Upload 12 files

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+modelfile/bighealth2.keras filter=lfs diff=lfs merge=lfs -text
+modelfile/bighr2.keras filter=lfs diff=lfs merge=lfs -text
+modelfile/bigit2.keras filter=lfs diff=lfs merge=lfs -text
+modelfile/bigothers2.keras filter=lfs diff=lfs merge=lfs -text
+modelfile/bigrsales2.keras filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,211 @@
+import pickle
+import numpy as np
+import spacy
+import re
+import string
+import streamlit as st
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+
+# Abbreviations dictionary for job market
+abbreviations = {
+    "mgr": "manager",
+    "sr": "senior",
+    "jr": "junior",
+    "asst": "assistant",
+    "assoc": "associate",
+    "dept": "department",
+    "exp": "experience",
+    "hr": "human resources",
+    "acct": "account",
+    "acctg": "accounting",
+    "fin": "finance",
+    "eng": "engineer",
+    "engg": "engineering",
+    "it": "information technology",
+    "qa": "quality assurance",
+    "dev": "development",
+    "devops": "development operations",
+    "proj": "project",
+    "mktg": "marketing",
+    "biz": "business",
+    "comm": "communication",
+    "adm": "administration",
+    "sec": "secretary",
+    "exec": "executive",
+    "corp": "corporation",
+    "intl": "international",
+    "rep": "representative",
+    "mfg": "manufacturing",
+    "prod": "production",
+    "purch": "purchasing",
+    "sales": "sales",
+    "cust": "customer",
+    "svc": "service",
+    "tech": "technical",
+    "sup": "supervisor",
+    "supv": "supervision",
+    "log": "logistics",
+    "inv": "inventory",
+    "sch": "schedule",
+    "edu": "education",
+    "lang": "language",
+    "pr": "public relations",
+    "hrd": "human resources development",
+    "cfo": "chief financial officer",
+    "ceo": "chief executive officer",
+    "coo": "chief operating officer",
+    "cmo": "chief marketing officer",
+    "cto": "chief technology officer",
+    "cio": "chief information officer",
+    "pmo": "project management office",
+    "pmp": "project management professional",
+    "ba": "business analyst",
+    "bpm": "business process management",
+    "ui": "user interface",
+    "ux": "user experience",
+    "svp": "senior vice president",
+    "vp": "vice president",
+    "gm": "general manager",
+    "doe": "depends on experience",
+    "r&d": "research and development",
+    "seo": "search engine optimization",
+    "sem": "search engine marketing",
+    "smm": "social media marketing",
+    "b2b": "business to business",
+    "b2c": "business to consumer",
+    "kpi": "key performance indicator",
+    "roi": "return on investment",
+    "saas": "software as a service",
+    "paas": "platform as a service",
+    "iaas": "infrastructure as a service",
+    "crm": "customer relationship management",
+    "erp": "enterprise resource planning",
+    "sd": "software development",
+    "pm": "project manager",
+    "pa": "personal assistant",
+    "exec": "executive",
+    "fin": "finance",
+    "hrm": "human resources management",
+    "it": "information technology",
+    "pr": "public relations",
+    "qa": "quality assurance",
+    "r&d": "research and development",
+    "scm": "supply chain management",
+    "seo": "search engine optimization",
+    "smm": "social media marketing",
+    "ux": "user experience",
+    "ui": "user interface",
+    "bi": "business intelligence",
+    "dev": "development",
+    "ops": "operations"
+}
+
+
+# Load Spacy model
+nlp = spacy.load("en_core_web_sm")
+
+def expand_abbreviations(text, abbreviations):
+    for abbr, expanded in abbreviations.items():
+        text = re.sub(r'\b{}\b'.format(abbr), expanded, text)
+    return text
+
+def clean_and_preprocess(text):
+    text = expand_abbreviations(text, abbreviations)
+    text = text.lower()
+    text = re.sub(r'\d+', '', text)
+    text = text.translate(str.maketrans('', '', string.punctuation))
+    text = re.sub(r'\s+', ' ', text).strip()
+    doc = nlp(text)
+    tokens = [token.lemma_ for token in doc if token.is_alpha and not token.is_stop]
+    return ' '.join(tokens)
+
+def extract_nouns(text):
+    doc = nlp(text)
+    nouns = [token.lemma_ for token in doc if token.pos_ == "NOUN"]
+    return nouns
+
+# Define the sector options and their corresponding model and tokenizer paths
+sectors = {
+    'HR': {
+        'model': r'modelfile\bighr2.keras',
+        'tokenizer': r'tokernizer\tokenizershr.pkl'
+    },
+    'IT': {
+        'model': r'modelfile\bigit2.keras',
+        'tokenizer': r'tokernizer\tokenizersit.pkl'
+    },
+    'Sales': {
+        'model': r'modelfile\bigrsales2.keras',
+        'tokenizer': r'tokernizer\tokenizerssales.pkl'
+    },
+    'Health': {
+        'model': r'modelfile\bighealth2.keras',
+        'tokenizer': r'tokernizer\tokenizershealth.pkl'
+    },
+    'Other': {
+        'model': r'modelfile\bigothers2.keras',
+        'tokenizer': r'tokernizer\tokenizersothers.pkl'
+    }
+}
+
+# Streamlit UI
+st.title("Resume and Job Description Analyzer")
+
+st.write("Upload your resume and job description, then select the job sector to analyze how well the resume fits the job description.")
+
+# Resume input
+resume = st.text_area("Paste your Resume:", height=150)
+
+# Job description input
+job_description = st.text_area("Paste Job Description:", height=150)
+
+# Sector selection
+sector = st.selectbox("Select Sector:", list(sectors.keys()))
+
+if st.button("Analyze Resume"):
+    if resume and job_description:
+        try:
+            # Load the selected model and tokenizer
+            model_path = sectors[sector]['model']
+            tokenizer_path = sectors[sector]['tokenizer']
+
+            model = load_model(model_path)
+
+            with open(tokenizer_path, 'rb') as f:
+                tokenizers = pickle.load(f)
+
+            resume_tokenizer = tokenizers['resume_tokenizer']
+            description_tokenizer = tokenizers['description_tokenizer']
+            common_nouns_tokenizer = tokenizers['common_nouns_tokenizer']
+
+            # Preprocess the resume
+            processed_resume = clean_and_preprocess(resume)
+
+            # Preprocess the job description
+            processed_description = clean_and_preprocess(job_description)
+
+            # Convert to sequences using the resume tokenizer
+            resume_sequence = resume_tokenizer.texts_to_sequences([processed_resume])
+            resume_data_padded = pad_sequences(resume_sequence, maxlen=1500)
+
+            # Convert to sequences using the description tokenizer
+            description_sequence = description_tokenizer.texts_to_sequences([processed_description])
+            description_data_padded = pad_sequences(description_sequence, maxlen=1500)
+
+            # Extract common nouns from the resume
+            common_nouns = set(extract_nouns(processed_resume))
+            common_nouns_str = ' '.join(common_nouns)
+
+            # Convert to sequences using the common nouns tokenizer
+            common_nouns_sequence = common_nouns_tokenizer.texts_to_sequences([common_nouns_str])
+            common_nouns_data = pad_sequences(common_nouns_sequence, maxlen=10)
+
+            # Make predictions
+            prediction = model.predict([resume_data_padded, description_data_padded, common_nouns_data])
+
+            st.success(f"Your predicted ATS Score is: {prediction[0][0]:.2f}")
+        except Exception as e:
+            st.error(f"An error occurred: {e}")
+    else:
+        st.error("Please paste both your resume and job description before analyzing.")

