Add Streamlit app for NHL player statistics with MongoDB integration

app.py

@@ -0,0 +1,155 @@
+import streamlit as st
+st.set_page_config(layout="wide")
+
+for name in dir():
+    if not name.startswith('_'):
+        del globals()[name]
+
+import pulp
+import numpy as np
+import pandas as pd
+import streamlit as st
+import pymongo
+from itertools import combinations
+
+@st.cache_resource
+def init_conn():
+        uri = st.secrets['mongo_uri']
+        client = pymongo.MongoClient(uri, retryWrites=True, serverSelectionTimeoutMS=500000)
+        db = client["NHL_Database"]
+
+        return db
+    
+db = init_conn()
+
+player_roo_format = {'Top_finish': '{:.2%}','Top_5_finish': '{:.2%}', 'Top_10_finish': '{:.2%}', '20+%': '{:.2%}', '2x%': '{:.2%}', '3x%': '{:.2%}',
+                   '4x%': '{:.2%}'}
+
+@st.cache_resource(ttl=200)
+def player_stat_table():
+    collection = db["Player_Level_ROO"] 
+    cursor = collection.find()
+    player_frame = pd.DataFrame(cursor)
+    player_frame = player_frame[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%', 'Own',
+                                 'Small Field Own%', 'Large Field Own%', 'Cash Own%', 'CPT_Own', 'Site', 'Type', 'Slate', 'player_id', 'timestamp']]
+
+    collection = db["Player_Lines_ROO"] 
+    cursor = collection.find()
+    line_frame = pd.DataFrame(cursor)
+    line_frame = line_frame[['Player', 'SK1', 'SK2', 'SK3', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '50+%', '2x%', '3x%', '4x%', 'Own', 'Site', 'Type', 'Slate']]
+
+    collection = db["Player_Powerplay_ROO"] 
+    cursor = collection.find()
+    pp_frame = pd.DataFrame(cursor)
+    pp_frame = pp_frame[['Player', 'SK1', 'SK2', 'SK3', 'SK4', 'SK5', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '75+%', '2x%', '3x%', '4x%', 'Own', 'Site', 'Type', 'Slate']]
+
+    timestamp = player_frame['timestamp'].values[0]
+
+    return player_frame, line_frame, pp_frame, timestamp
+
+@st.cache_data
+def convert_df_to_csv(df):
+    return df.to_csv().encode('utf-8')
+
+player_frame, line_frame, pp_frame, timestamp = player_stat_table()
+t_stamp = f"Last Update: " + str(timestamp) + f" CST"
+
+tab1, tab2, tab3 = st.tabs(["Player Range of Outcomes", "Line Combo Range of Outcomes", "Power Play Range of Outcomes"])
+
+with tab1:
+    col1, col2 = st.columns([1, 7])
+    with col1:
+        st.info(t_stamp)
+        if st.button("Load/Reset Data", key='reset1'):
+              st.cache_data.clear()
+              player_frame, line_frame, pp_frame, timestamp = player_stat_table()
+              t_stamp = f"Last Update: " + str(timestamp) + f" CST"
+        site_var1 = st.radio("What table would you like to display?", ('Draftkings', 'Fanduel'), key='site_var1')
+        main_var1 = st.radio("Main slate or secondary slate?", ('Main Slate', 'Secondary Slate'), key='main_var1')
+        split_var1 = st.radio("Would you like to view the whole slate or just specific games?", ('Full Slate Run', 'Specific Games'), key='split_var1')
+        if split_var1 == 'Specific Games':
+            team_var1 = st.multiselect('Which teams would you like to include in the ROO?', options = player_frame['Team'].unique(), key='team_var1')
+        elif split_var1 == 'Full Slate Run':
+            team_var1 = player_frame.Team.values.tolist()
+        pos_split1 = st.radio("Are you viewing all positions, specific groups, or specific positions?", ('All Positions', 'Specific Positions'), key='pos_split1')
+        if pos_split1 == 'Specific Positions':
+            pos_var1 = st.multiselect('What Positions would you like to view?', options = ['C', 'W', 'D', 'G'])
+        elif pos_split1 == 'All Positions':
+            pos_var1 = 'All'
+        sal_var1 = st.slider("Is there a certain price range you want to view?", 2000, 10000, (2000, 20000), key='sal_var1')
+    
+    with col2:
+        final_Proj = player_frame[player_frame['Site'] == str(site_var1)]
+        final_Proj = final_Proj[final_Proj['Type'] == 'Basic']
+        final_Proj = final_Proj[final_Proj['Slate'] == main_var1]
+        final_Proj = final_Proj[player_frame['Team'].isin(team_var1)]
+        final_Proj = final_Proj[final_Proj['Salary'] >= sal_var1[0]]
+        final_Proj = final_Proj[final_Proj['Salary'] <= sal_var1[1]]
+        if pos_var1 != 'All':
