Update app.py
Browse files
app.py
CHANGED
|
@@ -1,843 +1,843 @@
|
|
| 1 |
-
import polars as pl
|
| 2 |
-
import api_scraper
|
| 3 |
-
import pandas as pd
|
| 4 |
-
scrape = api_scraper.MLB_Scrape()
|
| 5 |
-
|
| 6 |
-
# import df_update
|
| 7 |
-
# update = df_update.df_update()
|
| 8 |
-
from matplotlib.colors import LinearSegmentedColormap, Normalize
|
| 9 |
-
import numpy as np
|
| 10 |
-
import requests
|
| 11 |
-
from io import BytesIO
|
| 12 |
-
from PIL import Image
|
| 13 |
-
from matplotlib.gridspec import GridSpec
|
| 14 |
-
|
| 15 |
-
import matplotlib.pyplot as plt
|
| 16 |
-
import matplotlib.patches as patches
|
| 17 |
-
import PIL
|
| 18 |
-
|
| 19 |
-
level_dict = {
|
| 20 |
-
'11':'AAA',
|
| 21 |
-
'14':'A',}
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
def player_bio(pitcher_id: str, ax: plt.Axes, sport_id: int, year_input: int):
|
| 26 |
-
"""
|
| 27 |
-
Display the player's bio information on the given axis.
|
| 28 |
-
Parameters
|
| 29 |
-
----------
|
| 30 |
-
pitcher_id : str
|
| 31 |
-
The player's ID.
|
| 32 |
-
ax : plt.Axes
|
| 33 |
-
The axis to display the bio information on.
|
| 34 |
-
sport_id : int
|
| 35 |
-
The sport ID (1 for MLB, other for minor leagues).
|
| 36 |
-
year_input : int
|
| 37 |
-
The season year.
|
| 38 |
-
"""
|
| 39 |
-
# Construct the URL to fetch player data
|
| 40 |
-
url = f"https://statsapi.mlb.com/api/v1/people?personIds={pitcher_id}&hydrate=currentTeam"
|
| 41 |
-
|
| 42 |
-
# Send a GET request to the URL and parse the JSON response
|
| 43 |
-
data = requests.get(url).json()
|
| 44 |
-
|
| 45 |
-
# Extract player information from the JSON data
|
| 46 |
-
player_name = data['people'][0]['fullName']
|
| 47 |
-
position = data['people'][0]['primaryPosition']['abbreviation']
|
| 48 |
-
bat_side = data['people'][0]['batSide']['code']
|
| 49 |
-
pitcher_hand = data['people'][0]['pitchHand']['code']
|
| 50 |
-
age = data['people'][0]['currentAge']
|
| 51 |
-
height = data['people'][0]['height']
|
| 52 |
-
weight = data['people'][0]['weight']
|
| 53 |
-
|
| 54 |
-
# Display the player's name, handedness, age, height, and weight on the axis
|
| 55 |
-
ax.text(0.5, 1, f'{player_name}', va='top', ha='center', fontsize=30)
|
| 56 |
-
ax.text(0.5, 0.65, f'{position}, B/T: {bat_side}/{pitcher_hand}, Age: {age}, {height}/{weight}', va='top', ha='center', fontsize=20)
|
| 57 |
-
if position == 'P':
|
| 58 |
-
ax.text(0.5, 0.38, f'Season Pitching Percentiles', va='top', ha='center', fontsize=16)
|
| 59 |
-
else:
|
| 60 |
-
ax.text(0.5, 0.41, f'Season Batting Percentiles', va='top', ha='center', fontsize=16)
|
| 61 |
-
|
| 62 |
-
# Make API call to retrieve sports information
|
| 63 |
-
response = requests.get(url='https://statsapi.mlb.com/api/v1/sports').json()
|
| 64 |
-
|
| 65 |
-
# Convert the JSON response into a Polars DataFrame
|
| 66 |
-
df_sport_id = pl.DataFrame(response['sports'])
|
| 67 |
-
abb = df_sport_id.filter(pl.col('id') == sport_id)['abbreviation'][0]
|
| 68 |
-
|
| 69 |
-
# Display the season and sport abbreviation
|
| 70 |
-
ax.text(0.5, 0.20, f'{year_input} {abb} Season', va='top', ha='center', fontsize=14, fontstyle='italic')
|
| 71 |
-
|
| 72 |
-
# Turn off the axis
|
| 73 |
-
ax.axis('off')
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
df_teams = scrape.get_teams()
|
| 77 |
-
team_dict = dict(zip(df_teams['team_id'],df_teams['parent_org_abbreviation']))
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
# List of MLB teams and their corresponding ESPN logo URLs
|
| 81 |
-
mlb_teams = [
|
| 82 |
-
{"team": "AZ", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/ari.png&h=500&w=500"},
|
| 83 |
-
{"team": "ATH", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/oak.png&h=500&w=500"},
|
| 84 |
-
{"team": "ATL", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/atl.png&h=500&w=500"},
|
| 85 |
-
{"team": "BAL", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/bal.png&h=500&w=500"},
|
| 86 |
-
{"team": "BOS", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/bos.png&h=500&w=500"},
|
| 87 |
-
{"team": "CHC", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/chc.png&h=500&w=500"},
|
| 88 |
-
{"team": "CWS", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/chw.png&h=500&w=500"},
|
| 89 |
-
{"team": "CIN", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/cin.png&h=500&w=500"},
|
| 90 |
-
{"team": "CLE", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/cle.png&h=500&w=500"},
|
| 91 |
-
{"team": "COL", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/col.png&h=500&w=500"},
|
| 92 |
-
{"team": "DET", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/det.png&h=500&w=500"},
|
| 93 |
-
{"team": "HOU", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/hou.png&h=500&w=500"},
|
| 94 |
-
{"team": "KC", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/kc.png&h=500&w=500"},
|
| 95 |
-
{"team": "LAA", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/laa.png&h=500&w=500"},
|
| 96 |
-
{"team": "LAD", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/lad.png&h=500&w=500"},
|
| 97 |
-
{"team": "MIA", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/mia.png&h=500&w=500"},
|
| 98 |
-
{"team": "MIL", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/mil.png&h=500&w=500"},
|
| 99 |
-
{"team": "MIN", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/min.png&h=500&w=500"},
|
| 100 |
-
{"team": "NYM", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/nym.png&h=500&w=500"},
|
| 101 |
-
{"team": "NYY", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/nyy.png&h=500&w=500"},
|
| 102 |
-
{"team": "PHI", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/phi.png&h=500&w=500"},
|
| 103 |
-
{"team": "PIT", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/pit.png&h=500&w=500"},
|
| 104 |
-
{"team": "SD", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/sd.png&h=500&w=500"},
|
| 105 |
-
{"team": "SF", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/sf.png&h=500&w=500"},
|
| 106 |
-
{"team": "SEA", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/sea.png&h=500&w=500"},
|
| 107 |
-
{"team": "STL", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/stl.png&h=500&w=500"},
|
| 108 |
-
{"team": "TB", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/tb.png&h=500&w=500"},
|
| 109 |
-
{"team": "TEX", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/tex.png&h=500&w=500"},
|
| 110 |
-
{"team": "TOR", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/tor.png&h=500&w=500"},
|
| 111 |
-
{"team": "WSH", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/wsh.png&h=500&w=500"},
|
| 112 |
-
{"team": "ZZZ", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/leagues/500/mlb.png&w=500&h=500"}
|
| 113 |
-
]
|
| 114 |
-
|
| 115 |
-
df_image = pd.DataFrame(mlb_teams)
|
| 116 |
-
image_dict = df_image.set_index('team')['logo_url'].to_dict()
|
| 117 |
-
image_dict_flip = df_image.set_index('logo_url')['team'].to_dict()
|
| 118 |
-
|
| 119 |
-
# level_dict = {'1':'MLB',
|
| 120 |
-
# '11':'AAA'}
|
| 121 |
-
|
| 122 |
-
level_dict = {
|
| 123 |
-
'11':'AAA',
|
| 124 |
-
'14':'A (FSL)',}
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
level_dict_file = {
|
| 128 |
-
'11':'aaa',
|
| 129 |
-
'14':'a',}
|
| 130 |
-
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
year_list = [2024]
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
from shiny import App, reactive, ui, render
|
| 137 |
-
from shiny.ui import h2, tags
|
| 138 |
-
|
| 139 |
-
# Define the UI layout for the app
|
| 140 |
-
app_ui = ui.page_fluid(
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
ui.tags.div(
|
| 144 |
-
{"style": "width:90%;margin: 0 auto;max-width: 1600px;"},
|
| 145 |
-
ui.tags.style(
|
| 146 |
-
"""
|
| 147 |
-
h4 {
|
| 148 |
-
margin-top: 1em;font-size:35px;
|
| 149 |
-
}
|
| 150 |
-
h2{
|
| 151 |
-
font-size:25px;
|
| 152 |
-
}
|
| 153 |
-
"""
|
| 154 |
-
),
|
| 155 |
-
|
| 156 |
-
ui.tags.h4("TJStats"),
|
| 157 |
-
ui.tags.i("Baseball Analytics and Visualizations"),
|
| 158 |
-
ui.markdown("""<a href='https://x.com/TJStats'>Follow me on Twitter</a><sup>1</sup>"""),
|
| 159 |
-
ui.markdown("""<a href='https://www.patreon.com/tj_stats'>Support me on Patreon for Access to 2024 Apps</a><sup>1</sup>"""),
|
| 160 |
-
|
| 161 |
-
ui.markdown("### MiLB Statcast Batting Summaries"),
|
| 162 |
-
ui.markdown("""This Shiny App allows you to generate Baseball Savant-style percentile bars for MiLB players in the 2024 Season.
|
| 163 |
-
Currently, MiLB Statcast is only available for AAA and A (Florida State League) levels."""),
|
| 164 |
-
|
| 165 |
-
ui.layout_sidebar(
|
| 166 |
-
ui.panel_sidebar(
|
| 167 |
-
# Row for selecting season and level
|
| 168 |
-
ui.row(
|
| 169 |
-
ui.column(6, ui.input_select('year_input', 'Select Season', year_list, selected=2024)),
|
| 170 |
-
ui.column(6, ui.input_select('level_input', 'Select Level', level_dict)),
|
| 171 |
-
),
|
| 172 |
-
# Row for the action button to get player list
|
| 173 |
-
ui.row(ui.input_action_button("player_button", "Get Player List", class_="btn-primary")),
|
| 174 |
-
# Row for selecting the player
|
| 175 |
-
ui.row(ui.column(12, ui.output_ui('player_select_ui', 'Select Player'))),
|
| 176 |
-
|
| 177 |
-
ui.row(
|
| 178 |
-
ui.column(6, ui.input_switch("switch", "Custom Team?", False)),
|
| 179 |
-
ui.column(6, ui.input_select('logo_select', 'Select Custom Logo', image_dict_flip, multiple=False))
|
| 180 |
-
),
|
| 181 |
-
|
| 182 |
-
# Row for the action button to generate plot
|
| 183 |
-
ui.row(ui.input_action_button("generate_plot", "Generate Plot", class_="btn-primary")),
|
| 184 |
-
width=3,
|
| 185 |
-
),
|
| 186 |
-
|
| 187 |
-
ui.panel_main(
|
| 188 |
-
ui.navset_tab(
|
| 189 |
-
# Tab for game summary plot
|
| 190 |
-
ui.nav("Batter Summary",
|
| 191 |
-
ui.output_text("status_batter"),
|
| 192 |
-
ui.output_plot('batter_plot', width='1200px', height='1200px')
|
| 193 |
-
),
|
| 194 |
-
ui.nav("Pitcher Summary",
|
| 195 |
-
ui.output_text("status_pitcher"),
|
| 196 |
-
ui.output_plot('pitcher_plot', width='1200px', height='1200px')
|
| 197 |
-
)
|
| 198 |
-
,id="tabset"
|
| 199 |
-
)
|
| 200 |
-
)
|
| 201 |
-
)
|
| 202 |
-
)
|
| 203 |
-
)
|
| 204 |
-
|
| 205 |
-
def server(input, output, session):
|
| 206 |
-
@render.ui
|
| 207 |
-
@reactive.event(input.player_button,input.tabset, ignore_none=False)
|
| 208 |
-
def player_select_ui():
|
| 209 |
-
if input.tabset() == "Batter Summary":
|
| 210 |
-
#Get the list of pitchers for the selected level and season
|
| 211 |
-
df_pitcher_info = scrape.get_players(sport_id=int(input.level_input()), season=int(input.year_input())).filter(
|
| 212 |
-
~pl.col("position").is_in(['P','TWP'])).sort("name")
|
| 213 |
-
|
| 214 |
-
|
| 215 |
-
|
| 216 |
-
# Create a dictionary of pitcher IDs and names
|
| 217 |
-
batter_dict_pos = dict(zip(df_pitcher_info['player_id'], df_pitcher_info['position']))
|
| 218 |
-
|
| 219 |
-
year = int(input.year_input())
|
| 220 |
-
sport_id = int(input.level_input())
|
| 221 |
-
batter_summary = pl.read_csv(f'data/statcast/batter_summary_{level_dict_file[str(sport_id)]}_{year}.csv').sort('batter_name',descending=False)
|
| 222 |
-
# Map elements in Polars DataFrame from a dictionary
|
| 223 |
-
batter_summary = batter_summary.with_columns(
|
| 224 |
-
pl.col("batter_id").map_elements(lambda x: batter_dict_pos.get(x, x)).alias("position")
|
| 225 |
-
)
|
| 226 |
-
|
| 227 |
-
|
| 228 |
-
batter_dict_pos = dict(zip(batter_summary['batter_id'], batter_summary['batter_name']))
|
| 229 |
-
# Create a dictionary of pitcher IDs and names
|
| 230 |
-
batter_dict = dict(zip(batter_summary['batter_id'], batter_summary['batter_name'] + ' - ' + batter_summary['position']))
|
| 231 |
-
|
| 232 |
-
# Return a select input for choosing a pitcher
|
| 233 |
-
return ui.input_select("batter_id", "Select Batter", batter_dict, selectize=True)
|
| 234 |
-
|
| 235 |
-
if input.tabset() == "Pitcher Summary":
|
| 236 |
-
#Get the list of pitchers for the selected level and season
|
| 237 |
-
df_pitcher_info = scrape.get_players(sport_id=int(input.level_input()), season=int(input.year_input())).filter(
|
| 238 |
-
pl.col("position").is_in(['P','TWP'])).sort("name")
|
| 239 |
-
|
| 240 |
-
|
| 241 |
-
|
| 242 |
-
# Create a dictionary of pitcher IDs and names
|
| 243 |
-
batter_dict_pos = dict(zip(df_pitcher_info['player_id'], df_pitcher_info['position']))
|
| 244 |
-
|
| 245 |
-
year = int(input.year_input())
|
| 246 |
-
sport_id = int(input.level_input())
|
| 247 |
-
batter_summary = pl.read_csv(f'data/statcast/pitcher_summary_{level_dict_file[str(sport_id)]}_{year}.csv').sort('pitcher_name',descending=False)
|
| 248 |
-
# Map elements in Polars DataFrame from a dictionary
|
| 249 |
-
batter_summary = batter_summary.with_columns(
|
| 250 |
-
pl.col("pitcher_id").map_elements(lambda x: batter_dict_pos.get(x, x)).alias("position")
|
| 251 |
-
)
|
| 252 |
-
|
| 253 |
-
|
| 254 |
-
batter_dict_pos = dict(zip(batter_summary['pitcher_id'], batter_summary['pitcher_name']))
|
| 255 |
-
# Create a dictionary of pitcher IDs and names
|
| 256 |
-
batter_dict = dict(zip(batter_summary['pitcher_id'], batter_summary['pitcher_name'] + ' - ' + batter_summary['position']))
|
| 257 |
-
|
| 258 |
-
# Return a select input for choosing a pitcher
|
| 259 |
-
return ui.input_select("pitcher_id", "Select Batter", batter_dict, selectize=True)
|
| 260 |
-
|
| 261 |
-
|
| 262 |
-
|
| 263 |
-
@output
|
| 264 |
-
@render.plot
|
| 265 |
-
@reactive.event(input.generate_plot, ignore_none=False)
|
| 266 |
-
def batter_plot():
|
| 267 |
-
|
| 268 |
-
|
| 269 |
-
merged_dict = {
|
| 270 |
-
"woba_percent": { "format": '.3f', "percentile_flip": False, "stat_title": "wOBA" },
|
| 271 |
-
"xwoba_percent": { "format": '.3f', "percentile_flip": False, "stat_title": "xwOBA" },
|
| 272 |
-
"launch_speed": { "format": '.1f', "percentile_flip": False, "stat_title": "Average EV"},
|
| 273 |
-
"launch_speed_90": { "format": '.1f', "percentile_flip": False, "stat_title": "90th% EV"},
|
| 274 |
-
"max_launch_speed": { "format": '.1f', "percentile_flip": False, "stat_title": "Max EV"},
|
| 275 |
-
"barrel_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Barrel%" },
|
| 276 |
-
"hard_hit_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Hard-Hit%" },
|
| 277 |
-
"sweet_spot_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "LA Sweet-Spot%" },
|
| 278 |
-
"zone_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Zone%" },
|
| 279 |
-
"zone_swing_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Z-Swing%" },
|
| 280 |
-
"chase_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "O-Swing%" },
|
| 281 |
-
"whiff_rate": { "format": '.1%', "percentile_flip": True, "stat_title": "Whiff%" },
|
| 282 |
-
"k_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "K%" },
|
| 283 |
-
"bb_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "BB%" },
|
| 284 |
-
"pull_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Pull%" },
|
| 285 |
-
"pulled_fly_ball_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Pull FB%" },
|
| 286 |
-
}
|
| 287 |
-
# Show progress/loading notification
|
| 288 |
-
with ui.Progress(min=0, max=1) as p:
|
| 289 |
-
|
| 290 |
-
def draw_baseball_savant_percentiles(new_player_metrics, new_player_percentiles, colors=None,
|
| 291 |
-
sport_id=None,
|
| 292 |
-
year_input=None):
|
| 293 |
-
"""
|
| 294 |
-
Draw Baseball Savant-style percentile bars with proper alignment and scaling.
