Create app.py

app.py

@@ -0,0 +1,114 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import re
+import pickle
+import pdfminer
+from pdfminer.high_level import extract_text
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Embedding, Conv1D, MaxPooling1D, LSTM, Dense, GlobalMaxPooling1D
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.utils import to_categorical
+from sklearn.preprocessing import LabelEncoder
+
+
+def cleanResume(resumeText):
+    # Your existing cleanResume function remains unchanged
+    resumeText = re.sub('http\S+\s*', ' ', resumeText)
+    resumeText = re.sub('RT|cc', ' ', resumeText)
+    resumeText = re.sub('#\S+', '', resumeText)
+    resumeText = re.sub('@\S+', '  ', resumeText)
+    resumeText = re.sub('[%s]' % re.escape("""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""), ' ', resumeText)
+    resumeText = re.sub(r'[^\x00-\x7f]',r' ', resumeText)
+    resumeText = re.sub('\s+', ' ', resumeText)
+    return resumeText
+
+def pdf_to_text(file):
+    # Use pdfminer.six to extract text from the PDF file
+    text = extract_text(file)
+    return text
+
+def predict_category(resumes_data, selected_category):
+    # Load the trained DeepRank model
+    model = load_deeprank_model()
+
+    # Process the resumes data
+    resumes_df = pd.DataFrame(resumes_data)
+    resumes_text = resumes_df['ResumeText'].values
+
+    # Tokenize the text and convert to sequences
+    tokenized_text = tokenizer.texts_to_sequences(resumes_text)
+
+    # Pad sequences to have the same length
+    max_sequence_length = 500  # Assuming maximum sequence length of 500 words
+    padded_text = pad_sequences(tokenized_text, maxlen=max_sequence_length)
+
+    # Make predictions
+    predicted_probs = model.predict(padded_text)
+
+    # Assign probabilities to respective job categories
+    for i, category in enumerate(label.classes_):
+        resumes_df[category] = predicted_probs[:, i]
+
+    resumes_df_sorted = resumes_df.sort_values(by=selected_category, ascending=False)
+
+    # Get the ranks for the selected category
+    ranks = []
+    for rank, (idx, row) in enumerate(resumes_df_sorted.iterrows()):
+        rank = rank + 1
+        file_name = row['FileName']
+        ranks.append({'Rank': rank, 'FileName': file_name})
+
+    return ranks
+
+def load_deeprank_model():
+    # Load the saved DeepRank model
+    model = Sequential()
+    # Add layers to the model (example architecture, adjust as needed)
+    model.add(Embedding(input_dim=vocab_size, output_dim=128, input_length=max_sequence_length))
+    model.add(Conv1D(filters=128, kernel_size=5, activation='relu'))
+    model.add(MaxPooling1D(pool_size=2))
+    model.add(LSTM(64))
+    model.add(Dense(num_classes, activation='softmax'))
+    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
+    model.load_weights('deeprank_model.h5')  # Replace 'deeprank_model.h5' with your saved model file
+    return model
+
+def main():
+    st.title("Resume Ranking App")
+    st.text("Upload resumes and select a category to rank them.")
+
+    resumes_data = []
+    selected_category = ""
+
+    # Handle multiple file uploads
+    files = st.file_uploader("Upload resumes", type=["pdf"], accept_multiple_files=True)
+    if files:
+        for file in files:
+            text = cleanResume(pdf_to_text(file))
+            resumes_data.append({'ResumeText': text, 'FileName': file.name})
+        selected_category = st.selectbox("Select a category to rank by", label.classes_)
+
+    if st.button("Rank Resumes"):
+        if not resumes_data or not selected_category:
+            st.warning("Please upload resumes and select a category to continue.")
+        else:
+            ranks = predict_category(resumes_data, selected_category)
+            st.write(pd.DataFrame(ranks))
+
+if __name__ == '__main__':
+    # Load label encoder and tokenizer
+    df = pd.read_csv('UpdatedResumeDataSet.csv')
+    df['cleaned'] = df['Resume'].apply(lambda x: cleanResume(x))
+    label = LabelEncoder()
+    df['Category'] = label.fit_transform(df['Category'])
+
+    # Tokenize text and get vocabulary size and number of classes
+    text = df['cleaned'].values
+    tokenizer = Tokenizer()
+    tokenizer.fit_on_texts(text)
+    vocab_size = len(tokenizer.word_index) + 1
+    num_classes = len(label.classes_)
+
+    main()