Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -9,7 +9,7 @@ import re
|
|
9 |
import pandas as pd
|
10 |
from functools import lru_cache
|
11 |
|
12 |
-
#
|
13 |
try:
|
14 |
from transformers import pipeline
|
15 |
has_pipeline = True
|
@@ -20,21 +20,11 @@ except ImportError:
|
|
20 |
st.warning("Using basic transformers functionality instead of pipeline API")
|
21 |
|
22 |
# Set page title and hide sidebar
|
23 |
-
st.set_page_config(
|
24 |
-
|
25 |
-
initial_sidebar_state="collapsed"
|
26 |
-
)
|
27 |
-
|
28 |
-
# Hide sidebar completely with custom CSS
|
29 |
-
st.markdown("""
|
30 |
-
<style>
|
31 |
-
[data-testid="collapsedControl"] {display: none;}
|
32 |
-
section[data-testid="stSidebar"] {display: none;}
|
33 |
-
</style>
|
34 |
-
""", unsafe_allow_html=True)
|
35 |
|
36 |
#####################################
|
37 |
-
# Preload Models
|
38 |
#####################################
|
39 |
@st.cache_resource(show_spinner=True)
|
40 |
def load_models():
|
@@ -44,107 +34,67 @@ def load_models():
|
|
44 |
|
45 |
# Load summarization model
|
46 |
if has_pipeline:
|
47 |
-
|
48 |
-
models['summarizer'] = pipeline(
|
49 |
-
"summarization",
|
50 |
-
model="Falconsai/text_summarization",
|
51 |
-
max_length=100,
|
52 |
-
truncation=True
|
53 |
-
)
|
54 |
else:
|
55 |
-
# Fall back to basic model loading using the updated summarization model
|
56 |
try:
|
57 |
models['summarizer_model'] = AutoModelForSeq2SeqLM.from_pretrained("Falconsai/text_summarization")
|
58 |
models['summarizer_tokenizer'] = AutoTokenizer.from_pretrained("Falconsai/text_summarization")
|
59 |
except Exception as e:
|
60 |
st.error(f"Error loading summarization model: {e}")
|
61 |
-
models['summarizer_model'] = None
|
62 |
-
models['summarizer_tokenizer'] = None
|
63 |
|
64 |
-
# Load
|
65 |
if has_pipeline:
|
66 |
-
|
67 |
-
models['evaluator'] = pipeline(
|
68 |
-
"sentiment-analysis",
|
69 |
-
model="CR7CAD/RobertaFinetuned"
|
70 |
-
)
|
71 |
else:
|
72 |
-
# Fall back to basic model loading using the updated evaluation model
|
73 |
try:
|
74 |
-
models['evaluator_model'] = AutoModelForSequenceClassification.from_pretrained(
|
75 |
-
|
76 |
-
)
|
77 |
-
models['evaluator_tokenizer'] = AutoTokenizer.from_pretrained(
|
78 |
-
"CR7CAD/RobertaFinetuned"
|
79 |
-
)
|
80 |
except Exception as e:
|
81 |
st.error(f"Error loading sentiment model: {e}")
|
82 |
-
models['evaluator_model'] = None
|
83 |
-
models['evaluator_tokenizer'] = None
|
84 |
|
85 |
return models
|
86 |
|
87 |
-
# Custom text summarization function that works with or without pipeline
|
88 |
def summarize_text(text, models, max_length=100):
|
89 |
-
"""Summarize text using available models"""
|
90 |
# Truncate input to prevent issues with long texts
|
91 |
-
input_text = text[:1024]
|
92 |
|
|
|
93 |
if has_pipeline and 'summarizer' in models:
|
94 |
-
# Use pipeline if available
|
95 |
try:
|
96 |
-
|
97 |
-
return summary
|
98 |
except Exception as e:
|
99 |
st.warning(f"Error in pipeline summarization: {e}")
|
100 |
|
101 |
-
#
|
102 |
if 'summarizer_model' in models and 'summarizer_tokenizer' in models and models['summarizer_model']:
|
103 |
try:
|
104 |
tokenizer = models['summarizer_tokenizer']
|
105 |
model = models['summarizer_model']
|
106 |
-
|
107 |
-
# Prepare inputs
|
108 |
inputs = tokenizer(input_text, return_tensors="pt", truncation=True, max_length=1024)
|
109 |
-
|
110 |
-
|
111 |
-
summary_ids = model.generate(
|
112 |
-
inputs.input_ids,
|
113 |
-
max_length=max_length,
|
114 |
-
min_length=30,
|
115 |
-
num_beams=4,
|
116 |
-
early_stopping=True
|
117 |
-
)
|
118 |
-
|
119 |
-
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
|
120 |
-
return summary
|
121 |
except Exception as e:
|
122 |
st.warning(f"Error in manual summarization: {e}")
|
123 |
|
124 |
-
#
|
125 |
return basic_summarize(text, max_length)
|
126 |
|
127 |
-
# Basic text summarization as last fallback
|
128 |
def basic_summarize(text, max_length=100):
|
129 |
-
"""Basic text summarization
|
130 |
-
# Split into sentences
|
131 |
sentences = re.split(r'(?<!\w\.\w.)(?<![A-Z][a-z]\.)(?<=\.|\?)\s', text)
|
132 |
|
133 |
-
# Score
|
134 |
scored_sentences = []
|
135 |
for i, sentence in enumerate(sentences):
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
# Simple scoring: earlier sentences get higher scores, penalize very long sentences
|
141 |
-
score = 1.0 / (i + 1) - (0.01 * max(0, len(sentence.split()) - 20))
|
142 |
-
scored_sentences.append((score, sentence))
|
143 |
|
144 |
-
#
|
145 |
scored_sentences.sort(reverse=True)
|
146 |
-
|
147 |
-
# Get top sentences until we reach max_length
|
148 |
summary_sentences = []
|
149 |
current_length = 0
|
150 |
|
@@ -155,183 +105,109 @@ def basic_summarize(text, max_length=100):
|
|
155 |
else:
|
156 |
break
|
157 |
|
158 |
-
#
|
159 |
if summary_sentences:
|
160 |
-
original_order = []
|
161 |
-
for sentence in summary_sentences:
|
162 |
-
original_order.append((sentences.index(sentence), sentence))
|
163 |
original_order.sort()
|
164 |
summary_sentences = [s for _, s in original_order]
|
165 |
|
166 |
-
|
167 |
-
summary = " ".join(summary_sentences)
|
168 |
-
return summary
|
169 |
-
|
170 |
-
# Modified job fit evaluation function that uses a direct scoring approach
|
171 |
-
def evaluate_job_fit(resume_summary, job_requirements, models):
|
172 |
-
"""
|
173 |
-
Use a more direct method to evaluate job fit, rather than relying solely on sentiment analysis
|
174 |
-
"""
