def hit_odds(self, batter, pitcher, bt, pt, xbo):
if type(batter) is list:
try:
batter_id = playerid_lookup(batter[1], batter[0])
if len(batter_id) > 1:
print(
"Choose the index corresponding to the desired player:"
)
print(batter_id)
desired_index = input("Index: ")
batter_id = batter_id.loc[int(desired_index), 'key_mlbam']
else:
batter_id = batter_id.loc[0, 'key_mlbam']
except:
print("Invalid batter name.")
return
else:
batter_id = batter
if type(pitcher) is list:
try:
pitcher_id = playerid_lookup(pitcher[1],
pitcher[0]).loc[0, 'key_mlbam']
except:
print("Invalid pitcher name.")
return
else:
pitcher_id = pitcher
if type(xbo) is list:
hit_options = {}
for i in xbo:
hitting = self.hit_odds_work(
batter_id, pitcher_id, pt, i,
self.mlb_games.query("Team == @bt").reset_index().loc[
0, 'moneyline'],
self.mlb_games.query("Team == @bt").reset_index().loc[
0, 'total'])
hit_options[i] = hitting
return hit_options
else:
hitting = self.hit_odds_work(
batter_id, pitcher_id, pt, xbo,
self.mlb_games.query("Team == @bt").reset_index().loc[
0, 'moneyline'],
self.mlb_games.query("Team == @bt").reset_index().loc[0,
'total'])
return hitting
def get_mlbam():
#from pybaseball import playerid_lookup
name_dict = {}
count = 0
for name in names:
if (count <= len(names)):
LastName = (name.split()[1])
LastName = LastName.lower()
FirstName = (name.split()[0])
FirstName = FirstName.lower()
#print(LastName)
#print(FirstName)
# J.A. Happ x
# Ronald Acuna Jr. => Ronald Acuna
# Henderson Alvarez III => Henderson Alvarez
temp_id = playerid_lookup(LastName,
FirstName) #(LastName,FirstName)
#print(len(temp_id))
if (len(temp_id) == 1):
name_dict[name] = int(temp_id['key_mlbam'])
else:
print(name, "Not added")
count += 1
#print(name_dict)
df = pd.DataFrame.from_dict(name_dict, orient='index', columns=['mlbam'])
df.reset_index(level=0, inplace=True)
df.rename(index=str, columns={"index": "name"}, inplace=True)
print(df)
df.to_csv(
r'/Users/blaisepage/Documents/CUBoulder/Sabermetrics/export_dataframe.csv'
)
def get_data(first_name, last_name, start_date, end_date):
try:
key = pb.playerid_lookup(
last_name,
first_name)["key_mlbam"].values[0] # get unique pitcher identifier
except:
pass
data = pb.statcast_pitcher(start_date, end_date,
key) # get dataset of pitches thrown by pitcher
data = data.sort_values(["pitch_number"
]) # sort pitches by order thrown, earliest first
data = data.dropna(subset=[
"pitch_type", "des", "description", "release_spin_rate"
]) # make sure dataset does not contain nulls
data["order"] = data.reset_index(
).index # create new column with pitch order
df = pd.DataFrame(data)
df = df.rename(
{
"des": "Play by Play",
"description": "Result of Pitch",
"order": "Pitch Number",
"pitch_name": "Pitch Type",
"release_speed": "Pitch Speed",
},
axis=1,
)
return df
def get_atbats(first, last):
# Lookup player
player_info = playerid_lookup(last, first)
player_id = player_info["key_mlbam"].iloc[0] # assume only one line
start_year = int(player_info["mlb_played_first"].iloc[0])
end_year = int(player_info["mlb_played_last"].iloc[0])
# ignore this year
if end_year == 2019:
end_year = 2018
# Get all the stats
start_date = "{0}-01-01".format(start_year)
end_date = "{0}-12-31".format(end_year)
print("Scraping from {0} to {1}".format(start_date, end_date))
d_all_stats = statcast_pitcher(start_date, end_date, player_id)
d_features = d_all_stats[features]
# Iterate over strikeout rows, build into AtBat Objects
strikeout_rows = d_all_stats.index[d_all_stats["events"] ==
"strikeout"].to_list()
at_bats, ab_arrays = [], []
for row in strikeout_rows:
this_ab = AtBat(d_features, row)
at_bats.append(this_ab)
ab_arrays.append(this_ab.np)
return at_bats, ab_arrays
def get_number(last, first):
playerTable = playerid_lookup(last, first)
playerTable = playerTable.loc[playerTable['mlb_played_last'].isin([2019])]
playerTable.index = range(len(playerTable['mlb_played_last']))
number = playerTable['key_mlbam']
number = number[0]
return number
def filter_batting_player(league_data='all_outcomes_2018.csv',
player_last='Vogelbach', player_first='Daniel',
fname=None):
"""
This function should be used *after* getting league-wide data
with get_league_batting_data(). If you already have league-wide data, this
is faster than calling get_batting_player() since it doesn't query statcast