|
| 295 |
-
|
| 296 |
-
:param new_player_metrics: DataFrame containing new player metrics.
|
| 297 |
-
:param new_player_percentiles: DataFrame containing new player percentiles.
|
| 298 |
-
:param colors: List of colors for bars (optional, red/blue default).
|
| 299 |
-
"""
|
| 300 |
-
# Extract player information
|
| 301 |
-
batter_id = new_player_metrics['batter_id'][0]
|
| 302 |
-
player_name = batter_name_id[batter_id]
|
| 303 |
-
stats = [merged_dict[x]['stat_title'] for x in merged_dict.keys()]
|
| 304 |
-
|
| 305 |
-
# Calculate percentiles and values
|
| 306 |
-
percentiles = [int((1 - x) * 100) if merged_dict[stat]["percentile_flip"] else int(x * 100) for x, stat in zip(new_player_percentiles.select(merged_dict.keys()).to_numpy()[0], merged_dict.keys())]
|
| 307 |
-
percentiles = np.clip(percentiles, 1, 100)
|
| 308 |
-
values = [str(f'{x:{merged_dict[stat]["format"]}}').strip('%') for x, stat in zip(new_player_metrics.select(merged_dict.keys()).to_numpy()[0], merged_dict.keys())]
|
| 309 |
-
|
| 310 |
-
# Get team logo URL
|
| 311 |
-
logo_url = image_dict[team_dict[player_team_dict[batter_id]]]
|
| 312 |
-
|
| 313 |
-
# Create a custom colormap
|
| 314 |
-
color_list = ['#3661AD', '#B4CFD1', '#D82129']
|
| 315 |
-
cmap = LinearSegmentedColormap.from_list("custom_cmap", color_list)
|
| 316 |
-
norm = Normalize(vmin=0.1, vmax=0.9)
|
| 317 |
-
norm_percentiles = norm(percentiles / 100)
|
| 318 |
-
colors = [cmap(p) for p in norm_percentiles]
|
| 319 |
-
|
| 320 |
-
# Figure setup
|
| 321 |
-
num_stats = len(stats)
|
| 322 |
-
bar_height = 4.5
|
| 323 |
-
spacing = 1
|
| 324 |
-
fig_height = (bar_height + spacing) * num_stats
|
| 325 |
-
fig = plt.figure(figsize=(12, 12))
|
| 326 |
-
gs = GridSpec(6, 5, height_ratios=[0.1, 1.5, 0.9, 0.9, 7.6, 0.1], width_ratios=[0.2, 1.5, 7, 1.5, 0.2])
|
| 327 |
-
|
| 328 |
-
# Define subplots
|
| 329 |
-
ax_title = fig.add_subplot(gs[1, 2])
|
| 330 |
-
ax_table = fig.add_subplot(gs[2, :])
|
| 331 |
-
ax_fv_table = fig.add_subplot(gs[3, :])
|
| 332 |
-
ax_fv_table.axis('off')
|
| 333 |
-
ax = fig.add_subplot(gs[4, :])
|
| 334 |
-
ax_logo = fig.add_subplot(gs[1, 3])
|
| 335 |
-
|
| 336 |
-
ax.set_xlim(-1, 99)
|
| 337 |
-
ax.set_ylim(-1, 99)
|
| 338 |
-
ax.set_aspect("equal")
|
| 339 |
-
ax.axis("off")
|
| 340 |
-
|
| 341 |
-
# Draw each bar
|
| 342 |
-
for i, (stat, percentile, value, color) in enumerate(zip(stats, percentiles, values, colors)):
|
| 343 |
-
y = fig_height - (i + 1) * (bar_height + spacing)
|
| 344 |
-
ax.add_patch(patches.Rectangle((0, y + bar_height / 4), 100, bar_height / 2, color="#C7DCDC", lw=0))
|
| 345 |
-
ax.add_patch(patches.Rectangle((0, y), percentile, bar_height, color=color, lw=0))
|
| 346 |
-
circle_y = y + bar_height - bar_height / 2
|
| 347 |
-
circle = plt.Circle((percentile, circle_y), bar_height / 2, color=color, ec='white', lw=1.5, zorder=10)
|
| 348 |
-
ax.add_patch(circle)
|
| 349 |
-
fs = 14
|
| 350 |
-
ax.text(percentile, circle_y, f"{percentile}", ha="center", va="center", fontsize=10, color='white', zorder=10, fontweight='bold')
|
| 351 |
-
ax.text(-5, y + bar_height / 2, stat, ha="right", va="center", fontsize=fs)
|
| 352 |
-
ax.text(115, y + bar_height / 2, str(value), ha="right", va="center", fontsize=fs, zorder=5)
|
| 353 |
-
if i < len(stats) and i > 0:
|
| 354 |
-
ax.hlines(y=y + bar_height + spacing / 2, color='#399098', linestyle=(0, (5, 5)), linewidth=1, xmin=-33, xmax=0)
|
| 355 |
-
ax.hlines(y=y + bar_height + spacing / 2, color='#399098', linestyle=(0, (5, 5)), linewidth=1, xmin=100, xmax=115)
|
| 356 |
-
|
| 357 |
-
# Draw vertical lines for 10%, 50%, and 90% with labels
|
| 358 |
-
for x, label, align, color in zip([10, 50, 90], ["Poor", "Average", "Great"], ['center', 'center', 'center'], color_list):
|
| 359 |
-
ax.axvline(x=x, ymin=0, ymax=1, color='#FFF', linestyle='-', lw=1, zorder=1, alpha=0.5)
|
| 360 |
-
ax.text(x, fig_height + 4, label, ha=align, va='center', fontsize=12, fontweight='bold', color=color)
|
| 361 |
-
triangle = patches.RegularPolygon((x, fig_height + 1), 3, radius=1, orientation=0, color=color, zorder=2)
|
| 362 |
-
ax.add_patch(triangle)
|
| 363 |
-
|
| 364 |
-
# # Title
|
| 365 |
-
# ax_title.set_ylim(0, 1)
|
| 366 |
-
# ax_title.text(0.5, 0.5, f"{player_name} - {player_position_dict[batter_id]}\nPercentile Rankings - 2024 AAA", ha="center", va="center", fontsize=24)
|
| 367 |
-
# ax_title.axis("off")
|
| 368 |
-
player_bio(batter_id, ax=ax_title, sport_id=sport_id, year_input=year_input)
|
| 369 |
-
|
| 370 |
-
# Add team logo
|
| 371 |
-
#response = requests.get(logo_url)
|
| 372 |
-
if input.switch():
|
| 373 |
-
response = requests.get(input.logo_select())
|
| 374 |
-
else:
|
| 375 |
-
response = requests.get(logo_url)
|
| 376 |
-
img = Image.open(BytesIO(response.content))
|
| 377 |
-
ax_logo.imshow(img)
|
| 378 |
-
ax_logo.axis("off")
|
| 379 |
-
ax.axis('equal')
|
| 380 |
-
|
| 381 |
-
# Metrics data table
|
| 382 |
-
metrics_data = {
|
| 383 |
-
"Pitches": new_player_metrics['pitches'][0],
|
| 384 |
-
"PA": new_player_metrics['pa'][0],
|
| 385 |
-
"BIP": new_player_metrics['bip'][0],
|
| 386 |
-
"HR": f"{new_player_metrics['home_run'][0]:.0f}",
|
| 387 |
-
"AVG": f"{new_player_metrics['avg'][0]:.3f}",
|
| 388 |
-
"OBP": f"{new_player_metrics['obp'][0]:.3f}",
|
| 389 |
-
"SLG": f"{new_player_metrics['slg'][0]:.3f}",
|
| 390 |
-
"OPS": f"{new_player_metrics['obp'][0] + new_player_metrics['slg'][0]:.3f}",
|
| 391 |
-
}
|
| 392 |
-
df_table = pd.DataFrame(metrics_data, index=[0])
|
| 393 |
-
ax_table.axis('off')
|
| 394 |
-
table = ax_table.table(cellText=df_table.values, colLabels=df_table.columns, cellLoc='center', loc='bottom', bbox=[0.07, 0, 0.86, 1])
|
| 395 |
-
for key, cell in table.get_celld().items():
|
| 396 |
-
if key[0] == 0:
|
| 397 |
-
cell.set_text_props(fontweight='bold')
|
| 398 |
-
table.auto_set_font_size(False)
|
| 399 |
-
table.set_fontsize(12)
|
| 400 |
-
table.scale(1, 1.5)
|
| 401 |
-
|
| 402 |
-
# Additional subplots for spacing
|
| 403 |
-
ax_top = fig.add_subplot(gs[0, :])
|
| 404 |
-
ax_bot = fig.add_subplot(gs[-1, :])
|
| 405 |
-
ax_top.axis('off')
|
| 406 |
-
ax_bot.axis('off')
|
| 407 |
-
ax_bot.text(0.05, 2, "By: Thomas Nestico (@TJStats)", ha="left", va="center", fontsize=14)
|
| 408 |
-
ax_bot.text(0.95, 2, "Data: MLB, Fangraphs", ha="right", va="center", fontsize=14)
|
| 409 |
-
fig.subplots_adjust(left=0.01, right=0.99, top=0.99, bottom=0.01)
|
| 410 |
-
|
| 411 |
-
# Player headshot
|
| 412 |
-
ax_headshot = fig.add_subplot(gs[1, 1])
|
| 413 |
-
try:
|
| 414 |
-
url = f'https://img.mlbstatic.com/mlb-photos/image/upload/c_fill,g_auto/w_640/v1/people/{batter_id}/headshot/milb/current.png'
|
| 415 |
-
response = requests.get(url)
|
| 416 |
-
img = Image.open(BytesIO(response.content))
|
| 417 |
-
ax_headshot.set_xlim(0, 1)
|
| 418 |
-
ax_headshot.set_ylim(0, 1)
|
| 419 |
-
ax_headshot.imshow(img, extent=[1/6, 5/6, 0, 1], origin='upper')
|
| 420 |
-
except PIL.UnidentifiedImageError:
|
| 421 |
-
ax_headshot.axis('off')
|
| 422 |
-
#return
|
| 423 |
-
ax_headshot.axis('off')
|
| 424 |
-
ax_table.set_title('Season Summary', style='italic')
|
| 425 |
-
|
| 426 |
-
# Fangraphs scouting grades table
|
| 427 |
-
print(batter_id)
|
| 428 |
-
|
| 429 |
-
if batter_id not in dict_mlb_fg.keys():
|
| 430 |
-
ax_fv_table.text(x=0.5, y=0.5, s='No Scouting Data', style='italic', ha='center', va='center', fontsize=20, bbox=dict(facecolor='white', alpha=1, pad=10))
|
| 431 |
-
return
|
| 432 |
-
df_fv_table = df_prospects[(df_prospects['minorMasterId'] == dict_mlb_fg[batter_id])][['cFV', 'Hit', 'Game', 'Raw', 'Spd', 'Fld']].reset_index(drop=True)
|
| 433 |
-
ax_fv_table.axis('off')
|
| 434 |
-
if df_fv_table.empty:
|
| 435 |
-
ax_fv_table.text(x=0.5, y=0.5, s='No Scouting Data', style='italic', ha='center', va='center', fontsize=20, bbox=dict(facecolor='white', alpha=1, pad=10))
|
| 436 |
-
return
|
| 437 |
-
df_fv_table.columns = ['FV', 'Hit', 'Game', 'Raw', 'Spd', 'Fld']
|
| 438 |
-
table_fv = ax_fv_table.table(cellText=df_fv_table.values, colLabels=df_fv_table.columns, cellLoc='center', loc='bottom', bbox=[0.07, 0, 0.86, 1])
|
| 439 |
-
for key, cell in table_fv.get_celld().items():
|
| 440 |
-
if key[0] == 0:
|
| 441 |
-
cell.set_text_props(fontweight='bold')
|
| 442 |
-
table_fv.auto_set_font_size(False)
|
| 443 |
-
table_fv.set_fontsize(12)
|
| 444 |
-
table_fv.scale(1, 1.5)
|
| 445 |
-
ax_fv_table.set_title('Fangraphs Scouting Grades', style='italic')
|
| 446 |
-
|
| 447 |
-
|
| 448 |
-
|
| 449 |
-
#plt.show()
|
| 450 |
-
|
| 451 |
-
|
| 452 |
-
def calculate_new_player_percentiles(player_id, new_player_metrics, player_summary_filtered):
|
| 453 |
-
"""
|
| 454 |
-
Calculate percentiles for a new player's metrics.
