File size: 12,063 Bytes
88c5476 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 |
import numpy as np
import pandas as pd
import streamlit as st
from itertools import combinations
import pymongo
st.set_page_config(layout="wide")
@st.cache_resource
def init_conn():
uri = st.secrets['mongo_uri']
client = pymongo.MongoClient(uri, retryWrites=True, serverSelectionTimeoutMS=500000)
db = client["MLB_Database"]
return db
db = init_conn()
game_format = {'Win Percentage': '{:.2%}','First Inning Lead Percentage': '{:.2%}',
'Fifth Inning Lead Percentage': '{:.2%}', '8+ runs': '{:.2%}', 'DK LevX': '{:.2%}', 'FD LevX': '{:.2%}'}
team_roo_format = {'Top Score%': '{:.2%}','0 Runs': '{:.2%}', '1 Run': '{:.2%}', '2 Runs': '{:.2%}', '3 Runs': '{:.2%}', '4 Runs': '{:.2%}',
'5 Runs': '{:.2%}','6 Runs': '{:.2%}', '7 Runs': '{:.2%}', '8 Runs': '{:.2%}', '9 Runs': '{:.2%}', '10 Runs': '{:.2%}'}
wrong_acro = ['WSH', 'AZ', 'CHW']
right_acro = ['WAS', 'ARI', 'CWS']
st.markdown("""
<style>
/* Tab styling */
.stTabs [data-baseweb="tab-list"] {
gap: 8px;
padding: 4px;
}
.stTabs [data-baseweb="tab"] {
height: 50px;
white-space: pre-wrap;
background-color: #FFD700;
color: white;
border-radius: 10px;
gap: 1px;
padding: 10px 20px;
font-weight: bold;
transition: all 0.3s ease;
}
.stTabs [aria-selected="true"] {
background-color: #DAA520;
color: white;
}
.stTabs [data-baseweb="tab"]:hover {
background-color: #DAA520;
cursor: pointer;
}
</style>""", unsafe_allow_html=True)
@st.cache_resource(ttl = 60)
def init_stat_load():
collection = db["Player_Range_Of_Outcomes"]
cursor = collection.find()
raw_display = pd.DataFrame(list(cursor))
raw_display = raw_display[['Player', 'Position', 'Team', 'Salary', 'Floor', 'Median', 'Ceiling', 'Own%', 'Site', 'Slate']]
raw_display = raw_display.rename(columns={'Own%': 'Own'})
initial_concat = raw_display.sort_values(by='Own', ascending=False)
return initial_concat
@st.cache_data
def convert_df_to_csv(df):
return df.to_csv().encode('utf-8')
proj_raw = init_stat_load()
col1, col2 = st.columns([1, 5])
with col1:
with st.expander("Info and Filters"):
if st.button("Load/Reset Data", key='reset1'):
st.cache_data.clear()
proj_raw, timestamp = init_stat_load()
t_stamp = f"Last Update: " + str(timestamp) + f" CST"
for key in st.session_state.keys():
del st.session_state[key]
site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel'), key='site_var1')
slate_var1 = st.radio("What slate are you working with?", ('Main Slate', 'Secondary Slate'), key='slate_var1')
if site_var1 == 'Draftkings':
raw_baselines = proj_raw[proj_raw['Site'] == 'Draftkings']
if slate_var1 == 'Main Slate':
raw_baselines = raw_baselines[raw_baselines['Slate'] == 'main_slate']
elif slate_var1 == 'Secondary Slate':
raw_baselines = raw_baselines[raw_baselines['Slate'] == 'secondary_slate']
raw_baselines = raw_baselines.sort_values(by='Own', ascending=False)
elif site_var1 == 'Fanduel':
raw_baselines = proj_raw[proj_raw['Site'] == 'Fanduel']
if slate_var1 == 'Main Slate':
raw_baselines = raw_baselines[raw_baselines['Slate'] == 'main_slate']
elif slate_var1 == 'Secondary Slate':
raw_baselines = raw_baselines[raw_baselines['Slate'] == 'secondary_slate']
raw_baselines = raw_baselines.sort_values(by='Own', ascending=False)
split_var2 = st.radio("Would you like to run stack analysis for the full slate or individual teams?", ('Full Slate Run', 'Specific Teams'), key='split_var2')
if split_var2 == 'Specific Teams':
team_var2 = st.multiselect('Which teams would you like to include in the analysis?', options = raw_baselines['Team'].unique(), key='team_var2')
elif split_var2 == 'Full Slate Run':
team_var2 = raw_baselines.Team.unique().tolist()
pos_split2 = st.radio("Are you viewing all positions, specific groups, or specific positions?", ('All Positions', 'Specific Positions'), key='pos_split2')
if pos_split2 == 'Specific Positions':
pos_var2 = st.multiselect('What Positions would you like to view?', options = ['SP', 'P', 'C', '1B', '2B', '3B', 'SS', 'OF'])
elif pos_split2 == 'All Positions':
pos_var2 = 'All'
if site_var1 == 'Draftkings':
max_sal2 = st.number_input('Max Salary', min_value = 5000, max_value = 50000, value = 35000, step = 100, key='max_sal2')
elif site_var1 == 'Fanduel':
max_sal2 = st.number_input('Max Salary', min_value = 5000, max_value = 35000, value = 25000, step = 100, key='max_sal2')
size_var2 = st.selectbox('What size of stacks are you analyzing?', options = ['3-man', '4-man', '5-man'])