data again
Arguments
league_data: any .csv file returned from get_league_batting_data
player_last: last name of player
player_first: first name of player
fname: name of .csv file to export
defaults to [player_last]_[player_first].csv
Returns
dataframe
Saves to file 'fname' 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
mlbam_id = playerid_lookup(
player_last, player_first
)['key_mlbam'].values[0]
league_df = pd.read_csv(league_data)
player_df = league_df[league_df['batter'] == mlbam_id]
player_df.reset_index(inplace=True, drop=True)
if fname is not None:
player_df.to_csv(fname, index=False)
return(player_df)
def get_player_batted_balls(playerFirst, playerLast, dateGT, dateLT):
results = []
#all batted balls for a single player
url = 'https://baseballsavant.mlb.com/statcast_search/csv?all=true&hfPT=&hfAB=single%7Cdouble%7Ctriple%7Chome%5C.%5C.run%7Cfield%5C.%5C.out%7Cdouble%5C.%5C.play%7Cfield%5C.%5C.error%7Cgrounded%5C.%5C.into%5C.%5C.double%5C.%5C.play%7Cfielders%5C.%5C.choice%7Cfielders%5C.%5C.choice%5C.%5C.out%7Cforce%5C.%5C.out%7Csac%5C.%5C.bunt%7Csac%5C.%5C.bunt%5C.%5C.double%5C.%5C.play%7Csac%5C.%5C.fly%7Csac%5C.%5C.fly%5C.%5C.double%5C.%5C.play%7Ctriple%5C.%5C.play%7C&hfBBT=&hfPR=&hfZ=&stadium=&hfBBL=&hfNewZones=&hfGT=R%7C&hfC=&hfSea=&hfSit=&player_type=batter&hfOuts=&opponent=&pitcher_throws=&batter_stands=&hfSA=&game_date_gt={}&game_date_lt={}&hfInfield=&team=&position=&hfOutfield=&hfRO=&home_road=&batters_lookup%5B%5D={}&hfFlag=&hfPull=&metric_1=&hfInn=&min_pitches=0&min_results=0&group_by=name-event&sort_col=pitches&player_event_sort=h_launch_speed&sort_order=desc&min_pas=0&type=details&'
#convert playername into Savant PlayerID for search
playerIDtable = pybaseball.playerid_lookup(playerLast, playerFirst)
player = playerIDtable.loc[0].key_mlbam
#convert year, month, and day into individual integers
monthGT = int(dateGT[5:7])
monthLT = int(dateLT[5:7])
yearGT = int(dateGT[0:4])
yearLT = int(dateLT[0:4])
dayGT = int(dateGT[8:10])
dayLT = int(dateLT[8:10])
#if spanning more than a month get needed days of first month, then months in between, then needed days of last month
if monthLT > monthGT:
dateGT = datetime.date(yearGT, monthGT, dayGT)
dateGT = dateGT.strftime("%Y-%m-%d")
dateLT = datetime.date(yearGT, monthGT + 1,
1) - datetime.timedelta(days=1)
dateLT = dateLT.strftime("%Y-%m-%d")
data = requests.get(url.format(dateGT, dateLT, player)).content
df = pd.read_csv(io.StringIO(data.decode('utf-8')))
results.append(df)
if ((monthLT - monthGT) > 1):
for month in range((monthGT + 1), monthLT):
dateGT = datetime.date(yearGT, month, 1)
dateGT = dateGT.strftime("%Y-%m-%d")
dateLT = datetime.date(yearGT, month + 1,
1) - datetime.timedelta(days=1)
dateLT = dateLT.strftime("%Y-%m-%d")
data = requests.get(url.format(dateGT, dateLT, player)).content
df = pd.read_csv(io.StringIO(data.decode('utf-8')))
results.append(df)
dateGT = datetime.date(yearGT, monthLT, 1)
dateGT = dateGT.strftime("%Y-%m-%d")
dateLT = datetime.date(yearGT, monthLT, dayLT)
dateLT = dateLT.strftime("%Y-%m-%d")
data = requests.get(url.format(dateGT, dateLT, player)).content
df = pd.read_csv(io.StringIO(data.decode('utf-8')))
results.append(df)
#if months equal just grab the days needed
if monthLT == monthGT:
dateGT = datetime.date(yearGT, monthGT, dayGT)
dateGT = dateGT.strftime("%Y-%m-%d")
dateLT = datetime.date(yearGT, monthLT, dayLT)
dateLT = dateLT.strftime("%Y-%m-%d")
data = requests.get(url.format(dateGT, dateLT, player)).content
df = pd.read_csv(io.StringIO(data.decode('utf-8')))
results.append(df)
return pd.concat(results)
def collect_statcast(sample_size, target, features, pitcher_names):
"""Scrapes the Statcast data for each pithcer based on specified criteria; see arguments.
Arguments:
sample_size {int} -- the number of pitches to collect for each pithcer
target {list} -- a list containing the categories desired in the resulting pitch
features {list} -- a list containing the desired features to keep for the resulting data.
pitcher_names {list} -- the list of pitcher names from the read_pitchers function.
Returns:
pandas dataframe -- a pandas dataframe where each row is a single pitch for a particular pitcher
and each column is a specified feature in the 'features' argument.
