def process_data(time, firstname, lastname, pos):
playerid = playerid_lookup(lastname, firstname)
if "to" in time:
if pos == 'batter':
return statcast_batter(time[0:10], time[14:], player_id=int(playerid['key_mlbam'][0]))
elif pos == 'pitcher':
return statcast_pitcher(time[0:10], time[14:], player_id=int(playerid['key_mlbam'][0]))
else:
return None
else:
if pos == 'batter':
return statcast_batter(time, player_id=int(playerid['key_mlbam'][0]))
elif pos == 'pitcher':
return statcast_pitcher(time, player_id=int(playerid['key_mlbam'][0]))
else:
return None
def player(first_name, last_name, start_date, end_date):
player_info = pybaseball.playerid_lookup(last_name, first_name)
# if (player_info['mlb_played_last'][0] - player_info['mlb_played_first'][0]) < 10:
# start_year = int(player_info['mlb_played_first'][0])
# else:
# start_year = int(player_info['mlb_played_last'][0] - 10)
player_id = player_info['key_mlbam'][0]
# player_info = [player_id,start_year,str(player_info['mlb_played_last'][0])]
data = pybaseball.statcast_batter(start_dt = start_date, end_dt = end_date, player_id = player_info[0])
data = data.reset_index(drop = True)
return data
def batter(self, name, team, throws='R'):
Xcols = ['pfx_x', 'pfx_z', 'release_speed', 'release_spin_rate']
if throws == 'R':
scaler = self.scalerR
kmeans = self.modelR
else:
scaler = self.scalerL
kmeans = self.modelL
fgh = self.fgh
player = fgh[(fgh.Name.str.lower() == name.lower())
& (fgh.Team.str.lower() == team.lower())].playerid
pid = int(playerid_reverse_lookup(player, 'fangraphs').key_mlbam)
bat = statcast_batter(start_dt='2015-03-28',
end_dt='2019-09-29',
player_id=pid)
bat.dropna(subset=Xcols, inplace=True)
bat.reset_index(drop=True, inplace=True)
bat = bat[bat.p_throws == throws]
bat['p_type'] = kmeans.predict(scaler.transform(bat[Xcols]))
batdict = {}
for i in range(12):
if throws == 'R':
if i == 7:
batnum = bat[(bat.p_type == 7) | (bat.p_type == 12)]
elif i == 12:
continue
else:
batnum = bat[bat.p_type == i]
else:
if i == 0:
batnum = bat[(bat.p_type == 0) | (bat.p_type == 4)]
elif i == 4:
continue
else:
batnum = bat[bat.p_type == i]
batdict[i] = [len(batnum)]
batdict[i] += [
round((np.sum(batnum.woba_value) / np.sum(batnum.woba_denom)),
3)
]
return pid, batdict
def data_from_name(last, first, year1=2020, num_years=1):
years = range(year1, year1 + num_years)
lookup = pybaseball.playerid_lookup(last, first)
if len(lookup) > 1:
print('Multiple players found, determining player by years.')
