def buy(self):
"""Buy upgrades for both attack and defense
Requires the confirmation popup button for EXP purchases in settings
to be turned OFF.
This uses all available exp, so use with caution.
"""
Stats.set_value_with_ocr("XP")
if Stats.OCR_failed:
print('OCR failed, exiting upgrade routine.')
return
current_exp = Stats.xp
if current_exp < 1000:
return
total_price = (coords.RATTACK_COST * self.attack)
total_price += (coords.RDEFENSE_COST * self.defense)
# Skip upgrading if we don't have enough exp to buy at least one
# complete set of upgrades, in order to maintain our perfect ratios :)
if total_price > current_exp:
if self.report:
print("No XP Upgrade :{:^8} of {:^8}".format(
Helper.human_format(current_exp),
Helper.human_format(total_price)))
return
amount = int(current_exp // total_price)
a_attack = amount * self.attack
a_defense = amount * self.defense
Navigation.exp_rich()
Inputs.click(*coords.EM_ADV_BOX)
Inputs.send_string(str(a_attack))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_ADV_BOX)
Inputs.send_string(str(a_defense))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_ADV_BOX)
Inputs.click(*coords.EM_ADV_BOX)
Stats.set_value_with_ocr("XP")
total_spent = coords.RATTACK_COST * a_attack
total_spent += coords.RDEFENSE_COST * a_defense
if self.report:
print("Spent XP:{:^8}{:^3}Attack:{:^8}{:^3}Defense:{:^8}".format(
Helper.human_format(total_spent), "|",
Helper.human_format(a_attack), "|",
Helper.human_format(a_defense)))
def save(photo, profile, text, filter, crest, folder):
# Open the image
background_image = Files.open_url(photo)
# Resize and crop
background_image = Images.treat_image(background_image)
# Set the black grandient layer
background_image = Images.set_gradient(background_image, 'full')
background_image = Images.set_gradient(background_image, 'footer')
# Apply the Data Science logo
logo = Files.open_local('./src/images/logo.png')
background_image = Images.apply_image(background_image, logo, (10, 10),
(75, 75))
# Stats
if profile:
stats = Stats.get_player_data(profile, filter)
background_image = Images.set_stats(background_image, stats, text)
# Apply the club crest
if crest:
thumb_size = 125, 125
for i in range(len(crest)):
crest_i = i + 1
crest_len = len(crest)
crest_item = Files.open_url(crest[i])
crest_item.thumbnail(thumb_size, Image.ANTIALIAS)
crest_position = Images.get_crest_position(
background_image, crest_item, stats['player'], crest_i,
crest_len)
background_image = Images.apply_image(background_image,
crest_item,
crest_position,
(crest_item.size))
file_name = Files.get_file_name(stats['player'], text)
Files.save(background_image, folder, file_name)
pd.options.mode.chained_assignment = None
from classes.preprocessing import Preprocessing
from classes.stats import Stats
if __name__ == '__main__':
# ************************************************** #
# PREPROCESSING OF THE DATASET #
# ************************************************** #
dir = os.path.dirname(os.path.realpath(__file__))
dataset = pd.read_csv(dir + '/dataset/IMDBDataset.csv')
stats = Stats()
prep = Preprocessing(dataset)
# Make a dictionary by tokenizing all words in the dataset
prep.make_dictionary()
# Encode all words with integer IDs
# Encode only the most used words in the dataset, any other words encode as 0
n_top_used_words = 10000
dataset = prep.encode_dataset_column(df=dataset, field="review", use_top_words=n_top_used_words)
# Encode target variables to binary representation
dataset = prep.string_to_int(df=dataset, params={"sentiment": {'positive': 1, 'negative': 0}})
# Pad all reviews, remove reviews that have no words, trim reviews that exceed the review_len value
review_len = 500
import pandas as pd
pd.options.mode.chained_assignment = None
from classes.preprocessing import Preprocessing
from classes.stats import Stats
if __name__ == '__main__':
# ************************************************** #
# PREPROCESSING OF THE DATASET #
# ************************************************** #
dir = os.path.dirname(os.path.realpath(__file__))
dataset = pd.read_csv(dir + '/dataset/IMDBDataset.csv')
stats = Stats()
prep = Preprocessing(dataset)
# Make a dictionary by tokenizing all words in the dataset
prep.make_dictionary()
# Encode all words with integer IDs
# Encode only the most used words in the dataset, any other words encode as 0
n_top_used_words = 10000
dataset = prep.encode_dataset_column(df=dataset,
field="review",
use_top_words=n_top_used_words)
# Encode target variables to binary representation
dataset = prep.string_to_int(