if size_var2 == '3-man':
stack_size = 3
if size_var2 == '4-man':
stack_size = 4
if size_var2 == '5-man':
stack_size = 5
team_dict = dict(zip(raw_baselines.Player, raw_baselines.Team))
proj_dict = dict(zip(raw_baselines.Player, raw_baselines.Median))
own_dict = dict(zip(raw_baselines.Player, raw_baselines.Own))
cost_dict = dict(zip(raw_baselines.Player, raw_baselines.Salary))
with col2:
stack_hold_container = st.empty()
if st.button('Run stack analysis'):
comb_list = []
if pos_split2 == 'All Positions':
raw_baselines = raw_baselines
elif pos_split2 != 'All Positions':
raw_baselines = raw_baselines[raw_baselines['Position'].str.contains('|'.join(pos_var2))]
for cur_team in team_var2:
working_baselines = raw_baselines
working_baselines = working_baselines[working_baselines['Team'] == cur_team]
working_baselines = working_baselines[working_baselines['Position'] != 'SP']
working_baselines = working_baselines[working_baselines['Position'] != 'P']
order_list = working_baselines['Player']
comb = combinations(order_list, stack_size)
for i in list(comb):
comb_list.append(i)
comb_DF = pd.DataFrame(comb_list)
if stack_size == 3:
comb_DF['Team'] = comb_DF[0].map(team_dict)
comb_DF['Proj'] = sum([comb_DF[0].map(proj_dict),
comb_DF[1].map(proj_dict),
comb_DF[2].map(proj_dict)])
comb_DF['Salary'] = sum([comb_DF[0].map(cost_dict),
comb_DF[1].map(cost_dict),
comb_DF[2].map(cost_dict)])
comb_DF['Own%'] = sum([comb_DF[0].map(own_dict),
comb_DF[1].map(own_dict),
comb_DF[2].map(own_dict)])
elif stack_size == 4:
comb_DF['Team'] = comb_DF[0].map(team_dict)
comb_DF['Proj'] = sum([comb_DF[0].map(proj_dict),
comb_DF[1].map(proj_dict),
comb_DF[2].map(proj_dict),
comb_DF[3].map(proj_dict)])
comb_DF['Salary'] = sum([comb_DF[0].map(cost_dict),
comb_DF[1].map(cost_dict),
comb_DF[2].map(cost_dict),
comb_DF[3].map(cost_dict)])
comb_DF['Own%'] = sum([comb_DF[0].map(own_dict),
comb_DF[1].map(own_dict),
comb_DF[2].map(own_dict),
comb_DF[3].map(own_dict)])
elif stack_size == 5:
comb_DF['Team'] = comb_DF[0].map(team_dict)
comb_DF['Proj'] = sum([comb_DF[0].map(proj_dict),
comb_DF[1].map(proj_dict),
comb_DF[2].map(proj_dict),
comb_DF[3].map(proj_dict),
comb_DF[4].map(proj_dict)])
comb_DF['Salary'] = sum([comb_DF[0].map(cost_dict),
comb_DF[1].map(cost_dict),
comb_DF[2].map(cost_dict),
comb_DF[3].map(cost_dict),
comb_DF[4].map(cost_dict)])
comb_DF['Own%'] = sum([comb_DF[0].map(own_dict),
comb_DF[1].map(own_dict),
comb_DF[2].map(own_dict),
comb_DF[3].map(own_dict),
comb_DF[4].map(own_dict)])
comb_DF = comb_DF.sort_values(by='Proj', ascending=False)
comb_DF = comb_DF.loc[comb_DF['Salary'] <= max_sal2]
cut_var = 0
if stack_size == 3:
while cut_var <= int(len(comb_DF)):
try:
if int(cut_var) == 0:
cur_proj = float(comb_DF.iat[cut_var,4])
cur_own = float(comb_DF.iat[cut_var,6])
elif int(cut_var) >= 1:
check_own = float(comb_DF.iat[cut_var,6])
if check_own > cur_own:
comb_DF = comb_DF.drop([cut_var])
cur_own = cur_own
cut_var = cut_var - 1
comb_DF = comb_DF.reset_index()
comb_DF = comb_DF.drop(['index'], axis=1)
elif check_own <= cur_own:
cur_own = float(comb_DF.iat[cut_var,6])
cut_var = cut_var
cut_var += 1
except:
cut_var += 1
elif stack_size == 4:
while cut_var <= int(len(comb_DF)):
try:
if int(cut_var) == 0:
cur_proj = float(comb_DF.iat[cut_var,5])
cur_own = float(comb_DF.iat[cut_var,7])
elif int(cut_var) >= 1:
check_own = float(comb_DF.iat[cut_var,7])
if check_own > cur_own:
comb_DF = comb_DF.drop([cut_var])
cur_own = cur_own
cut_var = cut_var - 1
comb_DF = comb_DF.reset_index()
comb_DF = comb_DF.drop(['index'], axis=1)
elif check_own <= cur_own:
cur_own = float(comb_DF.iat[cut_var,7])
cut_var = cut_var
cut_var += 1
except:
cut_var += 1
elif stack_size == 5:
while cut_var <= int(len(comb_DF)):
try:
if int(cut_var) == 0:
cur_proj = float(comb_DF.iat[cut_var,6])
cur_own = float(comb_DF.iat[cut_var,8])
elif int(cut_var) >= 1:
check_own = float(comb_DF.iat[cut_var,8])
if check_own > cur_own:
comb_DF = comb_DF.drop([cut_var])
cur_own = cur_own
cut_var = cut_var - 1
comb_DF = comb_DF.reset_index()
comb_DF = comb_DF.drop(['index'], axis=1)
elif check_own <= cur_own:
cur_own = float(comb_DF.iat[cut_var,8])
cut_var = cut_var
cut_var += 1
except:
cut_var += 1
with stack_hold_container:
stack_hold_container = st.empty()
st.dataframe(comb_DF.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(comb_DF),
file_name='MLB_Stack_Options_export.csv',
mime='text/csv',
) |