app.py

import streamlit as st
st.set_page_config(layout="wide")
import pandas as pd
import gspread
import pymongo
import time
import numpy as np
from scipy.stats import poisson

@st.cache_resource
def init_conn():
        scope = ['https://spreadsheets.google.com/feeds', 'https://www.googleapis.com/auth/drive']

        credentials = {
          "type": "service_account",
          "project_id": "model-sheets-connect",
          "private_key_id": "0e0bc2fdef04e771172fe5807392b9d6639d945e",
          "private_key": "-----BEGIN PRIVATE KEY-----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\nF/j9eUXfXjAlb042MphoF3ZC\n-----END PRIVATE KEY-----\n",
          "client_email": "[email protected]",
          "client_id": "100369174533302798535",
          "auth_uri": "https://accounts.google.com/o/oauth2/auth",
          "token_uri": "https://oauth2.googleapis.com/token",
          "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
          "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/gspread-connection%40model-sheets-connect.iam.gserviceaccount.com"
        }
     
        MLB_Data = 'https://docs.google.com/spreadsheets/d/1f42Ergav8K1VsOLOK9MUn7DM_MLMvv4GR2Fy7EfnZTc/edit#gid=340831852'

        gc_con = gspread.service_account_from_dict(credentials, scope)

        return gc_con, MLB_Data
    
gcservice_account, MLB_Data = init_conn()

@st.cache_data(ttl = 599)
def init_baselines():
    sh = gcservice_account.open_by_url(MLB_Data)
    
    worksheet = sh.worksheet('Hitter_Data (RHP)')
    load_display = pd.DataFrame(worksheet.get_all_records())
    load_display.replace('', np.nan, inplace=True)
    load_display = load_display.dropna(subset=['PA'])
    load_display = load_display.drop_duplicates(subset=['Player'], keep='first')
    load_display= load_display.sort_values(by='Player', ascending=False)
    
    hitter_rhp = load_display.copy()
    
    time.sleep(.5)
    
    worksheet = sh.worksheet('Hitter_Data (LHP)')
    load_display = pd.DataFrame(worksheet.get_all_records())
    load_display.replace('', np.nan, inplace=True)
    load_display = load_display.dropna(subset=['PA'])
    load_display = load_display.drop_duplicates(subset=['Player'], keep='first')
    load_display= load_display.sort_values(by='Player', ascending=False)
    
    hitter_lhp = load_display.copy()
    
    time.sleep(.5)
    
    worksheet = sh.worksheet('Pitcher_Data (RHH)')
    load_display = pd.DataFrame(worksheet.get_all_records())
    load_display.replace('', np.nan, inplace=True)
    load_display = load_display.dropna(subset=['True AVG'])
    load_display= load_display.sort_values(by='Names', ascending=False)
    
    pitcher_rhh = load_display.copy()
    
    time.sleep(.5)
    
    worksheet = sh.worksheet('Pitcher_Data (LHH)')
    load_display = pd.DataFrame(worksheet.get_all_records())
    load_display.replace('', np.nan, inplace=True)
    load_display = load_display.dropna(subset=['True AVG'])
    load_display= load_display.sort_values(by='Names', ascending=False)
    
    pitcher_lhh = load_display.copy()
    
    time.sleep(.5)
    
    worksheet = sh.worksheet('Bullpen_xData')
    load_display = pd.DataFrame(worksheet.get_all_records())
    load_display.replace('', np.nan, inplace=True)
    load_display = load_display.dropna(subset=['HWS Ratio'])
    load_display= load_display.sort_values(by='Names', ascending=False)
    
    bullpen_data = load_display.copy()

    return hitter_rhp, hitter_lhp, pitcher_rhh, pitcher_lhh, bullpen_data

@st.cache_resource
def calc_poisson(hitter_val, sp_val, bp_val, sp_count, bp_count):
    base_val = hitter_val
    opp_val = sp_val
    sp_combo_val = sum([base_val, opp_val]) / 2
    bp_combo_val = sum([base_val, bp_val]) / 2
    sp_instances = sp_count
    bp_instances = bp_count
    sp_mean = sp_combo_val * sp_instances
    bp_mean = bp_combo_val * bp_instances
    