"""
#loop through all the names
print('Begin scraping \n')
final_data = pd.DataFrame(columns=features)
for i, pitcher in enumerate(pitcher_names):
if len(pitcher) == 2:
fname, lname = pitcher[0], pitcher[1]
elif len(pitcher) >= 3:
fname, lname = pitcher[0], " ".join(pitcher[1:])
else:
pass
print(
f'\n Pitcher Name: {fname} {lname}, #: {i+1}/{len(pitcher_names)} \n'
)
#grap the unique identifier of the pitcher
player = playerid_lookup(lname, fname)
#to avoid any possible errors, execute following try statement:
# grab the unique identifier value
# get all available data in time frame
# filter data to only have appropriate targets, defined above
# append particular pitcher to 'master' dataframe
#if any of these steps fail, particularly the grabbing of 'ID'
#pass on to next pitcher
try:
ID = player['key_mlbam'].iloc[player['key_mlbam'].argmax()]
df = statcast_pitcher('2018-03-29', '2018-09-30', player_id=ID)
df = df[df['description'].isin(target)].sample(sample_size,
random_state=2019)
final_data = final_data.append(df[features], ignore_index=True)
except ValueError:
pass
print('Finsihed Scraping')
return final_data
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 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 getplayer(first, last):
"""
function for getting a list of players to select from
"""
if first == '':
first = None
players = playerid_lookup(last, first)
players = players[players.mlb_played_first.notnull()]
# TODO: figure out how to deal with players with the same name
temp_dict = {}
for r in players.iterrows():
first = r[1]['name_first']
last = r[1]['name_last']
sid = r[1]['key_mlbam'] # statcast ID
full = f'{first} {last} - {sid}'.title()
temp_dict[full] = sid
return temp_dict
def get_mlbam_id(player_dict):
if not player_dict["is_mlb"]:
return None
player_name = clean_name(player_dict["Player Name"])
first_name, last_name = player_name.split(maxsplit=1)
if "." in first_name:
# lookup has "A.J." as "A. J." for some reason
first_name = first_name.replace(".", ". ").strip()
id_lookup = playerid_lookup(last_name, first_name)
if id_lookup.shape[0] > 1:
mlbam_id = id_lookup.loc[id_lookup.mlb_played_last == id_lookup.
mlb_played_last.max()].key_mlbam.values[0]
elif id_lookup.shape[0] == 1:
mlbam_id = id_lookup.key_mlbam.values[0]
else:
# how could this happen?
mlbam_id = None
return mlbam_id
def getPlayerIDs(players):
listOfIDs = []
for i in range (0, len(players)):
splitPlayer = players[i].split(' ')
first = splitPlayer[0]
last = splitPlayer[1]
ident = playerid_lookup(last,first)
identList = ident['key_bbref'].tolist()
counter = len(identList) - 1
if len(identList) > 0:
while str(identList[counter]) == 'nan' and counter > -1:
counter -= 1
finalPlayerID = identList[counter]
listOfIDs.append(finalPlayerID)
else:
listOfIDs.append("PLAYER NOT FOUND")
print('added player ' + str(i))
print(listOfIDs)
def get_fangraphs_id(player_dict):
"""Figure out a way to refactor this and get_mlbam_id()"""
if not player_dict["is_mlb"]:
return None
player_name = clean_name(player_dict["Player Name"])
first_name, last_name = player_name.split(maxsplit=1)
if "." in first_name:
# lookup has "A.J." as "A. J." for some reason
first_name = first_name.replace(".", ". ").strip()
id_lookup = playerid_lookup(last_name, first_name)
if id_lookup.shape[0] > 1:
fangraphs_id = id_lookup.loc[
id_lookup.mlb_played_last ==
id_lookup.mlb_played_last.max()].key_fangraphs.values[0]
elif id_lookup.shape[0] == 1:
fangraphs_id = id_lookup.key_fangraphs.values[0]
else:
