app.py

import pulp
import numpy as np
import pandas as pd
import streamlit as st
import gspread
from itertools import combinations

scope = ['https://www.googleapis.com/auth/spreadsheets',
          "https://www.googleapis.com/auth/drive"]

credentials = {
  "type": "service_account",
  "project_id": "sheets-api-connect-378620",
  "private_key_id": "1005124050c80d085e2c5b344345715978dd9cc9",
  "private_key": "-----BEGIN PRIVATE KEY-----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\nJuElxA33rFEjbgbzdyrE768=\n-----END PRIVATE KEY-----\n",
  "client_email": "gspread-connection@sheets-api-connect-378620.iam.gserviceaccount.com",
  "client_id": "106625872877651920064",
  "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%40sheets-api-connect-378620.iam.gserviceaccount.com"
}

gc = gspread.service_account_from_dict(credentials)

st.set_page_config(layout="wide")

american_format = {'OwnAvg': '{:.2%}'}
mma_format = {'ML_perc': '{:.2%}', 'Min_%': '{:.2%}', 'Med_%': '{:.2%}', }

@st.cache_resource(ttl = 600)
def init_baselines():
    sh = gc.open_by_url("https://docs.google.com/spreadsheets/d/17OAf4OAfW92-loMNUFvIubNmgF9111dsObybo6xhtYY/edit?gid=1468336051#gid=1468336051")
    worksheet = sh.worksheet('QB')
    all_values = worksheet.get_all_values()
    cell_vals = [row[0:11] for row in all_values[2:500]]
    frame_hold = pd.DataFrame(cell_vals, columns=['Player', 'Team', 'Salary', 'OwnAvg', 'PointsAvg', 'Points per $', 'blank', 'drop', 'drop2', 'drop3', 'GPP Rank'])
    frame_hold['PointsAvg'] = frame_hold['PointsAvg'].astype(float)
    frame_hold['OwnAvg'] = frame_hold['OwnAvg'].str.replace('%', '').astype(float)/100
    frame_hold['Floor'] = frame_hold['PointsAvg'] * .15
    frame_hold['Ceiling'] = frame_hold['PointsAvg'] * 1.85
    qb_frame = frame_hold[['Player', 'Team', 'Salary', 'OwnAvg', 'Floor', 'PointsAvg', 'Ceiling', 'Points per $', 'GPP Rank']]
    string_cols = ['Team']
    qb_frame = qb_frame.drop_duplicates(subset='Player')
    qb_frame = qb_frame.set_index('Player')
    
    for col in qb_frame.columns:
        if col not in string_cols:
            try:
                qb_frame[col] = pd.to_numeric(qb_frame[col], errors='coerce')
            except ValueError:
                pass  # Ignore columns that cannot be converted
                
    qb_frame = qb_frame.sort_values(by='GPP Rank', ascending=False)
    
    worksheet = sh.worksheet('RB')
    all_values = worksheet.get_all_values()
    cell_vals = [row[0:11] for row in all_values[2:500]]
    frame_hold = pd.DataFrame(cell_vals, columns=['Player', 'Team', 'Salary', 'OwnAvg', 'PointsAvg', 'Points per $', 'blank', 'drop', 'drop2', 'drop3', 'GPP Rank'])
    frame_hold['PointsAvg'] = frame_hold['PointsAvg'].astype(float)
    frame_hold['OwnAvg'] = frame_hold['OwnAvg'].str.replace('%', '').astype(float)/100
    frame_hold['Floor'] = frame_hold['PointsAvg'] * .15
    frame_hold['Ceiling'] = frame_hold['PointsAvg'] * 1.85
    rb_frame = frame_hold[['Player', 'Team', 'Salary', 'OwnAvg', 'Floor', 'PointsAvg', 'Ceiling', 'Points per $', 'GPP Rank']]
    string_cols = ['Team']
    rb_frame = rb_frame.drop_duplicates(subset='Player')
    rb_frame = rb_frame.set_index('Player')
    
    for col in rb_frame.columns:
        if col not in string_cols:
            try:
                rb_frame[col] = pd.to_numeric(rb_frame[col], errors='coerce')
            except ValueError:
                pass  # Ignore columns that cannot be converted
                
    rb_frame = rb_frame.sort_values(by='GPP Rank', ascending=False)
    
