Update app.py

app.py

@@ -126,159 +126,4 @@ def get_text_embeddings(text):
     else: return np.mean([token.vector for token in doc if token.has_vector], axis=0) if [token.vector for token in doc if token.has_vector] else np.zeros(nlp.vocab.vectors.shape[1])
 
 def calculate_cosine_similarity(vec1, vec2):
-    if np.all(vec1 == 0) or np.all(vec2 == 0): return 0.0
-    vec1 = vec1.reshape(1, -1)
-    vec2 = vec2.reshape(1, -1)
-    return cosine_similarity(vec1, vec2)[0][0]
-
-# --- Main Processing Pipeline ---
-def analyze_document(doc_text):
-    doc_spacy = nlp(doc_text)
-    cleaned_text = preprocess_text(doc_text)
-    extracted_skills, general_entities = extract_skills(doc_spacy, skill_keywords=predefined_skills_list)
-    years_exp, education_level = extract_experience_and_education(doc_text)
-    text_embedding = get_text_embeddings(cleaned_text)
-    return {
-        "raw_text": doc_text, "cleaned_text": cleaned_text, "spacy_doc": doc_spacy,
-        "extracted_skills": extracted_skills, "general_entities": general_entities,
-        "years_experience": years_exp, "education_level": education_level,
-        "text_embedding": text_embedding
-    }
-
-# --- Matching and Scoring Logic ---
-def calculate_match_scores(cv_data, jd_data):
-    results = {}
-    overall_similarity = calculate_cosine_similarity(cv_data["text_embedding"], jd_data["text_embedding"])
-    results["overall_match_score"] = round(overall_similarity * 100, 2)
-    cv_skills = set(cv_data["extracted_skills"])
-    jd_skills = set(jd_data["extracted_skills"])
-    matched_skills = list(cv_skills.intersection(jd_skills))
-    missing_skills = list(jd_skills.difference(cv_skills))
-    extra_skills_in_cv = list(cv_skills.difference(jd_skills))
-    results["matched_skills"] = matched_skills
-    results["missing_skills"] = missing_skills
-    results["extra_skills_in_cv"] = extra_skills_in_cv
-    if jd_skills: skill_match_percentage = len(matched_skills) / len(jd_skills) * 100
-    else: skill_match_percentage = 0.0
-    results["skill_match_percentage"] = round(skill_match_percentage, 2)
-    corpus = [cv_data["cleaned_text"], jd_data["cleaned_text"]]
-    tfidf_vectorizer = TfidfVectorizer(max_features=100)
-    tfidf_matrix = tfidf_vectorizer.fit_transform(corpus)
-    feature_names = tfidf_vectorizer.get_feature_names_out()
-    cv_tfidf_scores = {feature_names[i]: tfidf_matrix[0, i] for i in tfidf_matrix[0].nonzero()[1]}
-    jd_tfidf_scores = {feature_names[i]: tfidf_matrix[1, i] for i in tfidf_matrix[1].nonzero()[1]}
-    top_cv_keywords = sorted(cv_tfidf_scores.items(), key=lambda x: x[1], reverse=True)[:15]
-    top_jd_keywords = sorted(jd_tfidf_scores.items(), key=lambda x: x[1], reverse=True)[:15]
-    results["top_cv_keywords"] = [k for k,v in top_cv_keywords]
-    results["top_jd_keywords"] = [k for k,v in top_jd_keywords]
-    common_keywords = set(results["top_cv_keywords"]).intersection(set(results["top_jd_keywords"]))
-    results["common_keywords"] = list(common_keywords)
-    cv_exp_years = cv_data["years_experience"]
-    jd_exp_years = jd_data["years_experience"]
-    results["cv_years_experience"] = cv_exp_years
-    results["jd_years_experience"] = jd_exp_years
-    exp_status = "Not specified by Job"
-    if jd_exp_years > 0:
-        if cv_exp_years >= jd_exp_years: exp_status = "Meets or Exceeds Requirement"
-        else: exp_status = f"Below Requirement (Needs {jd_exp_years - cv_exp_years} more years)"
-    results["experience_match_status"] = exp_status
-    cv_edu = cv_data["education_level"]
-    jd_edu = jd_data["education_level"]
-    results["cv_education_level"] = cv_edu
-    results["jd_education_level"] = jd_edu
-    edu_match_status = "Not Specified by Job"
-    if jd_edu != "Not Specified":
-        edu_order = {"Associate's": 1, "Bachelor's": 2, "Master's": 3, "Ph.D.": 4}
-        if edu_order.get(cv_edu, 0) >= edu_order.get(jd_edu, 0): edu_match_status = "Meets or Exceeds Requirement"
-        else: edu_match_status = "Below Requirement"
-    results["education_match_status"] = edu_match_status
-    return results
-
-# --- Overall Analysis Orchestrator ---
-def perform_cv_job_analysis(cv_text, job_desc_text):
-    cv_analysis_data = analyze_document(cv_text)
-    job_desc_analysis_data = analyze_document(job_desc_text)
-    match_results = calculate_match_scores(cv_analysis_data, job_desc_analysis_data)
-    return match_results
-
-# --- Visualization Functions ---
-def create_overall_match_plot(score):
-    fig, ax = plt.subplots(figsize=(6, 2))
