def extract_key_concepts(self) -> List[Dict]: """Extract and rank key urban planning concepts""" stop_words = set(stopwords.words('english')) # Urban planning specific terminology planning_terms = [ 'zoning', 'land use', 'transportation', 'infrastructure', 'sustainability', 'urban design', 'smart growth', 'new urbanism', 'gentrification', 'affordable housing', 'public space', 'transit-oriented development', 'mixed-use', 'walkability', 'green infrastructure', 'climate resilience', 'urban renewal', 'community engagement', 'comprehensive plan', 'subdivision', 'environmental impact', 'historic preservation', 'urban sprawl', 'density', 'parking', 'complete streets', 'placemaking' ] # Tokenize and find frequencies words = word_tokenize(self.full_text.lower()) words = [w for w in words if w.isalpha() and w not in stop_words] # Count frequencies of planning terms concept_counts = Counter() for term in planning_terms: count = self.full_text.lower().count(term) if count > 0: concept_counts[term] = count # Extract context for each concept concepts = [] for concept, count in concept_counts.most_common(20): # Find sentences containing the concept sentences = sent_tokenize(self.full_text) context_sentences = [s for s in sentences if concept.lower() in s.lower()] context = context_sentences[:2] if context_sentences else [] concepts.append( 'term': concept, 'frequency': count, 'context': context ) self.key_concepts = concepts return concepts
def _extract_principles(self) -> List[str]: """Extract core urban planning principles""" principle_patterns = [ r'(?i)principle[s]? of (.+?)[\.\n]', r'(?i)core (?:concept|principle)[s]?: (.+?)[\.\n]', r'(?i)([^.]*?(?:should|must|requires|essential|crucial|important)[^.]*?\.)' ] principles = [] for pattern in principle_patterns: matches = re.findall(pattern, self.full_text) principles.extend(matches[:5]) return principles[:10] urban planning lecture notes pdf
def search_similar_content(self, query: str, top_k: int = 3) -> List[Dict]: """Search for content similar to query using TF-IDF""" # Prepare documents (each page as a document) documents = [page['text'] for page in self.pages_text] documents.append(query) # Create TF-IDF matrix vectorizer = TfidfVectorizer(stop_words='english') tfidf_matrix = vectorizer.fit_transform(documents) # Calculate similarity cosine_similarities = cosine_similarity(tfidf_matrix[-1:], tfidf_matrix[:-1]) # Get top similar pages similar_indices = cosine_similarities.argsort()[0][-top_k:][::-1] results = [] for idx in similar_indices: if cosine_similarities[0][idx] > 0: results.append( 'page_number': self.pages_text[idx]['page_num'], 'similarity_score': float(cosine_similarities[0][idx]), 'excerpt': self.pages_text[idx]['text'][:500] ) return results def extract_key_concepts(self) ->
def _take_quiz(self): questions = self.analyzer.generate_study_questions()[:5] score = 0 print("\n📝 QUICK QUIZ (5 questions)") print("Answer in your own words, then press Enter for sample answer\n") for i, q in enumerate(questions, 1): print(f"\ni. q['question']") input("Press Enter to see sample answer...") print(f"\n Sample approach: q['hint']") print(" Review the relevant section for complete answer.\n") def main(): # Replace with your PDF path pdf_path = "urban_planning_lecture_notes.pdf" r'(?i)core (?:concept|principle)[s]?: (.+?)[\.\n]'
def generate_study_questions(self) -> List[Dict]: """Generate study questions based on key concepts and sections""" questions = [] # Generate questions from key concepts for concept in self.key_concepts[:10]: questions.append( 'type': 'concept', 'question': f"What are the key principles and applications of concept['term'] in urban planning?", 'related_concept': concept['term'], 'hint': f"Review section discussing concept['term'] (mentioned concept['frequency'] times)" ) # Generate questions from sections for section_name, section_text in list(self.sections.items())[:5]: if len(section_text) > 100: questions.append( 'type': 'section', 'question': f"Summarize the main arguments presented in 'section_name' regarding urban planning approaches.", 'related_section': section_name, 'hint': "Focus on the key definitions and examples provided" ) # Add comparative questions if len(self.case_studies) >= 2: questions.append( 'type': 'comparative', 'question': f"Compare and contrast the urban planning approaches in 'self.case_studies[0]['title']' vs 'self.case_studies[1]['title']'.", 'hint': "Consider differences in context, implementation, and outcomes" ) return questions