def logistic_GAM(x_tr, y_tr, x_tst, y_tst):
classifier = LogisticGAM()
classifier.fit(x_tr, y_tr)
tr_pred = classifier.predict(x_tr)
y_pred = classifier.predict(x_tst)
confusion_matrix = metrics.confusion_matrix(y_tst, y_pred)
print(confusion_matrix)
print('Accuracy of logistic regression classifier on test set: {:.2f}' \
.format(metrics.accuracy_score(y_pred, y_tst)))
print('Accuracy of logistic regression classifier on train set: {:.2f}' \
.format(metrics.accuracy_score(tr_pred, y_tr)))
'''
class AdaptiveLogisticGAM(BaseEstimator, RegressorMixin):
def __init__(self, param_grid=None, gam_params=None):
# create GAM
if gam_params is None:
gam_params = {}
self.model = LogisticGAM(**gam_params)
# set grid search parameters
if param_grid is None:
param_grid = GAM_GRID_BASE
self.param_grid = param_grid
def fit(self, X, y):
if isinstance(X, pd.DataFrame):
X = X.values
# fit using grid-search
self.model.gridsearch(X, y, progress=False, **self.param_grid)
def predict(self, X):
if isinstance(X, pd.DataFrame):
X = X.values
return self.model.predict(X)
def predict_proba(self, X):
if isinstance(X, pd.DataFrame):
X = X.values
return self.model.predict_proba(X)
def simulation(No_T,n,p,box_plot=True):
err=[]
for i in range (No_T):
#generate the test data
X_train,Y_train=generate_data(n,p)
X_test,Y_test= generate_data(n,p)
logit_gam = LogisticGAM()
logit_gam.gridsearch(X_train,Y_train)
#calculate test error
test_err=sum(logit_gam.predict(X_test)!=Y_test)/n
err.append(test_err)
if box_plot:
plt.figure(num=None,figsize=(8,6),dpi=80)
plt.boxplot(err)
plt.text(1.1,0.15,"Mean:{:.2f}".format(np.mean(err)))
plt.text(1.1,0.14,"Var:{:.3f}".format(np.var(err)))
plt.title("logisticGAM")
plt.ylabel("Test Error")
plt.show()
n_splines = [5, 10, 15, 20, 25]
lams = lams * 6 # shift values to -3, 3
lams = lams - 3
lams = np.exp(lams)
cons = [
'convex', 'concave', 'monotonic_inc', 'monotonic_dec', 'circular', 'none'
]
random = LogisticGAM(aa).gridsearch(trainX,
trainy,
weights=w,
lam=lams,
n_splines=n_splines)
random = random.gridsearch(trainX, trainy, constraints=cons)
print(random.lam)
print(random.n_splines)
print(random.constraints)
print(random.accuracy(testX, testy))
from sklearn.metrics import confusion_matrix
preds = random.predict(testX)
print(confusion_matrix(testy, preds))
for i, term in enumerate(random.terms):
if term.isintercept:
continue
XX = random.generate_X_grid(term=i)
pdep, confi = random.partial_dependence(term=i, X=XX, width=0.95)
plt.figure()
plt.plot(XX[:, term.feature], pdep)
plt.plot(XX[:, term.feature], confi, c='r', ls='--')
plt.title(names1[i])
plt.show()
gam_pred_prob = gam_model.predict_proba(X_test)
gam_preds, complete_gam_dat = top_15_predictions(entire_test_data, gam_pred_prob )
gam_performance = all_nba_test_report(complete_gam_dat)
players_missed(complete_gam_dat)
gam_predict_probs_2020 = gam_model.predict_proba(features_2020)
gam_predict_binary_2020 = gam_model.predict(features_2020)
gam_predictions_2020 = predict_2020(positions=position_encoder.inverse_transform(features_2020['All_NBA_Pos']),
player_names=current_dat['Player'],
binary_prediction= gam_predict_binary_2020,
probability_predictions= gam_predict_probs_2020)
gam_predictions_2020.to_csv("gam_predictions.csv")
##### ----- ##### ----- ##### ----- ##### -----# #### ----- ##### ----- ##### ----- ##### ----- #####
# Model 1.4 - KNN
# --> Standardize all continuous features
# NOTE: We standardize the train set
# To standardize the test set, we use the mean and sd obtained from the train set (can't have leakage of info onto the test set)
# Generalizing a GAM
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.metrics import log_loss
# We can split the data just like we usually would:
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
random_state=1)
gam4 = LogisticGAM().gridsearch(X_train, y_train)
predictions = gam4.predict(X_test)
print("Accuracy: {} ".format(accuracy_score(y_test, predictions)))
probas = gam4.predict_proba(X_test)
print("Log Loss: {} ".format(log_loss(y_test, probas)))
# Accuracy: 0.925531914893617
# Log Loss: 0.15704862623168236
lambda_ = np.logspace(-3, 3, 3)
n_splines = [2, 5, 10, 20, 50]
constraints = [None, 'monotonic_inc', 'monotonic_dec']
#[‘convex’, ‘concave’, ‘monotonic_inc’, ‘monotonic_dec’,’circular’, ‘none’]
gam5 = LogisticGAM().gridsearch(
X_train,
class EpidemicModels:
# Sequential 6 layer neural network
def returnSequential6(self):
model = Sequential()
model.add(Dense(50, input_dim=20, activation='relu'))
model.add(Dense(40, activation='relu'))
model.add(Dense(30, activation='relu'))
model.add(Dense(20, activation='relu'))
model.add(Dense(10, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
def returnSequential9(self):
model = Sequential()
model.add(Dense(80, input_dim=20, activation='relu'))
model.add(Dense(70, activation='relu'))
model.add(Dense(60, activation='relu'))
model.add(Dense(50, activation='relu'))
model.add(Dense(40, activation='relu'))
model.add(Dense(30, activation='relu'))