|
| 455 |
-
|
| 456 |
-
:param player_id: ID of the player.
|
| 457 |
-
:param new_player_metrics: DataFrame containing new player metrics.
|
| 458 |
-
:param player_summary_filtered: Filtered player summary DataFrame.
|
| 459 |
-
:return: DataFrame containing new player percentiles.
|
| 460 |
-
"""
|
| 461 |
-
filtered_summary_clone = player_summary_filtered[['batter_id'] + stat_list].filter(pl.col('batter_id') != player_id).clone()
|
| 462 |
-
combined_data = pl.concat([filtered_summary_clone, new_player_metrics], how="vertical").to_pandas()
|
| 463 |
-
combined_percentiles = pl.DataFrame(pd.concat([combined_data['batter_id'], combined_data[stat_list].rank(pct=True)], axis=1))
|
| 464 |
-
new_player_percentiles = combined_percentiles.filter(pl.col('batter_id') == player_id)
|
| 465 |
-
return new_player_percentiles
|
| 466 |
-
|
| 467 |
-
|
| 468 |
-
|
| 469 |
-
p.set(message="Generating plot", detail="This may take a while...")
|
| 470 |
-
|
| 471 |
-
|
| 472 |
-
p.set(0.3, "Gathering data...")
|
| 473 |
-
|
| 474 |
-
# Example: New player's metrics
|
| 475 |
-
year = int(input.year_input())
|
| 476 |
-
sport_id = int(input.level_input())
|
| 477 |
-
batter_id = int(input.batter_id())
|
| 478 |
-
|
| 479 |
-
|
| 480 |
-
df_player = scrape.get_players(sport_id=sport_id,season=year)
|
| 481 |
-
batter_name_id = dict(zip(df_player['player_id'],df_player['name']))
|
| 482 |
-
player_team_dict = dict(zip(df_player['player_id'],df_player['team']))
|
| 483 |
-
player_position_dict = dict(zip(df_player['player_id'],df_player['position']))
|
| 484 |
-
|
| 485 |
-
|
| 486 |
-
batter_summary = pl.read_csv(f'data/statcast/batter_summary_{level_dict_file[str(sport_id)]}_{year}.csv')
|
| 487 |
-
df_prospects = pd.read_csv(f'data/prospects/prospects_{year}.csv')
|
| 488 |
-
df_rosters = pd.read_csv(f'data/rosters/fangraphs_rosters_{year}.csv')
|
| 489 |
-
df_small = df_rosters[['minorbamid','minormasterid']].dropna()
|
| 490 |
-
dict_mlb_fg=dict(zip(df_small['minorbamid'].astype(int),df_small['minormasterid']))
|
| 491 |
-
|
| 492 |
-
|
| 493 |
-
|
| 494 |
-
|
| 495 |
-
batter_summary_filter = batter_summary.filter((pl.col('pa') >= 300) & (pl.col('launch_speed') >= 0))
|
| 496 |
-
stat_list = batter_summary.columns[2:]
|
| 497 |
-
batter_summary_filter_pd = batter_summary_filter.to_pandas()
|
| 498 |
-
new_player_metrics = batter_summary.filter(pl.col('batter_id') == batter_id)[['batter_id'] + stat_list]
|
| 499 |
-
|
| 500 |
-
# Get percentiles for the new player
|
| 501 |
-
new_player_percentiles = calculate_new_player_percentiles(batter_id, new_player_metrics, batter_summary_filter)
|
| 502 |
-
|
| 503 |
-
p.set(0.6, "Creating plot...")
|
| 504 |
-
# Draw Baseball Savant-style percentile bars
|
| 505 |
-
draw_baseball_savant_percentiles(new_player_metrics=new_player_metrics,
|
| 506 |
-
new_player_percentiles=new_player_percentiles,
|
| 507 |
-
sport_id=sport_id,
|
| 508 |
-
year_input=year)
|
| 509 |
-
|
| 510 |
-
@output
|
| 511 |
-
@render.plot
|
| 512 |
-
@reactive.event(input.generate_plot, ignore_none=False)
|
| 513 |
-
def pitcher_plot():
|
| 514 |
-
merged_dict = {
|
| 515 |
-
"avg_start_speed_ff": { "format": '.1f', "percentile_flip": False, "stat_title": "Fastball Velocity" },
|
| 516 |
-
"extension": { "format": '.1f', "percentile_flip": False, "stat_title": "Extension" },
|
| 517 |
-
"woba_percent": { "format": '.3f', "percentile_flip": True, "stat_title": "wOBA" },
|
| 518 |
-
"xwoba_percent": { "format": '.3f', "percentile_flip": True, "stat_title": "xwOBA" },
|
| 519 |
-
"launch_speed": { "format": '.1f', "percentile_flip": True, "stat_title": "Average EV"},
|
| 520 |
-
"barrel_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "Barrel%" },
|
| 521 |
-
"hard_hit_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "Hard-Hit%" },
|
| 522 |
-
"whiff_rate": { "format": '.1%', "percentile_flip": False, "stat_title": "Whiff%" },
|
| 523 |
-
"zone_contact_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "Z-Contact%" },
|
| 524 |
-
"zone_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Zone%" },
|
| 525 |
-
"chase_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "O-Swing%" },
|
| 526 |
-
"csw_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "CSW%" },
|
| 527 |
-
"k_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "K%" },
|
| 528 |
-
"bb_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "BB%" },
|
| 529 |
-
"k_minus_bb_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "K - BB%" },
|
| 530 |
-
"ground_ball_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "GB%" },
|
| 531 |
-
}
|
| 532 |
-
|
| 533 |
-
with ui.Progress(min=0, max=1) as p:
|
| 534 |
-
|
| 535 |
-
def draw_baseball_savant_percentiles(new_player_metrics, new_player_percentiles, colors=None,
|
| 536 |
-
sport_id=None,
|
| 537 |
-
year_input=None):
|
| 538 |
-
"""
|
| 539 |
-
Draw Baseball Savant-style percentile bars with proper alignment and scaling.
|
| 540 |
-
|
| 541 |
-
:param new_player_metrics: DataFrame containing new player metrics.
|
| 542 |
-
:param new_player_percentiles: DataFrame containing new player percentiles.
|
| 543 |
-
:param colors: List of colors for bars (optional, red/blue default).
|
| 544 |
-
"""
|
| 545 |
-
# Extract player information
|
| 546 |
-
pitcher_id = new_player_metrics['pitcher_id'][0]
|
| 547 |
-
player_name = pitcher_name_id[pitcher_id]
|
| 548 |
-
stats = [merged_dict[x]['stat_title'] for x in merged_dict.keys()]
|
| 549 |
-
|
| 550 |
-
# Calculate percentiles and values
|
| 551 |
-
percentiles = [int((1 - x) * 100) if merged_dict[stat]["percentile_flip"] else int(x * 100) for x, stat in zip(new_player_percentiles.select(merged_dict.keys()).to_numpy()[0], merged_dict.keys())]
|
| 552 |
-
percentiles = np.clip(percentiles, 1, 100)
|
| 553 |
-
values = [str(f'{x:{merged_dict[stat]["format"]}}').strip('%') for x, stat in zip(new_player_metrics.select(merged_dict.keys()).to_numpy()[0], merged_dict.keys())]
|
| 554 |
-
|
| 555 |
-
# Get team logo URL
|
| 556 |
-
logo_url = image_dict[team_dict[player_team_dict[pitcher_id]]]
|
| 557 |
-
|
| 558 |
-
# Create a custom colormap
|
| 559 |
-
color_list = ['#3661AD', '#B4CFD1', '#D82129']
|
| 560 |
-
cmap = LinearSegmentedColormap.from_list("custom_cmap", color_list)
|
| 561 |
-
norm = Normalize(vmin=0.1, vmax=0.9)
|
| 562 |
-
norm_percentiles = norm(percentiles / 100)
|
| 563 |
-
colors = [cmap(p) for p in norm_percentiles]
|
| 564 |
-
|
| 565 |
-
# Figure setup
|
| 566 |
-
num_stats = len(stats)
|
| 567 |
-
bar_height = 4.4
|
| 568 |
-
spacing = 0.7
|
| 569 |
-
fig_height = (bar_height + spacing) * num_stats
|
| 570 |
-
fig = plt.figure(figsize=(12, 12))
|
| 571 |
-
gs = GridSpec(7, 5, height_ratios=[0.05, 1.5, 0.75, 0.75,0.75, 7.7, 0.1], width_ratios=[0.2, 1.5, 7, 1.5, 0.2])
|
| 572 |
-
|
| 573 |
-
# Define subplots
|
| 574 |
-
ax_title = fig.add_subplot(gs[1, 2])
|
| 575 |
-
ax_table = fig.add_subplot(gs[2, :])
|
| 576 |
-
ax_fv_table = fig.add_subplot(gs[3, :])
|
| 577 |
-
ax_fv_table.axis('off')
|
| 578 |
-
ax_stuff = fig.add_subplot(gs[4, :])
|
| 579 |
-
ax = fig.add_subplot(gs[5, :])
|
| 580 |
-
ax_logo = fig.add_subplot(gs[1, 3])
|
| 581 |
-
|
| 582 |
-
ax.set_xlim(-1, 99)
|
| 583 |
-
ax.set_ylim(-1, 99)
|
| 584 |
-
ax.set_aspect("equal")
|
| 585 |
-
ax.axis("off")
|
| 586 |
-
|
| 587 |
-
# Draw each bar
|
| 588 |
-
for i, (stat, percentile, value, color) in enumerate(zip(stats, percentiles, values, colors)):
|
| 589 |
-
y = fig_height - (i + 1) * (bar_height + spacing)
|
| 590 |
-
ax.add_patch(patches.Rectangle((0, y + bar_height / 4), 100, bar_height / 2, color="#C7DCDC", lw=0))
|
| 591 |
-
ax.add_patch(patches.Rectangle((0, y), percentile, bar_height, color=color, lw=0))
|
| 592 |
-
circle_y = y + bar_height - bar_height / 2
|
| 593 |
-
circle = plt.Circle((percentile, circle_y), bar_height / 2, color=color, ec='white', lw=1.5, zorder=10)
|
| 594 |
-
ax.add_patch(circle)
|
| 595 |
-
fs = 14
|
| 596 |
-
ax.text(percentile, circle_y, f"{percentile}", ha="center", va="center", fontsize=10, color='white', zorder=10, fontweight='bold')
|
| 597 |
-
ax.text(-5, y + bar_height / 2, stat, ha="right", va="center", fontsize=fs)
|
| 598 |
-
ax.text(115, y + bar_height / 2, str(value), ha="right", va="center", fontsize=fs, zorder=5)
|
| 599 |
-
if i < len(stats) and i > 0:
|
| 600 |
-
ax.hlines(y=y + bar_height + spacing / 2, color='#399098', linestyle=(0, (5, 5)), linewidth=1, xmin=-33, xmax=0)
|
| 601 |
-
ax.hlines(y=y + bar_height + spacing / 2, color='#399098', linestyle=(0, (5, 5)), linewidth=1, xmin=100, xmax=115)
|
| 602 |
-
|
| 603 |
-
# Draw vertical lines for 10%, 50%, and 90% with labels
|
| 604 |
-
for x, label, align, color in zip([10, 50, 90], ["Poor", "Average", "Great"], ['center', 'center', 'center'], color_list):
|
| 605 |
-
ax.axvline(x=x, ymin=0, ymax=1, color='#FFF', linestyle='-', lw=1, zorder=1, alpha=0.5)
|
| 606 |
-
ax.text(x, fig_height + 4, label, ha=align, va='center', fontsize=12, fontweight='bold', color=color)
|
| 607 |
-
triangle = patches.RegularPolygon((x, fig_height + 1), 3, radius=1, orientation=0, color=color, zorder=2)
|
| 608 |
-
ax.add_patch(triangle)
|
| 609 |
-
|
| 610 |
-
# # Title
|
| 611 |
-
# ax_title.set_ylim(0, 1)
|
| 612 |
-
# ax_title.text(0.5, 0.5, f"{player_name} - {player_position_dict[pitcher_id]}\nPercentile Rankings - 2024 AAA", ha="center", va="center", fontsize=24)
|
| 613 |
-
# ax_title.axis("off")
|
| 614 |
-
player_bio(pitcher_id, ax=ax_title, sport_id=sport_id, year_input=year_input)
|
| 615 |
-
|
| 616 |
-
# Add team logo
|
| 617 |
-
#response = requests.get(logo_url)
|
| 618 |
-
#######if input.switch():
|
| 619 |
-
######## response = requests.get(input.logo_select())
|
| 620 |
-
######else:
|
| 621 |
-
response = requests.get(logo_url)
|
| 622 |
-
img = Image.open(BytesIO(response.content))
|
| 623 |
-
ax_logo.imshow(img)
|
| 624 |
-
ax_logo.axis("off")
|
| 625 |
-
ax.axis('equal')
|
| 626 |
-
lg_dict = {
|
| 627 |
-
11:'all',
|
| 628 |
-
14:10
|
| 629 |
-
}
|
| 630 |
-
levelt = {
|
| 631 |
-
11:1,
|
| 632 |
-
14:4
|
| 633 |
-
}
|
| 634 |
-
|
| 635 |
-
|
| 636 |
-
