def main():
model = LinearRegression()
train_data = get_train_data()
train_x, train_y = process_data(train_data)
train_x = pd.concat(
[train_x, np.square(train_x),
np.power(train_x, 3)], axis=1)
model.fit(train_x, train_y)
pred_y = np.round(model.predict(train_x))
print('Train mean absolute error:',
np.sum(np.absolute(pred_y - train_y)) / np.size(pred_y))
eval_data = get_eval_data()
eval_x, eval_y = process_data(eval_data)
eval_x = pd.concat([eval_x, np.square(eval_x),
np.power(eval_x, 3)],
axis=1)
pred_y = np.round(model.predict(eval_x))
print('Eval mean absolute error:',
np.sum(np.absolute(pred_y - eval_y)) / np.size(eval_y))
df = pd.DataFrame({
'Score1': pred_y[:int(pred_y.size / 2)],
'Score2': pred_y[int(pred_y.size / 2):]
})
df['Winner'] = df['Score1'] < df['Score2']
print(np.sum(df['Winner'] == eval_data['Winner']) / np.size(df['Winner']))
print(r2_score(eval_y, pred_y))
def main():
model = LogisticRegression(penalty='l2', solver='liblinear')
train_data = get_train_data()
train_x, train_y = process_data(train_data)
model.fit(train_x, train_y)
pred_y = model.predict(train_x)
print('Train accuracy:', np.sum(pred_y == train_y) / np.size(train_y))
eval_data = get_eval_data()
eval_x, eval_y = process_data(eval_data)
pred_y = model.predict(eval_x)
print('Eval accuracy:', np.sum(pred_y == eval_y) / np.size(eval_y))
print('\n')
demo_data = pd.concat([
eval_data.loc[eval_data['WTeamID'] == 1242].loc[
eval_data['Season'] == 2018], eval_data.loc[
eval_data['LTeamID'] == 1242].loc[eval_data['Season'] == 2018]
],
axis=0)
demo_x, demo_y = process_data(demo_data)
pred_y = model.predict(demo_x)
pred_y = pd.DataFrame(data=pred_y, columns=["Predicted"])
demo_data = lookup_teams(demo_data)
result = pd.concat([demo_data, pred_y], axis=1)
print(result[['Season', 'T0TeamName', 'T1TeamName', 'Winner',
'Predicted']])
def main():
train_data = get_train_data()
X, y = process_data(train_data)
train_X, test_X, train_y, test_y = train_test_split(X, y)
eval_data = get_eval_data()
eval_X, eval_y = process_data(eval_data)
tree = RandomForestClassifier(80)
tree.fit(train_X, train_y)
pred_y = tree.predict(test_X)
print("Training accuracy: ", np.sum(pred_y == test_y) / np.size(test_y))
pred_y = tree.predict(eval_X)
print('Eval accuracy:', np.sum(pred_y == eval_y) / np.size(eval_y))
def main():
train_data = get_train_data()
X, y = process_data(train_data)
train_X, test_X, train_y, test_y = train_test_split(X, y)
eval_data = get_eval_data()
eval_X, eval_y = process_data(eval_data)
for i in tqdm(range(2, 10)):
print(i)
tree = KNeighborsClassifier(n_neighbors=i)
tree.fit(train_X, train_y)
pred_y = tree.predict(test_X)
print("Training accuracy: ",
np.sum(pred_y == test_y) / np.size(test_y))
pred_y = tree.predict(eval_X)
print('Eval accuracy:', np.sum(pred_y == eval_y) / np.size(eval_y))
def train(args):
# all_input, all_output = get_data()
# 75% of data is training
# train_inp, train_out = all_input[:int(.75*len(all_input))], all_output[:int(.75*len(all_input))]
train_inp, train_out = get_train_data()
print "train data loaded"
no_of_batches = len(train_inp) / BATCH_SIZE
# 25% is testing data
# test_inp, test_out = all_input[int(.75*len(all_input)):], all_output[int(.75*len(all_input)):]
test_inp, test_out = get_test_data()
print "test data loaded"
data = tf.placeholder(tf.float32, [None, MAX_SEQ_LEN, WORD_DIM])
target = tf.placeholder(tf.float32, [None, MAX_SEQ_LEN, NUM_CLASSES])
dropout = tf.placeholder(tf.float32)
model = Model(data, target, dropout, NUM_HIDDEN, NUM_LAYERS)
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver()
if args.restore is not None:
saver.restore(sess, "model.ckpt")
print "last model restored"
for epoch in range(NUM_EPOCH):
ptr = 0
for _ in range(no_of_batches):
batch_inp, batch_out = train_inp[ptr : ptr + BATCH_SIZE], train_out[ptr : ptr + BATCH_SIZE]
ptr += BATCH_SIZE
sess.run(model.optimize, {data: batch_inp, target: batch_out, dropout: 0.5})
