def fight_stats_model():
x_train, y_train, x_test, y_test = get_train_test_data('Fight_Stats')
x_train, y_train = random_data_shuffle(x_train, y_train)
epochs = 1050
hidden1 = 350
dropout = 0.45
l2_reg = l2(0.005)
model = tf.keras.models.Sequential()
model.add(Dropout(dropout))
model.add(
Dense(hidden1,
input_dim=x_train.shape[1],
activation='relu',
kernel_initializer='normal',
kernel_regularizer=l2_reg))
model.add(Dense(y_train.shape[1], activation='linear'))
model.compile(loss='mse',
optimizer=tf.keras.optimizers.Adam(0.0001),
metrics=[r2])
history = model.fit(x_train,
y_train,
epochs=epochs,
batch_size=32,
validation_split=0.1,
shuffle=True)
scores = model.evaluate(x_test, y_test)
save(model, 'stats_model.h5')
results = model.predict(x_test)
predictor_cols = [
'pass_stat_f1', 'pass_stat_f2', 'str_stat_f1', 'str_stat_f2',
'sub_stat_f1', 'sub_stat_f2', 'td_stat_f1', 'td_stat_f2'
]
for i in range(0, 20):
rand_i = np.random.randint(0, 300)
print('*' * 20)
for prediction, actual, col in zip(results[rand_i], y_test[rand_i],
predictor_cols):
print(f'{col}: Prediction= {prediction} Actual = {actual}')
def winner_model():
""" Model for preidicting overall winner of a bout using static data and predicted bout stats"""
x_train, y_train, x_test, y_test = get_train_test_data('Fight_Winner')
x_train, y_train = random_data_shuffle(x_train, y_train)
hidden_units = 80
epochs = 170
dropout = 0.65
l2_reg = tf.keras.regularizers.l2(0.001)
model = tf.keras.models.Sequential()
model.add(
Dense(hidden_units,
input_dim=x_train.shape[1],
activation='relu',
kernel_initializer='normal',
kernel_regularizer=l2_reg,
name='layer1'))
model.add(Dropout(dropout))
model.add(
Dense(hidden_units,
activation='relu',
kernel_initializer='normal',
kernel_regularizer=l2_reg,
name='layer2'))
model.add(Dropout(dropout))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer=tf.keras.optimizers.Adam(0.0001),
metrics=['accuracy'])
model.fit(x_train,
y_train,
epochs=epochs,
batch_size=32,
validation_split=0.05)
scores = model.evaluate(x_test, y_test)
save(model, 'winner_model.h5')
print(model.summary())
def main(arguments):
X_train, X_test, y_train, y_test = get_train_test_data(task=arguments.task)
if arguments.method == 'all':
for model in MODELS:
model_class = MODELS.get(model)
print('=========== {0} ==========='.format(model_class.__name__))
model = model_class(X_train,
X_test,
y_train,
y_test,
task=arguments.task)
model.evaluate()
elif arguments.method in MODELS.keys():
model_class = MODELS.get(arguments.method)
print('=========== {0} ==========='.format(model_class.__name__))
model = model_class(X_train,
X_test,
y_train,
y_test,
task=arguments.task)
model.evaluate()
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestRegressor
import utils
import constants
if __name__ == "__main__":
data_array = utils.load_csv(constants.filename)
X, y = utils.get_train_test_data(data_array)
regressor = RandomForestRegressor(n_estimators=10, random_state=0)
print(scores)
print('Current Dir is' + current_dir)
#filepath = os.path.join(current_dir,'Saved_Models','Winner_Prediction_Models','bout_winner.h5')
filepath = os.path.join(current_dir, 'Saved_Models', 'Fight_Stats_Models',
'fighter_stats.h5')
#model = keras.models.load_model(filepath)
model = keras.models.load_model(filepath, custom_objects={'r2': r2})
with open('fight_stats_feature_names.txt', 'r', encoding='utf-8') as f:
contents = f.readlines()
feature_names = [x.strip() for x in contents]
#x_train, y_train, x_test, y_test = get_train_test_data('winner_prediction_data')
x_train, y_train, x_test, y_test = get_train_test_data(
'fighter_stats_prediction_data')
scaler = joblib.load(
os.path.join(os.getcwd(), 'fight_predictor', 'my_scaler.pkl'))
upper_index = 100
explainer = shap.DeepExplainer(model, x_train)
shap_values = explainer.shap_values(x_train[:upper_index])
feature_values = x_train[:upper_index]
feature_values = scaler.inverse_transform(feature_values)
#shap.summary_plot(shap_values,feature_names=feature_names)
# plot = shap.force_plot(
# explainer.expected_value[0],
# shap_values[0][:],feature_values,
import utils
import constants
import numpy as np
def load_csv_file():
data_loaded = utils.load_csv(constants.filename)
print(data_loaded)
if __name__ == "__main__":
data_loaded = utils.load_csv(constants.filename)
X, y = utils.get_train_test_data(data_loaded)
print("yo")
from utils import get_train_test_data
from models import multiclass_one_vs_rest
from features import compute_target_distribution
from plotting import plot_combined_roc_curve
x, y = get_train_test_data()
target_distribution = compute_target_distribution(y, plot=False, verbose=False)
plot_data = {}
for model_type in [
"logistic", "tree", "forest", "nnet", "adaboost", "extra", "SVC"
]:
# for model_type in ["logistic"] : #, "tree"] :
plot_data[model_type] = multiclass_one_vs_rest(x,
y,
model_type,
plot=False,
verbose=True,
run_cv=False)
plot_combined_roc_curve(plot_data)