-    sns.set_style("whitegrid")
-    ax.barh(["Overall Match"], [score], color='skyblue')
-    ax.set_xlim(0, 100)
-    ax.text(score + 2, 0, f'{score}%', va='center', color='black', fontsize=12)
-    ax.set_title("Overall CV-Job Description Match Score", fontsize=14)
-    ax.set_xlabel("Match Percentage", fontsize=12)
-    ax.get_yaxis().set_visible(False)
-    plt.tight_layout()
-    return fig
-
-def create_skill_match_plot(matched_skills, missing_skills):
-    labels = ['Matched Skills', 'Missing Skills']
-    sizes = [len(matched_skills), len(missing_skills)]
-    colors = ['#66b3ff', '#ff9999']
-    explode = (0.05, 0.05) if sizes[0] > 0 and sizes[1] > 0 else (0,0)
-    if sum(sizes) == 0: return None
-    fig, ax = plt.subplots(figsize=(7, 7))
-    ax.pie(sizes, explode=explode, labels=labels, colors=colors, autopct='%1.1f%%', shadow=True, startangle=90, textprops={'fontsize': 12})
-    ax.axis('equal')
-    ax.set_title("Skill Match Breakdown", fontsize=14)
-    plt.tight_layout()
-    return fig
-
-def create_top_keywords_plot(cv_keywords, jd_keywords):
-    fig, axes = plt.subplots(1, 2, figsize=(16, 6))
-    sns.set_style("whitegrid")
-    cv_df = pd.DataFrame(Counter(cv_keywords).most_common(10), columns=['Keyword', 'Count'])
-    if not cv_df.empty:
-        sns.barplot(x='Count', y='Keyword', data=cv_df, ax=axes[0], palette='viridis')
-        axes[0].set_title('Top Keywords in CV', fontsize=14)
-        axes[0].set_xlabel('Frequency/Importance', fontsize=12)
-        axes[0].set_ylabel('')
-    jd_df = pd.DataFrame(Counter(jd_keywords).most_common(10), columns=['Keyword', 'Count'])
-    if not jd_df.empty:
-        sns.barplot(x='Count', y='Keyword', data=jd_df, ax=axes[1], palette='plasma')
-        axes[1].set_title('Top Keywords in Job Description', fontsize=14)
-        axes[1].set_xlabel('Frequency/Importance', fontsize=12)
-        axes[1].set_ylabel('')
-    plt.tight_layout()
-    return fig
-
-# --- Main Gradio Interface Function ---
-def analyze_cv_match(cv_file_obj, cv_text_input, jd_text_input):
-    cv_content = ""
-    if cv_file_obj is not None:
-        cv_content = get_file_content(cv_file_obj)
-    elif cv_text_input:
-        cv_content = cv_text_input
-    if not cv_content:
-        return (f"<h4><p style='color:red;'>🚨 Error: Please upload a CV file or paste your CV text.</p></h4>",
-                None, None, None, "Analysis Failed")
-    if not jd_text_input:
-        return (f"<h4><p style='color:red;'>🚨 Error: Please paste the Job Description text.</p></h4>",
-                None, None, None, "Analysis Failed")
-    try:
-        analysis_results = perform_cv_job_analysis(cv_content, jd_text_input)
-        html_output = f"""
-        <h2 style='text-align: center;'>💡 Analysis Results Summary 💡</h2>
-        <div style='display: flex; justify-content: space-around; flex-wrap: wrap; text-align: center; margin-bottom: 20px;'>
-            <div style='background-color: #e0f7fa; padding: 15px; border-radius: 8px; margin: 5px; min-width: 200px; box-shadow: 2px 2px 5px rgba(0,0,0,0.1);'>
-                <h3>Overall Match Score</h3>
-                <h1 style='color: #007bb6;'>{analysis_results['overall_match_score']}%</h1>
-            </div>
-            <div style='background-color: #e8f5e9; padding: 15px; border-radius: 8px; margin: 5px; min-width: 200px; box-shadow: 2px 2px 5px rgba(0,0,0,0.1);'>
-                <h3>Skill Match</h3>
-                <h1 style='color: #43a047;'>{analysis_results['skill_match_percentage']}%</h1>
-            </div>
-            <div style='background-color: #fff3e0; padding: 15px; border-radius: 8px; margin: 5px; min-width: 200px; box-shadow: 2px 2px 5px rgba(0,0,0,0.1);'>
-                <h3>Experience Match</h3>
-                <h1 style='color: #fb8c00;'>{analysis_results['experience_match_status']}</h1>
-            </div>
-        </div>
-        <hr style='border-top: 2px solid #bbb; margin: 20px 0;'/>
-        <h2 style='text-align: center;'>📝 Detailed Breakdown</h2>
-        <h4>Skills Analysis</h4>
-        <p><strong>✅ Matched Skills:</strong> {', '.join(analysis_results['matched_skills']) if analysis_results['matched_skills'] else 'None found matching job description.'}</p>
-        <p><strong>❌ Missing Skills (from Job Description):</strong> {', '.join(analysis_results['missing_skills']) if analysis_results['missing_skills'] else '🥳 None! Your CV has all specified skills.'}</p>
-        <p><strong>💡 Extra Skills in CV (not in Job Description):</strong> {', '.join(
+    if np