error = sess.run(model.error, {data: test_inp, target: test_out, dropout: 1})
print ("Epoch {:2d} error {:3.1f}%".format(epoch + 1, error * 100))
if epoch % 10 == 0:
save_path = saver.save(sess, "model.ckpt")
print ("Model saved in file: %s" % save_path)
def train(args):
train_inp, train_out = get_train_data()
print "train data loaded"
no_of_batches = len(train_inp) / BATCH_SIZE
test_inp, test_out = get_test_data()
print "test data loaded"
data = tf.placeholder(tf.float32,[None, MAX_SEQ_LEN, WORD_DIM])
target = tf.placeholder(tf.float32, [None, MAX_SEQ_LEN, NUM_CLASSES])
dropout = tf.placeholder(tf.float32)
model = Model(data,target,dropout,NUM_HIDDEN,NUM_LAYERS)
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver()
if args.restore is not None:
saver.restore(sess, 'model.ckpt')
print "last model restored"
for epoch in range(100):
ptr=0
for _ in range(no_of_batches):
batch_inp, batch_out = train_inp[ptr:ptr+BATCH_SIZE], train_out[ptr:ptr+BATCH_SIZE]
ptr += BATCH_SIZE
sess.run(model.optimize,{data: batch_inp, target : batch_out, dropout: 0.5})
if epoch % 10 == 0:
save_path = saver.save(sess, "model.ckpt")
print("Model saved in file: %s" % save_path)
error = sess.run(model.error, { data:test_inp, target: test_out, dropout: 1})
print('Epoch {:2d} error {:3.1f}%'.format(epoch + 1, error*100))
pred = sess.run(model.prediction, {data: test_inp, target: test_out, dropout: 1})
pred,length = sess.run(model.getpredf1, {data: test_inp, target: test_out, dropout: 1})
f1(pred,test_out,length)
def main():
np.random.seed(2410)
train_data = get_train_data()
X, y = process_data(train_data)
train_X, test_X, train_y, test_y = train_test_split(X, y)
eval_data = get_eval_data()
eval_X, eval_y = process_data(eval_data)
model = Sequential()
model.add(Dense(20, input_dim=len(train_X.columns)))
model.add(Dense(10))
model.add(Dense(1, activation="sigmoid"))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(train_X, train_y, epochs=10, batch_size=32)
pred_y = np.round(model.predict(test_X).flatten())
print(np.unique(pred_y, return_counts=True))
print("Training accuracy: ", np.sum(pred_y == test_y) / np.size(test_y))
pred_y = np.round(model.predict(eval_X).flatten())
print('Eval accuracy:', np.sum(pred_y == eval_y) / np.size(eval_y))
model.save('model.h5')
def train(args):
train_inp, train_out = get_train_data()
print "train data loaded"
no_of_batches = (len(train_inp) + BATCH_SIZE - 1) / BATCH_SIZE
test_inp, test_out = get_test_data()
print "test data loaded"
final_inp, final_out = get_final_data()
print "final data loaded"
data = tf.placeholder(tf.float32, [None, MAX_SEQ_LEN, WORD_DIM])
target = tf.placeholder(tf.float32, [None, MAX_SEQ_LEN, NUM_CLASSES])
dropout = tf.placeholder(tf.float32)
model = Model(data, target, dropout, NUM_HIDDEN, NUM_LAYERS)
maximum = 0
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver()
if args.restore is not None:
saver.restore(sess, 'model.ckpt')
print "last model restored"
for epoch in range(200):
ptr = 0
for _ in range(no_of_batches):
batch_inp, batch_out = train_inp[
ptr:ptr + BATCH_SIZE], train_out[ptr:ptr + BATCH_SIZE]
ptr += BATCH_SIZE
sess.run(model.optimize, {
data: batch_inp,
target: batch_out,
dropout: 0.5
})
if epoch % 10 == 0:
save_path = saver.save(sess, "model.ckpt")
print("Model saved in file: %s" % save_path)
pred = sess.run(model.prediction, {
data: test_inp,
target: test_out,
dropout: 1
})
pred, length = sess.run(model.getpredf1, {
data: test_inp,
target: test_out,
dropout: 1
})
print "Epoch:" + str(epoch), "TestA score,"
m = f1(pred, test_out, length)
if m > maximum:
maximum = m
save_path = saver.save(sess, "model_max.ckpt")
print("Max Model saved in file: %s" % save_path)
pred = sess.run(model.prediction, {
data: final_inp,
target: final_out,
dropout: 1
})
pred, length = sess.run(model.getpredf1, {
data: final_inp,
target: final_out,
dropout: 1
})
print "TestB score,"
f1(pred, final_out, length)