Upload app.py

app.py

@@ -0,0 +1,153 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+import pandas_bokeh
+import seaborn as sns
+from pytrends.request import TrendReq
+import time
+import random
+# 글 쓰기(링크 삽입)
+st.title('VIETNAM DONGDAEMUN FOOOOOOOOOD!!!!!!!!!')
+
+st.header('Selection of Vietnamese Restaurants in Dongdaemun Area')
+st.subheader('Variety of dishes from different region in Vietnam, made affordable and delicious for local taste')
+st.subheader('Items such as Pho Soup, Bun Bo Hue, Cha Gio or Com Chien')
+st.write('''Write something here about the booming of Vietnamese Restaurant in Korea - particularly the fast growing food scene in Dongdaemun [푸드트럭](https://namu.wiki/w/%EB%B2%A0%ED%8A%B8%EB%82%A8%20%EC%9A%94%EB%A6%AC)
+.''' )
+
+# 사진 삽입
+st.image('final_image_2.jpg', caption='A Spread of Vietnamese Dishes You Might Be Able To Find')
+
+st.image('final_image_4.jpg', caption='A popular choice everywhere: Vietnamese Pho Soup')
+
+st.image('final_image_3.jpg', caption='Hidden Gem: Banh Xeo')
+
+
+st.header('Cheap and Delicious: One can find a variety of Vietnamese Restaurant in Dongdaemun Area')
+st.subheader('Hosting dishes from North to South Vietnam')
+st.subheader('The almost infinite choices will leave you looking for reviews!')
+st.write('''Before deciding on which dish you'd want ~ carefully browse through the Blog section for an intimate look at the local food joints''' )
+
+# 데이터 보여주기
+df_동대문구_베트남_맛집 = pd.read_excel('vietnam_food_dongdaemun_BLOGS.xlsx', index_col=0)
+st.write('We have narrowed down to 150 most relevant blogs!!',df_동대문구_베트남_맛집)
+
+df_동대문구_베트남_맛집_keyword = pd.read_excel('vietnam_food_KEYWORDS.xlsx', index_col=0)
+st.write('블로그 글에서 가장 많이 출현한 단어는 ~~~ 설명~~~', df_동대문구_베트남_맛집_keyword)
+
+
+
+# 워드클라우드 - WORDCLOUD
+st.write('주요  단어들을 워드클라우드로 보여주면 다음과 같다')
+st.image('final_WORDCLOUD.png')
+
+
+
+# 연결망 분석 - NETWORK
+st.write('''취재팀은 주요  단어들 간에 공동출현하는 관계를 바탕으로 의미연결망을 그려보았다.
+        분석결과, ~~설명~~''')
+st.image('final_NETWORK.png')
+
+#### The Section Below Is Extra Stuff We Gotta Think About
+
+#
+df_동대문구_베트남_맛집_2 = pd.read_excel('vietnam_food_dongdaemun_BLOGS.xlsx', index_col=0)
+st.write('Again, the list of blog posts on Dongdaemun Vietnamese Restaurant', df_동대문구_베트남_맛집_2)
+
+# 검색어 입력 받아 출력
+query = st.text_input('Enter Keyword such as: food name, restaurant name', key='region1_input')
+df_동대문구_베트남_맛집_2['select1']=df_동대문구_베트남_맛집_2['text'].apply(lambda x: 1 if query in x else 0)
+st.write('검색 결과:', df_동대문구_베트남_맛집_2[df_동대문구_베트남_맛집_2['select1']==1])
+
+##### HEATMAP #####
+
+
+# List of user-agents to rotate
+USER_AGENTS = [
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:91.0) Gecko/20100101 Firefox/91.0',
+    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:90.0) Gecko/20100101 Firefox/90.0'
+]
+
+def fetch_trends_data(kw_list, timeframe, geo):
+    pytrends = TrendReq(hl='en-US', tz=360)
+    pytrends.build_payload(kw_list, timeframe=timeframe, geo=geo)
+    df_trends = pytrends.interest_over_time()
