File size: 5,592 Bytes
814ee92 f70d907 814ee92 89a1dc0 42a07c0 89a1dc0 814ee92 b621a3b 814ee92 89a1dc0 42a07c0 89a1dc0 814ee92 b621a3b 814ee92 f70d907 814ee92 7007e97 814ee92 7007e97 814ee92 |
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 |
import streamlit as st
import pandas as pd
import numpy as np
from pymongo import MongoClient
from database import db
@st.cache_data(ttl = 599)
def init_DK_SD_seed_frames(slate, split, translation_dict):
# Now dynamic
collection = db[translation_dict[slate]]
cursor = collection.find().limit(split)
raw_display = pd.DataFrame(list(cursor))
raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
DK_seed = raw_display.to_numpy()
return DK_seed
@st.cache_data(ttl = 599)
def init_FD_SD_seed_frames(slate, split, translation_dict):
# Now dynamic
collection = db[translation_dict[slate]]
cursor = collection.find().limit(split)
raw_display = pd.DataFrame(list(cursor))
raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
FD_seed = raw_display.to_numpy()
return FD_seed
@st.cache_data(ttl = 599)
def init_SD_baselines(slate_var):
collection = db['DK_SD_NFL_ROO']
cursor = collection.find()
raw_display = pd.DataFrame(list(cursor))
raw_display = raw_display[raw_display['version'] == 'overall']
raw_display = raw_display[['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_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
raw_display = raw_display.rename(columns={'player_id': 'player_ID'})
raw_display['Small_Field_Own'] = raw_display['Large_Field_Own']
raw_display['small_CPT_Own_raw'] = (raw_display['Small_Field_Own'] / 2) * ((100 - (100-raw_display['Small_Field_Own']))/100)
small_cpt_own_var = 300 / raw_display['small_CPT_Own_raw'].sum()
raw_display['small_CPT_Own'] = raw_display['small_CPT_Own_raw'] * small_cpt_own_var
raw_display['cpt_Median'] = raw_display['Median'] * 1.25
raw_display['STDev'] = raw_display['Median'] / 4
raw_display['CPT_STDev'] = raw_display['cpt_Median'] / 4
dk_raw = raw_display.dropna(subset=['Median'])
collection = db['FD_SD_NFL_ROO']
cursor = collection.find()
raw_display = pd.DataFrame(list(cursor))
raw_display = raw_display[raw_display['version'] == 'overall']
raw_display = raw_display[['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_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
raw_display = raw_display.rename(columns={'player_id': 'player_ID'})
raw_display['Small_Field_Own'] = raw_display['Large_Field_Own']
raw_display['small_CPT_Own_raw'] = (raw_display['Small_Field_Own'] / 2) * ((100 - (100-raw_display['Small_Field_Own']))/100)
small_cpt_own_var = 300 / raw_display['small_CPT_Own_raw'].sum()
raw_display['small_CPT_Own'] = raw_display['small_CPT_Own_raw'] * small_cpt_own_var
raw_display['cpt_Median'] = raw_display['Median'] * 1.25
raw_display['STDev'] = raw_display['Median'] / 4
raw_display['CPT_STDev'] = raw_display['cpt_Median'] / 4
fd_raw = raw_display.dropna(subset=['Median'])
return dk_raw, fd_raw
@st.cache_data
def convert_df(array):
array = pd.DataFrame(array, columns=column_names)
return array.to_csv().encode('utf-8')
@st.cache_data
def calculate_SD_value_frequencies(np_array):
unique, counts = np.unique(np_array[:, :6], return_counts=True)
frequencies = counts / len(np_array) # Normalize by the number of rows
combined_array = np.column_stack((unique, frequencies))
return combined_array
@st.cache_data
def sim_SD_contest(Sim_size, seed_frame, maps_dict, Contest_Size):
SimVar = 1
Sim_Winners = []
# Pre-vectorize functions
vec_projection_map = np.vectorize(maps_dict['Projection_map'].__getitem__)
vec_cpt_projection_map = np.vectorize(maps_dict['cpt_projection_map'].__getitem__)
vec_stdev_map = np.vectorize(maps_dict['STDev_map'].__getitem__)
vec_cpt_stdev_map = np.vectorize(maps_dict['cpt_STDev_map'].__getitem__)
st.write('Simulating contest on frames')
while SimVar <= Sim_size:
fp_random = seed_frame[np.random.choice(seed_frame.shape[0], Contest_Size)]
sample_arrays1 = np.c_[
fp_random,
np.sum(np.random.normal(
loc=np.concatenate([
vec_cpt_projection_map(fp_random[:, 0:1]), # Apply cpt_projection_map to first column
vec_projection_map(fp_random[:, 1:-7]) # Apply original projection to remaining columns
], axis=1),
scale=np.concatenate([
vec_cpt_stdev_map(fp_random[:, 0:1]), # Apply cpt_projection_map to first column
vec_stdev_map(fp_random[:, 1:-7]) # Apply original projection to remaining columns
], axis=1)),
axis=1)
]
sample_arrays = sample_arrays1
final_array = sample_arrays[sample_arrays[:, 7].argsort()[::-1]]
best_lineup = final_array[final_array[:, -1].argsort(kind='stable')[::-1][:1]]
Sim_Winners.append(best_lineup)
SimVar += 1
return Sim_Winners |