud(' '.join(rp), 'Word Cloud for Resume Keywords')
-
+        
+        # st.write(f"The match score is: {score}", )
         st.write("The match score is:")
         st.write(score)
-
-        st.write("JD Keywords:")
+        
+        st.write("JD Keywords:" )
         st.write(jp)
-
-        st.write("Resume Keywords:")
+        
+        st.write("Resume Keywords:" )
         st.write(rp)
 
-        st.write("Missing Keywords in Resume:")
+        st.write("Missing Keywords in Resume:" )
         st.write(list(missing_keywords))
-
     else:
-        st.write("Please enter both the job description and resume.")
+        st.write("Please enter both the job description and resume.", )
+