Upload app.py

app.py

@@ -0,0 +1,62 @@
+import gradio as gr
+import os
+from pathlib import Path
+import numpy as np
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import PyPDF2, docx
+
+# ----------- CONFIG ------------
+RESUME_DIR = Path("resumes")
+MAX_FEATURES = 20000
+# -------------------------------
+
+def extract_text(path):
+    if path.suffix.lower() == ".pdf":
+        pdf = PyPDF2.PdfReader(open(path, "rb"))
+        return "\n".join([p.extract_text() or "" for p in pdf.pages])
+    elif path.suffix.lower() in [".docx", ".doc"]:
+        d = docx.Document(path)
+        return "\n".join([p.text for p in d.paragraphs])
+    else:
+        return path.read_text(encoding="utf-8", errors="ignore")
+
+def load_resumes():
+    texts, names = [], []
+    for p in RESUME_DIR.glob("**/*"):
+        if p.suffix.lower() in [".pdf", ".docx", ".doc", ".txt"]:
+            try:
+                txt = extract_text(p)
+                texts.append(" ".join(txt.lower().split()))
+                names.append(p.name)
+            except Exception:
+                pass
+    return names, texts
+
+filenames, texts = load_resumes()
+vectorizer = TfidfVectorizer(stop_words="english", max_features=MAX_FEATURES)
+X = vectorizer.fit_transform(texts)
+
+def match_resume(job_description):
+    jd = " ".join(job_description.lower().split())
+    jd_vec = vectorizer.transform([jd])
+    sims = cosine_similarity(jd_vec, X).flatten()
+    mean, std = sims.mean(), sims.std() or 1e-6
+    conf = 1 / (1 + np.exp(-((sims - mean) / std)))  # sigmoid confidence
+    df = pd.DataFrame({
+        "Resume": filenames,
+        "Match (%)": (sims * 100).round(2),
+        "Confidence (%)": (conf * 100).round(2)
+    }).sort_values("Match (%)", ascending=False).head(10)
+    return df
+
+iface = gr.Interface(
+    fn=match_resume,
+    inputs=gr.Textbox(lines=6, label="Paste Job Description"),
+    outputs=gr.Dataframe(label="Top Matching Resumes"),
+    title="AI Resume Analyzer + Job Matcher",
+    description="Upload your resume dataset and match against a job description using NLP (TF-IDF + Confidence Scoring)."
+)
+
+iface.launch()