박유진 내용 정리

import matplotlib.pyplot as plt plt.figure(figsize=(8, 5)) bars = plt.bar(city_counts['neighbourhood_group'], city_counts['listing_count']) # 라벨 붙이기 for bar in bars: height = bar.get_height() plt.text(bar.get_x() + bar.get_width()/2, height + 200, f'{height}', ha='center', va='bottom', fontsize=10, fontweight='bold') plt.title('대도시별 전체 숙소 수') plt.xlabel('대도시 (neighbourhood_group)') plt.ylabel('숙소 수') plt.tight_layout() plt.show()

import matplotlib.pyplot as plt import numpy as np # 지역별 평균 가격 구하기 region_price_stats = df.groupby('neighbourhood_group')['price'].agg(['mean', 'median', 'max', 'count']).sort_values(by='mean') # 평균값 반올림 (소수점 1자리) rounded_means = region_price_stats['mean'].round(1) # 시각화 plt.figure(figsize=(8, 6)) bars = plt.bar(rounded_means.index, rounded_means.values) # 라벨 추가 (막대 위에 평균 가격 표시) for bar, value in zip(bars, rounded_means): plt.text(bar.get_x() + bar.get_width()/2, bar.get_height() + 5, f'{value}', ha='center', va='bottom', fontsize=10, fontweight='bold') plt.title('지역별 평균 숙박 가격 (반올림)') plt.xlabel('지역 (neighbourhood_group)') plt.ylabel('평균 가격 ($)') plt.xticks(rotation=45) plt.tight_layout() plt.show()

import matplotlib.pyplot as plt import seaborn as sns # 데이터 준비 roomtype_counts = df.groupby(['neighbourhood_group', 'room_type']).size().reset_index(name='count') # 시각화 plt.figure(figsize=(10, 6)) ax = sns.barplot(data=roomtype_counts, x='neighbourhood_group', y='count', hue='room_type') # 막대 위에 값 표시 (굵게, 중앙 정렬) for container in ax.containers: ax.bar_label(container, fmt='%d', label_type='edge', fontsize=10, fontweight='bold') # 그래프 제목 및 축 plt.title('대도시별 방타입 구성 (숙소 수)', fontsize=14, fontweight='bold') plt.xlabel('대도시 (neighbourhood_group)', fontsize=12) plt.ylabel('숙소 수', fontsize=12) plt.legend(title='Room Type') plt.tight_layout() plt.show()

import pandas as pd import matplotlib.pyplot as plt # 1️⃣ 대도시별 동네 수 세기 city_neigh_counts = df.groupby('neighbourhood_group')['neighbourhood'].nunique().reset_index() city_neigh_counts.columns = ['neighbourhood_group', 'num_neighbourhoods'] # 2️⃣ 표 출력 print("📋 대도시별 포함된 동네 수") display(city_neigh_counts) # 주피터/콜랩 환경에서는 이게 예쁘게 출력됨 # 3️⃣ 막대그래프 시각화 plt.figure(figsize=(8, 5)) bars = plt.bar(city_neigh_counts['neighbourhood_group'], city_neigh_counts['num_neighbourhoods']) # 숫자 라벨 추가 for bar in bars: height = bar.get_height() plt.text(bar.get_x() + bar.get_width()/2, height + 1, f'{int(height)}', ha='center', va='bottom', fontsize=10, fontweight='bold') plt.title('대도시별 포함된 동네 수 (개수 기준)') plt.ylabel('동네 수') plt.xlabel('대도시 (neighbourhood_group)') plt.xticks(rotation=45) plt.tight_layout() plt.show()

# 전체에서 고유한 지역 수 확인 num_neighbourhoods = df['neighbourhood'].nunique() print(f"전체 지역(동네)의 수는 총 {num_neighbourhoods}개입니다.")