fg_api = f'https://www.fangraphs.com/api/leaders/minor-league/data?pos=all&level={levelt[sport_id]}&lg={lg_dict[sport_id]}&stats=pit&qual=0&type=2&team=&season=2024&seasonEnd=2024&org=&ind=0&splitTeam=false'
|
| 637 |
-
response = requests.get(fg_api)
|
| 638 |
-
data = response.json()
|
| 639 |
-
df_fg = pl.DataFrame(data)
|
| 640 |
-
if pitcher_id not in dict_mlb_fg.keys():
|
| 641 |
-
#ax_fv_table.text(x=0.5, y=0.5, s='No Scouting Data', style='italic', ha='center', va='center', fontsize=20, bbox=dict(facecolor='white', alpha=1, pad=10))
|
| 642 |
-
metrics_data = {
|
| 643 |
-
"Pitches": new_player_metrics['pitches'][0],
|
| 644 |
-
"PA": new_player_metrics['pa'][0],
|
| 645 |
-
"BIP": new_player_metrics['bip'][0],
|
| 646 |
-
"HR": f"{new_player_metrics['home_run'][0]:.0f}",
|
| 647 |
-
"K": f"{new_player_metrics['k'][0]:.0f}",
|
| 648 |
-
"BB": f"{new_player_metrics['bb'][0]:.0f}",
|
| 649 |
-
}
|
| 650 |
-
else:
|
| 651 |
-
df_fg_filter = df_fg.filter(pl.col('minormasterid') == dict_mlb_fg[pitcher_id])
|
| 652 |
-
# Metrics data table
|
| 653 |
-
metrics_data = {
|
| 654 |
-
"G": f"{df_fg_filter['G'][0]:.0f}",
|
| 655 |
-
"IP": f"{df_fg_filter['IP'][0]:.1f}",
|
| 656 |
-
"Pitches": f"{new_player_metrics['pitches'][0]:.0f}",
|
| 657 |
-
"PA": f"{df_fg_filter['TBF'][0]:.0f}",
|
| 658 |
-
"BIP": new_player_metrics['bip'][0],
|
| 659 |
-
"ERA": f"{df_fg_filter['ERA'][0]:.2f}",
|
| 660 |
-
"FIP": f"{df_fg_filter['FIP'][0]:.2f}",
|
| 661 |
-
"WHIP": f"{df_fg_filter['WHIP'][0]:.2f}",
|
| 662 |
-
}
|
| 663 |
-
df_table = pd.DataFrame(metrics_data, index=[0])
|
| 664 |
-
ax_table.axis('off')
|
| 665 |
-
table = ax_table.table(cellText=df_table.values, colLabels=df_table.columns, cellLoc='center', loc='bottom', bbox=[0.07, 0, 0.86, 1])
|
| 666 |
-
for key, cell in table.get_celld().items():
|
| 667 |
-
if key[0] == 0:
|
| 668 |
-
cell.set_text_props(fontweight='bold')
|
| 669 |
-
table.auto_set_font_size(False)
|
| 670 |
-
table.set_fontsize(12)
|
| 671 |
-
table.scale(1, 1.5)
|
| 672 |
-
|
| 673 |
-
# Additional subplots for spacing
|
| 674 |
-
ax_top = fig.add_subplot(gs[0, :])
|
| 675 |
-
ax_bot = fig.add_subplot(gs[-1, :])
|
| 676 |
-
ax_top.axis('off')
|
| 677 |
-
ax_bot.axis('off')
|
| 678 |
-
ax_bot.text(0.05, 2, "By: Thomas Nestico (@TJStats)", ha="left", va="center", fontsize=14)
|
| 679 |
-
ax_bot.text(0.95, 2, "Data: MLB, Fangraphs", ha="right", va="center", fontsize=14)
|
| 680 |
-
|
| 681 |
-
|
| 682 |
-
# Player headshot
|
| 683 |
-
ax_headshot = fig.add_subplot(gs[1, 1])
|
| 684 |
-
try:
|
| 685 |
-
url = f'https://img.mlbstatic.com/mlb-photos/image/upload/c_fill,g_auto/w_640/v1/people/{pitcher_id}/headshot/milb/current.png'
|
| 686 |
-
response = requests.get(url)
|
| 687 |
-
img = Image.open(BytesIO(response.content))
|
| 688 |
-
ax_headshot.set_xlim(0, 1)
|
| 689 |
-
ax_headshot.set_ylim(0, 1)
|
| 690 |
-
ax_headshot.imshow(img, extent=[1/6, 5/6, 0, 1], origin='upper')
|
| 691 |
-
except PIL.UnidentifiedImageError:
|
| 692 |
-
ax_headshot.axis('off')
|
| 693 |
-
#return
|
| 694 |
-
ax_headshot.axis('off')
|
| 695 |
-
ax_table.set_title('Season Summary', style='italic')
|
| 696 |
-
|
| 697 |
-
# Fangraphs scouting grades table
|
| 698 |
-
print(pitcher_id)
|
| 699 |
-
|
| 700 |
-
if pitcher_id not in dict_mlb_fg.keys():
|
| 701 |
-
ax_fv_table.text(x=0.5, y=0.5, s='No Scouting Data', style='italic', ha='center', va='center', fontsize=20, bbox=dict(facecolor='white', alpha=1, pad=10))
|
| 702 |
-
#return
|
| 703 |
-
df_fv_table = df_prospects[(df_prospects['minorMasterId'] == dict_mlb_fg[pitcher_id])][['cFV','FB', 'SL', 'CB', 'CH', 'SPL', 'CT','CMD']].dropna(axis=1).reset_index(drop=True)
|
| 704 |
-
ax_fv_table.axis('off')
|
| 705 |
-
if df_fv_table.empty:
|
| 706 |
-
ax_fv_table.text(x=0.5, y=0.5, s='No Scouting Data', style='italic', ha='center', va='center', fontsize=20, bbox=dict(facecolor='white', alpha=1, pad=10))
|
| 707 |
-
#return
|
| 708 |
-
else:
|
| 709 |
-
df_fv_table.columns = ['FV']+[x.upper() for x in df_fv_table.columns[1:]]
|
| 710 |
-
table_fv = ax_fv_table.table(cellText=df_fv_table.values, colLabels=df_fv_table.columns, cellLoc='center', loc='bottom', bbox=[0.07, 0, 0.86, 1])
|
| 711 |
-
for key, cell in table_fv.get_celld().items():
|
| 712 |
-
if key[0] == 0:
|
| 713 |
-
cell.set_text_props(fontweight='bold')
|
| 714 |
-
table_fv.auto_set_font_size(False)
|
| 715 |
-
table_fv.set_fontsize(12)
|
| 716 |
-
table_fv.scale(1, 1.5)
|
| 717 |
-
ax_fv_table.set_title('Fangraphs Scouting Grades', style='italic')
|
| 718 |
-
|
| 719 |
-
|
| 720 |
-
# df_stuff_filter = df_stuff.filter(pl.col('pitcher_id')==pitcher_id)
|
| 721 |
-
|
| 722 |
-
stuff_table = ax_stuff.table(cellText=[df_stuff_filter['tj_stuff_plus']],
|
| 723 |
-
colLabels=df_stuff_filter['pitch_type'],
|
| 724 |
-
cellLoc='center',
|
| 725 |
-
loc='center', bbox=[0.07, 0, 0.86, 1])
|
| 726 |
-
stuff_table.auto_set_font_size(False)
|
| 727 |
-
stuff_table.set_fontsize(12)
|
| 728 |
-
stuff_table.scale(1, 1.5)
|
| 729 |
-
ax_stuff.axis('off')
|
| 730 |
-
ax_stuff.set_title('tjStuff+', style='italic')
|
| 731 |
-
for key, cell in stuff_table.get_celld().items():
|
| 732 |
-
if key[0] == 0:
|
| 733 |
-
cell.set_text_props(fontweight='bold')
|
| 734 |
-
|
| 735 |
-
# Color the stuff_table values based on the cmap defined
|
| 736 |
-
for (i, j), cell in stuff_table.get_celld().items():
|
| 737 |
-
if i == 0:
|
| 738 |
-
cell.set_text_props(fontweight='bold')
|
| 739 |
-
else:
|
| 740 |
-
norm = Normalize(vmin=90, vmax=110)
|
| 741 |
-
value = float(cell.get_text().get_text())
|
| 742 |
-
color = cmap(norm(value))
|
| 743 |
-
cell.set_facecolor(color)
|
| 744 |
-
#cell.set_text_props(color='white' if value < 100 else 'black')
|
| 745 |
-
|
| 746 |
-
|
| 747 |
-
|
| 748 |
-
|
| 749 |
-
|
| 750 |
-
fig.subplots_adjust(left=0.01, right=0.99, top=0.99, bottom=0.01)
|
| 751 |
-
|
| 752 |
-
|
| 753 |
-
|
| 754 |
-
|
| 755 |
-
|
| 756 |
-
def calculate_new_player_percentiles(player_id, new_player_metrics, player_summary_filtered):
|
| 757 |
-
"""
|
| 758 |
-
Calculate percentiles for a new player's metrics.
|
| 759 |
-
|
| 760 |
-
:param player_id: ID of the player.
|
| 761 |
-
:param new_player_metrics: DataFrame containing new player metrics.
|
| 762 |
-
:param player_summary_filtered: Filtered player summary DataFrame.
|
| 763 |
-
:return: DataFrame containing new player percentiles.
|
| 764 |
-
"""
|
| 765 |
-
filtered_summary_clone = player_summary_filtered[['pitcher_id'] + stat_list].filter(pl.col('pitcher_id') != player_id).clone()
|
| 766 |
-
combined_data = pl.concat([filtered_summary_clone, new_player_metrics], how="vertical").to_pandas()
|
| 767 |
-
combined_percentiles = pl.DataFrame(pd.concat([combined_data['pitcher_id'], combined_data[stat_list].rank(pct=True)], axis=1))
|
| 768 |
-
new_player_percentiles = combined_percentiles.filter(pl.col('pitcher_id') == player_id)
|
| 769 |
-
return new_player_percentiles
|
| 770 |
-
|
| 771 |
-
p.set(message="Generating plot", detail="This may take a while...")
|
| 772 |
-
|
| 773 |
-
|
| 774 |
-
p.set(0.3, "Gathering data...")
|
| 775 |
-
|
| 776 |
-
|
| 777 |
-
df_teams = scrape.get_teams()
|
| 778 |
-
team_dict = dict(zip(df_teams['team_id'],df_teams['parent_org_abbreviation']))
|
| 779 |
-
|
| 780 |
-
# Example: New player's metrics
|
| 781 |
-
# Example: New player's metrics
|
| 782 |
-
year = int(input.year_input())
|
| 783 |
-
sport_id = int(input.level_input())
|
| 784 |
-
pitcher_id = int(input.pitcher_id())
|
| 785 |
-
|
| 786 |
-
df_player = scrape.get_players(sport_id=sport_id,season=2024)
|
| 787 |
-
pitcher_name_id = dict(zip(df_player['player_id'],df_player['name']))
|
| 788 |
-
player_team_dict = dict(zip(df_player['player_id'],df_player['team']))
|
| 789 |
-
player_position_dict = dict(zip(df_player['player_id'],df_player['position']))
|
| 790 |
-
player_position_dict = dict(zip(df_player['player_id'],df_player['position']))
|
| 791 |
-
|
| 792 |
-
|
| 793 |
-
|
| 794 |
-
|
| 795 |
-
pitcher_summary = pl.read_csv(f'data/statcast/pitcher_summary_{level_dict_file[str(sport_id)]}_{year}.csv')
|
| 796 |
-
df_prospects = pd.read_csv(f'data/prospects/prospects_{year}.csv')
|
| 797 |
-
df_rosters = pd.read_csv(f'data/rosters/fangraphs_rosters_{year}.csv')
|
| 798 |
-
df_small = df_rosters[['minorbamid','minormasterid']].dropna()
|
| 799 |
-
dict_mlb_fg=dict(zip(df_small['minorbamid'].astype(int),df_small['minormasterid']))
|
| 800 |
-
|
| 801 |
-
df_stuff = pl.read_csv(f'data/stuff/stuff_{level_dict_file[str(sport_id)]}_{year}.csv')
|
| 802 |
-
# Filter out the "All" row
|
| 803 |
-
filtered_df = df_stuff.filter(pl.col("pitch_type") != "All")
|
| 804 |
-
|
| 805 |
-
filtered_all_df = df_stuff.filter(pl.col("pitch_type") == "All")
|
| 806 |
-
# Calculate total pitches for each pitcher and proportion of each pitch type
|
| 807 |
-
result_df = (
|
| 808 |
-
filtered_df
|
| 809 |
-
.with_columns([
|
| 810 |
-
# Total pitches for each pitcher
|
| 811 |
-
pl.col("pitches").sum().over("pitcher_id").alias("total_pitches"),
|
| 812 |
-
# Proportion of pitches
|
| 813 |
-
(pl.col("pitches") / pl.col("pitches").sum().over("pitcher_id")).alias("pitch_proportion"),
|
| 814 |
-
])
|
| 815 |
-
).filter(pl.col("pitch_proportion") > 0.05)
|
| 816 |
-
|
| 817 |
-
df_stuff = pl.concat([filtered_all_df.with_columns(
|
| 818 |
-
[pl.col("pitches").sum().over("pitcher_id").alias("total_pitches"),
|
| 819 |
-
(pl.col("pitches") / pl.col("pitches").sum().over("pitcher_id")).alias("pitch_proportion")]
|
| 820 |
-
), result_df])
|
| 821 |
-
|
| 822 |
-
|
| 823 |
-
|
| 824 |
-
|
| 825 |
-
df_stuff_filter = df_stuff.filter(pl.col('pitcher_id')==pitcher_id)
|
| 826 |
-
|
| 827 |
-
pitcher_summary_filter = pitcher_summary.filter((pl.col('pa') >= 300) & (pl.col('launch_speed') >= 0))
|
| 828 |
-
stat_list = pitcher_summary.columns[2:]
|
| 829 |
-
pitcher_summary_filter_pd = pitcher_summary_filter.to_pandas()
|
| 830 |
-
new_player_metrics = pitcher_summary.filter(pl.col('pitcher_id') == pitcher_id)[['pitcher_id'] + stat_list]
|
| 831 |
-
|
| 832 |
-
# Get percentiles for the new player
|
| 833 |
-
new_player_percentiles = calculate_new_player_percentiles(pitcher_id, new_player_metrics, pitcher_summary_filter)
|
| 834 |
-
|
| 835 |
-
p.set(0.6, "Creating plot...")