# how could this happen?
fangraphs_id = None
return fangraphs_id
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
# https://pypi.org/project/baseball-scraper/
# https://pypi.org/project/vigorish/
# Useful source to compare packages:
# https://snyk.io/advisor/python
############## Statcast data ##############
data = statcast(start_dt='2021-04-01', end_dt='2021-04-02', team='SEA')
data.loc[data.game_date == '2021-04-01', :]
data.head()
############## Team Crosswalk #############
team_cross = teams()
team_cross = team_ids()
############# Player Crosswalk ############
player = playerid_lookup('Sheffield', 'Justus')
############## Date Range #################
dt_lst = pd.date_range(start='2021-04-01', end='2021-05-31', freq='D')
dt_range = []
for i in dt_lst:
dt_range.append(i.strftime('%Y-%m-%d'))
############### Pitcher Profile ##############
# Game by Game
# TODO remove data.GS filter if want to look at all pitchers ; for now just looking at starters
table_lst = []
for x in dt_range:
data = pitching_stats_range(start_dt=x, end_dt=x)
data = data.loc[data.GS == 1, :]
table_lst.append(data)
def get_data(first_name, last_name):
train_filename = 'Data/' + str(last_name) + "_" + str(
first_name) + "_train.csv"
test_filename = 'Data/' + str(last_name) + "_" + str(
first_name) + "_test.csv"
if os.path.isfile(train_filename) and os.path.isfile(
test_filename): #If we've already gotten the data, read it in
train_data = pd.read_csv(train_filename)
test_data = pd.read_csv(test_filename)
else:
#If we haven't, get it off the web and store it for future runs
#training is done on data from 2015 through 2017
train_data = statcast_pitcher(
start_dt='2015-01-01',
end_dt='2017-12-31',
player_id=int(playerid_lookup('sale', 'chris')['key_mlbam']))
train_data.to_csv(train_filename)
#testing is done on data from the beginning of 2018 to present
test_data = statcast_pitcher(
start_dt='2018-01-01',
end_dt='2019-12-31',
player_id=int(playerid_lookup('sale', 'chris')['key_mlbam']))
test_data.to_csv(test_filename)
#Get all of the pitch types that a pitcher throws, then encode them using our system
train_data = train_data[train_data['pitch_type'].isin(pitcher_pitches)]
train_data = train_data.dropna(subset=['pitch_type'])
train_data['pitch_code'] = train_data.apply(
lambda row: get_pitch_code(row, pitcher_pitches), axis=1)
#Do the same as above but for the testing data in case they added a new pitch
test_data = test_data[test_data['pitch_type'].isin(pitcher_pitches)]
test_data = test_data.dropna(subset=['pitch_type'])
#Encode all the pitch type/location info to a unique int
test_data['pitch_code'] = test_data.apply(
lambda row: get_pitch_code(row, pitcher_pitches), axis=1)
train_data = get_prev_pitch(train_data)
test_data = get_prev_pitch(test_data)
#Fills the Na values, turns the batter ID for the player on base into a bool value
train_data['on_3b'] = train_data['on_3b'].fillna(
value=0).astype(bool).astype(int)
train_data['on_2b'] = train_data['on_2b'].fillna(
value=0).astype(bool).astype(int)
train_data['on_1b'] = train_data['on_1b'].fillna(
value=0).astype(bool).astype(int)
test_data['on_3b'] = test_data['on_3b'].fillna(
value=0).astype(bool).astype(int)
test_data['on_2b'] = test_data['on_2b'].fillna(
value=0).astype(bool).astype(int)
test_data['on_1b'] = test_data['on_1b'].fillna(
value=0).astype(bool).astype(int)
#Get the data we need and drop any null values (which is why it double selects)
train_data_input = train_data[[
'prev_pitch_3', 'prev_pitch_2', 'prev_pitch_1', 'balls', 'strikes',
'stand', 'on_3b', 'on_2b', 'on_1b', 'outs_when_up', 'pitch_number',
'pitch_code'
]].dropna()
train_data_result = train_data_input[['pitch_code']]
train_data_input = train_data_input[[
'prev_pitch_3', 'prev_pitch_2', 'prev_pitch_1', 'balls', 'strikes',
'stand', 'on_3b', 'on_2b', 'on_1b', 'outs_when_up', 'pitch_number'
]]
test_data = test_data[[
'prev_pitch_3', 'prev_pitch_2', 'prev_pitch_1', 'balls', 'strikes',
'stand', 'on_3b', 'on_2b', 'on_1b', 'outs_when_up', 'pitch_number',
'pitch_code'
]].dropna()
return train_data_input, train_data_result, test_data
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)
df = pd.read_csv('gather_ids.csv')
df_noIDs = df[df['mlb_id'].isnull()]
df_noIDs = df_noIDs[['First','Last']]
df_noIDs.to_csv('df_noIDs.csv')
'''
# Loading the hitter dataframe; will ammend each individual here and then re-save and overwrite the loaded file
df_hitters = pd.read_csv('./data/gather_ids.csv')
'''
I have loaded each individual player missing IDs below,
commenting each of their names out and I will go through them one-by-one and update their IDs...