# 피벗: 대도시 + 동네를 인덱스로, room_type을 컬럼으로 pivot_df = roomtype_ratio.pivot_table( index=['neighbourhood_group', 'neighbourhood'], columns='room_type', values='ratio', fill_value=0 ).reset_index()

import matplotlib.pyplot as plt # 맨해튼 필터링 manhattan_df = pivot_df[pivot_df['neighbourhood_group'] == 'Manhattan'] # 인덱스 설정 manhattan_df = manhattan_df.set_index('neighbourhood') # 방타입만 선택 (비율) room_types = ['Entire home/apt', 'Private room', 'Shared room'] manhattan_df = manhattan_df[room_types] # 시각화 manhattan_df.plot(kind='bar', stacked=True, figsize=(12, 6)) plt.title('🗽 맨해튼 지역별 방타입 비율') plt.ylabel('비율 (%)') plt.xlabel('동네') plt.xticks(rotation=45, ha='right') plt.legend(title='Room Type') plt.tight_layout() plt.show()

import matplotlib.pyplot as plt import seaborn as sns # 브루클린 데이터만 추출 brooklyn = roomtype_ratio[roomtype_ratio['neighbourhood_group'] == 'Brooklyn'] # 시각화 plt.figure(figsize=(16, 6)) sns.barplot( data=brooklyn, x='neighbourhood', y='ratio', hue='room_type' ) plt.title('🏙 브루클린 지역별 방타입 비율') plt.xlabel('동네') plt.ylabel('비율 (%)') plt.xticks(rotation=90) plt.legend(title='Room Type') plt.tight_layout() plt.show()

import matplotlib.pyplot as plt import seaborn as sns # 브루클린 데이터만 피벗 brooklyn_pivot = roomtype_ratio[roomtype_ratio['neighbourhood_group'] == 'Brooklyn'] \ .pivot(index='neighbourhood', columns='room_type', values='ratio') # 히트맵 그리기 plt.figure(figsize=(12, 16)) sns.heatmap( brooklyn_pivot, annot=True, # 숫자 표시 fmt='.1f', # 소수점 한 자리 cmap='YlGnBu', # 색상맵 linewidths=0.3, # 셀 사이 경계선 cbar_kws={'label': '방타입 비율 (%)'} # 색상바에 라벨 추가! ) plt.title('🔥 브루클린 지역별 방타입 비율 히트맵', fontsize=14, fontweight='bold') plt.xlabel('Room Type') plt.ylabel('동네') plt.xticks(rotation=0) plt.tight_layout() plt.show()

import pandas as pd import matplotlib.pyplot as plt import seaborn as sns # 데이터 불러오기 df = pd.read_csv('AB_NYC_2019.csv') # 파일 경로에 맞게 수정해주세요! # 1. 지역별 방타입 숙소 수 계산 roomtype_by_area = df.groupby(['neighbourhood_group', 'neighbourhood', 'room_type']).size().reset_index(name='count') # 2. 동네별 총 숙소 수 total_by_area = roomtype_by_area.groupby(['neighbourhood_group', 'neighbourhood'])['count'].sum().reset_index(name='total') # 3. 비율 계산 roomtype_ratio = roomtype_by_area.merge(total_by_area, on=['neighbourhood_group', 'neighbourhood']) roomtype_ratio['ratio'] = (roomtype_ratio['count'] / roomtype_ratio['total'] * 100).round(1) # 4. 퀸스 데이터만 필터링 queens = roomtype_ratio[roomtype_ratio['neighbourhood_group'] == 'Queens'] # 5. 시각화 plt.figure(figsize=(16, 6)) sns.barplot( data=queens, x='neighbourhood', y='ratio', hue='room_type' ) plt.title('🏙 퀸스 지역별 방타입 비율') plt.xlabel('동네') plt.ylabel('비율 (%)') plt.xticks(rotation=90) plt.legend(title='Room Type') plt.tight_layout() plt.show()

import pandas as pd import matplotlib.pyplot as plt import seaborn as sns # 데이터 불러오기 df = pd.read_csv('AB_NYC_2019.csv') # 1. 지역별 방타입별 숙소 수 계산 roomtype_by_area = df.groupby(['neighbourhood_group', 'neighbourhood', 'room_type']).size().reset_index(name='count') # 2. 동네별 총 숙소 수 total_by_area = roomtype_by_area.groupby(['neighbourhood_group', 'neighbourhood'])['count'].sum().reset_index(name='total') # 3. 병합하여 방타입 비율 계산 roomtype_ratio = roomtype_by_area.merge(total_by_area, on=['neighbourhood_group', 'neighbourhood']) roomtype_ratio['ratio'] = (roomtype_ratio['count'] / roomtype_ratio['total'] * 100).round(1) # 4. 퀸스 데이터만 필터링 queens = roomtype_ratio[roomtype_ratio['neighbourhood_group'] == 'Queens'] # 5. 히트맵용 데이터 변환 heatmap_data = queens.pivot(index='neighbourhood', columns='room_type', values='ratio') # 6. 히트맵 시각화 plt.figure(figsize=(12, 10)) sns.heatmap(heatmap_data, annot=True, fmt=".1f", cmap='Blues') plt.title('퀸스 지역별 방타입 비율 히트맵') plt.xlabel('Room Type') plt.ylabel('Neighbourhood') plt.tight_layout() plt.show()