lookup['int'] = lookup.apply(lambda row: len(
set(
range(int(row['mlb_played_first']), int(row['mlb_played_last'])
)) & set(years)),
axis=1)
lookup = lookup[lookup['int'] == max(lookup['int'])]
if len(lookup) > 1:
print('Unable to determine player')
else:
mlb_id = int(lookup['key_mlbam'])
data = pybaseball.statcast_batter(f'{year1}-01-01',
f'{year1+num_years}-01-01', mlb_id)
data = data[data.apply(
lambda row: 'hit_into_play' in row['description'], axis=1)]
data = data[data['events'] != 'home_run']
data = data.dropna(
how='any', subset=['launch_angle', 'launch_speed', 'hc_x', 'hc_y'])
return data
#get players for both team
players = [("corey", "kluber"), ("yan", "gomes"), ("yonder", "alonso"),
("jose", "ramirez"), ("josh", "donaldson"), ("francisco", "lindor"),
("melky", "cabrera"), ("jason", "kipnis"), ("michael", "brantley"),
("luis", "castillo"), ("tucker", "barnhart"), ("joey", "votto"),
("scooter", "gennett"), ("eugenio", "suarez"),
("mason", "williams"), ("billy", "hamilton"), ("preston", "tucker"),
("jose", "peraza")]
mycursor = mydb.cursor()
#get player data
for player in players:
id = playerid_lookup(player[1], player[0])
print(len(id))
if len(id) == 1:
stats = statcast_batter('2018-3-29', '2018-10-02',
id.key_mlbam.iloc[0])
hr = 0
bip = 0
tot = 0
for event in stats.events:
tot = tot + 1
if event == 'home_run':
hr = hr + 1
if type(
event
) != float and event != "strikeout" and event != "walk" and event != "home_run":
bip = bip + 1
sql = "INSERT INTO batters (NAME, HR, BIP) VALUES (%s, %s, %s)"
val = (f'{player[0]} {player[1]}', hr / tot, bip / tot)
mycursor.execute(sql, val)
mydb.commit()
def retrieve_data():
"""
Function for retrieving data from Statcast and performing some custom
formatting
"""
run_button.label = 'Running...'
reset_data()
global p_dict
global h_dict
global data
global data_cds
global pitch_cds_p
global pitches_p
global pitcher_data
global batter_data
global sub_batter
# update plot title
pitchername = pitcherselect.value.split(' -')[0]
battername = hitterselect.value.split(' -')[0]
plot.title.text = f'{pitchername} vs. {battername}'
pitcher_id = p_dict[pitcherselect.value]
hitter_id = h_dict[hitterselect.value]
# all the data for the batter in the time frame
batter_data_temp = statcast_batter(str(start_date.value),
str(end_date.value), hitter_id)
batter_data = pitch_info(batter_data_temp)
# all data for the pitcher in the time frame
pitcher_data_temp = statcast_pitcher(str(start_date.value),
str(end_date.value), pitcher_id)
pitcher_data = pitch_info(pitcher_data_temp)
# filter to only the pitches thrown to selected batter
data = pitcher_data[pitcher_data['batter'] == hitter_id].copy()
sub_batter = batter_data[batter_data['pitcher'] == pitcher_id].copy()
if len(data) == 0:
warning_txt = 'No matchups in specified time frame'
warning_label.text = warning_txt
else:
warning_label.text = ''
result = []
count = []
for r in data.iterrows():
# assign event names
event = results(r[1]['events'], r[1]['description'])
result.append(event)
count_str = f"{r[1]['balls']}, {r[1]['strikes']}"
count.append(count_str)
data['result'] = result
data['count'] = count
# update column data source
new_data = {
'pitch': data['pitch_name'],
'speed': data['release_speed'],
'result': data['result'],
'count': data['count'],
'color': data['color'],
'plate_x': data['plate_x'],
'plate_z': data['plate_z']
}
data_cds.data = new_data
