Spaces:
Sleeping
Sleeping
File size: 2,863 Bytes
2005bec 21d54a4 4aa5719 2005bec 1f5134c 21d54a4 2005bec 1f5134c 4aa5719 1f5134c 4aa5719 1f5134c 2005bec 4aa5719 2005bec 4aa5719 2005bec 1f5134c 2005bec 4aa5719 2005bec 4aa5719 2005bec 4aa5719 1f5134c 2005bec 1f5134c 2005bec 1f5134c 4aa5719 1f5134c 4aa5719 1f5134c 4aa5719 1f5134c 4aa5719 1f5134c 4aa5719 1f5134c 4aa5719 2005bec | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 | import spacy
import re
from difflib import get_close_matches
# Safe model load
try:
nlp = spacy.load("en_core_web_sm")
except:
from spacy.cli import download
download("en_core_web_sm")
nlp = spacy.load("en_core_web_sm")
# Common skills list (used for fuzzy matching)
common_skills = [
"python", "sql", "java", "c++", "machine learning", "deep learning", "nlp", "tensorflow",
"keras", "pandas", "numpy", "matplotlib", "power bi", "excel", "html", "css", "django", "flask",
"scikit-learn", "seaborn", "fastapi", "pytorch"
]
edu_keywords = ["bachelor", "bs", "msc", "ms", "phd", "b.sc", "b.s.", "university", "institute", "college"]
def extract_skills(text):
doc = nlp(text)
# Extract noun phrases
noun_phrases = set(chunk.text.lower().strip() for chunk in doc.noun_chunks)
# Add common skills if fuzzy matched
matched_common = set()
words = set(text.lower().split())
for skill in common_skills:
if get_close_matches(skill.lower(), words, n=1, cutoff=0.85):
matched_common.add(skill.lower())
# Combine and clean
all_skills = noun_phrases.union(matched_common)
filtered = [s for s in all_skills if 2 <= len(s.split()) <= 5 and not s.startswith(("i ", "my ", "our "))]
return list(set(filtered))
def extract_entities(text):
doc = nlp(text)
entities = {
"Name": None,
"Email": None,
"Phone": None,
"Skills": [],
"Education": [],
"Experience": [],
"Certifications": [],
"Projects": []
}
# ✅ Extract Name
for ent in doc.ents:
if ent.label_ == "PERSON":
entities["Name"] = ent.text
break
# ✅ Extract Email & Phone
entities["Email"] = next(iter(re.findall(r"[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+", text)), None)
entities["Phone"] = next(iter(re.findall(r"\+?\d[\d\s\-]{8,15}", text)), None)
# ✅ Extract Skills
entities["Skills"] = extract_skills(text)
# ✅ Section-based parsing
current_section = None
lines = text.split("\n")
for line in lines:
clean_line = line.strip()
if not clean_line:
continue
line_lower = clean_line.lower()
if "experience" in line_lower:
current_section = "Experience"
elif "project" in line_lower:
current_section = "Projects"
elif "certification" in line_lower:
current_section = "Certifications"
elif any(kw in line_lower for kw in edu_keywords):
entities["Education"].append(clean_line)
elif current_section:
entities[current_section].append(clean_line)
# ✅ Deduplicate list entries
for key in entities:
if isinstance(entities[key], list):
entities[key] = list(set(entities[key]))
return entities
|