|
| 836 |
-
# Draw Baseball Savant-style percentile bars
|
| 837 |
-
draw_baseball_savant_percentiles(new_player_metrics=new_player_metrics,
|
| 838 |
-
new_player_percentiles=new_player_percentiles,
|
| 839 |
-
sport_id=sport_id,
|
| 840 |
-
year_input=year)
|
| 841 |
-
|
| 842 |
-
|
| 843 |
app = App(app_ui, server)
|
|
|
|
| 1 |
+
import polars as pl
|
| 2 |
+
import api_scraper
|
| 3 |
+
import pandas as pd
|
| 4 |
+
scrape = api_scraper.MLB_Scrape()
|
| 5 |
+
|
| 6 |
+
# import df_update
|
| 7 |
+
# update = df_update.df_update()
|
| 8 |
+
from matplotlib.colors import LinearSegmentedColormap, Normalize
|
| 9 |
+
import numpy as np
|
| 10 |
+
import requests
|
| 11 |
+
from io import BytesIO
|
| 12 |
+
from PIL import Image
|
| 13 |
+
from matplotlib.gridspec import GridSpec
|
| 14 |
+
|
| 15 |
+
import matplotlib.pyplot as plt
|
| 16 |
+
import matplotlib.patches as patches
|
| 17 |
+
import PIL
|
| 18 |
+
|
| 19 |
+
level_dict = {'1':'MLB',
|
| 20 |
+
'11':'AAA',
|
| 21 |
+
'14':'A',}
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
def player_bio(pitcher_id: str, ax: plt.Axes, sport_id: int, year_input: int):
|
| 26 |
+
"""
|
| 27 |
+
Display the player's bio information on the given axis.
|
| 28 |
+
Parameters
|
| 29 |
+
----------
|
| 30 |
+
pitcher_id : str
|
| 31 |
+
The player's ID.
|
| 32 |
+
ax : plt.Axes
|
| 33 |
+
The axis to display the bio information on.
|
| 34 |
+
sport_id : int
|
| 35 |
+
The sport ID (1 for MLB, other for minor leagues).
|
| 36 |
+
year_input : int
|
| 37 |
+
The season year.
|
| 38 |
+
"""
|
| 39 |
+
# Construct the URL to fetch player data
|
| 40 |
+
url = f"https://statsapi.mlb.com/api/v1/people?personIds={pitcher_id}&hydrate=currentTeam"
|
| 41 |
+
|
| 42 |
+
# Send a GET request to the URL and parse the JSON response
|
| 43 |
+
data = requests.get(url).json()
|
| 44 |
+
|
| 45 |
+
# Extract player information from the JSON data
|
| 46 |
+
player_name = data['people'][0]['fullName']
|
| 47 |
+
position = data['people'][0]['primaryPosition']['abbreviation']
|
| 48 |
+
bat_side = data['people'][0]['batSide']['code']
|
| 49 |
+
pitcher_hand = data['people'][0]['pitchHand']['code']
|
| 50 |
+
age = data['people'][0]['currentAge']
|
| 51 |
+
height = data['people'][0]['height']
|
| 52 |
+
weight = data['people'][0]['weight']
|
| 53 |
+
|
| 54 |
+
# Display the player's name, handedness, age, height, and weight on the axis
|
| 55 |
+
ax.text(0.5, 1, f'{player_name}', va='top', ha='center', fontsize=30)
|
| 56 |
+
ax.text(0.5, 0.65, f'{position}, B/T: {bat_side}/{pitcher_hand}, Age: {age}, {height}/{weight}', va='top', ha='center', fontsize=20)
|
| 57 |
+
if position == 'P':
|
| 58 |
+
ax.text(0.5, 0.38, f'Season Pitching Percentiles', va='top', ha='center', fontsize=16)
|
| 59 |
+
else:
|
| 60 |
+
ax.text(0.5, 0.41, f'Season Batting Percentiles', va='top', ha='center', fontsize=16)
|
| 61 |
+
|
| 62 |
+
# Make API call to retrieve sports information
|
| 63 |
+
response = requests.get(url='https://statsapi.mlb.com/api/v1/sports').json()
|
| 64 |
+
|
| 65 |
+
# Convert the JSON response into a Polars DataFrame
|
| 66 |
+
df_sport_id = pl.DataFrame(response['sports'])
|
| 67 |
+
abb = df_sport_id.filter(pl.col('id') == sport_id)['abbreviation'][0]
|
| 68 |
+
|
| 69 |
+
# Display the season and sport abbreviation
|
| 70 |
+
ax.text(0.5, 0.20, f'{year_input} {abb} Season', va='top', ha='center', fontsize=14, fontstyle='italic')
|
| 71 |
+
|
| 72 |
+
# Turn off the axis
|
| 73 |
+
ax.axis('off')
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
df_teams = scrape.get_teams()
|
| 77 |
+
team_dict = dict(zip(df_teams['team_id'],df_teams['parent_org_abbreviation']))
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
# List of MLB teams and their corresponding ESPN logo URLs
|
| 81 |
+
mlb_teams = [
|
| 82 |
+
{"team": "AZ", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/ari.png&h=500&w=500"},
|
| 83 |
+
{"team": "ATH", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/oak.png&h=500&w=500"},
|
| 84 |
+
{"team": "ATL", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/atl.png&h=500&w=500"},
|
| 85 |
+
{"team": "BAL", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/bal.png&h=500&w=500"},
|
| 86 |
+
{"team": "BOS", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/bos.png&h=500&w=500"},
|
| 87 |
+
{"team": "CHC", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/chc.png&h=500&w=500"},
|
| 88 |
+
{"team": "CWS", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/chw.png&h=500&w=500"},
|
| 89 |
+
{"team": "CIN", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/cin.png&h=500&w=500"},
|
| 90 |
+
{"team": "CLE", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/cle.png&h=500&w=500"},
|
| 91 |
+
{"team": "COL", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/col.png&h=500&w=500"},
|
| 92 |
+
{"team": "DET", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/det.png&h=500&w=500"},
|
| 93 |
+
{"team": "HOU", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/hou.png&h=500&w=500"},
|
| 94 |
+
{"team": "KC", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/kc.png&h=500&w=500"},
|
| 95 |
+
{"team": "LAA", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/laa.png&h=500&w=500"},
|
| 96 |
+
{"team": "LAD", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/lad.png&h=500&w=500"},
|
| 97 |
+
{"team": "MIA", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/mia.png&h=500&w=500"},
|
| 98 |
+
{"team": "MIL", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/mil.png&h=500&w=500"},
|
| 99 |
+
{"team": "MIN", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/min.png&h=500&w=500"},
|
| 100 |
+
{"team": "NYM", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/nym.png&h=500&w=500"},
|
| 101 |
+
{"team": "NYY", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/nyy.png&h=500&w=500"},
|
| 102 |
+
{"team": "PHI", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/phi.png&h=500&w=500"},
|
| 103 |
+
{"team": "PIT", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/pit.png&h=500&w=500"},
|
| 104 |
+
{"team": "SD", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/sd.png&h=500&w=500"},
|
| 105 |
+
{"team": "SF", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/sf.png&h=500&w=500"},
|
| 106 |
+
{"team": "SEA", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/sea.png&h=500&w=500"},
|
| 107 |
+
{"team": "STL", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/stl.png&h=500&w=500"},
|
| 108 |
+
{"team": "TB", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/tb.png&h=500&w=500"},
|
| 109 |
+
{"team": "TEX", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/tex.png&h=500&w=500"},
|
| 110 |
+
{"team": "TOR", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/tor.png&h=500&w=500"},
|
| 111 |
+
{"team": "WSH", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/mlb/500/scoreboard/wsh.png&h=500&w=500"},
|
| 112 |
+
{"team": "ZZZ", "logo_url": "https://a.espncdn.com/combiner/i?img=/i/teamlogos/leagues/500/mlb.png&w=500&h=500"}
|
| 113 |
+
]
|
| 114 |
+
|
| 115 |
+
df_image = pd.DataFrame(mlb_teams)
|
| 116 |
+
image_dict = df_image.set_index('team')['logo_url'].to_dict()
|
| 117 |
+
image_dict_flip = df_image.set_index('logo_url')['team'].to_dict()
|
| 118 |
+
|
| 119 |
+
# level_dict = {'1':'MLB',
|
| 120 |
+
# '11':'AAA'}
|
| 121 |
+
|
| 122 |
+
level_dict = {'1':'MLB',
|
| 123 |
+
'11':'AAA',
|
| 124 |
+
'14':'A (FSL)',}
|
| 125 |
+
|
| 126 |
+
|
| 127 |
+
level_dict_file = {'1':'mlb',
|
| 128 |
+
'11':'aaa',
|
| 129 |
+
'14':'a',}
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
year_list = [2024]
|
| 134 |
+
|
| 135 |
+
|
| 136 |
+
from shiny import App, reactive, ui, render
|
| 137 |
+
from shiny.ui import h2, tags
|
| 138 |
+
|
| 139 |
+
# Define the UI layout for the app
|
| 140 |
+
app_ui = ui.page_fluid(
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
ui.tags.div(
|
| 144 |
+
{"style": "width:90%;margin: 0 auto;max-width: 1600px;"},
|
| 145 |
+
ui.tags.style(
|
| 146 |
+
"""
|
| 147 |
+
h4 {
|
| 148 |
+
margin-top: 1em;font-size:35px;
|
| 149 |
+
}
|
| 150 |
+
h2{
|
| 151 |
+
font-size:25px;
|
| 152 |
+
}
|
| 153 |
+
"""
|
| 154 |
+
),
|
| 155 |
+
|
| 156 |
+
ui.tags.h4("TJStats"),
|
| 157 |
+
ui.tags.i("Baseball Analytics and Visualizations"),
|
| 158 |
+
ui.markdown("""<a href='https://x.com/TJStats'>Follow me on Twitter</a><sup>1</sup>"""),
|
| 159 |
+
ui.markdown("""<a href='https://www.patreon.com/tj_stats'>Support me on Patreon for Access to 2024 Apps</a><sup>1</sup>"""),
|
| 160 |
+
|
| 161 |
+
ui.markdown("### MiLB Statcast Batting Summaries"),
|
| 162 |
+
ui.markdown("""This Shiny App allows you to generate Baseball Savant-style percentile bars for MiLB players in the 2024 Season.
|
| 163 |
+
Currently, MiLB Statcast is only available for AAA and A (Florida State League) levels."""),
|
| 164 |
+
|
| 165 |
+
ui.layout_sidebar(
|
| 166 |
+
ui.panel_sidebar(
|
| 167 |
+
# Row for selecting season and level
|
| 168 |
+
ui.row(
|
| 169 |
+
ui.column(6, ui.input_select('year_input', 'Select Season', year_list, selected=2024)),
|
| 170 |
+
ui.column(6, ui.input_select('level_input', 'Select Level', level_dict)),
|
| 171 |
+
),
|
| 172 |
+
# Row for the action button to get player list
|
| 173 |
+
ui.row(ui.input_action_button("player_button", "Get Player List", class_="btn-primary")),
|
| 174 |
+
# Row for selecting the player
|
| 175 |
+
ui.row(ui.column(12, ui.output_ui('player_select_ui', 'Select Player'))),
|
| 176 |
+
|
| 177 |
+
ui.row(
|
| 178 |
+
ui.column(6, ui.input_switch("switch", "Custom Team?", False)),
|
| 179 |
+
ui.column(6, ui.input_select('logo_select', 'Select Custom Logo', image_dict_flip, multiple=False))
|
| 180 |
+
),
|
| 181 |
+
|
| 182 |
+
# Row for the action button to generate plot
|
| 183 |
+
ui.row(ui.input_action_button("generate_plot", "Generate Plot", class_="btn-primary")),
|
| 184 |
+
width=3,
|
| 185 |
+
),
|
| 186 |
+
|
| 187 |
+
ui.panel_main(
|
| 188 |
+
ui.navset_tab(
|
| 189 |
+
# Tab for game summary plot
|
| 190 |
+
ui.nav("Batter Summary",
|
| 191 |
+
ui.output_text("status_batter"),
|
| 192 |
+
ui.output_plot('batter_plot', width='1200px', height='1200px')
|
| 193 |
+
),
|
| 194 |
+
ui.nav("Pitcher Summary",
|
| 195 |
+
ui.output_text("status_pitcher"),
|
| 196 |
+
ui.output_plot('pitcher_plot', width='1200px', height='1200px')
|
| 197 |
+
)
|
| 198 |
+
,id="tabset"
|
| 199 |
+
)
|
| 200 |
+
)
|
| 201 |
+
)
|
| 202 |
+
)
|
| 203 |
+
)
|
| 204 |
+
|
| 205 |
+
def server(input, output, session):
|
| 206 |
+
@render.ui
|
| 207 |
+
@reactive.event(input.player_button,input.tabset, ignore_none=False)
|
| 208 |
+
def player_select_ui():
|
| 209 |
+
if input.tabset() == "Batter Summary":
|
| 210 |
+
#Get the list of pitchers for the selected level and season
|
| 211 |
+
df_pitcher_info = scrape.get_players(sport_id=int(input.level_input()), season=int(input.year_input())).filter(
|
| 212 |
+
~pl.col("position").is_in(['P','TWP'])).sort("name")
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
|
| 216 |
+
# Create a dictionary of pitcher IDs and names
|
| 217 |
+
batter_dict_pos = dict(zip(df_pitcher_info['player_id'], df_pitcher_info['position']))
|
| 218 |
+
|
| 219 |
+
year = int(input.year_input())
|
| 220 |
+
sport_id = int(input.level_input())
|
| 221 |
+
batter_summary = pl.read_csv(f'data/statcast/batter_summary_{level_dict_file[str(sport_id)]}_{year}.csv').sort('batter_name',descending=False)
|
| 222 |
+
# Map elements in Polars DataFrame from a dictionary
|
| 223 |
+
batter_summary = batter_summary.with_columns(
|
| 224 |
+
pl.col("batter_id").map_elements(lambda x: batter_dict_pos.get(x, x)).alias("position")
|
| 225 |
+
)
|
| 226 |
+
|
| 227 |
+
|
| 228 |
+
batter_dict_pos = dict(zip(batter_summary['batter_id'], batter_summary['batter_name']))
|
| 229 |
+
# Create a dictionary of pitcher IDs and names
|
| 230 |
+
batter_dict = dict(zip(batter_summary['batter_id'], batter_summary['batter_name'] + ' - ' + batter_summary['position']))
|
| 231 |
+
|
| 232 |
+
# Return a select input for choosing a pitcher
|
| 233 |
+
return ui.input_select("batter_id", "Select Batter", batter_dict, selectize=True)
|
| 234 |
+
|
| 235 |
+
if input.tabset() == "Pitcher Summary":
|
| 236 |
+
#Get the list of pitchers for the selected level and season
|
| 237 |
+
df_pitcher_info = scrape.get_players(sport_id=int(input.level_input()), season=int(input.year_input())).filter(
|
| 238 |
+
pl.col("position").is_in(['P','TWP'])).sort("name")
|
| 239 |
+
|
| 240 |
+
|
| 241 |
+
|
| 242 |
+
# Create a dictionary of pitcher IDs and names
|
| 243 |
+
batter_dict_pos = dict(zip(df_pitcher_info['player_id'], df_pitcher_info['position']))
|
| 244 |
+
|
| 245 |
+
year = int(input.year_input())
|
| 246 |
+
sport_id = int(input.level_input())
|
| 247 |
+
batter_summary = pl.read_csv(f'data/statcast/pitcher_summary_{level_dict_file[str(sport_id)]}_{year}.csv').sort('pitcher_name',descending=False)
|
| 248 |
+
# Map elements in Polars DataFrame from a dictionary
|
| 249 |
+
batter_summary = batter_summary.with_columns(
|
| 250 |
+
pl.col("pitcher_id").map_elements(lambda x: batter_dict_pos.get(x, x)).alias("position")
|
| 251 |
+
)
|
| 252 |
+
|
| 253 |
+
|
| 254 |
+
batter_dict_pos = dict(zip(batter_summary['pitcher_id'], batter_summary['pitcher_name']))
|
| 255 |
+
# Create a dictionary of pitcher IDs and names
|
| 256 |
+
batter_dict = dict(zip(batter_summary['pitcher_id'], batter_summary['pitcher_name'] + ' - ' + batter_summary['position']))
|
| 257 |
+
|
| 258 |
+
# Return a select input for choosing a pitcher
|
| 259 |
+
return ui.input_select("pitcher_id", "Select Batter", batter_dict, selectize=True)
|
| 260 |
+
|
| 261 |
+
|
| 262 |
+
|
| 263 |
+
@output
|
| 264 |
+
@render.plot
|
| 265 |
+
@reactive.event(input.generate_plot, ignore_none=False)
|
| 266 |
+
def batter_plot():
|
| 267 |
+
|
| 268 |
+
|
| 269 |
+
merged_dict = {
|
| 270 |
+
"woba_percent": { "format": '.3f', "percentile_flip": False, "stat_title": "wOBA" },
|
| 271 |
+
"xwoba_percent": { "format": '.3f', "percentile_flip": False, "stat_title": "xwOBA" },
|
| 272 |
+
"launch_speed": { "format": '.1f', "percentile_flip": False, "stat_title": "Average EV"},
|
| 273 |
+
"launch_speed_90": { "format": '.1f', "percentile_flip": False, "stat_title": "90th% EV"},
|
| 274 |
+
"max_launch_speed": { "format": '.1f', "percentile_flip": False, "stat_title": "Max EV"},
|
| 275 |
+
"barrel_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Barrel%" },
|
| 276 |
+
"hard_hit_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Hard-Hit%" },
|
| 277 |
+
"sweet_spot_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "LA Sweet-Spot%" },
|
| 278 |
+
"zone_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Zone%" },
|
| 279 |
+
"zone_swing_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Z-Swing%" },
|
| 280 |
+
"chase_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "O-Swing%" },
|
| 281 |
+
"whiff_rate": { "format": '.1%', "percentile_flip": True, "stat_title": "Whiff%" },
|
| 282 |
+
"k_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "K%" },
|
| 283 |
+
"bb_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "BB%" },
|
| 284 |
+
"pull_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Pull%" },
|
| 285 |
+
"pulled_fly_ball_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Pull FB%" },
|
| 286 |
+
}
|
| 287 |
+
# Show progress/loading notification
|
| 288 |
+
with ui.Progress(min=0, max=1) as p:
|
| 289 |
+
|
| 290 |
+
def draw_baseball_savant_percentiles(new_player_metrics, new_player_percentiles, colors=None,
|
| 291 |
+
sport_id=None,
|
| 292 |
+
year_input=None):
|
| 293 |
+
"""
|
| 294 |
+
Draw Baseball Savant-style percentile bars with proper alignment and scaling.
