def inference():
configs = read_config(FLAGS.config_path)
class_ids = read_config(FLAGS.class_config)
img_data = read_data(FLAGS.data_dir, int(configs['width']),
int(configs['height']))
cyc_GAN = CycleGAN(configs)
cyc_GAN.build_model()
# You must define saver after you build a tensorflow graph
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, FLAGS.model_path)
meta_data = meta_initializer(
int(class_ids[FLAGS.t]),
[int(configs['width']),
int(configs['height'])])
idx = 0
for img in img_data:
img_vec = np.expand_dims(img, axis=0)
if int(class_ids[FLAGS.f]) < int(class_ids[FLAGS.t]):
mode = "AtoB"
else:
mode = "BtoA"
output_img = sess.run(cyc_GAN.predict(mode),
feed_dict={
cyc_GAN.sample_vector: img_vec,
cyc_GAN.sample_meta_data: meta_data
})
output_img = sess.run(tf.image.encode_jpeg(tf.squeeze(output_img)))
with open(join(FLAGS.output_dir, str(idx) + '.jpg'), 'wb') as f:
f.write(output_img)
idx += 1
def main(args):
# Read data from local disk
print("[info] Reading data from disk ...")
X, y = read_data(path=args['data_path'])
# Normalize data
# X = min_max_normalization(X=X)
# Build model
print("[info] Building model ...")
model = LinearRegression(args=args)
# Fitting model with data
print("[info] learning ...")
model.learn(X=X, y=y, output_log='logs/linear_regression.csv')
# Plot the training progress
plot_progress(path='log', save=True)
# Evaluate on test set
model.evaluate()
from utils.read_data import read_data
from utils.plot import plot_var
from utils.var import var, select_lr
if __name__ == "__main__":
df = read_data("data/cee.xls", f="1963Q3")
lag = select_lr(df, maxlags=15)
print("LR ratio: ", lag)
standard_res = var(df, lags=4)
plot_var(standard_res,
impulse="FF",
response=df.columns,
folder="cee/ex",
autocorr=True)
ic = "bic"
standard_res = var(df, trend="c", lags=2)
plot_var(standard_res, impulse="FF", folder=f"cee/{ic}")
new_order = ["Y", "P", "PCOM", "FF", "TR", "NBR", "M1"]
reindexed = df.reindex(columns=new_order)
standard_res = var(reindexed, lags=4)
plot_var(standard_res,
impulse="FF",
response=df.columns,
folder="cee/swapped",
autocorr=True)
def train(config):
"""Train a en->fr translation model using WMT data."""
# Prepare WMT data.
print("Preparing WMT data in %s" % config.data_dir)
en_embd_name = ""
en_train, fr_train, en_dev, fr_dev, _, _, embd_mat_en, embd_mat_fr = data_utils.prepare_wmt_data(
config.data_dir, config.en_vocab_size, config.fr_vocab_size)
#config.embedding_en_path, config.embedding_fr_path, 'enc_embedding', 'dec_embedding')
with tf.Session() as sess:
if not os.path.exists(FLAGS.model_dir):
os.makedirs(FLAGS.model_dir)
# Create model.
print("Creating %d layers of %d units." %
(config.num_layers, config.size))
model = create_model(sess, config, False)
#if not config.probabilistic:
# self.kl_rate_update(0.0)
train_writer = tf.summary.FileWriter(os.path.join(
FLAGS.model_dir, "train"),
graph=sess.graph)
dev_writer = tf.summary.FileWriter(os.path.join(
FLAGS.model_dir, "test"),
graph=sess.graph)
# Read data into buckets and compute their sizes.
print("Reading development and training data (limit: %d)." %
config.max_train_data_size)
dev_set = read_data.read_data(en_dev, fr_dev, config)
train_set = read_data.read_data(en_train, fr_train, config,
config.max_train_data_size)
train_bucket_sizes = [
len(train_set[b]) for b in xrange(len(config.buckets))
]
train_total_size = float(sum(train_bucket_sizes))
