From c860a556c8b4bc6ba483dc06734f5553ce540cca Mon Sep 17 00:00:00 2001
From: Chanin Nantasenamat <51851491+dataprofessor@users.noreply.github.com>
Date: Tue, 7 Jul 2020 16:45:55 +0700
Subject: [PATCH] Add files via upload

---
 streamlit/basketball_app.py | 68 +++++++++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)
 create mode 100644 streamlit/basketball_app.py

diff --git a/streamlit/basketball_app.py b/streamlit/basketball_app.py
new file mode 100644
index 0000000..9dc7283
--- /dev/null
+++ b/streamlit/basketball_app.py
@@ -0,0 +1,68 @@
+import streamlit as st
+import pandas as pd
+import base64
+import matplotlib.pyplot as plt
+import seaborn as sns
+import numpy as np
+
+st.title('NBA Player Stats Explorer')
+
+st.markdown("""
+This app performs simple webscraping of NBA player stats data!
+* **Python libraries:** base64, pandas, streamlit
+* **Data source:** [Basketball-reference.com](https://www.basketball-reference.com/).
+""")
+
+st.sidebar.header('User Input Features')
+selected_year = st.sidebar.selectbox('Year', list(reversed(range(1950,2020))))
+
+# Web scraping of NBA player stats
+@st.cache
+def load_data(year):
+    url = "https://www.basketball-reference.com/leagues/NBA_" + str(year) + "_per_game.html"
+    html = pd.read_html(url, header = 0)
+    df = html[0]
+    raw = df.drop(df[df.Age == 'Age'].index) # Deletes repeating headers in content
+    raw = raw.fillna(0)
+    playerstats = raw.drop(['Rk'], axis=1)
+    return playerstats
+playerstats = load_data(selected_year)
+
+# Sidebar - Team selection
+sorted_unique_team = sorted(playerstats.Tm.unique())
+selected_team = st.sidebar.multiselect('Team', sorted_unique_team, sorted_unique_team)
+
+# Sidebar - Position selection
+unique_pos = ['C','PF','SF','PG','SG']
+selected_pos = st.sidebar.multiselect('Position', unique_pos, unique_pos)
+
+# Filtering data
+df_selected_team = playerstats[(playerstats.Tm.isin(selected_team)) & (playerstats.Pos.isin(selected_pos))]
+
+st.header('Display Player Stats of Selected Team(s)')
+st.write('Data Dimension: ' + str(df_selected_team.shape[0]) + ' rows and ' + str(df_selected_team.shape[1]) + ' columns.')
+st.dataframe(df_selected_team)
+
+# Download NBA player stats data
+# https://discuss.streamlit.io/t/how-to-download-file-in-streamlit/1806
+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="playerstats.csv">Download CSV File</a>'
+    return href
+
+st.markdown(filedownload(df_selected_team), unsafe_allow_html=True)
+
+# Heatmap
+if st.button('Intercorrelation Heatmap'):
+    st.header('Intercorrelation Matrix Heatmap')
+    df_selected_team.to_csv('output.csv',index=False)
+    df = pd.read_csv('output.csv')
+
+    corr = df.corr()
+    mask = np.zeros_like(corr)
+    mask[np.triu_indices_from(mask)] = True
+    with sns.axes_style("white"):
+        f, ax = plt.subplots(figsize=(7, 5))
+        ax = sns.heatmap(corr, mask=mask, vmax=1, square=True)
+    st.pyplot()