model.add(Dense(20, activation='relu'))
model.add(Dense(10, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
def RNN(self):
model = Sequential()
model.add(SimpleRNN(2, input_dim=20))
model.add(Dense(1, activation='linear'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
def multi_RNN(self):
model = Sequential()
model.add(SimpleRNN(2, input_dim=20))
model.add(Dense(40, activation='relu'))
model.add(Dense(20, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
def baseline(self):
# Create model
model = Sequential()
model.add(Dense(20, input_dim=20, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
def lstm(self):
model = Sequential()
model.add(LSTM(10, input_dim=20))
model.add(Dense(1, activation='linear'))
model.compile(loss='mean_absolute_error', optimizer='adam')
return model
def multi_lstm(self):
model = Sequential()
model.add(LSTM(4, input_dim=20, return_sequences=True))
model.add(LSTM(4, input_dim=20))
model.add(Dense(1, activation='linear'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
# Sequential 4 layer neural network
def returnSequential2(self):
model = Sequential()
model.add(Dense(14, activation='relu', input_dim=20))
model.add(Dense(units=7, activation='relu'))
model.add(Dense(units=1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
def __init__(self, m=1):
if m == 0:
self.model = self.baseline()
self.type = 0
elif m == 1:
self.model = self.returnSequential2()
self.type = 2
elif m == 2:
self.model = self.returnSequential6()
self.type = 2
elif m == 3:
self.model = self.RNN()
self.type = 1
elif m == 4:
self.model = self.multi_RNN()
self.type = 1
elif m == 5:
self.model = self.lstm()
self.type = 1
elif m == 6:
self.model = self.multi_lstm()
self.type = 1
elif m == 7:
self.model = LogisticGAM()
self.type = 3
elif m == 8:
self.model = self.returnSequential9()
self.type = 2
def returnModel(self):
return self.model
def train(self, X, y, bs=10, epochs=100):
if self.type == 1:
X = np.reshape(X, (X.shape[0], 1, X.shape[1]))
if self.type == 3:
self.model.gridsearch(X, y)
else:
self.model.fit(X, y, batch_size=bs, epochs=epochs, shuffle=True)
def prediction(self, X):
if self.type == 1:
X = np.reshape(X, (X.shape[0], 1, X.shape[1]))
return self.model.predict(X)
def cross_eval(self, X, y, bs=10, ep=100, k=5):
scores = []
if self.type == 0:
kf = KFold(n_splits=k, shuffle=True, random_state=0)
for train_index, test_index in kf.split(X):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
self.model.fit(X_train, y_train, batch_size=bs, epochs=ep, verbose=0)
a, score = self.model.evaluate(X_test, y_test, verbose=0)
scores.append(score)
return sum(scores) / len(scores)
elif self.type == 1:
kf = KFold(n_splits=k, shuffle=False, random_state=0)
scores = []
for train_index, test_index in kf.split(X):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
X_train = np.reshape(X_train, (X_train.shape[0], 1, X_train.shape[1]))
X_test = np.reshape(X_test, (X_test.shape[0], 1, X_test.shape[1]))
self.model.fit(X_train, y_train, batch_size=bs, epochs=ep, verbose=0)
score = self.model.evaluate(X_test, y_test, verbose=0)
scores.append(score)
return sum(scores) / len(scores)
elif self.type == 2:
kf = KFold(n_splits=k, shuffle=True, random_state=0)
for train_index, test_index in kf.split(X):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
self.model.fit(X_train, y_train, batch_size=bs, epochs=ep, verbose=0)
a, score = self.model.evaluate(X_test, y_test, verbose=0)
print(score)
scores.append(score)
return sum(scores) / len(scores)
elif self.type == 3:
kf = KFold(n_splits=k, shuffle=False, random_state=0)
for train_index, test_index in kf.split(X):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
self.model.gridsearch(X_train, y_train)
y_pre = self.model.predict(X_test)
print(y_pre)
scores.append(f1_score(y_pre, y_test))
return sum(scores) / len(scores)
for i in dates:
# Fit Model to 90 Days of Data Lagged
mask = (called_pitches['game_date'] <= i) & (called_pitches['game_date'] >=
(i - dt.timedelta(days=90)))
set = called_pitches.loc[mask]
df = pd.DataFrame(set)
target_df = pd.Series(set.strikeCall)
X = df[['plate_x', 'plate_z', 'sz_top', 'sz_bot']] # 'bsCount'
y = target_df
gam_fit = LogisticGAM().fit(X, y)
# Predict Each Day of Games Using 90 Day Model
games = called_pitches.loc[called_pitches['game_date'] == i]
x_games = games[['plate_x', 'plate_z', 'sz_top', 'sz_bot']]
results = gam_fit.predict(x_games)
called_pitches.at[called_pitches['game_date'] == i,
'pred_zone_last90'] = results
# Track Progress and Reset Model
print("Inserted..." + str(i))
gam_fit = ""
called_pitches['zone_dev_last90'] = called_pitches[
'strikeCall'] - called_pitches['pred_zone_last90']
# Create Unique Umpire-Date ID, Average Zone Deviation for each Umpire-Game, # of Called_Pitches
called_pitches['umpire_date'] = called_pitches['umpire'] + called_pitches[
'game_date'].map(str)
umpDev90 = called_pitches[['game_date', 'umpire_date', 'umpire', 'game_pk']]
umpDev90 = pd.DataFrame(umpDev90)