'''
#16,J.P.,Arencibia
jp_arencibia = pybaseball.playerid_lookup(last='arencibia')
df_hitters['mlb_id'] = np.where( ((df_hitters.First == 'J.P.') & (df_hitters.Last == 'Arencibia')), int(jp_arencibia['key_mlbam'].item()), df_hitters['mlb_id'] )
df_hitters['retro_id'] = np.where( ((df_hitters.First == 'J.P.') & (df_hitters.Last == 'Arencibia')), str(jp_arencibia['key_retro'].item()), df_hitters['retro_id'] )
df_hitters['bbref_id'] = np.where( ((df_hitters.First == 'J.P.') & (df_hitters.Last == 'Arencibia')), str(jp_arencibia['key_bbref'].item()), df_hitters['bbref_id'] )
df_hitters['fangraphs_id'] = np.where( ((df_hitters.First == 'J.P.') & (df_hitters.Last == 'Arencibia')), int(jp_arencibia['key_fangraphs'].item()), df_hitters['fangraphs_id'] )
df_hitters['first_played'] = np.where( ((df_hitters.First == 'J.P.') & (df_hitters.Last == 'Arencibia')), int(jp_arencibia['mlb_played_first'].item()), df_hitters['first_played'] )
df_hitters['last_played'] = np.where( ((df_hitters.First == 'J.P.') & (df_hitters.Last == 'Arencibia')), int(jp_arencibia['mlb_played_last'].item()), df_hitters['last_played'] )
print(df_hitters[df_hitters['Last'] == 'Arencibia'])
#28,Jose,Bautista
jose_bautista = pybaseball.playerid_lookup(last='bautista', first='jose').iloc[1]
df_hitters['mlb_id'] = np.where( ((df_hitters.First == 'Jose') & (df_hitters.Last == 'Bautista')), int(jose_bautista['key_mlbam'].item()), df_hitters['mlb_id'] )
df_hitters['retro_id'] = np.where( ((df_hitters.First == 'Jose') & (df_hitters.Last == 'Bautista')), str(jose_bautista['key_retro']), df_hitters['retro_id'] )
df_hitters['bbref_id'] = np.where( ((df_hitters.First == 'Jose') & (df_hitters.Last == 'Bautista')), str(jose_bautista['key_bbref']), df_hitters['bbref_id'] )
df_hitters['fangraphs_id'] = np.where( ((df_hitters.First == 'Jose') & (df_hitters.Last == 'Bautista')), int(jose_bautista['key_fangraphs'].item()), df_hitters['fangraphs_id'] )
df_hitters['first_played'] = np.where( ((df_hitters.First == 'Jose') & (df_hitters.Last == 'Bautista')), int(jose_bautista['mlb_played_first'].item()), df_hitters['first_played'] )
df_hitters['last_played'] = np.where( ((df_hitters.First == 'Jose') & (df_hitters.Last == 'Bautista')), int(jose_bautista['mlb_played_last'].item()), df_hitters['last_played'] )
print("Enter player's first name: ")
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)
def main():
league_id = "953" # put this in env
base_url = "https://ottoneu.fangraphs.com"
current_year = 2020
auction_url = f"{base_url}/{league_id}/transactions"
# for testing
auction_url = "https://ottoneu.fangraphs.com/953/transactions?filters%5B%5D=cut&filters%5B%5D=increase"
resp = requests.get(auction_url)
soup = BeautifulSoup(resp.content, "html.parser")
table = soup.find("table")
thead = [th.get_text() for th in table.find("thead").find_all("th")]
auction_players = list()
for tr in tqdm(table.find("tbody").find_all("tr")):
player_data = [td.get_text().strip() for td in tr.find_all("td")]
player_page_url = [
a["href"] for a in tr.find_all("a") if "playercard" in a["href"]
].pop()
player_dict = dict(zip(thead, player_data))
if player_dict["Transaction Type"] != "add":
continue
player_dict["ottoneu_id"] = player_page_url.rsplit("=")[1]
player_salary_dict = get_ottoneu_player_page(player_dict["ottoneu_id"],
league_id)
player_dict.update(player_salary_dict)
player_name = clean_name(player_dict["Player Name"])
first_name, last_name = player_name.split(maxsplit=1)
if player_dict["is_mlb"]:
if "." in first_name:
# lookup has "A.J." as "A. J." for some reason
first_name = first_name.replace(".", ". ").strip()
id_lookup = playerid_lookup(last_name, first_name)
if id_lookup.shape[0] > 1:
player_dict["mlbam_id"] = id_lookup.loc[
id_lookup.mlb_played_last ==
id_lookup.mlb_played_last.max()].key_mlbam.values[0]
else:
player_dict["mlbam_id"] = id_lookup.key_mlbam.values[0]
is_hitter, is_pitcher = get_position_group(player_dict["positions"])
player_dict["is_hitter"] = is_hitter
player_dict["is_pitcher"] = is_pitcher
auction_players.append(player_dict)
hitters = [player for player in auction_players if player["is_hitter"]]
pitchers = [player for player in auction_players if player["is_pitcher"]]
if hitters:
# setting minBBE = 0 to avoid not getting someone
# get rid of this indentation and just pull exit velo #s regardless?
exit_velo_data = statcast_batter_exitvelo_barrels(current_year,
minBBE=0)
for player in hitters:
if not player["is_mlb"]:
# avoid index error for minor leaguers
continue
player_exit_velo = (exit_velo_data.loc[exit_velo_data.player_id ==
player["mlbam_id"]].to_dict(
"records").pop())
# add anything else?
player["avg_exit_velo"] = player_exit_velo["avg_hit_speed"]
player["max_exit_velo"] = player_exit_velo["max_hit_speed"]
player["barrel_pa_rate"] = player_exit_velo["brl_pa"]
player["barrel_bbe_rate"] = player_exit_velo["brl_percent"]
if pitchers:
# currently pybaseball only has individual pitcher data
pass
print(auction_players[0])
def get_data(year = 2018, minimum_starts = 5):
if not os.path.exists(str(year)):
os.mkdir(str(year))
if not os.path.exists(os.path.join(str(year), "Players_Stats_"+str(year)+".csv")):
player_stats = pitching_stats(year, year)
player_stats = player_stats[player_stats['GS']>minimum_starts]
player_stats.to_csv(os.path.join(str(year), "Players_Stats_"+str(year)+".csv"))
else:
player_stats = pd.read_csv(os.path.join(str(year), "Players_Stats_"+str(year)+".csv"))
out = None
for name in player_stats['Name']:
if not os.path.exists(os.path.join(str(year),'player')):
os.mkdir(os.path.join(str(year),'player'))
splitname = name.split(' ')
# Database is really good and has some mistakes, so when we go to the lookup table for MLB Player IDs sometimes
# it doesn't match up. This corrects the issues that I've found. Obviously this won't work for every year
# out of the box because of this.
splitname[0] = splitname[0].replace('.', '. ', 1)
# print(splitname[0])
if splitname[0] == 'J.A.':
splitname[0] = 'J. A.'