|
175 |
-
start_time = time.time()
|
176 |
-
|
177 |
-
# Extract basic information for context
|
178 |
-
required_skills = job_requirements["required_skills"]
|
179 |
-
years_required = job_requirements["years_experience"]
|
180 |
-
job_title = job_requirements["title"]
|
181 |
-
job_summary = job_requirements["summary"]
|
182 |
-
|
183 |
-
# Extract skills from resume
|
184 |
-
skills_mentioned = extract_skills(resume_summary)
|
185 |
-
|
186 |
-
# Calculate skill match percentage
|
187 |
-
matching_skills = [skill for skill in required_skills if skill in skills_mentioned]
|
188 |
-
skill_match_percentage = len(matching_skills) / len(required_skills) if required_skills else 0
|
189 |
-
|
190 |
-
# Extract experience level from resume
|
191 |
-
experience_pattern = r'(\d+)\+?\s*years?\s*(?:of)?\s*experience'
|
192 |
-
experience_match = re.search(experience_pattern, resume_summary, re.IGNORECASE)
|
193 |
-
years_experience = 0
|
194 |
-
if experience_match:
|
195 |
-
try:
|
196 |
-
years_experience = int(experience_match.group(1))
|
197 |
-
except:
|
198 |
-
years_experience = 0
|
199 |
-
|
200 |
-
# Experience match
|
201 |
-
exp_match_ratio = min(1.0, years_experience / max(1, years_required)) if years_required > 0 else 0.5
|
202 |
-
|
203 |
-
# Check job title match
|
204 |
-
job_title_lower = job_title.lower()
|
205 |
-
title_match = 0
|
206 |
-
|
207 |
-
# Look for job title words in resume
|
208 |
-
title_words = [word for word in job_title_lower.split() if len(word) > 3]
|
209 |
-
title_matches = sum(1 for word in title_words if word in resume_summary.lower())
|
210 |
-
title_match = title_matches / len(title_words) if title_words else 0
|
211 |
-
|
212 |
-
# Calculate scores for each dimension
|
213 |
-
skill_score = min(2, skill_match_percentage * 3) # 0-2 scale
|
214 |
-
exp_score = min(2, exp_match_ratio * 2) # 0-2 scale
|
215 |
-
title_score = min(2, title_match * 2) # 0-2 scale
|
216 |
-
|
217 |
-
# Extract name, age, industry from resume summary
|
218 |
-
name_match = re.search(r'Name:\s*(.*?)(?=\n|\Z)', resume_summary)
|
219 |
-
name = name_match.group(1).strip() if name_match else "The candidate"
|
220 |
-
|
221 |
-
age_match = re.search(r'Age:\s*(.*?)(?=\n|\Z)', resume_summary)
|
222 |
-
age = age_match.group(1).strip() if age_match else "unspecified age"
|
223 |
-
|
224 |
-
industry_match = re.search(r'Expected Industry:\s*(.*?)(?=\n|\Z)', resume_summary)
|
225 |
-
industry = industry_match.group(1).strip() if industry_match else "unspecified industry"
|
226 |
-
|
227 |
-
# Calculate weighted final score
|
228 |
-
# Skills: 50%, Experience: 30%, Title match: 20%
|
229 |
-
weighted_score = (skill_score * 0.5) + (exp_score * 0.3) + (title_score * 0.2)
|
230 |
-
|
231 |
-
# Convert to integer score (0-2)
|
232 |
-
if weighted_score >= 1.5:
|
233 |
-
fit_score = 2 # Good fit
|
234 |
-
elif weighted_score >= 0.8:
|
235 |
-
fit_score = 1 # Potential fit
|
236 |
-
else:
|
237 |
-
fit_score = 0 # Not a fit
|
238 |
-
|
239 |
-
# Generate assessment text based on score
|
240 |
-
missing_skills = [skill for skill in required_skills if skill not in skills_mentioned]
|
241 |
-
|
242 |
-
if fit_score == 2:
|
243 |
-
fit_assessment = f"{fit_score}: GOOD FIT - {name} demonstrates strong alignment with the {job_title} position. Their background in {industry} and professional experience appear well-suited for this role's requirements. The technical expertise matches what the position demands."
|
244 |
-
elif fit_score == 1:
|
245 |
-
fit_assessment = f"{fit_score}: POTENTIAL FIT - {name} shows potential for the {job_title} role with some relevant experience, though there are gaps in certain technical areas. Their {industry} background provides partial alignment with the position requirements. Additional training might be needed in {', '.join(missing_skills[:2])} if pursuing this opportunity."
|
246 |
-
else:
|
247 |
-
fit_assessment = f"{fit_score}: NO FIT - {name}'s current background shows limited alignment with this {job_title} position. Their experience level and technical background differ significantly from the role requirements. A position better matching their {industry} expertise might be more suitable."
|
248 |
-
|
249 |
-
execution_time = time.time() - start_time
|
250 |
-
|
251 |
-
return fit_assessment, fit_score, execution_time
|
252 |
|
253 |
#####################################
|
254 |
-
#
|
255 |
#####################################
|
256 |
@st.cache_data(show_spinner=False)
|
257 |
def extract_text_from_file(file_obj):
|
258 |
-
"""
|
259 |
-
Extract text from .docx and .doc files.
|
260 |
-
Returns the extracted text or an error message if extraction fails.
|
261 |
-
"""
|
262 |
filename = file_obj.name
|
263 |
ext = os.path.splitext(filename)[1].lower()
|
264 |
-
|
265 |
-
|
266 |
if ext == ".docx":
|
267 |
try:
|
268 |
document = docx.Document(file_obj)
|
269 |
text = "\n".join(para.text for para in document.paragraphs if para.text.strip())
|
270 |
except Exception as e:
|
271 |
-
|
272 |
elif ext == ".doc":
|
273 |
try:
|
274 |
-
# For .doc files, we need to save to a temp file
|
275 |
with tempfile.NamedTemporaryFile(delete=False, suffix='.doc') as temp_file:
|
276 |
temp_file.write(file_obj.getvalue())
|
277 |
temp_path = temp_file.name
|
278 |
-
|
279 |
-
|
280 |
-
try:
|
281 |
-
text = docx2txt.process(temp_path)
|
282 |
-
except Exception:
|
283 |
-
text = "Could not process .doc file. Please convert to .docx format."