# A bucket scale is a list of increasing numbers from 0 to 1 that we'll use
# to select a bucket. Length of [scale[i], scale[i+1]] is proportional to
# the size if i-th training bucket, as used later.
train_buckets_scale = [
sum(train_bucket_sizes[:i + 1]) / train_total_size
for i in xrange(len(train_bucket_sizes))
]
# This is the training loop.
step_time, loss = 0.0, 0.0
KL_loss = 0.0
current_step = model.global_step.eval()
step_loss_summaries = []
step_KL_loss_summaries = []
overall_start_time = time.time()
while True:
# Choose a bucket according to data distribution. We pick a random number
# in [0, 1] and use the corresponding interval in train_buckets_scale.
random_number_01 = np.random.random_sample()
bucket_id = min([
i for i in xrange(len(train_buckets_scale))
if train_buckets_scale[i] > random_number_01
])
# Get a batch and make a step.
start_time = time.time()
encoder_inputs, decoder_inputs, target_weights = model.get_batch(
train_set, bucket_id)
_, step_loss, step_KL_loss, _ = model.step(sess, encoder_inputs,
decoder_inputs,
target_weights,
bucket_id, False,
config.probabilistic)
if config.anneal and model.global_step.eval(
) > config.kl_rate_rise_time and model.kl_rate < 1:
new_kl_rate = model.kl_rate.eval() + config.kl_rate_rise_factor
sess.run(model.kl_rate_update,
feed_dict={'new_kl_rate': new_kl_rate})
step_time += (time.time() -
start_time) / config.steps_per_checkpoint
step_loss_summaries.append(
tf.Summary(value=[
tf.Summary.Value(tag="step loss",
simple_value=float(step_loss))
]))
step_KL_loss_summaries.append(
tf.Summary(value=[
tf.Summary.Value(tag="KL step loss",
simple_value=float(step_KL_loss))
]))
loss += step_loss / config.steps_per_checkpoint
KL_loss += step_KL_loss / config.steps_per_checkpoint
current_step = model.global_step.eval()
# Once in a while, we save checkpoint, print statistics, and run evals.
if current_step % config.steps_per_checkpoint == 0:
# Print statistics for the previous epoch.
perplexity = math.exp(
float(loss)) if loss < 300 else float("inf")
print(
"global step %d learning rate %.4f step-time %.2f perplexity "
"%.2f" %
(model.global_step.eval(), model.learning_rate.eval(),
step_time, perplexity))
print(
"global step %d learning rate %.4f step-time %.2f KL divergence "
"%.2f" % (model.global_step.eval(),
model.learning_rate.eval(), step_time, KL_loss))
wall_time = time.time() - overall_start_time
print("time passed: {0}".format(wall_time))
# Add perplexity, KL divergence to summary and stats.
perp_summary = tf.Summary(value=[
tf.Summary.Value(tag="train perplexity",
simple_value=perplexity)
])
train_writer.add_summary(perp_summary, current_step)
KL_loss_summary = tf.Summary(value=[
tf.Summary.Value(tag="KL divergence", simple_value=KL_loss)
])
train_writer.add_summary(KL_loss_summary, current_step)
for i, summary in enumerate(step_loss_summaries):
train_writer.add_summary(summary, current_step - 200 + i)
step_loss_summaries = []
for i, summary in enumerate(step_KL_loss_summaries):
train_writer.add_summary(summary, current_step - 200 + i)
step_KL_loss_summaries = []
# Save checkpoint and zero timer and loss.
checkpoint_path = os.path.join(FLAGS.model_dir,
FLAGS.model_name + ".ckpt")
model.saver.save(sess,
checkpoint_path,
global_step=model.global_step)