if name == 'Zack Wheeler':
splitname[0] = 'Zach'
if name == 'Matthew Boyd':
splitname[0] = 'Matt'
if name == 'C.J. Wilson':
splitname[0] = 'c. j.'
if name == 'R.A. Dickey':
splitname[0] = 'R. A.'
if name == 'Jon Niese':
splitname[0] = 'Jonathon'
if name == 'A.J. Burnett':
splitname[0] = 'A. J.'
if name == 'Jorge De La Rosa':
splitname[0] = 'Jorge'
splitname[1] = 'De La Rosa'
if name == 'Rubby de la Rosa':
splitname[0] = 'Rubby'
splitname[1] = 'de la Rosa'
if name == 'Cole DeVries':
splitname[1] = 'De Vries'
if name == 'Samuel Deduno':
splitname[0] = 'Sam'
if name == 'JC Ramirez':
splitname[0] = 'J. C.'
if name == 'Nathan Karns':
splitname[0] = 'Nate'
if name == 'Daniel Ponce de Leon':
splitname[1] = 'Ponce de Leon'
if name == 'Chi Chi Gonzalez':
splitname[0] = 'Chi Chi'
splitname[1] = 'Gonzalez'
if name == 'Josh A. Smith':
splitname[0] = 'Josh'
splitname[1] = 'Smith'
if name == 'Joel De La Cruz':
splitname[1] = 'De La Cruz'
if not os.path.exists(os.path.join(str(year), 'player', name+'-'+str(year)+'.csv')):
player_id = playerid_lookup(splitname[1], splitname[0])
print(year)
player_id = player_id[player_id['mlb_played_first'] <= year]
player_id = player_id[player_id['mlb_played_last'] >= year]
print(player_id)
print(len(player_id))
if len(player_id) != 1:
print(player_id)
print(name)
print("Concerning")
player = statcast_pitcher(str(year)+'-1-01', str(year)+'-12-31', player_id['key_mlbam'].iloc(0)[0])
player.to_csv(os.path.join(str(year), 'player', name+'-'+str(year)+'.csv'))
else:
player = pd.read_csv(os.path.join(str(year), 'player', name+'-'+str(year)+'.csv'))
# ['SL' 'FF' 'CU' 'FT' 'CH' nan 'FC' 'KC' 'SI' 'PO' 'FS' 'EP' 'SC']
player_row = pd.DataFrame({'Name':[name]})
pitch_types = ['SL','FF','CU','FT','CH','FC','KC','SI','PO','FS','EP','SC','KN']
soi = ['release_speed','release_pos_x','release_pos_z','pfx_x','pfx_z','vx0','vy0','vz0','ax','ay','az','effective_speed','release_spin_rate']
for pitch in pitch_types:
pitches = player[player['pitch_type'] == pitch]
pitches = pitches[soi]
for stat in soi:
mean = np.mean(pitches[stat])
if math.isnan(mean):
mean = 0
std = np.std(pitches[stat])+0
if math.isnan(std):
std = 0
min = np.min(pitches[stat])+0
if math.isnan(min):
min = 0
max = np.max(pitches[stat])+0
if math.isnan(max):
max = 0
player_row[pitch+"_"+stat + '_std'] = std
player_row[pitch+"_"+stat + '_mean'] = mean
player_row[pitch + "_" + stat + '_min'] = min
player_row[pitch + "_" + stat + '_max'] = max
if out is None:
out = player_row
else:
out = pd.concat([out,player_row])
out
out.to_csv(str(year)+".csv")
'''
Example from pybaseball github on gathering ids:
pid = pybaseball.playerid_lookup('kershaw', 'clayton')
print(pid)
print(pid.key_bbref.item())
'''
# Iterate over dataframe to gather first & last names and then get their ids
for idx, row in hitters.iterrows():
first = str(row['First'])
last = str(row['Last'])
# How to set values while iterating: hitters.at[idx, '']
pid = pybaseball.playerid_lookup(last, first)
if len(pid) == 1:
hitters.at[idx, 'mlb_id'] = int(pid.key_mlbam.item())
hitters.at[idx, 'retro_id'] = str(pid.key_retro.item())
hitters.at[idx, 'bbref_id'] = str(pid.key_bbref.item())
hitters.at[idx, 'fangraphs_id'] = int(pid.key_fangraphs.item())
hitters.at[idx, 'first_played'] = int(pid.mlb_played_first.item())
hitters.at[idx, 'last_played'] = int(pid.mlb_played_last.item())
else:
continue
# Save the updated dataframe to a new csv file
hitters.to_csv('./data/gather_ids.csv')
print(hitters.head())
from pybaseball import statcast
import pandas as pd
import numpy as np
from pybaseball import statcast_pitcher
from pybaseball import playerid_lookup
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from imblearn.over_sampling import SMOTE
from keras.utils import to_categorical
from tensorflow import feature_column
from tensorflow.keras import layers
import tensorflow as tf
pid = playerid_lookup('berrios', 'jose')["key_mlbam"][0]
print(pid)
# get all available data
data = statcast_pitcher('2017-03-01', '2019-10-10', player_id=pid)
data = data[[
"pitch_type", "bat_score", "fld_score", "on_3b", "on_2b", "on_1b",
"outs_when_up", "inning", "inning_topbot", "pitch_number", "p_throws",
"balls", "strikes", "stand", "batter", "release_speed", "description"
]]
data = data[data.pitch_type != 'EP']
data = data[data.pitch_type != 'PO']
data[["on_3b", "on_2b", "on_1b"]] = data[["on_3b", "on_2b",
"on_1b"]].replace(np.nan, 0)
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 main(input_files):
# get the player that we'll be excluding from the neural network
first = input('First Name: ')
last = input('Last Name: ')
possibles = (playerid_lookup(last, first))
print(possibles)
index = int(input('Which player do you want?'))