|
284 |
-
|
285 |
-
# Clean up temp file
|
286 |
os.unlink(temp_path)
|
287 |
except Exception as e:
|
288 |
-
|
289 |
elif ext == ".txt":
|
290 |
try:
|
291 |
text = file_obj.getvalue().decode("utf-8")
|
292 |
except Exception as e:
|
293 |
-
|
294 |
else:
|
295 |
-
|
296 |
|
297 |
-
# Limit text size for faster processing
|
298 |
return text[:15000] if text else text
|
299 |
|
300 |
-
|
301 |
-
|
302 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
303 |
|
304 |
-
# Extract age from resume
|
305 |
def extract_age(text):
|
306 |
"""Extract candidate age from resume text"""
|
307 |
-
# Simplified: just check a few common patterns
|
308 |
age_patterns = [
|
309 |
r'age:?\s*(\d{1,2})',
|
310 |
r'(\d{1,2})\s*years\s*old',
|
311 |
-
r'dob:.*(\d{4})',
|
312 |
-
r'date of birth:.*(\d{4})'
|
313 |
]
|
314 |
|
315 |
text_lower = text.lower()
|
316 |
for pattern in age_patterns:
|
317 |
matches = re.search(pattern, text_lower)
|
318 |
if matches:
|
319 |
-
#
|
320 |
-
if len(matches.group(1)) == 4:
|
321 |
try:
|
322 |
-
|
323 |
-
current_year = 2025 # Current year
|
324 |
-
return str(current_year - birth_year)
|
325 |
except:
|
326 |
pass
|
327 |
return matches.group(1)
|
328 |
|
329 |
return "Not specified"
|
330 |
|
331 |
-
# Extract industry preference
|
332 |
def extract_industry(text):
|
333 |
"""Extract expected job industry from resume"""
|
334 |
-
# Common industry keywords
|
335 |
industry_keywords = {
|
336 |
"Technology": ["software", "programming", "developer", "IT", "tech", "computer", "digital"],
|
337 |
"Finance": ["banking", "financial", "accounting", "finance", "analyst"],
|
@@ -346,23 +222,13 @@ def extract_industry(text):
|
|
346 |
}
|
347 |
|
348 |
text_lower = text.lower()
|
349 |
-
industry_counts = {
|
350 |
-
|
351 |
-
for industry, keywords in industry_keywords.items():
|
352 |
-
count = sum(text_lower.count(keyword.lower()) for keyword in keywords)
|
353 |
-
if count > 0:
|
354 |
-
industry_counts[industry] = count
|
355 |
-
|
356 |
-
if industry_counts:
|
357 |
-
# Return the industry with the highest keyword count
|
358 |
-
return max(industry_counts.items(), key=lambda x: x[1])[0]
|
359 |
|
360 |
-
return "Not clearly specified"
|
361 |
|
362 |
-
# Extract job position preference
|
363 |
def extract_job_position(text):
|
364 |
"""Extract expected job position from resume"""
|
365 |
-
# Look for objective or summary section
|
366 |
objective_patterns = [
|
367 |
r'objective:?\s*(.*?)(?=\n\n|\n\w+:|\Z)',
|
368 |
r'career\s*objective:?\s*(.*?)(?=\n\n|\n\w+:|\Z)',
|
@@ -376,28 +242,21 @@ def extract_job_position(text):
|
|
376 |
match = re.search(pattern, text_lower, re.IGNORECASE | re.DOTALL)
|
377 |
if match:
|
378 |
objective_text = match.group(1).strip()
|
379 |
-
# Look for job titles in the objective
|
380 |
job_titles = ["developer", "engineer", "analyst", "manager", "director", "specialist",
|
381 |
"coordinator", "consultant", "designer", "architect", "administrator"]
|
382 |
|
383 |
for title in job_titles:
|
384 |
if title in objective_text:
|
385 |
-
# Try to get the full title with context
|
386 |
title_pattern = r'(?:a|an)?\s*(\w+\s+' + title + r'|\w+\s+\w+\s+' + title + r')'
|
387 |
title_match = re.search(title_pattern, objective_text)
|
388 |
if title_match:
|
389 |
return title_match.group(1).strip().title()
|
390 |
return title.title()
|
391 |
|
392 |
-
# If no specific title found but we have objective text, return a summary
|
393 |
if len(objective_text) > 10:
|
394 |
-
# Truncate and clean up objective
|
395 |
words = objective_text.split()
|
396 |
-
if len(words) > 10
|
397 |
-
return " ".join(words[:10]).title() + "..."
|
398 |
-
return objective_text.title()
|
399 |
|
400 |
-
# Check current/most recent job title
|
401 |
job_patterns = [
|
402 |
r'experience:.*?(\w+\s+\w+(?:\s+\w+)?)(?=\s*at|\s*\(|\s*-|\s*,|\s*\d{4}|\n)',
|
403 |
r'(\w+\s+\w+(?:\s+\w+)?)\s*\(\s*current\s*\)',
|
@@ -411,64 +270,11 @@ def extract_job_position(text):
|
|
411 |
|
412 |
return "Not explicitly stated"
|
413 |
|
414 |
-
# Extract name
|
415 |
-
@lru_cache(maxsize=32)
|
416 |
-
def extract_name(text_start):
|
417 |
-
"""Extract candidate name from the beginning of resume text"""
|
418 |
-
# Only use the first 500 characters to speed up processing
|
419 |
-
lines = text_start.split('\n')
|
420 |
-
|
421 |
-
# Check first few non-empty lines for potential names
|
422 |
-
potential_name_lines = [line.strip() for line in lines[:5] if line.strip()]
|
423 |
-
|
424 |
-
if potential_name_lines:
|
425 |
-
# First line is often the name if it's short and doesn't contain common headers
|
426 |
-
first_line = potential_name_lines[0]
|
427 |
-
if 5 <= len(first_line) <= 40 and not any(x in first_line.lower() for x in ["resume", "cv", "curriculum", "vitae", "profile"]):
|
428 |
-
return first_line
|
429 |
-
|
430 |
-
# Look for lines that might contain a name
|
431 |
-
for line in potential_name_lines[:3]:
|
432 |
-
if len(line.split()) <= 4 and not any(x in line.lower() for x in ["address", "phone", "email", "resume", "cv"]):
|
433 |
-
return line
|
434 |
-
|
435 |
-
return "Unknown (please extract from resume)"
|
436 |
-
|
437 |
-
# Extract skills
|
438 |
-
def extract_skills(text):
|
439 |
-
"""Extract key skills from the resume"""
|
440 |
-
# Common skill categories - reduced keyword list for speed
|
441 |
-
skill_categories = {
|
442 |
-
"Programming": ["Python", "Java", "JavaScript", "HTML", "CSS", "SQL", "C++", "C#", "Go", "React", "Angular", "Vue", "Node.js"],
|
443 |
-
"Data Science": ["Machine Learning", "Data Analysis", "Statistics", "TensorFlow", "PyTorch", "AI", "Algorithms", "NLP", "Deep Learning"],
|
444 |
-
"Database": ["SQL", "MySQL", "MongoDB", "Database", "NoSQL", "PostgreSQL", "Oracle", "Redis"],
|
445 |
-
"Web Development": ["React", "Angular", "Node.js", "Frontend", "Backend", "Full-Stack", "REST API", "GraphQL"],
|
446 |
-
"Software Development": ["Agile", "Scrum", "Git", "DevOps", "Docker", "System Design", "CI/CD", "Jenkins"],