step_time, loss, KL_loss = 0.0, 0.0, 0.0
# Run evals on development set and print their perplexity.
eval_losses = []
eval_KL_losses = []
eval_bucket_num = 0
for bucket_id in xrange(len(config.buckets)):
if len(dev_set[bucket_id]) == 0:
print(" eval: empty bucket %d" % (bucket_id))
continue
eval_bucket_num += 1
encoder_inputs, decoder_inputs, target_weights = model.get_batch(
dev_set, bucket_id)
_, eval_loss, eval_KL_loss, _ = model.step(
sess, encoder_inputs, decoder_inputs, target_weights,
bucket_id, True, config.probabilistic)
eval_losses.append(float(eval_loss))
eval_KL_losses.append(float(eval_KL_loss))
eval_ppx = math.exp(
float(eval_loss)) if eval_loss < 300 else float("inf")
print(" eval: bucket %d perplexity %.2f" %
(bucket_id, eval_ppx))
eval_perp_summary = tf.Summary(value=[
tf.Summary.Value(tag="eval perplexity for bucket {0}".
format(bucket_id),
simple_value=eval_ppx)
])
dev_writer.add_summary(eval_perp_summary, current_step)
mean_eval_loss = sum(eval_losses) / float(eval_bucket_num)
mean_eval_KL_loss = sum(eval_KL_losses) / float(
eval_bucket_num)
mean_eval_ppx = math.exp(float(mean_eval_loss))
print(" eval: mean perplexity {0}".format(mean_eval_ppx))
eval_loss_summary = tf.Summary(value=[
tf.Summary.Value(tag="mean eval loss",
simple_value=float(mean_eval_ppx))
])
dev_writer.add_summary(eval_loss_summary, current_step)
eval_KL_loss_summary = tf.Summary(value=[
tf.Summary.Value(tag="mean eval loss",
simple_value=float(mean_eval_KL_loss))
])
dev_writer.add_summary(eval_KL_loss_summary, current_step)
len_argv = len(sys.argv)
K = 10
L = 5
try:
flag = sys.argv[1]
K = int(sys.argv[2])
L = int(sys.argv[3])
except:
pass
print '*' * 30
# make generalization hierarchies
gen_gh_trees()
#read gentree tax
att_trees = read_tree()
#read record
data = read_data()
# APA need only GH for transaction
if flag == 'k':
get_result_K(att_trees, data)
elif flag == 'l':
get_result_L(att_trees, data)
elif flag == 'data':
get_result_dataset(att_trees, data)
elif flag == 'apa':
if len_argv > 2:
get_result_one(att_trees, data, K, L)
else:
get_result_one(att_trees, data)
elif flag == '':
get_result_one(att_trees, data)
else:
if __name__ == "__main__":
FLAG = ""
try:
FLAG = sys.argv[1]
except:
pass
# read record
print "*" * 30
# make generalization hierarchies
gen_gh_trees()
# read gentree tax
ATT_TREES = read_tree()
# read record
DATA = read_data()
# Separation_Gen need only GH for transaction
if FLAG == "k":
get_result_k(ATT_TREES, DATA)
elif FLAG == "l":
get_result_l(ATT_TREES, DATA)
elif FLAG == "data":
get_result_dataset(ATT_TREES, DATA)
elif FLAG == "":
# cProfile.run('get_result_one(ATT_TREE, DATA, TYPE_ALG)')
get_result_one(ATT_TREES, DATA)
else:
try:
INPUT_K = int(FLAG)
get_result_one(ATT_TREEs, DATA)
except ValueError:
INPUT_K = 10
# read record
RELAX = True if mode_config.model == "relax" else False
if RELAX:
print("Relax Mondrian")
else:
print("Strict Mondrian")
# print("Adult data")
# INTUITIVE_ORDER is an intuitive order for
# categorical attributes. This order is produced
# by the reading (from data set) order.
DATA, INTUITIVE_ORDER = read_data()
print(INTUITIVE_ORDER)
FLAG = mode_config.flag
if FLAG == 'k':
get_result_k(DATA)
elif FLAG == 'qi':
get_result_qi(DATA)
elif FLAG == 'data':
get_result_dataset(DATA)
elif FLAG == '':
get_result_one(DATA, mode_config.k)
else:
try:
get_result_one(DATA, 10)
except ValueError:
""" run anatomize with given parameters """ # !/usr/bin/env python # coding=utf-8 # by Qiyuan Gong # [email protected] from anatomize import anatomize from utils.read_data import read_data import sys if __name__ == '__main__': L = 10 try: L = int(sys.argv[1]) except IndexError: pass # read record RAW_DATA = read_data() # remove duplicate items print "Begin Anatomizer" RESULT = anatomize(RAW_DATA, L) print "No. groups in result=%d" % len(RESULT) print "Finish Anatomizer!!"