    # Generate a large number of samples from the Poisson distribution
    SP_run = poisson.rvs(sp_mean, size=10000)
    BP_run = poisson.rvs(bp_mean, size=10000)
    
    # Calculate the sample mean
    sp_outcome = np.mean(SP_run)
    bp_outcome = np.mean(BP_run)
    
    mean_outcome = sp_outcome + bp_outcome
    
    return sp_outcome, bp_outcome, mean_outcome

hitter_rhp, hitter_lhp, pitcher_rhh, pitcher_lhh, bullpen_data = init_baselines()

col1, col2 = st.columns([1, 7])

with col1:
    if st.button("Load/Reset Data", key='reset1'):
          st.cache_data.clear()
          hitter_rhp, hitter_lhp, pitcher_rhh, pitcher_lhh, bullpen_data = init_baselines()
          
    pitcher_var1 = st.selectbox("Which pitcher are you looking at?", options = pitcher_rhh['Names'].unique())
    working_pitcher = pitcher_rhh.copy()
    pitcher_check = working_pitcher[working_pitcher['Names'] == pitcher_var1]
    pitcher_hand = pitcher_check['Hand'].iloc[0]
    if pitcher_hand == 'RHP':
        hitter_var1 = st.selectbox("What hitter are you looking at?", options = hitter_rhp['Player'].unique())
        working_hitters = hitter_rhp.copy()
        hitter_check = working_hitters[working_hitters['Player'] == hitter_var1]
    else:
        hitter_var1 = st.selectbox("What hitter are you looking at?", options = hitter_lhp['Player'].unique())
        working_hitters = hitter_lhp.copy()
        hitter_check = working_hitters[working_hitters['Player'] == hitter_var1]
    bullpen_var1 = st.selectbox("Which Bullpen are you looking at?", options = bullpen_data['Names'].unique())
    working_bullpen = bullpen_data.copy()
    bullpen_check = working_bullpen[working_bullpen['Names'] == bullpen_var1]
    sp_count = st.number_input("How many PA against the Pitcher?", step = 1)
    bp_count = st.number_input("How many PA against the Bullpen?", step = 1)
    stat_var1 = st.selectbox("What Stat are you looking at?", options = ['Projected Walks', 'Projected Strikeouts', 'Projected HRs'])

with col2:
    if st.button('calculate theoretical means'):
        if stat_var1 == 'Projected Walks':
            hitter_val = hitter_check['BB%'].iloc[0]
            sp_val = pitcher_check['BB%'].iloc[0]
            bp_val = bullpen_check['Walkper'].iloc[0] / 100
        elif stat_var1 == 'Projected Strikeouts':
            hitter_val = hitter_check['K%'].iloc[0]
            sp_val = pitcher_check['K%'].iloc[0]
            bp_val = bullpen_check['Strikeoutper'].iloc[0] / 100
        elif stat_var1 == 'Projected HRs':
            hitter_val = hitter_check['xHRs'].iloc[0] / hitter_check['PA'].iloc[0]
            sp_val = pitcher_check['xHR/PA'].iloc[0]
            bp_val = bullpen_check['Homeruns'].iloc[0] / bullpen_check['PA'].iloc[0]
        value = calc_poisson(hitter_val, sp_val, bp_val, sp_count, bp_count)
        
        st.table(hitter_check)
        st.write(f"Theoretical mean of the SP instances: {value[0]}")
        st.table(pitcher_check)
        st.write(f"Theoretical mean of the BP instances: {value[1]}")
        st.table(bullpen_check)
        st.write(f"Sample mean from generated data: {value[2]}")