|
447 |
-
"Cloud": ["AWS", "Azure", "Google Cloud", "Cloud Computing", "Lambda", "S3", "EC2"],
|
448 |
-
"Security": ["Cybersecurity", "Network Security", "Encryption", "Security"],
|
449 |
-
"Business": ["Project Management", "Business Analysis", "Leadership", "Teamwork", "Agile", "Scrum"],
|
450 |
-
"Design": ["UX/UI", "User Experience", "Design Thinking", "Adobe", "Figma"]
|
451 |
-
}
|
452 |
-
|
453 |
-
# Process everything at once
|
454 |
-
text_lower = text.lower()
|
455 |
-
|
456 |
-
# Skills extraction
|
457 |
-
all_skills = []
|
458 |
-
for category, skills in skill_categories.items():
|
459 |
-
for skill in skills:
|
460 |
-
if skill.lower() in text_lower:
|
461 |
-
all_skills.append(skill)
|
462 |
-
|
463 |
-
return all_skills
|
464 |
-
|
465 |
#####################################
|
466 |
-
#
|
467 |
#####################################
|
468 |
def summarize_resume_text(resume_text, models):
|
469 |
-
"""
|
470 |
-
Generates a structured summary of the resume text with the critical information
|
471 |
-
"""
|
472 |
start_time = time.time()
|
473 |
|
474 |
# Extract critical information
|
@@ -478,27 +284,17 @@ def summarize_resume_text(resume_text, models):
|
|
478 |
job_position = extract_job_position(resume_text)
|
479 |
skills = extract_skills(resume_text)
|
480 |
|
481 |
-
# Generate overall summary
|
482 |
try:
|
483 |
if has_pipeline and 'summarizer' in models:
|
484 |
-
|
485 |
-
truncated_text = resume_text[:2000] # Limit input to 2000 chars
|
486 |
-
|
487 |
-
# Use pipeline model to generate the summary
|
488 |
-
model_summary = models['summarizer'](
|
489 |
-
truncated_text,
|
490 |
-
max_length=100,
|
491 |
-
min_length=30,
|
492 |
-
do_sample=False
|
493 |
-
)[0]['summary_text']
|
494 |
else:
|
495 |
-
# Fallback if pipeline is not available
|
496 |
model_summary = summarize_text(resume_text, models, max_length=100)
|
497 |
except Exception as e:
|
498 |
st.warning(f"Error in resume summarization: {e}")
|
499 |
model_summary = "Error generating summary. Please check the original resume."
|
500 |
|
501 |
-
# Format the structured summary
|
502 |
formatted_summary = f"Name: {name}\n\n"
|
503 |
formatted_summary += f"Age: {age}\n\n"
|
504 |
formatted_summary += f"Expected Industry: {industry}\n\n"
|
@@ -506,33 +302,18 @@ def summarize_resume_text(resume_text, models):
|
|
506 |
formatted_summary += f"Skills: {', '.join(skills)}\n\n"
|
507 |
formatted_summary += f"Summary: {model_summary}"
|
508 |
|
509 |
-
|
510 |
-
|
511 |
-
return formatted_summary, execution_time
|
512 |
|
513 |
-
#####################################
|
514 |
-
# Function: Extract Job Requirements
|
515 |
-
#####################################
|
516 |
def extract_job_requirements(job_description, models):
|
517 |
-
"""
|
518 |
-
|
519 |
-
"""
|
520 |
-
# Common technical skills to look for - expanded list for better matching
|
521 |
tech_skills = [
|
522 |
-
"Python", "Java", "C++", "JavaScript", "TypeScript", "
|
523 |
-
"
|
524 |
-
"
|
525 |
-
"
|
526 |
-
"MySQL", "PostgreSQL", "MongoDB", "Redis", "Elasticsearch", "DynamoDB", "Cassandra", "Oracle",
|
527 |
-
"Project Management", "Agile", "Scrum", "UX/UI", "Design", "Leadership", "Team Management",
|
528 |
-
"Communication Skills", "Problem Solving", "Critical Thinking", "Blockchain", "Information Security",
|
529 |
-
"Networking", "Linux", "Windows Server", "Excel", "PowerPoint", "Word", "Tableau", "Power BI", "R",
|
530 |
-
"SPSS", "SAS", "Spark", "Hadoop", "JIRA", "Confluence", "Git", "SVN", "Testing", "QA", "DevOps",
|
531 |
-
"Full Stack", "Mobile Development", "Android", "iOS", "React Native", "Flutter", "SEO", "Marketing",
|
532 |
-
"Sales", "Customer Service", "Business Analysis", "Data Analysis", "Accounting", "Finance"
|
533 |
]
|
534 |
|
535 |
-
# Clean the text for processing
|
536 |
clean_job_text = job_description.lower()
|
537 |
|
538 |
# Extract job title
|
@@ -547,7 +328,7 @@ def extract_job_requirements(job_description, models):
|
|
547 |
title_match = re.search(pattern, clean_job_text, re.IGNORECASE)
|
548 |
if title_match:
|
549 |
potential_title = title_match.group(1).strip() if len(title_match.groups()) >= 1 else title_match.group(2).strip()
|
550 |
-
if 3 <= len(potential_title) <= 50:
|
551 |
job_title = potential_title.capitalize()
|
552 |
break
|
553 |
|
@@ -570,52 +351,98 @@ def extract_job_requirements(job_description, models):
|
|
570 |
# Extract required skills
|
571 |
required_skills = [skill for skill in tech_skills if re.search(r'\b' + re.escape(skill.lower()) + r'\b', clean_job_text)]
|
572 |
|
573 |
-
#
|
574 |
if not required_skills:
|
575 |
-
# Extract some common words that might be skills
|
576 |
words = re.findall(r'\b\w{4,}\b', clean_job_text)
|
577 |
word_counts = {}
|
578 |
for word in words:
|
579 |
if word not in ["with", "that", "this", "have", "from", "they", "will", "what", "your", "their", "about"]:
|
580 |
word_counts[word] = word_counts.get(word, 0) + 1
|
581 |
-
|
582 |
-
# Get the top 5 most common words as potential skills
|
583 |
sorted_words = sorted(word_counts.items(), key=lambda x: x[1], reverse=True)
|
584 |
required_skills = [word.capitalize() for word, _ in sorted_words[:5]]
|
585 |
|
586 |
-
# Create a simple summary of the job using the summarize_text function
|
587 |
job_summary = summarize_text(job_description, models, max_length=100)
|
588 |
|
589 |
-
|
590 |
-
job_requirements = {
|
591 |
"title": job_title,
|
592 |
"years_experience": years_required,
|
593 |
"required_skills": required_skills,
|
594 |
"summary": job_summary
|
595 |
}
|
596 |
-
|
597 |
-
return job_requirements
|
598 |
|
599 |
-
|
600 |
-
|
601 |
-
#####################################
|
602 |
-
def analyze_job_fit(resume_summary, job_description, models):
|
603 |
-
"""
|
604 |
-
Analyze how well the candidate fits the job requirements.
|
605 |
-
Returns a fit score (0-2) and an assessment.