|
| 295 |
+
|
| 296 |
+
:param new_player_metrics: DataFrame containing new player metrics.
|
| 297 |
+
:param new_player_percentiles: DataFrame containing new player percentiles.
|
| 298 |
+
:param colors: List of colors for bars (optional, red/blue default).
|
| 299 |
+
"""
|
| 300 |
+
# Extract player information
|
| 301 |
+
batter_id = new_player_metrics['batter_id'][0]
|
| 302 |
+
player_name = batter_name_id[batter_id]
|
| 303 |
+
stats = [merged_dict[x]['stat_title'] for x in merged_dict.keys()]
|
| 304 |
+
|
| 305 |
+
# Calculate percentiles and values
|
| 306 |
+
percentiles = [int((1 - x) * 100) if merged_dict[stat]["percentile_flip"] else int(x * 100) for x, stat in zip(new_player_percentiles.select(merged_dict.keys()).to_numpy()[0], merged_dict.keys())]
|
| 307 |
+
percentiles = np.clip(percentiles, 1, 100)
|
| 308 |
+
values = [str(f'{x:{merged_dict[stat]["format"]}}').strip('%') for x, stat in zip(new_player_metrics.select(merged_dict.keys()).to_numpy()[0], merged_dict.keys())]
|
| 309 |
+
|
| 310 |
+
# Get team logo URL
|
| 311 |
+
logo_url = image_dict[team_dict[player_team_dict[batter_id]]]
|
| 312 |
+
|
| 313 |
+
# Create a custom colormap
|
| 314 |
+
color_list = ['#3661AD', '#B4CFD1', '#D82129']
|
| 315 |
+
cmap = LinearSegmentedColormap.from_list("custom_cmap", color_list)
|
| 316 |
+
norm = Normalize(vmin=0.1, vmax=0.9)
|
| 317 |
+
norm_percentiles = norm(percentiles / 100)
|
| 318 |
+
colors = [cmap(p) for p in norm_percentiles]
|
| 319 |
+
|
| 320 |
+
# Figure setup
|
| 321 |
+
num_stats = len(stats)
|
| 322 |
+
bar_height = 4.5
|
| 323 |
+
spacing = 1
|
| 324 |
+
fig_height = (bar_height + spacing) * num_stats
|
| 325 |
+
fig = plt.figure(figsize=(12, 12))
|
| 326 |
+
gs = GridSpec(6, 5, height_ratios=[0.1, 1.5, 0.9, 0.9, 7.6, 0.1], width_ratios=[0.2, 1.5, 7, 1.5, 0.2])
|
| 327 |
+
|
| 328 |
+
# Define subplots
|
| 329 |
+
ax_title = fig.add_subplot(gs[1, 2])
|
| 330 |
+
ax_table = fig.add_subplot(gs[2, :])
|
| 331 |
+
ax_fv_table = fig.add_subplot(gs[3, :])
|
| 332 |
+
ax_fv_table.axis('off')
|
| 333 |
+
ax = fig.add_subplot(gs[4, :])
|
| 334 |
+
ax_logo = fig.add_subplot(gs[1, 3])
|
| 335 |
+
|
| 336 |
+
ax.set_xlim(-1, 99)
|
| 337 |
+
ax.set_ylim(-1, 99)
|
| 338 |
+
ax.set_aspect("equal")
|
| 339 |
+
ax.axis("off")
|
| 340 |
+
|
| 341 |
+
# Draw each bar
|
| 342 |
+
for i, (stat, percentile, value, color) in enumerate(zip(stats, percentiles, values, colors)):
|
| 343 |
+
y = fig_height - (i + 1) * (bar_height + spacing)
|
| 344 |
+
ax.add_patch(patches.Rectangle((0, y + bar_height / 4), 100, bar_height / 2, color="#C7DCDC", lw=0))
|
| 345 |
+
ax.add_patch(patches.Rectangle((0, y), percentile, bar_height, color=color, lw=0))
|
| 346 |
+
circle_y = y + bar_height - bar_height / 2
|
| 347 |
+
circle = plt.Circle((percentile, circle_y), bar_height / 2, color=color, ec='white', lw=1.5, zorder=10)
|
| 348 |
+
ax.add_patch(circle)
|
| 349 |
+
fs = 14
|
| 350 |
+
ax.text(percentile, circle_y, f"{percentile}", ha="center", va="center", fontsize=10, color='white', zorder=10, fontweight='bold')
|
| 351 |
+
ax.text(-5, y + bar_height / 2, stat, ha="right", va="center", fontsize=fs)
|
| 352 |
+
ax.text(115, y + bar_height / 2, str(value), ha="right", va="center", fontsize=fs, zorder=5)
|
| 353 |
+
if i < len(stats) and i > 0:
|
| 354 |
+
ax.hlines(y=y + bar_height + spacing / 2, color='#399098', linestyle=(0, (5, 5)), linewidth=1, xmin=-33, xmax=0)
|
| 355 |
+
ax.hlines(y=y + bar_height + spacing / 2, color='#399098', linestyle=(0, (5, 5)), linewidth=1, xmin=100, xmax=115)
|
| 356 |
+
|
| 357 |
+
# Draw vertical lines for 10%, 50%, and 90% with labels
|
| 358 |
+
for x, label, align, color in zip([10, 50, 90], ["Poor", "Average", "Great"], ['center', 'center', 'center'], color_list):
|
| 359 |
+
ax.axvline(x=x, ymin=0, ymax=1, color='#FFF', linestyle='-', lw=1, zorder=1, alpha=0.5)
|
| 360 |
+
ax.text(x, fig_height + 4, label, ha=align, va='center', fontsize=12, fontweight='bold', color=color)
|
| 361 |
+
triangle = patches.RegularPolygon((x, fig_height + 1), 3, radius=1, orientation=0, color=color, zorder=2)
|
| 362 |
+
ax.add_patch(triangle)
|
| 363 |
+
|
| 364 |
+
# # Title
|
| 365 |
+
# ax_title.set_ylim(0, 1)
|
| 366 |
+
# ax_title.text(0.5, 0.5, f"{player_name} - {player_position_dict[batter_id]}\nPercentile Rankings - 2024 AAA", ha="center", va="center", fontsize=24)
|
| 367 |
+
# ax_title.axis("off")
|
| 368 |
+
player_bio(batter_id, ax=ax_title, sport_id=sport_id, year_input=year_input)
|
| 369 |
+
|
| 370 |
+
# Add team logo
|
| 371 |
+
#response = requests.get(logo_url)
|
| 372 |
+
if input.switch():
|
| 373 |
+
response = requests.get(input.logo_select())
|
| 374 |
+
else:
|
| 375 |
+
response = requests.get(logo_url)
|
| 376 |
+
img = Image.open(BytesIO(response.content))
|
| 377 |
+
ax_logo.imshow(img)
|
| 378 |
+
ax_logo.axis("off")
|
| 379 |
+
ax.axis('equal')
|
| 380 |
+
|
| 381 |
+
# Metrics data table
|
| 382 |
+
metrics_data = {
|
| 383 |
+
"Pitches": new_player_metrics['pitches'][0],
|
| 384 |
+
"PA": new_player_metrics['pa'][0],
|
| 385 |
+
"BIP": new_player_metrics['bip'][0],
|
| 386 |
+
"HR": f"{new_player_metrics['home_run'][0]:.0f}",
|
| 387 |
+
"AVG": f"{new_player_metrics['avg'][0]:.3f}",
|
| 388 |
+
"OBP": f"{new_player_metrics['obp'][0]:.3f}",
|
| 389 |
+
"SLG": f"{new_player_metrics['slg'][0]:.3f}",
|
| 390 |
+
"OPS": f"{new_player_metrics['obp'][0] + new_player_metrics['slg'][0]:.3f}",
|
| 391 |
+
}
|
| 392 |
+
df_table = pd.DataFrame(metrics_data, index=[0])
|
| 393 |
+
ax_table.axis('off')
|
| 394 |
+
table = ax_table.table(cellText=df_table.values, colLabels=df_table.columns, cellLoc='center', loc='bottom', bbox=[0.07, 0, 0.86, 1])
|
| 395 |
+
for key, cell in table.get_celld().items():
|
| 396 |
+
if key[0] == 0:
|
| 397 |
+
cell.set_text_props(fontweight='bold')
|
| 398 |
+
table.auto_set_font_size(False)
|
| 399 |
+
table.set_fontsize(12)
|
| 400 |
+
table.scale(1, 1.5)
|
| 401 |
+
|
| 402 |
+
# Additional subplots for spacing
|
| 403 |
+
ax_top = fig.add_subplot(gs[0, :])
|
| 404 |
+
ax_bot = fig.add_subplot(gs[-1, :])
|
| 405 |
+
ax_top.axis('off')
|
| 406 |
+
ax_bot.axis('off')
|
| 407 |
+
ax_bot.text(0.05, 2, "By: Thomas Nestico (@TJStats)", ha="left", va="center", fontsize=14)
|
| 408 |
+
ax_bot.text(0.95, 2, "Data: MLB, Fangraphs", ha="right", va="center", fontsize=14)
|
| 409 |
+
fig.subplots_adjust(left=0.01, right=0.99, top=0.99, bottom=0.01)
|
| 410 |
+
|
| 411 |
+
# Player headshot
|
| 412 |
+
ax_headshot = fig.add_subplot(gs[1, 1])
|
| 413 |
+
try:
|
| 414 |
+
url = f'https://img.mlbstatic.com/mlb-photos/image/upload/c_fill,g_auto/w_640/v1/people/{batter_id}/headshot/milb/current.png'
|
| 415 |
+
response = requests.get(url)
|
| 416 |
+
img = Image.open(BytesIO(response.content))
|
| 417 |
+
ax_headshot.set_xlim(0, 1)
|
| 418 |
+
ax_headshot.set_ylim(0, 1)
|
| 419 |
+
ax_headshot.imshow(img, extent=[1/6, 5/6, 0, 1], origin='upper')
|
| 420 |
+
except PIL.UnidentifiedImageError:
|
| 421 |
+
ax_headshot.axis('off')
|
| 422 |
+
#return
|
| 423 |
+
ax_headshot.axis('off')
|
| 424 |
+
ax_table.set_title('Season Summary', style='italic')
|
| 425 |
+
|
| 426 |
+
# Fangraphs scouting grades table
|
| 427 |
+
print(batter_id)
|
| 428 |
+
|
| 429 |
+
if batter_id not in dict_mlb_fg.keys():
|
| 430 |
+
ax_fv_table.text(x=0.5, y=0.5, s='No Scouting Data', style='italic', ha='center', va='center', fontsize=20, bbox=dict(facecolor='white', alpha=1, pad=10))
|
| 431 |
+
return
|
| 432 |
+
df_fv_table = df_prospects[(df_prospects['minorMasterId'] == dict_mlb_fg[batter_id])][['cFV', 'Hit', 'Game', 'Raw', 'Spd', 'Fld']].reset_index(drop=True)
|
| 433 |
+
ax_fv_table.axis('off')
|
| 434 |
+
if df_fv_table.empty:
|
| 435 |
+
ax_fv_table.text(x=0.5, y=0.5, s='No Scouting Data', style='italic', ha='center', va='center', fontsize=20, bbox=dict(facecolor='white', alpha=1, pad=10))
|
| 436 |
+
return
|
| 437 |
+
df_fv_table.columns = ['FV', 'Hit', 'Game', 'Raw', 'Spd', 'Fld']
|
| 438 |
+
table_fv = ax_fv_table.table(cellText=df_fv_table.values, colLabels=df_fv_table.columns, cellLoc='center', loc='bottom', bbox=[0.07, 0, 0.86, 1])
|
| 439 |
+
for key, cell in table_fv.get_celld().items():
|
| 440 |
+
if key[0] == 0:
|
| 441 |
+
cell.set_text_props(fontweight='bold')
|
| 442 |
+
table_fv.auto_set_font_size(False)
|
| 443 |
+
table_fv.set_fontsize(12)
|
| 444 |
+
table_fv.scale(1, 1.5)
|
| 445 |
+
ax_fv_table.set_title('Fangraphs Scouting Grades', style='italic')
|
| 446 |
+
|
| 447 |
+
|
| 448 |
+
|
| 449 |
+
#plt.show()
|
| 450 |
+
|
| 451 |
+
|
| 452 |
+
def calculate_new_player_percentiles(player_id, new_player_metrics, player_summary_filtered):
|
| 453 |
+
"""
|
| 454 |
+
Calculate percentiles for a new player's metrics.