    worksheet = sh.worksheet('WR')
    all_values = worksheet.get_all_values()
    cell_vals = [row[0:11] for row in all_values[2:500]]
    frame_hold = pd.DataFrame(cell_vals, columns=['Player', 'Team', 'Salary', 'OwnAvg', 'PointsAvg', 'Points per $', 'blank', 'drop', 'drop2', 'drop3', 'GPP Rank'])
    frame_hold['PointsAvg'] = frame_hold['PointsAvg'].astype(float)
    frame_hold['OwnAvg'] = frame_hold['OwnAvg'].str.replace('%', '').astype(float)/100
    frame_hold['Floor'] = frame_hold['PointsAvg'] * .15
    frame_hold['Ceiling'] = frame_hold['PointsAvg'] * 1.85
    wr_frame = frame_hold[['Player', 'Team', 'Salary', 'OwnAvg', 'Floor', 'PointsAvg', 'Ceiling', 'Points per $', 'GPP Rank']]
    string_cols = ['Team']
    wr_frame = wr_frame.drop_duplicates(subset='Player')
    wr_frame = wr_frame.set_index('Player')
    
    for col in wr_frame.columns:
        if col not in string_cols:
            try:
                wr_frame[col] = pd.to_numeric(wr_frame[col], errors='coerce')
            except ValueError:
                pass  # Ignore columns that cannot be converted
                
    wr_frame = wr_frame.sort_values(by='GPP Rank', ascending=False)
    
    worksheet = sh.worksheet('Flex')
    all_values = worksheet.get_all_values()
    cell_vals = [row[0:11] for row in all_values[2:500]]
    frame_hold = pd.DataFrame(cell_vals, columns=['Player', 'Team', 'Salary', 'OwnAvg', 'PointsAvg', 'Points per $', 'blank', 'drop', 'drop2', 'drop3', 'GPP Rank'])
    frame_hold['PointsAvg'] = frame_hold['PointsAvg'].astype(float)
    frame_hold['OwnAvg'] = frame_hold['OwnAvg'].str.replace('%', '').astype(float)/100
    frame_hold['Floor'] = frame_hold['PointsAvg'] * .15
    frame_hold['Ceiling'] = frame_hold['PointsAvg'] * 1.85
    flex_frame = frame_hold[['Player', 'Team', 'Salary', 'OwnAvg', 'Floor', 'PointsAvg', 'Ceiling', 'Points per $', 'GPP Rank']]
    string_cols = ['Team']
    flex_frame = flex_frame.drop_duplicates(subset='Player')
    flex_frame = flex_frame.set_index('Player')
    
    for col in flex_frame.columns:
        if col not in string_cols:
            try:
                flex_frame[col] = pd.to_numeric(flex_frame[col], errors='coerce')
            except ValueError:
                pass  # Ignore columns that cannot be converted
                
    flex_frame = flex_frame.sort_values(by='GPP Rank', ascending=False)
    
    return qb_frame, rb_frame, wr_frame, flex_frame

@st.cache_resource()
def convert_df_to_csv(df):
    return df.to_csv().encode('utf-8')

qb_frame, rb_frame, wr_frame, flex_frame = init_baselines()

tab1, tab2, tab3, tab4 = st.tabs(['QB data', 'RB data', 'WR data', 'Flex data'])

with tab1:
    with st.container():
              st.dataframe(qb_frame.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(american_format, precision=2), height = 1000, use_container_width = True)
              st.download_button(
                      label="Export Tables",
                      data=convert_df_to_csv(qb_frame),
                      file_name='NCAAF_QB_model_export.csv',
                      mime='text/csv',
              )
with tab2:
    with st.container():
              st.dataframe(rb_frame.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(american_format, precision=2), height = 1000, use_container_width = True)
              st.download_button(
                      label="Export Tables",
                      data=convert_df_to_csv(rb_frame),
                      file_name='NCAAF_RB_model_export.csv',
                      mime='text/csv',
              )
with tab3:
    with st.container():
              st.dataframe(wr_frame.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(american_format, precision=2), height = 1000, use_container_width = True)
              st.download_button(
                      label="Export Tables",
                      data=convert_df_to_csv(wr_frame),
                      file_name='NCAAF_WR_model_export.csv',
                      mime='text/csv',
              )
with tab4:
    with st.container():
              st.dataframe(flex_frame.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(american_format, precision=2), height = 1000, use_container_width = True)
              st.download_button(
                      label="Export Tables",
                      data=convert_df_to_csv(flex_frame),
                      file_name='NCAAF_Flex_model_export.csv',
                      mime='text/csv',
              )