|
606 |
-
"""
|
607 |
start_time = time.time()
|
608 |
|
609 |
-
# Extract
|
610 |
-
|
|
|
|
|
|
|
611 |
|
612 |
-
#
|
613 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
614 |
|
615 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
616 |
|
617 |
-
|
618 |
-
|
|
|
|
|
|
|
|
|
619 |
|
620 |
#####################################
|
621 |
# Main Function
|
@@ -623,21 +450,17 @@ models = load_models()
|
|
623 |
def main():
|
624 |
"""Main function for the Streamlit application"""
|
625 |
st.title("Resume-Job Fit Analyzer")
|
626 |
-
st.markdown(
|
627 |
-
"""
|
628 |
-
Upload your resume file in **.docx**, **.doc**, or **.txt** format and enter a job description to see how well you match with the job requirements.
|
629 |
-
"""
|
630 |
-
)
|
631 |
|
632 |
-
#
|
|
|
|
|
|
|
633 |
uploaded_file = st.file_uploader("Upload your resume (.docx, .doc, or .txt)", type=["docx", "doc", "txt"])
|
634 |
-
|
635 |
-
# Job description input
|
636 |
job_description = st.text_area("Enter Job Description", height=200, placeholder="Paste the job description here...")
|
637 |
|
638 |
-
# Process button
|
639 |
if uploaded_file is not None and job_description and st.button("Analyze Job Fit"):
|
640 |
-
# Create a placeholder for the progress bar
|
641 |
progress_bar = st.progress(0)
|
642 |
status_text = st.empty()
|
643 |
|
@@ -662,31 +485,19 @@ def main():
|
|
662 |
status_text.text("Step 3/3: Evaluating job fit (this will take a moment)...")
|
663 |
assessment, fit_score, assessment_time = analyze_job_fit(summary, job_description, models)
|
664 |
progress_bar.progress(100)
|
665 |
-
|
666 |
-
# Clear status messages
|
667 |
status_text.empty()
|
668 |
|
669 |
-
# Display
|
670 |
st.subheader("Job Fit Assessment")
|
671 |
-
|
672 |
-
# Display fit score with label
|
673 |
-
fit_labels = {
|
674 |
-
0: "NOT FIT",
|
675 |
-
1: "POTENTIAL FIT",
|
676 |
-
2: "GOOD FIT"
|
677 |
-
}
|
678 |
|
679 |
-
#
|
680 |
-
|
681 |
score_colors = {0: "red", 1: "orange", 2: "green"}
|
682 |
-
st.markdown(f"<h2 style='color: {score_colors[fit_score]};'>{
|
683 |
-
|
684 |
-
# Display assessment
|
685 |
st.markdown(assessment)
|
686 |
-
|
687 |
st.info(f"Analysis completed in {(summarization_time + assessment_time):.2f} seconds")
|
688 |
|
689 |
-
#
|
690 |
st.subheader("Recommended Next Steps")
|
691 |
|
692 |
if fit_score == 2:
|
@@ -708,6 +519,5 @@ def main():
|
|
708 |
- Consider similar roles with fewer experience requirements
|
709 |
""")
|
710 |
|
711 |
-
# Run the main function
|
712 |
if __name__ == "__main__":
|
713 |
main()
|
|
|
9 |
import pandas as pd
|
10 |
from functools import lru_cache
|
11 |
|
12 |
+
# Handle imports
|
13 |
try:
|
14 |
from transformers import pipeline
|
15 |
has_pipeline = True
|
|
|
20 |
st.warning("Using basic transformers functionality instead of pipeline API")
|
21 |
|
22 |
# Set page title and hide sidebar
|
23 |
+
st.set_page_config(page_title="Resume-Job Fit Analyzer", initial_sidebar_state="collapsed")
|
24 |
+
st.markdown("""<style>[data-testid="collapsedControl"] {display: none;}section[data-testid="stSidebar"] {display: none;}</style>""", unsafe_allow_html=True)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
|
26 |
#####################################
|
27 |
+
# Preload Models & Helper Functions
|
28 |
#####################################
|
29 |
@st.cache_resource(show_spinner=True)
|
30 |
def load_models():
|
|
|
34 |
|
35 |
# Load summarization model
|
36 |
if has_pipeline:
|
37 |
+
models['summarizer'] = pipeline("summarization", model="Falconsai/text_summarization", max_length=100, truncation=True)
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
else:
|
|
|
39 |
try:
|
40 |
models['summarizer_model'] = AutoModelForSeq2SeqLM.from_pretrained("Falconsai/text_summarization")
|
41 |
models['summarizer_tokenizer'] = AutoTokenizer.from_pretrained("Falconsai/text_summarization")
|
42 |
except Exception as e:
|
43 |
st.error(f"Error loading summarization model: {e}")
|
44 |
+
models['summarizer_model'] = models['summarizer_tokenizer'] = None
|
|
|
45 |
|
46 |
+
# Load evaluation model
|
47 |
if has_pipeline:
|
48 |
+
models['evaluator'] = pipeline("sentiment-analysis", model="CR7CAD/RobertaFinetuned")
|
|
|
|
|
|
|
|
|
49 |
else:
|
|
|
50 |
try:
|
51 |
+
models['evaluator_model'] = AutoModelForSequenceClassification.from_pretrained("CR7CAD/RobertaFinetuned")
|
52 |
+
models['evaluator_tokenizer'] = AutoTokenizer.from_pretrained("CR7CAD/RobertaFinetuned")
|
|
|
|
|
|
|
|
|
53 |
except Exception as e:
|
54 |
st.error(f"Error loading sentiment model: {e}")
|
55 |
+
models['evaluator_model'] = models['evaluator_tokenizer'] = None
|
|
|
56 |
|
57 |
return models
|
58 |
|
|
|
59 |
def summarize_text(text, models, max_length=100):
|
60 |
+
"""Summarize text using available models with fallbacks"""
|
61 |
# Truncate input to prevent issues with long texts
|
62 |
+
input_text = text[:1024]
|
63 |
|
64 |
+
# Try pipeline first
|
65 |
if has_pipeline and 'summarizer' in models:
|
|
|
66 |
try:
|
67 |
+
return models['summarizer'](input_text)[0]['summary_text']
|
|
|
68 |
except Exception as e:
|
69 |
st.warning(f"Error in pipeline summarization: {e}")
|
70 |
|
71 |
+
# Try manual model
|
72 |
if 'summarizer_model' in models and 'summarizer_tokenizer' in models and models['summarizer_model']:
|
73 |
try:
|
74 |
tokenizer = models['summarizer_tokenizer']
|
75 |
model = models['summarizer_model']
|
|
|
|
|
76 |
inputs = tokenizer(input_text, return_tensors="pt", truncation=True, max_length=1024)
|
77 |
+
summary_ids = model.generate(inputs.input_ids, max_length=max_length, min_length=30, num_beams=4, early_stopping=True)
|
78 |
+
return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
79 |
except Exception as e:
|
80 |
st.warning(f"Error in manual summarization: {e}")