def initialize_game(self, difficulty):
self.canvas.clear()
self.state = "game"
self.difficulty = difficulty
self.audio_controller = AudioController(self.difficulty)
self.audio_controller.toggle()
self.notes_down = [
] # an array that keeps track of all notes that are currently being played on midi keyboard
# The display for the gems, now bar, and bar lines
self.canvas.add(Color(1, 1, 1))
rect = Rectangle(pos=(0, 0),
size=(Window.width, Window.height),
texture=Image('assets/bg_c.png').texture)
self.canvas.add(rect)
self.lane_manager = LaneManager()
# Display the status of the game through the text labels
self.canvas.add(Color(1, 1, 1))
self.hud = Rectangle(pos=(0, Window.height / 1.12),
size=(Window.width / 4, Window.height / 9),
texture=Image('assets/tophub.png').texture)
self.canvas.add(self.hud)
self.canvas.add(Color(1, 1, 1))
self.hud_score = Rectangle(
pos=(Window.width / 1.4, Window.height / 1.12),
size=(Window.width / 3.5, Window.height / 9),
texture=Image('assets/topscore.png').texture)
self.canvas.add(self.hud_score)
self.score_label = score_label()
self.add_widget(self.score_label)
self.hp_label = hp_label()
self.add_widget(self.hp_label)
self.enemy_times = []
self.enemy_lanes = []
self.enemy_types = []
self.enemy_chords = []
self.enemy_manager = EnemyManager()
self.canvas.add(self.enemy_manager)
if difficulty == "easy":
read_data("song_annotations/hallelujah_left_hand_test.txt", None,
self.enemy_times, self.enemy_lanes, self.enemy_types,
self.enemy_chords)
self.song_length = 140
elif difficulty == "medium":
read_data("song_annotations/falling_left_hand_test.txt",
"song_annotations/falling_right_hand_test.txt",
self.enemy_times, self.enemy_lanes, self.enemy_types,
self.enemy_chords)
self.song_length = 44
elif difficulty == "hard":
read_data("song_annotations/hallelujah_left_hand_test.txt",
"song_annotations/hallelujah_right_hand_test.txt",
self.enemy_times,
self.enemy_lanes,
self.enemy_types,
self.enemy_chords,
inversions=True)
self.song_length = 140
self.prev_time = time.time()
self.elapsed_time = 0
self.note_index = 0
window_size = 4 # 4 seconds of notes are displayed
x_scale = Window.width / window_size # pixels / sec
# Create the player object which will store and control the state of the game
self.player = Player(self.hp_label, self.score_label, self.enemy_times,
self.enemy_lanes, self.enemy_types,
self.enemy_chords, self.enemy_manager,
self.audio_controller)
self.canvas.add(self.player)
self.player.toggle()
"""Returns a LaTeX pmatrix
:a: numpy array
:returns: LaTeX pmatrix as a string
"""
if len(a.shape) > 2:
raise ValueError('pmatrix can at most display two dimensions')
lines = str(a).replace('[', '').replace(']', '').splitlines()
rv = [r'\begin{pmatrix}']
rv += [' ' + ' & '.join(l.split()) + r'\\' for l in lines]
rv += [r'\end{pmatrix}']
return '\n'.join(rv)
if __name__ == "__main__":
df = read_data("data/bp.xls")
scaled_df, unscaled_df = parse_data(df)
pre_elas, post_elas = G_Y_multiplier(scaled_df, unscaled_df)
print(f"Multiplier: {pre_elas} (pre) and {post_elas} (post)")
dummy_df = scaled_df.copy()
dummy_df["D"] = 0.