# update strike zoe
new_top = data.sz_top.sum() / len(data.sz_top)
new_bottom = data.sz_bot.sum() / len(data.sz_bot)
new_zone = {
'x': [-8.5 / 12, 8.5 / 12],
'x_side1': [-8.5 / 12, -8.5 / 12],
'x_side2': [8.5 / 12, 8.5 / 12],
'top': [new_top, new_top],
'bottom': [new_bottom, new_bottom],
'side1': [new_top, new_bottom],
'side2': [new_bottom, new_top]
}
strike_zone_cds.data = new_zone
# update pitch plots
p_unique, p_matchup, p_overall = pitch_frequency(pitcher_data, data)
pitches_p.x_range.factors = p_unique
new_data_pitcher = {
'pitches': p_unique,
'matchup': p_matchup,
'overall': p_overall
}
pitch_cds_p.data = new_data_pitcher
b_unique, b_matchup, b_overall = pitch_frequency(
batter_data, sub_batter)
pitches_b.x_range.factors = b_unique
new_data_batter = {
'pitches': b_unique,
'matchup': b_matchup,
'overall': b_overall
}
pitch_cds_b.data = new_data_batter
run_button.label = 'Run'
firstName = input()
print("Enter player's last name: ")
lastName = input()
print("Enter Start Date (YYYY-MM-DD): ")
fromDate = input()
print("Enter End Date (YYYY-MM-DD): ")
toDate = input()
playerBattedBalls = get_player_batted_balls(firstName, lastName, fromDate,
toDate)
playerBattedBalls = playerBattedBalls.reset_index(drop=True)
xBA = playerBattedBalls["estimated_ba_using_speedangle"]
playerIDtable = pybaseball.playerid_lookup(lastName, firstName)
player = playerIDtable.loc[0].key_mlbam
playerBattedBallsMore = pybaseball.statcast_batter(fromDate, toDate, player)
BAlist = []
for x in range(100000):
hit = 0
for i in range(0, len(xBA)):
rand = random.uniform(0, 1)
if rand < xBA[i]:
hit = hit + 1
BA = hit / ((len(xBA) + len(playerBattedBallsMore.events[
playerBattedBallsMore.events == 'strikeout'])))
BAlist.append(BA)
hits = len(playerBattedBallsMore.events[
playerBattedBallsMore.events == 'single']) + len(
playerBattedBallsMore.events[playerBattedBallsMore.events == 'double']
async def on_message(message):
if message.content.startswith('!istimcool'): # Tim is cool, duh.
await client.send_message(message.channel, 'Well of course.')
elif message.content.startswith('!hidrricks'): # Tim is cool, duh.
await client.send_message(message.channel,
'Hello! It must be lab day.')
elif message.content.startswith('!whattimeisit'): # Returns current time
await client.send_message(message.channel,
datetime.datetime.now().time())
await client.send_message(message.channel, 'Central Time')
elif message.content.startswith('!coinflip'): # Flips a coin
resultOfFlip = random.choice(['Heads', 'Tails'])
await client.send_message(message.channel, resultOfFlip)
elif message.content.startswith(
'!addquote'): # Adds a quote to a running quote file.!
if not os.path.isfile("quote_file.pk1"):
quote_list = []
else:
with open("quote_file.pk1", "r") as quote_file:
quote_list = json.load(quote_file)
quote_list.append(message.content[9:])
with open("quote_file.pk1", "w") as quote_file:
json.dump(quote_list, quote_file)
elif message.content.startswith(
'!quote'): # Pulls a random quote from the quote file.
with open("quote_file.pk1", "r") as quote_file:
quote_list = json.load(quote_file)
await client.send_message(message.channel, random.choice(quote_list))
elif message.content.startswith('!rps'): # Play rock paper scissors.
rps = random.choice(["Rock", "Paper", "Scissors"])
await client.send_message(message.channel, rps)
elif message.content.startswith('!emoji'): # Turns to emoji text.