|
81 |
|
82 |
+
# Fallback to basic summarization
|
83 |
return basic_summarize(text, max_length)
|
84 |
|
|
|
85 |
def basic_summarize(text, max_length=100):
|
86 |
+
"""Basic extractive text summarization"""
|
|
|
87 |
sentences = re.split(r'(?<!\w\.\w.)(?<![A-Z][a-z]\.)(?<=\.|\?)\s', text)
|
88 |
|
89 |
+
# Score and filter sentences
|
90 |
scored_sentences = []
|
91 |
for i, sentence in enumerate(sentences):
|
92 |
+
if len(sentence.split()) >= 4:
|
93 |
+
score = 1.0 / (i + 1) - (0.01 * max(0, len(sentence.split()) - 20))
|
94 |
+
scored_sentences.append((score, sentence))
|
|
|
|
|
|
|
|
|
95 |
|
96 |
+
# Get top sentences
|
97 |
scored_sentences.sort(reverse=True)
|
|
|
|
|
98 |
summary_sentences = []
|
99 |
current_length = 0
|
100 |
|
|
|
105 |
else:
|
106 |
break
|
107 |
|
108 |
+
# Restore original sentence order
|
109 |
if summary_sentences:
|
110 |
+
original_order = [(sentences.index(s), s) for s in summary_sentences]
|
|
|
|
|
111 |
original_order.sort()
|
112 |
summary_sentences = [s for _, s in original_order]
|
113 |
|
114 |
+
return " ".join(summary_sentences)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
115 |
|
116 |
#####################################
|
117 |
+
# Information Extraction Functions
|
118 |
#####################################
|
119 |
@st.cache_data(show_spinner=False)
|
120 |
def extract_text_from_file(file_obj):
|
121 |
+
"""Extract text from uploaded document file"""
|
|
|
|
|
|
|
122 |
filename = file_obj.name
|
123 |
ext = os.path.splitext(filename)[1].lower()
|
124 |
+
|
|
|
125 |
if ext == ".docx":
|
126 |
try:
|
127 |
document = docx.Document(file_obj)
|
128 |
text = "\n".join(para.text for para in document.paragraphs if para.text.strip())
|
129 |
except Exception as e:
|
130 |
+
return f"Error processing DOCX file: {e}"
|
131 |
elif ext == ".doc":
|
132 |
try:
|
|
|
133 |
with tempfile.NamedTemporaryFile(delete=False, suffix='.doc') as temp_file:
|
134 |
temp_file.write(file_obj.getvalue())
|
135 |
temp_path = temp_file.name
|
136 |
+
|
137 |
+
text = docx2txt.process(temp_path)
|
|
|
|
|
|
|
|
|
|
|
|
|
138 |
os.unlink(temp_path)
|
139 |
except Exception as e:
|
140 |
+
return f"Error processing DOC file: {e}"
|
141 |
elif ext == ".txt":
|
142 |
try:
|
143 |
text = file_obj.getvalue().decode("utf-8")
|
144 |
except Exception as e:
|
145 |
+
return f"Error processing TXT file: {e}"
|
146 |
else:
|
147 |
+
return "Unsupported file type. Please upload a .docx, .doc, or .txt file."
|
148 |
|
|
|
149 |
return text[:15000] if text else text
|
150 |
|
151 |
+
def extract_skills(text):
|
152 |
+
"""Extract key skills from the resume"""
|
153 |
+
skill_keywords = {
|
154 |
+
"Programming": ["Python", "Java", "JavaScript", "HTML", "CSS", "SQL", "C++", "C#", "Go", "React", "Angular", "Vue", "Node.js"],
|
155 |
+
"Data Science": ["Machine Learning", "Data Analysis", "Statistics", "TensorFlow", "PyTorch", "AI", "Algorithms", "NLP", "Deep Learning"],
|
156 |
+
"Database": ["SQL", "MySQL", "MongoDB", "Database", "NoSQL", "PostgreSQL", "Oracle", "Redis"],
|
157 |
+
"Web Development": ["React", "Angular", "Node.js", "Frontend", "Backend", "Full-Stack", "REST API", "GraphQL"],
|
158 |
+
"Software Development": ["Agile", "Scrum", "Git", "DevOps", "Docker", "System Design", "CI/CD", "Jenkins"],
|
159 |
+
"Cloud": ["AWS", "Azure", "Google Cloud", "Cloud Computing", "Lambda", "S3", "EC2"],
|
160 |
+
"Security": ["Cybersecurity", "Network Security", "Encryption", "Security"],
|
161 |
+
"Business": ["Project Management", "Business Analysis", "Leadership", "Teamwork", "Agile", "Scrum"],
|
162 |
+
"Design": ["UX/UI", "User Experience", "Design Thinking", "Adobe", "Figma"]
|
163 |
+
}
|
164 |
+
|
165 |
+
text_lower = text.lower()
|
166 |
+
return [skill for category, skills in skill_keywords.items()
|
167 |
+
for skill in skills if skill.lower() in text_lower]
|
168 |
+
|
169 |
+
@lru_cache(maxsize=32)
|
170 |
+
def extract_name(text_start):
|
171 |
+
"""Extract candidate name from the beginning of resume text"""
|
172 |
+
lines = text_start.split('\n')
|
173 |
+
potential_name_lines = [line.strip() for line in lines[:5] if line.strip()]
|
174 |
+
|
175 |
+
if potential_name_lines:
|
176 |
+
first_line = potential_name_lines[0]
|
177 |
+
if 5 <= len(first_line) <= 40 and not any(x in first_line.lower() for x in ["resume", "cv", "curriculum", "vitae", "profile"]):
|
178 |
+
return first_line
|
179 |
+
|
180 |
+
for line in potential_name_lines[:3]:
|
181 |
+
if len(line.split()) <= 4 and not any(x in line.lower() for x in ["address", "phone", "email", "resume", "cv"]):
|
182 |
+
return line
|
183 |
+
|
184 |
+
return "Unknown (please extract from resume)"
|
185 |
|
|
|
186 |
def extract_age(text):
|
187 |
"""Extract candidate age from resume text"""
|
|
|
188 |
age_patterns = [
|
189 |
r'age:?\s*(\d{1,2})',
|
190 |
r'(\d{1,2})\s*years\s*old',
|
191 |
+
r'dob:.*(\d{4})',
|
192 |
+
r'date of birth:.*(\d{4})'
|
193 |
]
|
194 |
|
195 |
text_lower = text.lower()
|
196 |
for pattern in age_patterns:
|
197 |
matches = re.search(pattern, text_lower)
|
198 |
if matches:
|
199 |
+
# Convert birth year to age if needed
|
200 |
+
if len(matches.group(1)) == 4:
|
201 |
try:
|
202 |
+
return str(2025 - int(matches.group(1)))
|
|
|
|
|
203 |
except:
|
204 |
pass
|
205 |
return matches.group(1)
|
206 |
|
207 |
return "Not specified"
|
208 |
|
|
|
209 |
def extract_industry(text):
|
210 |
"""Extract expected job industry from resume"""
|
|
|
211 |
industry_keywords = {
|
212 |
"Technology": ["software", "programming", "developer", "IT", "tech", "computer", "digital"],
|
213 |
"Finance": ["banking", "financial", "accounting", "finance", "analyst"],
|
|
|
222 |
}
|
223 |
|
224 |
text_lower = text.lower()
|
225 |
+
industry_counts = {industry: sum(text_lower.count(keyword.lower()) for keyword in keywords)
