Create app.py

app.py

@@ -0,0 +1,76 @@
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+import base64
+import yfinance as yf
+import streamlit as st
+st.set_option('deprecation.showPyplotGlobalUse', False)
+
+st.title('Scrapping Yahoo Finance App')
+st.markdown("""
+This app retrieves the list of the S&P 500 (from Wikipedia) and its corresponding stock closing price (year-to-date)!
+* Python libraries: base64, pandas, streamlit, numpy, matplotlib, seaborn
+* Data source: [Wikipedia](https://en.wikipedia.org/wiki/List_of_S%26P_500_companies).
+""")
+st.sidebar.header('User Input Features')
+
+#Scrappage des donnees sur Wikipedia
+@st.cache_data
+def load_data():
+    url = "https://en.wikipedia.org/wiki/List_of_S%26P_500_companies"
+    html = pd.read_html(url,header= 0)
+    df = html[0]
+    return df
+df = load_data()
+sector = df.groupby('GICS Sector')
+
+#Sidebar - Sector Selection
+sorted_sector_unique = sorted(df['GICS Sector'].unique())
+selected_sector = st.sidebar.multiselect('Sector',sorted_sector_unique)
+
+
+#Filtering datas
+df_selected_sector = df[(df['GICS Sector'].isin(selected_sector))]
+st.header('Display companies in Selected sector')
+st.write('Data Dimension: ' + str(df_selected_sector.shape[0]) + ' rows and ' + str(df_selected_sector.shape[1]) + ' columns.')
+st.dataframe(df_selected_sector)
+
+#Download des datas selectionnees dans le sidebar
+def filedownload(df):
+    csv = df.to_csv(index=False)
+    b64 = base64.b64encode(csv.encode()).decode()  # strings <-> bytes conversions
+    href = f'<a href="data:file/csv;base64,{b64}" download="SP500.csv">Download CSV File</a>'
+    return href
+
+st.markdown(filedownload(df_selected_sector), unsafe_allow_html=True)
+
+#Download datas correspondantes de yahoo finance
+data = yf.download(
+    tickers = list(df_selected_sector[:10].Symbol),
+    period="ytd",
+    interval="1d",
+    group_by="ticker",
+    auto_adjust=True,
+    prepost=True,
+    threads=True,
+    proxy=None
+)
+#Plot Closing price of Selected Symbols
+def price_plot(symbol):
+  df = pd.DataFrame(data[symbol].Close)
+  df['Date'] = df.index
+  plt.fill_between(df.Date, df.Close, color='skyblue', alpha=0.3)
+  plt.plot(df.Date, df.Close, color='skyblue', alpha=0.8)
+  plt.xticks(rotation=90)
+  plt.title(symbol, fontweight='bold')
+  plt.xlabel('Date', fontweight='bold')
+  plt.ylabel('Closing Price', fontweight='bold')
+  return st.pyplot()
+
+num_company = st.sidebar.slider('Number of companies',1,5)
+
+if st.button('Show plots'):
+   st.header('Show Closing price')
+   for i in list(df_selected_sector.Symbol)[:num_company]:
+      price_plot(i)