model = MLPClassifier(alpha=c, max_iter=100000)
b = pd.DataFrame()
b["binSpread"] = y_cvTest
model.fit(X=x_cvTrain, y=y_cvTrain)
for p in model.predict_proba(x_cvTest):
if (model.classes_[1] == 1):
predictions.append(p[1])
else:
predictions.append(p[0])
b["PFITS"] = predictions
predictions = []
allSums.append(
testClassification(b,
300,
'Kelly',
Year=False,
Week=False,
odds=-105,
betType="Spread",
printOption=False))
allScores.append(model.score(x_cvTest, y_cvTest))
counter += 1
print(c, np.average(allScores), np.average(allSums))
if (np.average(allScores) > best):
bestC = c
best = np.average(allScores)
allScores = []
allSums = []
counter = 0
print("The best C was", bestC)
model = MLPClassifier(max_iter=100000, alpha=bestC)
b = pd.DataFrame()
import pandas as pd
import numpy as np
from cfbFcns import standardizeTeamName
from evalPredictions import testClassification
#Spread Part
a = pd.read_csv(
'./csv_Data/LogisticPythonPredictionsLRWeek5+Leave-One-OutNoStepwiseScaled.csv',
encoding="ISO-8859-1")
testClassification(a,
300,
'Kelly',
Year=True,
Week=True,
odds=-105,
betType="Spread")
a = pd.read_csv(
'./csv_Data/LogisticPythonPredictionsLRWeek5+Leave-One-OutNoStepwiseScaledC0.25.csv',
encoding="ISO-8859-1")
testClassification(a,
300,
'Kelly',
Year=True,
Week=True,
odds=-105,
betType="Spread")
a = pd.read_csv(
'./csv_Data/LogisticPythonPredictionsLRWeek5+Leave-One-OutNoStepwiseScaledC0.1.csv',
encoding="ISO-8859-1")
model = LogisticRegression(max_iter=100000)
X_train, X_test, y_train, y_test = train_test_split(temp,
Y,
test_size=0.33,
random_state=42)
model.fit(X=X_train, y=y_train)
for p in model.predict_proba(X_test):
if (model.classes_[1] == 1):
predictions.append(p[1])
else:
predictions.append(p[0])
b = pd.DataFrame()
b["binTotal"] = y_test
b["PFITS"] = predictions
predictions = []
netWin = testClassification(b, 300, 'Standard', betType="O/U")
best = netWin
bestCols = []
removedCols = []
noImprovement = True
colCount = 0
removedCount = 0
bestImproved = 0
for col in temp.columns:
bestCols.append(col)
colCount += 1
random.shuffle(bestCols)
X = temp.copy()
print("Starting Removal of Features")
while (bestImproved < colCount):
print(bestImproved, colCount)
# for p in model.predict_proba(x1.reshape(-1,1)):
# if (model.classes_[1] == 1):
# predictions.append(p[1])
# if (p[1] > 0.5122):
# z.append(p[1])
# else:
# predictions.append(p[0])
bSpread["PFITS"] = x
bSpread["binSpread"] = y
print(
"SPREAD ------------------------------------------------------------------------"
)
testClassification(bSpread,
300,
'Kelly',
Year=False,
Week=False,
odds=-105,
betType="Spread",
printOption=True)
print(
"-------------------------------------------------------------------------------"
)
predictions = []
allSums = []
x = []
y = []
z = []
allScores = []
a = pd.read_csv('./new_csv_Data/bigboyBinClassificationTotalsALTTrain.csv',
encoding="ISO-8859-1")
trainRows.append(j)
tempTrainX = X_train.iloc[trainRows]
tempTrainY = y_train.iloc[trainRows]
tempValX = X_train.iloc[valRows]
tempValY = y_train.iloc[valRows]
b = pd.DataFrame()
b["binSpread"] = tempValY
model.fit(X = tempTrainX, y = tempTrainY)
for p in model.predict_proba(tempValX):
if (model.classes_[1] == 1):
predictions.append(p[1])
else:
predictions.append(p[0])
b["PFITS"] = predictions
predictions = []
cvSum += testClassification(b, 300, 'Kelly', Year = False, Week = False, odds = -105, betType = "Spread", print = False)
allSums.append(cvSum)
cvSum = 0
print ("Initial cvSum =", np.average(allSums))
best = np.average(allSums)
bestCols = []
removedCols = []
noImprovement = True
colCount = 1
removedCount = 0
bestImproved = 0
for col in xCols:
if ("Elo" not in col):
removedCols.append(col)
removedCount += 1
bestCols.append("Elo_diff_aboveAvg")
best = 0
bestCols = []
temp = X.copy()
model = LogisticRegression(max_iter = 100000)
X_train, X_test, y_train, y_test = train_test_split(temp, Y, test_size=0.33, random_state=42)
model.fit(X = X_train, y = y_train)
for p in model.predict_proba(X_test):
if (model.classes_[1] == 1):
predictions.append(p[1])
else:
predictions.append(p[0])
b = pd.DataFrame()
b["binSpread"] = y_test
b["PFITS"] = predictions
predictions = []
netWin = testClassification(b, 300, 'Standard')
best = netWin
bestCols = []
removedCols = []
noImprovement = True
colCount = 0
removedCount = 0
bestImproved = 0
for col in temp.columns:
bestCols.append(col)
colCount += 1
random.shuffle(bestCols)
X = temp.copy()
print ("Starting Removal of Features")
while (bestImproved < colCount):
print (bestImproved, colCount)