Update app.py

app.py

@@ -3,115 +3,59 @@ 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
+import nltk
+from nltk.corpus import stopwords
+from tensorflow.keras.models import load_model
 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
 
+nltk.download('stopwords')
+stop_words = set(stopwords.words('english'))
 
 def cleanResume(resumeText):
-    
-    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)
+    resumeText = re.sub(r'http\S+\s*', ' ', resumeText)
+    resumeText = re.sub(r'RT|cc', ' ', resumeText)
+    resumeText = re.sub(r'#\S+', '', resumeText)
+    resumeText = re.sub(r'@\S+', ' ', resumeText)
+    resumeText = re.sub(r'[%s]' % re.escape("!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"), ' ', resumeText)
+    resumeText = re.sub(r'[^\x00-\x7f]', r' ', resumeText)
+    resumeText = re.sub(r'\s+', ' ', resumeText)
+    resumeText = ' '.join([word for word in resumeText.split() if word.lower() not in stop_words])
     return resumeText
 
-def pdf_to_text(file):
-    
-    text = extract_text(file)
-    return text
-
-def predict_category(resumes_data, selected_category,max_sequence_length):
-   
-    model = load_deeprank_model(max_sequence_length)
-
-    
-    resumes_df = pd.DataFrame(resumes_data)
-    resumes_text = resumes_df['ResumeText'].values
-
-    
-    tokenized_text = tokenizer.texts_to_sequences(resumes_text)
-
-    
-    max_sequence_length = 500  
-    padded_text = pad_sequences(tokenized_text, maxlen=max_sequence_length)
-
-    
-    predicted_probs = model.predict(padded_text)
-
-    
-    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)
-
-    
-    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(max_sequence_length):
-
-    model.load_weights('deeprank_model.h5') 
-    model = Sequential()
-    
-    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'])
-    return model
-
-def main():
-    st.title("Resume Ranking App")
-    st.text("Upload resumes and select a category to rank them.")
-
-    resumes_data = []
-    selected_category = ""
-
-    
-    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,max_sequence_length)
-            st.write(pd.DataFrame(ranks))
-
-if __name__ == '__main__':
-    
-    df = pd.read_csv('UpdatedResumeDataSet.csv')
-    df['cleaned'] = df['Resume'].apply(lambda x: cleanResume(x))
-    label = LabelEncoder()
-    df['Category'] = label.fit_transform(df['Category'])
-
-    
-    text = df['cleaned'].values
-    #text=df['Resume'].values
-    tokenizer = Tokenizer()
-    tokenizer.fit_on_texts(text)
-    vocab_size = len(tokenizer.word_index) + 1
-    num_classes = len(label.classes_)
-
-    max_sequence_length = 500
-    
-    main()
+def load_resources():
+    with open('tokenizer.pkl', 'rb') as f:
+        tokenizer = pickle.load(f)
+    with open('label_encoder.pkl', 'rb') as f:
+        label_encoder = pickle.load(f)
+    model = load_model('deeprank_model_v2.h5')
+    return tokenizer, label_encoder, model
+
+def infer(text, tokenizer, label_encoder, model):
+    cleaned_text = cleanResume(text)
+    sequence = tokenizer.texts_to_sequences([cleaned_text])
+    padded_sequence = pad_sequences(sequence, maxlen=500)
+    prediction = model.predict(padded_sequence)
+    predicted_class = label_encoder.inverse_transform([np.argmax(prediction)])
+    return predicted_class[0]
+
+st.title("Resume Category Predictor")
+
+st.write("Upload a resume text file or enter text below to predict the job category.")
+
+uploaded_file = st.file_uploader("Upload Resume (TXT file)", type=["txt"])
+user_input = st.text_area("Or paste resume text here:")
+
+if uploaded_file is not None:
+    resume_text = uploaded_file.read().decode("utf-8")
+    st.session_state["resume_text"] = resume_text
+elif user_input:
+    resume_text = user_input
+    st.session_state["resume_text"] = resume_text
+else:
+    resume_text = ""
+
+if st.button("Predict Category") and resume_text:
+    tokenizer, label_encoder, model = load_resources()
+    prediction = infer(resume_text, tokenizer, label_encoder, model)
+    st.write(f"Predicted Category: **{prediction}**")