+
+    # Introduce random delays to avoid being blocked
+    time.sleep(random.uniform(1, 5))
+    
+    # Rotate user-agents
+    user_agent = random.choice(USER_AGENTS)
+    pytrends = TrendReq(hl='en-US', tz=360, custom_useragent=user_agent)
+    pytrends.build_payload(kw_list, timeframe=timeframe, geo=geo)
+    df_trends = pytrends.interest_over_time()
+
+    return df_trends
+
+# Fetch data for the year 2023
+kw_list = ['베트남 음식']
+timeframe = '2023-01-01 2023-12-31'
+geo = 'KR'
+
+df_trends = fetch_trends_data(kw_list, timeframe, geo)
+
+# Streamlit app
+st.title('Monthly Google Trends Data for Vietnamese Food in Seoul (2023)')
+if not df_trends.empty:
+    df_trends = df_trends.drop(columns=['isPartial'])
+    df_trends.reset_index(inplace=True)
+    
+    # Extract month from date
+    df_trends['month'] = df_trends['date'].dt.to_period('M')
+    monthly_counts = df_trends.groupby('month')[kw_list].sum().reset_index()
+    
+    # Display the data
+    st.write('Number of searches for each month:')
+    st.write(monthly_counts)
+    
+    # Create the heatmap
+    plt.figure(figsize=(10, 6))
+    monthly_counts_pivot = monthly_counts.pivot_table(index='month', values=kw_list)
+    sns.heatmap(monthly_counts_pivot.T, annot=True, fmt="d", cmap='YlGnBu', cbar=False)
+    st.pyplot(plt)
+else:
+    st.write("No data received from Google Trends.")
+
+# 교통사고 유형과 연도에 따른 pivot table 보여주기
+#df_교통사고_pivot=df_교통사고.pivot_table(index='사고유형구분', columns='사고연도', values='사고건수', aggfunc='sum')
+#df_교통사고_heatmap=df_교통사고_pivot.style.background_gradient(cmap='Oranges').format("{:.2f}")
+#st.write('다음 표는 교통사고 건수를 유형과 연도에 따라 구분한 것이다', df_교통사고_heatmap)
+
+# 검색어 입력 받아 pivot table 출력
+#query_pivot = st.text_input('이 곳에 지역명(시군구)을 입력하면 관련 데이터만 검색해 보여줍니다', key='region2_input')
+#df_교통사고['select2']=df_교통사고['사고지역위치명'].apply(lambda x: 1 if query_pivot in x else 0)
+#df_교통사고_pivot_selected=df_교통사고[df_교통사고['select2']==1].pivot_table(index='사고유형구분', columns='사고연도', values='사고건수', aggfunc='sum')
+#df_교통사고_heatmap_selected=df_교통사고_pivot_selected.style.background_gradient(cmap='Oranges').format("{:.2f}")
+#st.write('검색 결과:', df_교통사고_heatmap_selected)
+
+# pandas_bokeh 그래프 보여주기
+#st.write('전국 교통사고 데이터에 따르면, 사고건수와 중상자수는 밀접한 관련을 맺고 있다. ~~~설명~~. *그래프 내 점에 커서를 대면 지역명이 나타난다')
+#p_scatter = df_교통사고.plot_bokeh.scatter(
+#    x="사고건수",
+#    y="중상자수",
+#    title="사고건수와 중상자수",
+#    size=10,
+#    hovertool_string="""<h6>위치:@{사고지역위치명}</h6>"""
+#)
+#st.bokeh_chart(p_scatter, use_container_width=True)
+
+# 선택한 조건에 따라 출력
+#option = st.selectbox('연도를 선택하면 해당 시기의 그래프를 보여줍니다',
+#                 (2012, 2013, 2014, 2015, 2016, 2018, 2017, 2019, 2020, 2021), key='year_input')
+
+#p_scatter_selected = df_교통사고[df_교통사고['사고연도']==option].plot_bokeh.scatter(
+#    x="사고건수",
+#    y="중상자수",
+#    title="사고건수와 중상자수",
+#    size=10,
+#    hovertool_string="""<h6>위치:@{사고지역위치명}</h6>"""
+#)
+#st.write('검색 결과:')
+#st.bokeh_chart(p_scatter_selected, use_container_width=True)