target_id = possibles['key_mlbam'][
index] # sometimes need to change index depending on player name
inputs = []
training = []
testing = []
years = {'2015': {}, '2016': {}, '2017': {}, '2018': {}}
diamond = [
"fielder_1", "fielder_2", "fielder_3", "fielder_4", "fielder_5",
"fielder_6", "fielder_7", "fielder_8", "fielder_9"
]
team_dict = {
"ARI": 0,
"ATL": 1,
"BAL": 2,
"BOS": 3,
"CHC": 4,
"CWS": 5,
"CIN": 6,
"CLE": 7,
"COL": 8,
"DET": 9,
"MIA": 10,
"HOU": 11,
"KC": 12,
"LAA": 13,
"LAD": 14,
"MIL": 15,
"MIN": 16,
"NYM": 17,
"NYY": 18,
"OAK": 19,
"PHI": 20,
"PIT": 21,
"SD": 22,
"SF": 23,
"SEA": 24,
"STL": 25,
"TB": 26,
"TEX": 27,
"TOR": 28,
"WSH": 29
}
print("begin")
for input_file in input_files:
with open(input_file) as file_r:
reader = csv.DictReader(file_r)
missing = 0
for row in reader:
# sets the on_base variables to binary
on_1 = 0 if row['on_1b'] == "" else 1
on_2 = 0 if row['on_2b'] == "" else 1
on_3 = 0 if row['on_3b'] == "" else 1
# handles missing values
if row['hc_x'] == "" or row['hc_y'] == "" or row[
'launch_angle'] == "" or row['launch_speed'] == "" or row[
'estimated_ba_using_speedangle'] == "" or row[
'outs_when_up'] == "" or row[
'total_bases'] == "" or row[
'hit_location'] == "": # add or row['home_team'] == ""
missing += 1
else:
# creates input to be fed into the NN
new_input = [
float(row['hc_x']),
float(row['hc_y']),
float(row['launch_angle']),
float(row['launch_speed']),
float(row['estimated_ba_using_speedangle']),
int(float(row['outs_when_up'])), on_1, on_2, on_3,
int(float(row['total_bases'])) + 6
] # row['home_team'], # team_dict[row['home_team']],
# inputs.append(new_input)
if int(float(row['total_bases'])) > 6:
print("Above 6", int(float(row['total_bases'])))
# keeps track of the players associated with each event
# print(row['hit_location'])
location = int(float(row['hit_location'])) - 1
# for some reason, we don't have pitcher and catcher id's in here???
if location != 0 and location != 1:
player = row[diamond[location]]
if player != "":
# Add to training and testing set
if float(player) == target_id:
testing.append(new_input)
if int(float(row["hit_location"])
) not in target_position:
target_position.append(
int(float(row["hit_location"])))
# print("Added to testing")
else:
training.append(new_input)
current_dict = years[input_file[-8:-4]]
if (player, location + 1) in current_dict.keys():
current_dict[(player,
location + 1)].append(new_input)
else:
current_dict[(player,
location + 1)] = [new_input]
file_r.close()
# print(years['2015'].keys())
print(input_file, "missing data:", missing)
print("closed file")
print("completed split")
train_x = []
train_y = []
test_x = []
test_y = []
# handled by just adding 6 when setting inputs . . .
for row in training:
train_x.append(row[:-1])
train_y.append(row[-1]) # shifted by 6 bases, CHANGE THIS!!!
for row in testing:
test_x.append(row[:-1])
test_y.append(row[-1]) # shifted by 6 bases, CHANGE THIS!!!