Message = message.content[7:]
if Message == 'hello': # hello
await client.send_message(
message.channel,
':regional_indicator_h::regional_indicator_e::regional_indicator_l::regional_indicator_l::regional_indicator_o:'
)
elif Message == 'liam sucks': # liam sucks
await client.send_message(
message.channel,
':regional_indicator_l::regional_indicator_i::regional_indicator_a::regional_indicator_m: :regional_indicator_s::regional_indicator_u::regional_indicator_c::regional_indicator_k::regional_indicator_s:'
)
elif message.content.startswith(
'!stats'): # Returns batting stats for player
playerName = message.content[7:]
print(playerName)
if playerName == 'Mike Moustakas':
from pybaseball import statcast_batter
playerID = 519058
moustakasStats = statcast_batter('2017-04-01', '2017-09-01',
playerID)
print('success')
await client.send_message(message.channel, moustakasStats)
elif message.content.startswith('!censor'): # NO SWEARING
await client.send_message(
message.channel,
'http://i0.kym-cdn.com/photos/images/original/001/299/189/6bb.jpg')
elif message.content.startswith(
'!weather'): # Returns condition and temp at location
location = message.content[9:]
from weather import Weather
weather = Weather()
lookup = weather.lookup_by_location(location)
condition = lookup.condition().text()
temp = lookup.condition().temp()
desc = lookup.description()
await client.send_message(message.channel, condition)
await client.send_message(message.channel, temp)
await client.send_message(message.channel, desc)
elif message.content.startswith('!steam'): # Steam info
steamapi.core.APIConnection(api_key=steamToken, validate_key=True)
me = steamapi.user.SteamUser(userurl="acanceroustwzlr")
steamCommand = message.content[7:]
if steamCommand == 'level':
await client.send_message(message.channel, me.level)
elif steamCommand == 'friends':
await client.send_message(message.channel, me.friends)
elif steamCommand == 'recently_played':
await client.send_message(message.channel, me.recently_played)
elif steamCommand == 'games':
await client.send_message(message.channel, me.games)
from pybaseball import statcast_batter
from pybaseball import playerid_lookup
from pybaseball import statcast_pitcher
hoskins_id = playerid_lookup('hoskins', 'rhys')
print(hoskins_id)
print("statcast stats from march 1st to april 1st")
hoskins_statcast = statcast_batter('2019-03-01', '2019-04-01', 656555)
print(hoskins_statcast)
"""
kersh = playerid_lookup('kershaw', 'clayton')
kershaw_stats = statcast_pitcher('2017-06-01', '2017-07-01', kersh)
print(kershaw_stats.head(5))
"""
def __init__(self, playerid, start="2019-03-01", end="2019-11-03"):
# Wrangle the DF
player = statcast_batter(start, end, int(playerid))
player = player[~player["events"].isna()] # Drop nas
player = player[player["game_type"] == "R"] # Regular Season games only
# Add other features
player = add_spray_angle(player)
player = add_park_factors(player, 2018)
player = add_sprint_speed(player, 2018)
# Save the DF
self.df = player
self.model_input = player[['launch_speed',
'launch_angle',
'adj_spray_angle',
'1b_park_factor',
'2b_park_factor',
'3b_park_factor',
'hr_park_factor',
'sprint_speed']]
# keep playerid for later
self.playerid = playerid
# Keep year if consistent
if start.split("-")[0] == end.split("-")[0]:
self.year = start.split("-")[0]
else:
self.year = None
# Set properties
vc = player["events"].value_counts()
# If an event hasn't happend, a KeyError will happen
if "walk" in vc:
self.bb = vc["walk"]
else:
self.bb = 0
if "single" in vc:
self.single = vc["single"]
else:
self.single = 0
if "double" in vc:
self.double = vc["double"]
else:
self.double = 0
if "triple" in vc:
self.triple = vc["triple"]
else:
self.triple = 0
if "home_run" in vc:
self.hr = vc["home_run"]
else:
self.hr = 0
if "sac_fly" in vc:
self.sf = vc["sac_fly"]
else:
self.sf = 0
if "hit_by_pitch" in vc:
self.hbp = vc["hit_by_pitch"]
else:
self.hbp = 0
# Still need ABs from FG, set later
self.fg_ab = None
self.fg_woba = None