import pandas as pd import matplotlib.pyplot as plt import seaborn as sns # CSV 데이터 불러오기 df = pd.read_csv('AB_NYC_2019.csv') # 1. 지역별 방타입별 숙소 수 roomtype_by_area = df.groupby(['neighbourhood_group', 'neighbourhood', 'room_type']).size().reset_index(name='count') # 2. 동네별 전체 숙소 수 total_by_area = roomtype_by_area.groupby(['neighbourhood_group', 'neighbourhood'])['count'].sum().reset_index(name='total') # 3. 병합하여 비율 계산 roomtype_ratio = roomtype_by_area.merge(total_by_area, on=['neighbourhood_group', 'neighbourhood']) roomtype_ratio['ratio'] = (roomtype_ratio['count'] / roomtype_ratio['total'] * 100).round(1) # 4. 🟠 브롱크스만 필터링 bronx = roomtype_ratio[roomtype_ratio['neighbourhood_group'] == 'Bronx'] # 5. 피벗 테이블로 히트맵용 데이터 구성 heatmap_data = bronx.pivot(index='neighbourhood', columns='room_type', values='ratio') # 6. 히트맵 시각화 plt.figure(figsize=(12, 8)) sns.heatmap(heatmap_data, annot=True, fmt=".1f", cmap='Oranges') plt.title('브롱크스 지역별 방타입 비율 히트맵') plt.xlabel('Room Type') plt.ylabel('Neighbourhood') plt.tight_layout() plt.show()

import pandas as pd import matplotlib.pyplot as plt import seaborn as sns # CSV 데이터 불러오기 df = pd.read_csv('AB_NYC_2019.csv') # 1. 지역별 방타입별 숙소 수 계산 roomtype_by_area = df.groupby(['neighbourhood_group', 'neighbourhood', 'room_type']).size().reset_index(name='count') # 2. 동네별 전체 숙소 수 total_by_area = roomtype_by_area.groupby(['neighbourhood_group', 'neighbourhood'])['count'].sum().reset_index(name='total') # 3. 병합하여 비율 계산 roomtype_ratio = roomtype_by_area.merge(total_by_area, on=['neighbourhood_group', 'neighbourhood']) roomtype_ratio['ratio'] = (roomtype_ratio['count'] / roomtype_ratio['total'] * 100).round(1) # 4. 💚 Staten Island만 필터링 staten = roomtype_ratio[roomtype_ratio['neighbourhood_group'] == 'Staten Island'] # 5. 히트맵용 데이터 구성 heatmap_data = staten.pivot(index='neighbourhood', columns='room_type', values='ratio') # 6. 히트맵 시각화 plt.figure(figsize=(10, 6)) sns.heatmap(heatmap_data, annot=True, fmt=".1f", cmap='Greens') plt.title('Staten Island 지역별 방타입 비율 히트맵') plt.xlabel('Room Type') plt.ylabel('Neighbourhood') plt.tight_layout() plt.show()

import pandas as pd import matplotlib.pyplot as plt import seaborn as sns # CSV 파일 불러오기 df = pd.read_csv('AB_NYC_2019.csv') # 대도시별, 방타입별 평균 가격 계산 city_room_price = ( df.groupby(['neighbourhood_group', 'room_type'])['price'] .mean() .round(1) .reset_index() ) # 시각화 (막대그래프 + 숫자 라벨) plt.figure(figsize=(12, 8)) ax = sns.barplot( data=city_room_price, x='neighbourhood_group', y='price', hue='room_type' ) # 제목 및 축 설정 plt.title('대도시별 방타입 평균 숙소 가격', fontsize=16, fontweight='bold') plt.xlabel('대도시 (neighbourhood_group)', fontsize=12) plt.ylabel('평균 가격 ($)', fontsize=12) # 막대 위에 숫자 표시 for p in ax.patches: height = p.get_height() if not pd.isna(height): ax.annotate(f'{height:.0f}', (p.get_x() + p.get_width() / 2., height + 3), ha='center', va='bottom', fontsize=10, fontweight='bold') # 범례 설정 plt.legend(title='Room Type', bbox_to_anchor=(1.05, 1), loc='upper left') plt.tight_layout() plt.show()