|
| 455 |
+
|
| 456 |
+
:param player_id: ID of the player.
|
| 457 |
+
:param new_player_metrics: DataFrame containing new player metrics.
|
| 458 |
+
:param player_summary_filtered: Filtered player summary DataFrame.
|
| 459 |
+
:return: DataFrame containing new player percentiles.
|
| 460 |
+
"""
|
| 461 |
+
filtered_summary_clone = player_summary_filtered[['batter_id'] + stat_list].filter(pl.col('batter_id') != player_id).clone()
|
| 462 |
+
combined_data = pl.concat([filtered_summary_clone, new_player_metrics], how="vertical").to_pandas()
|
| 463 |
+
combined_percentiles = pl.DataFrame(pd.concat([combined_data['batter_id'], combined_data[stat_list].rank(pct=True)], axis=1))
|
| 464 |
+
new_player_percentiles = combined_percentiles.filter(pl.col('batter_id') == player_id)
|
| 465 |
+
return new_player_percentiles
|
| 466 |
+
|
| 467 |
+
|
| 468 |
+
|
| 469 |
+
p.set(message="Generating plot", detail="This may take a while...")
|
| 470 |
+
|
| 471 |
+
|
| 472 |
+
p.set(0.3, "Gathering data...")
|
| 473 |
+
|
| 474 |
+
# Example: New player's metrics
|
| 475 |
+
year = int(input.year_input())
|
| 476 |
+
sport_id = int(input.level_input())
|
| 477 |
+
batter_id = int(input.batter_id())
|
| 478 |
+
|
| 479 |
+
|
| 480 |
+
df_player = scrape.get_players(sport_id=sport_id,season=year)
|
| 481 |
+
batter_name_id = dict(zip(df_player['player_id'],df_player['name']))
|
| 482 |
+
player_team_dict = dict(zip(df_player['player_id'],df_player['team']))
|
| 483 |
+
player_position_dict = dict(zip(df_player['player_id'],df_player['position']))
|
| 484 |
+
|
| 485 |
+
|
| 486 |
+
batter_summary = pl.read_csv(f'data/statcast/batter_summary_{level_dict_file[str(sport_id)]}_{year}.csv')
|
| 487 |
+
df_prospects = pd.read_csv(f'data/prospects/prospects_{year}.csv')
|
| 488 |
+
df_rosters = pd.read_csv(f'data/rosters/fangraphs_rosters_{year}.csv')
|
| 489 |
+
df_small = df_rosters[['minorbamid','minormasterid']].dropna()
|
| 490 |
+
dict_mlb_fg=dict(zip(df_small['minorbamid'].astype(int),df_small['minormasterid']))
|
| 491 |
+
|
| 492 |
+
|
| 493 |
+
|
| 494 |
+
|
| 495 |
+
batter_summary_filter = batter_summary.filter((pl.col('pa') >= 300) & (pl.col('launch_speed') >= 0))
|
| 496 |
+
stat_list = batter_summary.columns[2:]
|
| 497 |
+
batter_summary_filter_pd = batter_summary_filter.to_pandas()
|
| 498 |
+
new_player_metrics = batter_summary.filter(pl.col('batter_id') == batter_id)[['batter_id'] + stat_list]
|
| 499 |
+
|
| 500 |
+
# Get percentiles for the new player
|
| 501 |
+
new_player_percentiles = calculate_new_player_percentiles(batter_id, new_player_metrics, batter_summary_filter)
|
| 502 |
+
|
| 503 |
+
p.set(0.6, "Creating plot...")
|
| 504 |
+
# Draw Baseball Savant-style percentile bars
|
| 505 |
+
draw_baseball_savant_percentiles(new_player_metrics=new_player_metrics,
|
| 506 |
+
new_player_percentiles=new_player_percentiles,
|
| 507 |
+
sport_id=sport_id,
|
| 508 |
+
year_input=year)
|
| 509 |
+
|
| 510 |
+
@output
|
| 511 |
+
@render.plot
|
| 512 |
+
@reactive.event(input.generate_plot, ignore_none=False)
|
| 513 |
+
def pitcher_plot():
|
| 514 |
+
merged_dict = {
|
| 515 |
+
"avg_start_speed_ff": { "format": '.1f', "percentile_flip": False, "stat_title": "Fastball Velocity" },
|
| 516 |
+
"extension": { "format": '.1f', "percentile_flip": False, "stat_title": "Extension" },
|
| 517 |
+
"woba_percent": { "format": '.3f', "percentile_flip": True, "stat_title": "wOBA" },
|
| 518 |
+
"xwoba_percent": { "format": '.3f', "percentile_flip": True, "stat_title": "xwOBA" },
|
| 519 |
+
"launch_speed": { "format": '.1f', "percentile_flip": True, "stat_title": "Average EV"},
|
| 520 |
+
"barrel_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "Barrel%" },
|
| 521 |
+
"hard_hit_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "Hard-Hit%" },
|
| 522 |
+
"whiff_rate": { "format": '.1%', "percentile_flip": False, "stat_title": "Whiff%" },
|
| 523 |
+
"zone_contact_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "Z-Contact%" },
|
| 524 |
+
"zone_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "Zone%" },
|
| 525 |
+
"chase_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "O-Swing%" },
|
| 526 |
+
"csw_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "CSW%" },
|
| 527 |
+
"k_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "K%" },
|
| 528 |
+
"bb_percent": { "format": '.1%', "percentile_flip": True, "stat_title": "BB%" },
|
| 529 |
+
"k_minus_bb_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "K - BB%" },
|
| 530 |
+
"ground_ball_percent": { "format": '.1%', "percentile_flip": False, "stat_title": "GB%" },
|
| 531 |
+
}
|
| 532 |
+
|
| 533 |
+
with ui.Progress(min=0, max=1) as p:
|
| 534 |
+
|
| 535 |
+
def draw_baseball_savant_percentiles(new_player_metrics, new_player_percentiles, colors=None,
|
| 536 |
+
sport_id=None,
|
| 537 |
+
year_input=None):
|
| 538 |
+
"""
|
| 539 |
+
Draw Baseball Savant-style percentile bars with proper alignment and scaling.
|
| 540 |
+
|
| 541 |
+
:param new_player_metrics: DataFrame containing new player metrics.
|
| 542 |
+
:param new_player_percentiles: DataFrame containing new player percentiles.
|
| 543 |
+
:param colors: List of colors for bars (optional, red/blue default).
|
| 544 |
+
"""
|
| 545 |
+
# Extract player information
|
| 546 |
+
pitcher_id = new_player_metrics['pitcher_id'][0]
|
| 547 |
+
player_name = pitcher_name_id[pitcher_id]
|
| 548 |
+
stats = [merged_dict[x]['stat_title'] for x in merged_dict.keys()]
|
| 549 |
+
|
| 550 |
+
# Calculate percentiles and values
|
| 551 |
+
percentiles = [int((1 - x) * 100) if merged_dict[stat]["percentile_flip"] else int(x * 100) for x, stat in zip(new_player_percentiles.select(merged_dict.keys()).to_numpy()[0], merged_dict.keys())]
|
| 552 |
+
percentiles = np.clip(percentiles, 1, 100)
|
| 553 |
+
values = [str(f'{x:{merged_dict[stat]["format"]}}').strip('%') for x, stat in zip(new_player_metrics.select(merged_dict.keys()).to_numpy()[0], merged_dict.keys())]
|
| 554 |
+
|
| 555 |
+
# Get team logo URL
|
| 556 |
+
logo_url = image_dict[team_dict[player_team_dict[pitcher_id]]]
|
| 557 |
+
|
| 558 |
+
# Create a custom colormap
|
| 559 |
+
color_list = ['#3661AD', '#B4CFD1', '#D82129']
|
| 560 |
+
cmap = LinearSegmentedColormap.from_list("custom_cmap", color_list)
|
| 561 |
+
norm = Normalize(vmin=0.1, vmax=0.9)
|
| 562 |
+
norm_percentiles = norm(percentiles / 100)
|
| 563 |
+
colors = [cmap(p) for p in norm_percentiles]
|
| 564 |
+
|
| 565 |
+
# Figure setup
|
| 566 |
+
num_stats = len(stats)
|
| 567 |
+
bar_height = 4.4
|
| 568 |
+
spacing = 0.7
|
| 569 |
+
fig_height = (bar_height + spacing) * num_stats
|
| 570 |
+
fig = plt.figure(figsize=(12, 12))
|
| 571 |
+
gs = GridSpec(7, 5, height_ratios=[0.05, 1.5, 0.75, 0.75,0.75, 7.7, 0.1], width_ratios=[0.2, 1.5, 7, 1.5, 0.2])
|
| 572 |
+
|
| 573 |
+
# Define subplots
|
| 574 |
+
ax_title = fig.add_subplot(gs[1, 2])
|
| 575 |
+
ax_table = fig.add_subplot(gs[2, :])
|
| 576 |
+
ax_fv_table = fig.add_subplot(gs[3, :])
|
| 577 |
+
ax_fv_table.axis('off')
|
| 578 |
+
ax_stuff = fig.add_subplot(gs[4, :])
|
| 579 |
+
ax = fig.add_subplot(gs[5, :])
|
| 580 |
+
ax_logo = fig.add_subplot(gs[1, 3])
|
| 581 |
+
|
| 582 |
+
ax.set_xlim(-1, 99)
|
| 583 |
+
ax.set_ylim(-1, 99)
|
| 584 |
+
ax.set_aspect("equal")
|
| 585 |
+
ax.axis("off")
|
| 586 |
+
|
| 587 |
+
# Draw each bar
|
| 588 |
+
for i, (stat, percentile, value, color) in enumerate(zip(stats, percentiles, values, colors)):
|
| 589 |
+
y = fig_height - (i + 1) * (bar_height + spacing)
|
| 590 |
+
ax.add_patch(patches.Rectangle((0, y + bar_height / 4), 100, bar_height / 2, color="#C7DCDC", lw=0))
|
| 591 |
+
ax.add_patch(patches.Rectangle((0, y), percentile, bar_height, color=color, lw=0))
|
| 592 |
+
circle_y = y + bar_height - bar_height / 2
|
| 593 |
+
circle = plt.Circle((percentile, circle_y), bar_height / 2, color=color, ec='white', lw=1.5, zorder=10)
|
| 594 |
+
ax.add_patch(circle)
|
| 595 |
+
fs = 14
|
| 596 |
+
ax.text(percentile, circle_y, f"{percentile}", ha="center", va="center", fontsize=10, color='white', zorder=10, fontweight='bold')
|
| 597 |
+
ax.text(-5, y + bar_height / 2, stat, ha="right", va="center", fontsize=fs)
|
| 598 |
+
ax.text(115, y + bar_height / 2, str(value), ha="right", va="center", fontsize=fs, zorder=5)
|
| 599 |
+
if i < len(stats) and i > 0:
|
| 600 |
+
ax.hlines(y=y + bar_height + spacing / 2, color='#399098', linestyle=(0, (5, 5)), linewidth=1, xmin=-33, xmax=0)
|
| 601 |
+
ax.hlines(y=y + bar_height + spacing / 2, color='#399098', linestyle=(0, (5, 5)), linewidth=1, xmin=100, xmax=115)
|
| 602 |
+
|
| 603 |
+
# Draw vertical lines for 10%, 50%, and 90% with labels
|
| 604 |
+
for x, label, align, color in zip([10, 50, 90], ["Poor", "Average", "Great"], ['center', 'center', 'center'], color_list):
|
| 605 |
+
ax.axvline(x=x, ymin=0, ymax=1, color='#FFF', linestyle='-', lw=1, zorder=1, alpha=0.5)
|
| 606 |
+
ax.text(x, fig_height + 4, label, ha=align, va='center', fontsize=12, fontweight='bold', color=color)
|
| 607 |
+
triangle = patches.RegularPolygon((x, fig_height + 1), 3, radius=1, orientation=0, color=color, zorder=2)
|
| 608 |
+
ax.add_patch(triangle)
|
| 609 |
+
|
| 610 |
+
# # Title
|
| 611 |
+
# ax_title.set_ylim(0, 1)
|
| 612 |
+
# ax_title.text(0.5, 0.5, f"{player_name} - {player_position_dict[pitcher_id]}\nPercentile Rankings - 2024 AAA", ha="center", va="center", fontsize=24)
|
| 613 |
+
# ax_title.axis("off")
|
| 614 |
+
player_bio(pitcher_id, ax=ax_title, sport_id=sport_id, year_input=year_input)
|
| 615 |
+
|
| 616 |
+
# Add team logo
|
| 617 |
+
#response = requests.get(logo_url)
|
| 618 |
+
#######if input.switch():
|
| 619 |
+
######## response = requests.get(input.logo_select())
|
| 620 |
+
######else:
|
| 621 |
+
response = requests.get(logo_url)
|
| 622 |
+
img = Image.open(BytesIO(response.content))
|
| 623 |
+
ax_logo.imshow(img)
|
| 624 |
+
ax_logo.axis("off")
|
| 625 |
+
ax.axis('equal')
|
| 626 |
+
lg_dict = {
|
| 627 |
+
11:'all',
|
| 628 |
+
14:10
|
| 629 |
+
}
|
| 630 |
+
levelt = {
|
| 631 |
+
11:1,
|
| 632 |
+
14:4
|
| 633 |
+
}
|
| 634 |
+
|
| 635 |
+
|
| 636 |
+
fg_api = f'https://www.fangraphs.com/api/leaders/minor-league/data?pos=all&level={levelt[sport_id]}&lg={lg_dict[sport_id]}&stats=pit&qual=0&type=2&team=&season=2024&seasonEnd=2024&org=&ind=0&splitTeam=false'
|
| 637 |
+