from typing import Any, Union
import pybaseball
from pandas import DataFrame, Series
from pandas.io.parsers import TextFileReader
b = pybaseball.batting()
b2 = pybaseball.batting_stats_bref()
b3 = pybaseball.bwar_bat()
s = pybaseball.statcast_batter(start_dt='2020-7-31',
end_dt='2020-08-01',
player_id=596019)
import numpy as np
np.set_printoptions(threshold=np.inf)
r: Union[Union[TextFileReader, Series, DataFrame, None],
Any] = pybaseball.retrosheet.season_game_logs(2019)
r = np.array(r.columns)
l = pybaseball.lahman.batting()
import pandas as pd
path = '/Users/ryangerda/PycharmProjects/DFS_Baseball/Data/playing-2019.csv'
p = pd.read_csv(path)
p = np.array(p.columns)
path = '/Users/ryangerda/PycharmProjects/DFS_Baseball/Data/teams-2019.csv'
t = pd.read_csv(path)
t = np.array(t.columns)
def get_batting_player(
start_dt=None, end_dt=None, player_last='Vogelbach', player_first='Daniel',
fname_all=None, fname_bb=None, features=[
'events', 'description', 'batter', 'stand', 'launch_angle',
'launch_speed', 'hc_x', 'hc_y', 'pitcher', 'p_throws', 'pitch_type',
'release_speed', 'release_spin_rate'
]
):
"""
Pull player statcast batting data from baseballsavant using pybaseball
https://github.com/jldbc/pybaseball
https://baseballsavant.mlb.com/statcast_search
Arguments
start_dt: get data from start_dt forward
stop_dt: get data up to stop_dt
player_last: player's last name
player_first: player's first name
fname_all: export csv of all statcast at bat outcomes to this file
**must be .csv**
fname_bb: export csv of all outcomes with a batted ball to this file
**must be .csv**
Returns
(all_outcomes, batted_balls) tuple of dataframes
Saves to files 'fname_all' and 'fname_bb' if fname is not None
"""
# get player's mlbam_id (mlb advanced metrics id)
# note: for players the same first+last name, this will get the
# player who entered the league first
# need to fix -- for now pick players with unique names
# sorry Chris Davis :p
player_id = playerid_lookup(
player_last, player_first
)['key_mlbam'].values[0]
# get statcast data (this can take awhile)
print('Querying batting stats for {} {}'.format(player_first, player_last))
df = statcast_batter(start_dt, end_dt, player_id)
# discard null events
all_outcomes = df[df['events'].notnull()]
# get the specified features only
all_outcomes = all_outcomes[features]
if fname_all is not None:
# export to csv
all_outcomes.to_csv(fname_all, index=False)
print('Exported: {}'.format(fname_all))
# get batted balls only
batted_balls = filter_batted_balls(all_outcomes)
if fname_bb is not None:
# export data
batted_balls.to_csv(fname_bb, index=False)
print('Exported: {}'.format(fname_bb))
return(all_outcomes, batted_balls)
'Split-Finger': 8,
'Sinker': 9
}
'''
# For the hitting stats, I only care about non-bunted balls in play, so will filter statcast data based on that
ball_in_play = ['hit_into_play', 'hit_into_play_score', 'hit_into_play_no_out']
bb_types = ['ground_ball', 'fly_ball', 'line_drive', 'popup']
# Now, will fill each row w/ the respective statcast data
for idx, row in test_df.iterrows():
name = row.Name
id = int(row.mlb_id)
start = int(row.first_played)
end = int(row.last_played)
stats = pybaseball.statcast_batter(f'{start}-01-01', f'{end}-12-31', id)
# This is where I will filter out all events that do not result in a ball in play
stats = stats[(stats.description.isin(ball_in_play))]
groundBallRate = len(stats[stats.bb_type == bb_types[0]]) / len(stats)
flyBallRate = len(stats[stats.bb_type == bb_types[1]]) / len(stats)
lineDriveRate = len(stats[stats.bb_type == bb_types[2]]) / len(stats)
popUpRate = len(stats[stats.bb_type == bb_types[3]]) / len(stats)
print(groundBallRate, flyBallRate, lineDriveRate, popUpRate)
#print(stats.launch_speed) This returns NaNs
#print(stats.launch_angle) As does this
test_df.at[idx, 'bbType_flyBall'] = flyBallRate
test_df.at[idx, 'bbType_groundBall'] = groundBallRate
test_df.at[idx, 'bbType_lineDrive'] = lineDriveRate
test_df.at[idx, 'bbType_popUp'] = popUpRate