print("completed x/y var separation")
train_data = numpy.asarray(train_x)
train_labels = numpy.asarray(train_y)
eval_data = numpy.asarray(test_x)
eval_labels = numpy.asarray(test_y)
print("---------------CREATING CLASSIFIER----------------")
# create estimator
model = tf.estimator.Estimator(model_fn=neural_net,
model_dir="checkpoints/")
print("---------------TRAINING CLASSIFIER----------------")
# train the classifier
model = train(train_data, train_labels, model)
print("---------------EVALUATING CLASSIFIER----------------")
# evaluate effectiveness
results, pred_gen = test(eval_data, eval_labels, model)
print(results)
#print(test_y)
# print(pred)
# pred_gen = list(pred_gen)
# predict = []
# for row in pred_gen:
# predict.append(row["classes"])
#print(pred)
# matrix = tf.math.confusion_matrix(test_y, predict)
# print(matrix)
# with tf.Session() as sess:
# confusion_matrix = tf.confusion_matrix(labels=test_y, predictions=predict)
# confusion_matrix_to_Print = sess.run(confusion_matrix)
# print(confusion_matrix_to_Print)
# start evaluating players
yearly_results = {}
for year, players in years.items():
print("Processing", year)
individual_results = {}
for key, value in players.items():
if int(key[1]) not in target_position:
continue
# key is (player id, location_played)
# value is all of the plays identified with them
curr_x = []
curr_y = []
for row in value:
curr_x.append(row[:-1])
curr_y.append(row[-1])
individual_predictions = list(
predict(numpy.asarray(curr_x), numpy.asarray(curr_y), model))
actual_pred = []
for row in individual_predictions:
actual_pred.append(row['classes'] - 6)
tally = 0
for i in range(len(curr_y)):
# overlook drastically missed predictions
# if actual_pred[i] < -1:
# continue
tally += actual_pred[i] - (curr_y[i] - 6)
# print(tally)
individual_results[key] = {
"total_bases": tally,
"opportunities": len(curr_y)
}
yearly_results[year] = individual_results
return (last, yearly_results)
playerDatapath = '../../playerStats/data_raw/'
for row in range(3980, df.shape[0]):
#df = pd.read_csv('./player_lookup/players.csv')
ID = df['RetroID'][row]
relevant = df[df['RetroID'] == ID]
#print(relevant.shape)
LastName = relevant['LastName'].values[0]
FirstName = relevant['FirstName'].values[0]
ndf.iloc[row, 1] = LastName
ndf.iloc[row, 2] = FirstName
playerInfo = pb.playerid_lookup(last=LastName,
first=FirstName) #['key_mlbam']
playerInfo = playerInfo[playerInfo['key_retro'] == ID]
playerInfo = playerInfo['key_mlbam']
df.iloc[row, 3] = playerInfo.values
print(row)
if row % 100 == 0:
print('row ' + str(row) + ' of ' + str(ndf.shape[0]))
#ndf.to_csv('player_lookup/players.csv', index = False)
ndf.to_csv('player_lookup/players.csv', index=False)
for row in range(0, playerdf.shape[0]):
try:
playerdf['MLBAM'][row] = int(playerdf['MLBAM'][row].replace(
']', '').replace('[', ''))
# Made by Noah Mitchem for MLB Pitchers
# Vertical pitch breaks seem off, don't know what other data can be used
import plotly.graph_objs as go
from plotly import tools
from plotly.offline import plot
import numpy as np
from matplotlib import cm
from pybaseball import playerid_lookup
from pybaseball import statcast_pitcher
file = statcast_pitcher("2019-03-25", "2019-10-01",
playerid_lookup("scherzer", "max")["key_mlbam"][0])
def colorcode(speed):
speed1 = int((speed - 50) * 4.3)
co = np.array(cm.magma(speed1)) * 255
return "rgb(" + str(int(co[0])) + "," + str(int(co[1])) + "," + str(
int(co[2])) + ")"
data = []
data1 = []
pitchTrack = 0
breaks = 0
x = {}
extremes = []
differentPitches = file["pitch_type"].unique().size
totalPitches = file.index.size
color = [
"rgb(102, 204, 0)", "rgb(0, 214, 214)", "rgb(204, 0, 0)",
"rgb(255, 153, 0)", "rgb(153, 0, 255)"
user="******",
database="baseball")
#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
from pybaseball import statcast
from pybaseball import playerid_lookup
import pandas as pd
# First we have to find all of the player_ids for the Red Sox batters to filter to just their at-bats
redsox_batters = [('christian', 'vazquez'), ('christian', 'arroyo'),
('xander', 'bogaerts'), ('rafael', 'devers'),
('alex', 'verdugo'), ('enrique', 'hernandez'),
('hunter', 'renfroe'), ('kyle', 'schwarber'),
('kevin', 'plawecki')]
redsox_batters_dict = {
"jd+martinez": 502110.0
} # Had to look up jd martinez manually because I could not figure out what search parameter to use for his first name
for batter in redsox_batters:
id = playerid_lookup(batter[1], batter[0])
redsox_batters_dict[f"{batter[0]}+{batter[1]}"] = float(id['key_mlbam'])
pd.DataFrame.from_dict(data=redsox_batters_dict,
orient='index').to_csv('redsox_batters.csv',
header=False)
# Now, collect all statcast data from the ALCS dates (15OCT21 thru 22OCT21) and filter based on player_ids found above
data = statcast(start_dt="2021-10-15", end_dt="2021-10-22")
data = data.loc[(data['batter'].isin(redsox_batters_dict.values()))]
data.to_csv('unfilteredAtBats.csv')