dummy_df["D"]["1975Q2"] = 1.
standard_res = var(dummy_df, lags=4)
plot_var(standard_res,
impulse="G",
response=dummy_df.columns,
folder="bp/base",
if __name__ == '__main__':
# set K=10 as default
FLAG = ''
DATA_SELECT = ''
# gen_even_BMS_tree(5)
try:
DATA_SELECT = sys.argv[1]
FLAG = sys.argv[2]
except IndexError:
pass
INPUT_K = 10
if DATA_SELECT == 'i':
print "INFORMS data"
DATA = read_data(1)
ATT_TREE = read_tree(2)
else:
print "BMS-WebView data"
DATA = read_data(0)
ATT_TREE = read_tree(0)
# read generalization hierarchy
# read record
# remove duplicate items
for i in range(len(DATA)):
DATA[i] = list(set(DATA[i]))
print "Begin Partition"
if FLAG == 'k':
get_result_k(ATT_TREE, DATA)
elif FLAG == 'data':
get_result_dataset(ATT_TREE, DATA)
def parse_data(df: pd.DataFrame) -> pd.DataFrame:
new_df = df.copy()
pop = new_df["POP"]
for transf_var in transform:
trans_data = np.log(new_df[transf_var] / pop)
new_df[name_map[transf_var]] = trans_data
return new_df.drop(transform, axis=1)
if __name__ == "__main__":
df = read_data("data/ramey.xls")
parsed_df = parse_data(df)["1960Q1":]
restr_var = ["G", "T", "Y"]
restr_df = parsed_df[restr_var]
res = var(restr_df, trend="ctt", lags=4)
plot_var(res, impulse="G", folder="ramey/base")
aug_var = restr_var + ["CONS", "INV"]
aug_df = parsed_df[aug_var]
res = var(aug_df, trend="ctt", lags=4)
plot_var(res, impulse="G", folder="ramey/aug")
war_var = ["WAR"] + aug_var
war_df = parsed_df[war_var]
res = var(war_df, trend="ctt", lags=4)
len_argv = len(sys.argv)
K = 10
L = 5
try:
flag = sys.argv[1]
K = int(sys.argv[2])
L = int(sys.argv[3])
except:
pass
print '*'*30
# make generalization hierarchies
gen_gh_trees()
#read gentree tax
att_trees = read_tree()
#read record
data = read_data()
# PAA need only GH for transaction
if flag == 'k':
get_result_K(att_trees, data)
elif flag == 'l':
get_result_L(att_trees, data)
elif flag == 'data':
get_result_dataset(att_trees, data)
elif flag == 'paa':
if len_argv > 2:
get_result_one(att_trees, data, K, L)
else:
get_result_one(att_trees, data)
elif flag =='':
get_result_one(att_trees, data)
else:
FLAG = ''
# gen_even_BMS_tree(5)
try:
TYPE_ALG = sys.argv[1]
DATA_SELECT = sys.argv[2]
FLAG = sys.argv[3]
except IndexError:
pass
INPUT_K = 10
if TYPE_ALG == 'DA' or TYPE_ALG == 'da':
print "Begin DA"
else:
print "Begin AA"
if DATA_SELECT == 'i':
print "INFORMS data"
DATA = read_data(1)
ATT_TREE = read_tree(2)
else:
print "BMS-WebView data"
DATA = read_data(0)
ATT_TREE = read_tree(0)
print "*" * 30
# read generalization hierarchy
# read record
# remove duplicate items
# DATA = DATA[:1000]
# for i in range(len(DATA)):
# if len(DATA[i]) <= 40:
# DATA[i] = list(set(DATA[i]))
# else:
# DATA[i] = list(set(DATA[i][:40]))
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from utils.read_data import read_data
from utils.plot import plot_series
if __name__ == '__main__':
df = read_data("data/rz.xls", time_name="quarter")
plot_series(df, folder="rz")
df.to_csv("data/parsed_rz.xls")