|
226 |
+
for industry, keywords in industry_keywords.items()}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
227 |
|
228 |
+
return max(industry_counts.items(), key=lambda x: x[1])[0] if any(industry_counts.values()) else "Not clearly specified"
|
229 |
|
|
|
230 |
def extract_job_position(text):
|
231 |
"""Extract expected job position from resume"""
|
|
|
232 |
objective_patterns = [
|
233 |
r'objective:?\s*(.*?)(?=\n\n|\n\w+:|\Z)',
|
234 |
r'career\s*objective:?\s*(.*?)(?=\n\n|\n\w+:|\Z)',
|
|
|
242 |
match = re.search(pattern, text_lower, re.IGNORECASE | re.DOTALL)
|
243 |
if match:
|
244 |
objective_text = match.group(1).strip()
|
|
|
245 |
job_titles = ["developer", "engineer", "analyst", "manager", "director", "specialist",
|
246 |
"coordinator", "consultant", "designer", "architect", "administrator"]
|
247 |
|
248 |
for title in job_titles:
|
249 |
if title in objective_text:
|
|
|
250 |
title_pattern = r'(?:a|an)?\s*(\w+\s+' + title + r'|\w+\s+\w+\s+' + title + r')'
|
251 |
title_match = re.search(title_pattern, objective_text)
|
252 |
if title_match:
|
253 |
return title_match.group(1).strip().title()
|
254 |
return title.title()
|
255 |
|
|
|
256 |
if len(objective_text) > 10:
|
|
|
257 |
words = objective_text.split()
|
258 |
+
return " ".join(words[:10]).title() + "..." if len(words) > 10 else objective_text.title()
|
|
|
|
|
259 |
|
|
|
260 |
job_patterns = [
|
261 |
r'experience:.*?(\w+\s+\w+(?:\s+\w+)?)(?=\s*at|\s*\(|\s*-|\s*,|\s*\d{4}|\n)',
|
262 |
r'(\w+\s+\w+(?:\s+\w+)?)\s*\(\s*current\s*\)',
|
|
|
270 |
|
271 |
return "Not explicitly stated"
|
272 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
273 |
#####################################
|
274 |
+
# Core Analysis Functions
|
275 |
#####################################
|
276 |
def summarize_resume_text(resume_text, models):
|
277 |
+
"""Generate a structured summary of resume text"""
|
|
|
|
|
278 |
start_time = time.time()
|
279 |
|
280 |
# Extract critical information
|
|
|
284 |
job_position = extract_job_position(resume_text)
|
285 |
skills = extract_skills(resume_text)
|
286 |
|
287 |
+
# Generate overall summary
|
288 |
try:
|
289 |
if has_pipeline and 'summarizer' in models:
|
290 |
+
model_summary = models['summarizer'](resume_text[:2000], max_length=100, min_length=30, do_sample=False)[0]['summary_text']
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
291 |
else:
|
|
|
292 |
model_summary = summarize_text(resume_text, models, max_length=100)
|
293 |
except Exception as e:
|
294 |
st.warning(f"Error in resume summarization: {e}")
|
295 |
model_summary = "Error generating summary. Please check the original resume."
|
296 |
|
297 |
+
# Format the structured summary
|
298 |
formatted_summary = f"Name: {name}\n\n"
|
299 |
formatted_summary += f"Age: {age}\n\n"
|
300 |
formatted_summary += f"Expected Industry: {industry}\n\n"
|
|
|
302 |
formatted_summary += f"Skills: {', '.join(skills)}\n\n"
|
303 |
formatted_summary += f"Summary: {model_summary}"
|
304 |
|
305 |
+
return formatted_summary, time.time() - start_time
|
|
|
|
|
306 |
|
|
|
|
|
|
|
307 |
def extract_job_requirements(job_description, models):
|
308 |
+
"""Extract key requirements from a job description"""
|
309 |
+
# Combined skill list (abridged for brevity)
|
|
|
|
|
310 |
tech_skills = [
|
311 |
+
"Python", "Java", "C++", "JavaScript", "TypeScript", "SQL", "HTML", "CSS", "React", "Angular",
|
312 |
+
"Machine Learning", "Data Science", "AI", "AWS", "Azure", "Docker", "Kubernetes", "MySQL",
|
313 |
+
"MongoDB", "PostgreSQL", "Project Management", "Agile", "Scrum", "Leadership", "Communication",
|
314 |
+
"Problem Solving", "Git", "DevOps", "Full Stack", "Mobile Development", "Android", "iOS"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
315 |
]
|
316 |
|
|
|
317 |
clean_job_text = job_description.lower()
|
318 |
|
319 |
# Extract job title
|
|
|
328 |
title_match = re.search(pattern, clean_job_text, re.IGNORECASE)
|
329 |
if title_match:
|
330 |
potential_title = title_match.group(1).strip() if len(title_match.groups()) >= 1 else title_match.group(2).strip()
|
331 |
+
if 3 <= len(potential_title) <= 50:
|
332 |
job_title = potential_title.capitalize()
|
333 |
break
|
334 |
|
|
|
351 |
# Extract required skills
|
352 |
required_skills = [skill for skill in tech_skills if re.search(r'\b' + re.escape(skill.lower()) + r'\b', clean_job_text)]
|
353 |
|
354 |
+
# Fallback if no skills found
|
355 |
if not required_skills:
|
|
|
356 |
words = re.findall(r'\b\w{4,}\b', clean_job_text)
|
357 |
word_counts = {}
|
358 |
for word in words:
|
359 |
if word not in ["with", "that", "this", "have", "from", "they", "will", "what", "your", "their", "about"]:
|
360 |
word_counts[word] = word_counts.get(word, 0) + 1
|
|
|
|
|
361 |
sorted_words = sorted(word_counts.items(), key=lambda x: x[1], reverse=True)
|
362 |
required_skills = [word.capitalize() for word, _ in sorted_words[:5]]
|
363 |
|
|
|
364 |
job_summary = summarize_text(job_description, models, max_length=100)
|
365 |
|
366 |
+
return {
|
|
|
367 |
"title": job_title,
|
368 |
"years_experience": years_required,
|
369 |
"required_skills": required_skills,
|
370 |
"summary": job_summary
|
371 |
}
|
|
|
|
|
372 |
|
373 |
+
def evaluate_job_fit(resume_summary, job_requirements, models):
|
374 |
+
"""Evaluate how well a resume matches job requirements"""
|
|
|
|
|
|
|
|
|
|
|
|
|
375 |
start_time = time.time()
|
376 |
|
377 |
+
# Extract information
|
378 |
+
required_skills = job_requirements["required_skills"]
|
379 |
+
years_required = job_requirements["years_experience"]
|
380 |
+
job_title = job_requirements["title"]
|
381 |
+
skills_mentioned = extract_skills(resume_summary)
|
382 |
|
383 |
+
# Calculate match percentages
|
384 |
+