modelfile/bighealth2.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e13d30646e87cd5126a8ce9cfae4d342bdbc9b911e77370766160ed471b8c3
+size 16911730

modelfile/bighr2.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e6dd10cbe7f909a8b822d12c6034ba32d69787d705309ff759c2ad1869aea1
+size 16412530

modelfile/bigit2.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73da88d0d26c37d70ee686f574c0b13c8417b013eb3e8adec4c77204ad5f1ba5
+size 16614130

modelfile/bigothers2.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff736f59baac8310c0cdb9753cac6b0d54f470fbfadaa7cd3687dee426846020
+size 20487730

modelfile/bigrsales2.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b55191182605377b6fc865fd8e39e5b2b31816a004ad90d165545a1a7228b9
+size 15355330

requirements.txt

@@ -0,0 +1,6 @@
+pickle
+numpy
+spacy
+string
+streamlit
+tensorflow

tokernizer/tokenizershealth.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71e617104ae224680bec66de7c645d9ed154a817c32873d61acaec8668753d1
+size 476060

tokernizer/tokenizershr.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdca68e1dcd818834d10a8579028d648e5a7dd97c668279da3b95f05bd212985
+size 456963

tokernizer/tokenizersit.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23767d74bbbd5a43ffc374c9316b1c01cff1e08f34a2476df2a319c745dc887d
+size 414524

tokernizer/tokenizersothers.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6b59669ea9a266a27522d6a13e0ac26d97f1b46b5c69cd888bbd4d78c0f85b
+size 611798

tokernizer/tokenizerssales.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c2e0e86f847720d17bdb146263a3a9ade7baee0b3767db69597876ac7f2d6d
+size 414524