response = requests.get(fg_api)
|
| 638 |
+
data = response.json()
|
| 639 |
+
df_fg = pl.DataFrame(data)
|
| 640 |
+
if pitcher_id not in dict_mlb_fg.keys():
|
| 641 |
+
#ax_fv_table.text(x=0.5, y=0.5, s='No Scouting Data', style='italic', ha='center', va='center', fontsize=20, bbox=dict(facecolor='white', alpha=1, pad=10))
|
| 642 |
+
metrics_data = {
|
| 643 |
+
"Pitches": new_player_metrics['pitches'][0],
|
| 644 |
+
"PA": new_player_metrics['pa'][0],
|
| 645 |
+
"BIP": new_player_metrics['bip'][0],
|
| 646 |
+
"HR": f"{new_player_metrics['home_run'][0]:.0f}",
|
| 647 |
+
"K": f"{new_player_metrics['k'][0]:.0f}",
|
| 648 |
+
"BB": f"{new_player_metrics['bb'][0]:.0f}",
|
| 649 |
+
}
|
| 650 |
+
else:
|
| 651 |
+
df_fg_filter = df_fg.filter(pl.col('minormasterid') == dict_mlb_fg[pitcher_id])
|
| 652 |
+
# Metrics data table
|
| 653 |
+
metrics_data = {
|
| 654 |
+
"G": f"{df_fg_filter['G'][0]:.0f}",
|
| 655 |
+
"IP": f"{df_fg_filter['IP'][0]:.1f}",
|
| 656 |
+
"Pitches": f"{new_player_metrics['pitches'][0]:.0f}",
|
| 657 |
+
"PA": f"{df_fg_filter['TBF'][0]:.0f}",
|
| 658 |
+
"BIP": new_player_metrics['bip'][0],
|
| 659 |
+
"ERA": f"{df_fg_filter['ERA'][0]:.2f}",
|
| 660 |
+
"FIP": f"{df_fg_filter['FIP'][0]:.2f}",
|
| 661 |
+
"WHIP": f"{df_fg_filter['WHIP'][0]:.2f}",
|
| 662 |
+
}
|
| 663 |
+
df_table = pd.DataFrame(metrics_data, index=[0])
|
| 664 |
+
ax_table.axis('off')
|
| 665 |
+
table = ax_table.table(cellText=df_table.values, colLabels=df_table.columns, cellLoc='center', loc='bottom', bbox=[0.07, 0, 0.86, 1])
|
| 666 |
+
for key, cell in table.get_celld().items():
|
| 667 |
+
if key[0] == 0:
|
| 668 |
+
cell.set_text_props(fontweight='bold')
|
| 669 |
+
table.auto_set_font_size(False)
|
| 670 |
+
table.set_fontsize(12)
|
| 671 |
+
table.scale(1, 1.5)
|
| 672 |
+
|
| 673 |
+
# Additional subplots for spacing
|
| 674 |
+
ax_top = fig.add_subplot(gs[0, :])
|
| 675 |
+
ax_bot = fig.add_subplot(gs[-1, :])
|
| 676 |
+
ax_top.axis('off')
|
| 677 |
+
ax_bot.axis('off')
|
| 678 |
+
ax_bot.text(0.05, 2, "By: Thomas Nestico (@TJStats)", ha="left", va="center", fontsize=14)
|
| 679 |
+
ax_bot.text(0.95, 2, "Data: MLB, Fangraphs", ha="right", va="center", fontsize=14)
|
| 680 |
+
|
| 681 |
+
|
| 682 |
+
# Player headshot
|
| 683 |
+
ax_headshot = fig.add_subplot(gs[1, 1])
|
| 684 |
+
try:
|
| 685 |
+
url = f'https://img.mlbstatic.com/mlb-photos/image/upload/c_fill,g_auto/w_640/v1/people/{pitcher_id}/headshot/milb/current.png'
|
| 686 |
+
response = requests.get(url)
|
| 687 |
+
img = Image.open(BytesIO(response.content))
|
| 688 |
+
ax_headshot.set_xlim(0, 1)
|
| 689 |
+
ax_headshot.set_ylim(0, 1)
|
| 690 |
+
ax_headshot.imshow(img, extent=[1/6, 5/6, 0, 1], origin='upper')
|
| 691 |
+
except PIL.UnidentifiedImageError:
|
| 692 |
+
ax_headshot.axis('off')
|
| 693 |
+
#return
|
| 694 |
+
ax_headshot.axis('off')
|
| 695 |
+
ax_table.set_title('Season Summary', style='italic')
|
| 696 |
+
|
| 697 |
+
# Fangraphs scouting grades table
|
| 698 |
+
print(pitcher_id)
|
| 699 |
+
|
| 700 |
+
if pitcher_id not in dict_mlb_fg.keys():
|
| 701 |
+
ax_fv_table.text(x=0.5, y=0.5, s='No Scouting Data', style='italic', ha='center', va='center', fontsize=20, bbox=dict(facecolor='white', alpha=1, pad=10))
|
| 702 |
+
#return
|
| 703 |
+
df_fv_table = df_prospects[(df_prospects['minorMasterId'] == dict_mlb_fg[pitcher_id])][['cFV','FB', 'SL', 'CB', 'CH', 'SPL', 'CT','CMD']].dropna(axis=1).reset_index(drop=True)
|
| 704 |
+
ax_fv_table.axis('off')
|
| 705 |
+
if df_fv_table.empty:
|
| 706 |
+
ax_fv_table.text(x=0.5, y=0.5, s='No Scouting Data', style='italic', ha='center', va='center', fontsize=20, bbox=dict(facecolor='white', alpha=1, pad=10))
|
| 707 |
+
#return
|
| 708 |
+
else:
|
| 709 |
+
df_fv_table.columns = ['FV']+[x.upper() for x in df_fv_table.columns[1:]]
|
| 710 |
+
table_fv = ax_fv_table.table(cellText=df_fv_table.values, colLabels=df_fv_table.columns, cellLoc='center', loc='bottom', bbox=[0.07, 0, 0.86, 1])
|
| 711 |
+
for key, cell in table_fv.get_celld().items():
|
| 712 |
+
if key[0] == 0:
|
| 713 |
+
cell.set_text_props(fontweight='bold')
|
| 714 |
+
table_fv.auto_set_font_size(False)
|
| 715 |
+
table_fv.set_fontsize(12)
|
| 716 |
+
table_fv.scale(1, 1.5)
|
| 717 |
+
ax_fv_table.set_title('Fangraphs Scouting Grades', style='italic')
|
| 718 |
+
|
| 719 |
+
|
| 720 |
+
# df_stuff_filter = df_stuff.filter(pl.col('pitcher_id')==pitcher_id)
|
| 721 |
+
|
| 722 |
+
stuff_table = ax_stuff.table(cellText=[df_stuff_filter['tj_stuff_plus']],
|
| 723 |
+
colLabels=df_stuff_filter['pitch_type'],
|
| 724 |
+
cellLoc='center',
|
| 725 |
+
loc='center', bbox=[0.07, 0, 0.86, 1])
|
| 726 |
+
stuff_table.auto_set_font_size(False)
|
| 727 |
+
stuff_table.set_fontsize(12)
|
| 728 |
+
stuff_table.scale(1, 1.5)
|
| 729 |
+
ax_stuff.axis('off')
|
| 730 |
+
ax_stuff.set_title('tjStuff+', style='italic')
|
| 731 |
+
for key, cell in stuff_table.get_celld().items():
|
| 732 |
+
if key[0] == 0:
|
| 733 |
+
cell.set_text_props(fontweight='bold')
|
| 734 |
+
|
| 735 |
+
# Color the stuff_table values based on the cmap defined
|
| 736 |
+
for (i, j), cell in stuff_table.get_celld().items():
|
| 737 |
+
if i == 0:
|
| 738 |
+
cell.set_text_props(fontweight='bold')
|
| 739 |
+
else:
|
| 740 |
+
norm = Normalize(vmin=90, vmax=110)
|
| 741 |
+
value = float(cell.get_text().get_text())
|
| 742 |
+
color = cmap(norm(value))
|
| 743 |
+
cell.set_facecolor(color)
|
| 744 |
+
#cell.set_text_props(color='white' if value < 100 else 'black')
|
| 745 |
+
|
| 746 |
+
|
| 747 |
+
|
| 748 |
+
|
| 749 |
+
|
| 750 |
+
fig.subplots_adjust(left=0.01, right=0.99, top=0.99, bottom=0.01)
|
| 751 |
+
|
| 752 |
+
|
| 753 |
+
|
| 754 |
+
|
| 755 |
+
|
| 756 |
+
def calculate_new_player_percentiles(player_id, new_player_metrics, player_summary_filtered):
|
| 757 |
+
"""
|
| 758 |
+
Calculate percentiles for a new player's metrics.
|
| 759 |
+
|
| 760 |
+
:param player_id: ID of the player.
|
| 761 |
+
:param new_player_metrics: DataFrame containing new player metrics.
|
| 762 |
+
:param player_summary_filtered: Filtered player summary DataFrame.
|
| 763 |
+
:return: DataFrame containing new player percentiles.
|
| 764 |
+
"""
|
| 765 |
+
filtered_summary_clone = player_summary_filtered[['pitcher_id'] + stat_list].filter(pl.col('pitcher_id') != player_id).clone()
|
| 766 |
+
combined_data = pl.concat([filtered_summary_clone, new_player_metrics], how="vertical").to_pandas()
|
| 767 |
+
combined_percentiles = pl.DataFrame(pd.concat([combined_data['pitcher_id'], combined_data[stat_list].rank(pct=True)], axis=1))
|
| 768 |
+
new_player_percentiles = combined_percentiles.filter(pl.col('pitcher_id') == player_id)
|
| 769 |
+
return new_player_percentiles
|
| 770 |
+
|
| 771 |
+
p.set(message="Generating plot", detail="This may take a while...")
|
| 772 |
+
|
| 773 |
+
|
| 774 |
+
p.set(0.3, "Gathering data...")
|
| 775 |
+
|
| 776 |
+
|
| 777 |
+
df_teams = scrape.get_teams()
|
| 778 |
+
team_dict = dict(zip(df_teams['team_id'],df_teams['parent_org_abbreviation']))
|
| 779 |
+
|
| 780 |
+
# Example: New player's metrics
|
| 781 |
+
# Example: New player's metrics
|
| 782 |
+
year = int(input.year_input())
|
| 783 |
+
sport_id = int(input.level_input())
|
| 784 |
+
pitcher_id = int(input.pitcher_id())
|
| 785 |
+
|
| 786 |
+
df_player = scrape.get_players(sport_id=sport_id,season=2024)
|
| 787 |
+
pitcher_name_id = dict(zip(df_player['player_id'],df_player['name']))
|
| 788 |
+
player_team_dict = dict(zip(df_player['player_id'],df_player['team']))
|
| 789 |
+
player_position_dict = dict(zip(df_player['player_id'],df_player['position']))
|
| 790 |
+
player_position_dict = dict(zip(df_player['player_id'],df_player['position']))
|
| 791 |
+
|
| 792 |
+
|
| 793 |
+
|
| 794 |
+
|
| 795 |
+
pitcher_summary = pl.read_csv(f'data/statcast/pitcher_summary_{level_dict_file[str(sport_id)]}_{year}.csv')
|
| 796 |
+
df_prospects = pd.read_csv(f'data/prospects/prospects_{year}.csv')
|
| 797 |
+
df_rosters = pd.read_csv(f'data/rosters/fangraphs_rosters_{year}.csv')
|
| 798 |
+
df_small = df_rosters[['minorbamid','minormasterid']].dropna()
|
| 799 |
+
dict_mlb_fg=dict(zip(df_small['minorbamid'].astype(int),df_small['minormasterid']))
|
| 800 |
+
|
| 801 |
+
df_stuff = pl.read_csv(f'data/stuff/stuff_{level_dict_file[str(sport_id)]}_{year}.csv')
|
| 802 |
+
# Filter out the "All" row
|
| 803 |
+
filtered_df = df_stuff.filter(pl.col("pitch_type") != "All")
|
| 804 |
+
|
| 805 |
+
filtered_all_df = df_stuff.filter(pl.col("pitch_type") == "All")
|
| 806 |
+
# Calculate total pitches for each pitcher and proportion of each pitch type
|
| 807 |
+
result_df = (
|
| 808 |
+
filtered_df
|
| 809 |
+
.with_columns([
|
| 810 |
+
# Total pitches for each pitcher
|
| 811 |
+
pl.col("pitches").sum().over("pitcher_id").alias("total_pitches"),
|
| 812 |
+
# Proportion of pitches
|
| 813 |
+
(pl.col("pitches") / pl.col("pitches").sum().over("pitcher_id")).alias("pitch_proportion"),
|
| 814 |
+
])
|
| 815 |
+
).filter(pl.col("pitch_proportion") > 0.05)
|
| 816 |
+
|
| 817 |
+
df_stuff = pl.concat([filtered_all_df.with_columns(
|
| 818 |
+
[pl.col("pitches").sum().over("pitcher_id").alias("total_pitches"),
|
| 819 |
+
(pl.col("pitches") / pl.col("pitches").sum().over("pitcher_id")).alias("pitch_proportion")]
|
| 820 |
+
), result_df])
|
| 821 |
+
|
| 822 |
+
|
| 823 |
+
|
| 824 |
+
|
| 825 |
+
df_stuff_filter = df_stuff.filter(pl.col('pitcher_id')==pitcher_id)
|
| 826 |
+
|
| 827 |
+
pitcher_summary_filter = pitcher_summary.filter((pl.col('pa') >= 300) & (pl.col('launch_speed') >= 0))
|
| 828 |
+
stat_list = pitcher_summary.columns[2:]
|
| 829 |
+
pitcher_summary_filter_pd = pitcher_summary_filter.to_pandas()
|
| 830 |
+
new_player_metrics = pitcher_summary.filter(pl.col('pitcher_id') == pitcher_id)[['pitcher_id'] + stat_list]
|
| 831 |
+
|
| 832 |
+
# Get percentiles for the new player
|
| 833 |
+
new_player_percentiles = calculate_new_player_percentiles(pitcher_id, new_player_metrics, pitcher_summary_filter)
|
| 834 |
+
|
| 835 |
+
p.set(0.6, "Creating plot...")
|
| 836 |
+
# Draw Baseball Savant-style percentile bars
|
| 837 |
+
draw_baseball_savant_percentiles(new_player_metrics=new_player_metrics,
|
| 838 |
+
new_player_percentiles=new_player_percentiles,
|
| 839 |
+
sport_id=sport_id,
|
| 840 |
+
year_input=year)
|
| 841 |
+
|
| 842 |
+
|
| 843 |
app = App(app_ui, server)
|