matching_skills = [skill for skill in required_skills if skill in skills_mentioned]
|
385 |
+
skill_match_percentage = len(matching_skills) / len(required_skills) if required_skills else 0
|
386 |
+
|
387 |
+
# Extract experience level from resume
|
388 |
+
experience_pattern = r'(\d+)\+?\s*years?\s*(?:of)?\s*experience'
|
389 |
+
years_experience = 0
|
390 |
+
experience_match = re.search(experience_pattern, resume_summary, re.IGNORECASE)
|
391 |
+
if experience_match:
|
392 |
+
try:
|
393 |
+
years_experience = int(experience_match.group(1))
|
394 |
+
except:
|
395 |
+
pass
|
396 |
+
|
397 |
+
# Calculate match scores
|
398 |
+
exp_match_ratio = min(1.0, years_experience / max(1, years_required)) if years_required > 0 else 0.5
|
399 |
|
400 |
+
# Job title match score
|
401 |
+
title_words = [word for word in job_title.lower().split() if len(word) > 3]
|
402 |
+
title_matches = sum(1 for word in title_words if word in resume_summary.lower())
|
403 |
+
title_match = title_matches / len(title_words) if title_words else 0
|
404 |
+
|
405 |
+
# Calculate individual scores
|
406 |
+
skill_score = min(2, skill_match_percentage * 3)
|
407 |
+
exp_score = min(2, exp_match_ratio * 2)
|
408 |
+
title_score = min(2, title_match * 2)
|
409 |
+
|
410 |
+
# Extract candidate info
|
411 |
+
name_match = re.search(r'Name:\s*(.*?)(?=\n|\Z)', resume_summary)
|
412 |
+
name = name_match.group(1).strip() if name_match else "The candidate"
|
413 |
+
|
414 |
+
industry_match = re.search(r'Expected Industry:\s*(.*?)(?=\n|\Z)', resume_summary)
|
415 |
+
industry = industry_match.group(1).strip() if industry_match else "unspecified industry"
|
416 |
+
|
417 |
+
# Calculate final weighted score
|
418 |
+
weighted_score = (skill_score * 0.5) + (exp_score * 0.3) + (title_score * 0.2)
|
419 |
+
|
420 |
+
# Determine fit score
|
421 |
+
if weighted_score >= 1.5:
|
422 |
+
fit_score = 2 # Good fit
|
423 |
+
elif weighted_score >= 0.8:
|
424 |
+
fit_score = 1 # Potential fit
|
425 |
+
else:
|
426 |
+
fit_score = 0 # Not a fit
|
427 |
+
|
428 |
+
# Generate assessment text
|
429 |
+
missing_skills = [skill for skill in required_skills if skill not in skills_mentioned]
|
430 |
+
|
431 |
+
if fit_score == 2:
|
432 |
+
fit_assessment = f"{fit_score}: GOOD FIT - {name} demonstrates strong alignment with the {job_title} position. Their background in {industry} and professional experience appear well-suited for this role's requirements. The technical expertise matches what the position demands."
|
433 |
+
elif fit_score == 1:
|
434 |
+
fit_assessment = f"{fit_score}: POTENTIAL FIT - {name} shows potential for the {job_title} role with some relevant experience, though there are gaps in certain technical areas. Their {industry} background provides partial alignment with the position requirements. Additional training might be needed in {', '.join(missing_skills[:2])} if pursuing this opportunity."
|
435 |
+
else:
|
436 |
+
fit_assessment = f"{fit_score}: NO FIT - {name}'s current background shows limited alignment with this {job_title} position. Their experience level and technical background differ significantly from the role requirements. A position better matching their {industry} expertise might be more suitable."
|
437 |
+
|
438 |
+
return fit_assessment, fit_score, time.time() - start_time
|
439 |
|
440 |
+
def analyze_job_fit(resume_summary, job_description, models):
|
441 |
+
"""End-to-end job fit analysis"""
|
442 |
+
start_time = time.time()
|
443 |
+
job_requirements = extract_job_requirements(job_description, models)
|
444 |
+
assessment, fit_score, execution_time = evaluate_job_fit(resume_summary, job_requirements, models)
|
445 |
+
return assessment, fit_score, time.time() - start_time
|
446 |
|
447 |
#####################################
|
448 |
# Main Function
|
|
|
450 |
def main():
|
451 |
"""Main function for the Streamlit application"""
|
452 |
st.title("Resume-Job Fit Analyzer")
|
453 |
+
st.markdown("Upload your resume file in **.docx**, **.doc**, or **.txt** format and enter a job description to see how well you match with the job requirements.")
|
|
|
|
|
|
|
|
|
454 |
|
455 |
+
# Load models
|
456 |
+
models = load_models()
|
457 |
+
|
458 |
+
# User inputs
|
459 |
uploaded_file = st.file_uploader("Upload your resume (.docx, .doc, or .txt)", type=["docx", "doc", "txt"])
|
|
|
|
|
460 |
job_description = st.text_area("Enter Job Description", height=200, placeholder="Paste the job description here...")
|
461 |
|
462 |
+
# Process when button clicked
|
463 |
if uploaded_file is not None and job_description and st.button("Analyze Job Fit"):
|
|
|
464 |
progress_bar = st.progress(0)
|
465 |
status_text = st.empty()
|
466 |
|
|
|
485 |
status_text.text("Step 3/3: Evaluating job fit (this will take a moment)...")
|
486 |
assessment, fit_score, assessment_time = analyze_job_fit(summary, job_description, models)
|
487 |
progress_bar.progress(100)
|
|
|
|
|
488 |
status_text.empty()
|
489 |
|
490 |
+
# Display results
|
491 |
st.subheader("Job Fit Assessment")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
492 |
|
493 |
+
# Display score with appropriate styling
|
494 |
+
fit_labels = {0: "NOT FIT", 1: "POTENTIAL FIT", 2: "GOOD FIT"}
|
495 |
score_colors = {0: "red", 1: "orange", 2: "green"}
|
496 |
+
st.markdown(f"<h2 style='color: {score_colors[fit_score]};'>{fit_labels[fit_score]}</h2>", unsafe_allow_html=True)
|
|
|
|
|
497 |
st.markdown(assessment)
|
|
|
498 |
st.info(f"Analysis completed in {(summarization_time + assessment_time):.2f} seconds")
|
499 |
|
500 |
+
# Recommendations
|
501 |
st.subheader("Recommended Next Steps")
|
502 |
|
503 |
if fit_score == 2:
|
|
|
519 |
- Consider similar roles with fewer experience requirements
|
520 |
""")
|
521 |
|
|
|
522 |
if __name__ == "__main__":
|
523 |
main()
|