+               final_Proj = final_Proj[final_Proj['Position'].str.contains('|'.join(pos_var1))]
+               final_Proj = final_Proj.sort_values(by='Median', ascending=False)
+        if pos_var1 == 'All':
+               final_Proj = final_Proj.sort_values(by='Median', ascending=False)
+        st.dataframe(final_Proj.iloc[:, :-3].style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(player_roo_format, precision=2), use_container_width = True)
+        st.download_button(
+              label="Export Tables",
+              data=convert_df_to_csv(final_Proj),
+              file_name='NHL_player_export.csv',
+              mime='text/csv',
+        )
+
+with tab2:
+    col1, col2 = st.columns([1, 7])
+    with col1:
+        st.info(t_stamp)
+        if st.button("Load/Reset Data", key='reset2'):
+              st.cache_data.clear()
+              player_frame, line_frame, pp_frame, timestamp = player_stat_table()
+              t_stamp = f"Last Update: " + str(timestamp) + f" CST"
+        site_var2 = st.radio("What table would you like to display?", ('Draftkings', 'Fanduel'), key='site_var2')
+        main_var2 = st.radio("Main slate or secondary slate?", ('Main Slate', 'Secondary Slate'), key='main_var2')
+        sal_var2 = st.slider("Is there a certain price range you want to view?", 5000, 40000, (5000, 40000), key='sal_var2')
+    
+    with col2:
+        final_line_combos = line_frame[line_frame['Site'] == str(site_var2)]
+        final_line_combos = final_line_combos[final_line_combos['Type'] == 'Basic']
+        final_line_combos = final_line_combos[final_line_combos['Slate'] == main_var2]
+        final_line_combos = final_line_combos[final_line_combos['Salary'] >= sal_var2[0]]
+        final_line_combos = final_line_combos[final_line_combos['Salary'] <= sal_var2[1]]
+        final_line_combos = final_line_combos.drop_duplicates(subset=['Player'])
+        final_line_combos = final_line_combos.sort_values(by='Median', ascending=False)
+        st.dataframe(final_line_combos.iloc[:, :-3].style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), use_container_width = True)
+        st.download_button(
+              label="Export Tables",
+              data=convert_df_to_csv(final_line_combos),
+              file_name='NHL_linecombos_export.csv',
+              mime='text/csv',
+        )
+
+with tab3:
+    col1, col2 = st.columns([1, 7])
+    with col1:
+        st.info(t_stamp)
+        if st.button("Load/Reset Data", key='reset3'):
+              st.cache_data.clear()
+              player_frame, line_frame, pp_frame, timestamp = player_stat_table()
+              t_stamp = f"Last Update: " + str(timestamp) + f" CST"
+        site_var3 = st.radio("What table would you like to display?", ('Draftkings', 'Fanduel'), key='site_var3')
+        main_var3 = st.radio("Main slate or secondary slate?", ('Main Slate', 'Secondary Slate'), key='main_var3')
+        sal_var3 = st.slider("Is there a certain price range you want to view?", 5000, 40000, (5000, 40000), key='sal_var3')
+    
+    with col2:
+        final_pp_combos = pp_frame[pp_frame['Site'] == str(site_var3)]
+        final_pp_combos = final_pp_combos[final_pp_combos['Type'] == 'Basic']
+        final_pp_combos = final_pp_combos[final_pp_combos['Slate'] == main_var3]
+        final_pp_combos = final_pp_combos[final_pp_combos['Salary'] >= sal_var3[0]]
+        final_pp_combos = final_pp_combos[final_pp_combos['Salary'] <= sal_var3[1]]
+        final_pp_combos = final_pp_combos.drop_duplicates(subset=['Player'])
+        final_pp_combos = final_pp_combos.sort_values(by='Median', ascending=False)
+        st.dataframe(final_pp_combos.iloc[:, :-3].style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), use_container_width = True)
+        st.download_button(
+              label="Export Tables",
+              data=convert_df_to_csv(final_pp_combos),
+              file_name='NHL_powerplay_export.csv',
+              mime='text/csv',
+        )

app.yaml

@@ -0,0 +1,10 @@
+runtime: python
+env: flex
+
+runtime_config:
+  python_version: 3
+
+entrypoint: streamlit run streamlit-app.py --server.port $PORT
+
+automatic_scaling:
+  max_num_instances: 200

requirements.txt

@@ -0,0 +1,10 @@
+streamlit
+gspread
+openpyxl
+matplotlib
+streamlit-aggrid
+pulp
+docker
+plotly
+scipy
+pymongo