df=dataset, params={"sentiment": {
# ************************************************** #
stats_bank = {"lstm":[], "lstm_cnn":[]}
state_size = 256
max_words = n_top_used_words
vector_size = 32
input_size = X_train.shape[1]
batch_size = 250
epochs = 4
# ************************************************** #
# THE CNN LSTM MODEL #
# ************************************************** #
lstmcnn_stats = Stats()
lstmcnn_model=Sequential([
Embedding(max_words + 1, output_dim=vector_size, input_length=input_size, batch_input_shape=[batch_size, None]),
Conv1D(filters=128, kernel_size=32, padding='same', activation=tf.nn.tanh),
MaxPooling1D(),
LSTM(state_size, return_sequences=True, stateful=True, activation=tf.nn.tanh),
Flatten(),
Dense(128, activation=tf.nn.relu, use_bias=True),
Dense(1, activation=tf.nn.sigmoid)
])
# print_layer_config(lstmcnn_model.layers)
lstmcnn_model.compile(loss=losses.binary_crossentropy, optimizer='adam', metrics=['accuracy'])
# Train the model
for i in range(epochs):
import pandas as pd
pd.options.mode.chained_assignment = None
from classes.preprocessing import Preprocessing
from classes.stats import Stats
if __name__ == '__main__':
# ************************************************** #
# PREPROCESSING OF THE DATASET #
# ************************************************** #
dir = os.path.dirname(os.path.realpath(__file__))
dataset = pd.read_csv(dir + '/../IMDB/dataset/IMDBDataset.csv')
stats = Stats()
prep = Preprocessing(dataset)
# Make a dictionary by tokenizing all words in the dataset
prep.make_dictionary()
# Encode all words with integer IDs
# Encode only the most used words in the dataset, any other words encode as 0
n_top_used_words = 10000
dataset = prep.encode_dataset_column(df=dataset,
field="review",
use_top_words=n_top_used_words)
# Encode target variables to binary representation
dataset = prep.string_to_int(
df=dataset, params={"sentiment": {
def buy(self):
"""Buy upgrades for both energy and magic.
Requires the confirmation popup button for EXP purchases in settings
to be turned OFF.
This uses all available exp, so use with caution.
"""
if self.ecap < 10000 or self.ecap % 250 != 0:
print("Ecap value not divisible by 250 or lower than 10000, not" +
" spending exp.")
return
if self.mcap < 10000 or self.mcap % 250 != 0:
print("Mcap value not divisible by 250 or lower than 10000, not" +
" spending exp.")
return
Stats.set_value_with_ocr("XP")
if Stats.OCR_failed:
print('OCR failed, exiting upgrade routine.')
return
current_exp = Stats.xp
e_cost = coords.EPOWER_COST + coords.ECAP_COST * self.ecap + (
coords.EBAR_COST * self.ebar)
m_cost = coords.MPOWER_COST + coords.MCAP_COST * self.mcap + (
coords.MBAR_COST * self.mbar)
total_price = m_cost + self.e2m_ratio * e_cost
# Skip upgrading if we don't have enough exp to buy at least one
# complete set of upgrades, in order to maintain our perfect ratios :)
if total_price > current_exp:
if self.report:
print("No XP Upgrade :{:^8} of {:^8}".format(
Helper.human_format(current_exp),
Helper.human_format(total_price)))
return
amount = int(current_exp // total_price)
e_power = amount * self.e2m_ratio
e_cap = amount * self.ecap * self.e2m_ratio
e_bars = amount * self.ebar * self.e2m_ratio
m_power = amount
m_cap = amount * self.mcap
m_bars = amount * self.mbar
Navigation.exp()
Inputs.click(*coords.EM_POW_BOX)
Inputs.send_string(str(e_power))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_CAP_BOX)
Inputs.send_string(str(e_cap))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_BAR_BOX)
Inputs.send_string(str(e_bars))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_POW_BUY)
Inputs.click(*coords.EM_CAP_BUY)
Inputs.click(*coords.EM_BAR_BUY)
Navigation.exp_magic()
Inputs.click(*coords.EM_POW_BOX)
Inputs.send_string(str(m_power))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_CAP_BOX)
Inputs.send_string(str(m_cap))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_BAR_BOX)
Inputs.send_string(str(m_bars))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_POW_BUY)
Inputs.click(*coords.EM_CAP_BUY)
Inputs.click(*coords.EM_BAR_BUY)
Stats.set_value_with_ocr("XP")
total_spent = coords.EPOWER_COST * e_power + coords.ECAP_COST * e_cap + coords.EBAR_COST * e_bars
total_spent += coords.MPOWER_COST * m_power + coords.MCAP_COST * m_cap + coords.MBAR_COST * m_bars
if self.report:
print("Spent XP:{:^8}".format(Helper.human_format(total_spent)))
print(
"Energy | Pow:{:^8}{:^3}Cap:{:^8}{:^3}Bar:{:^8}{:^3}Magic | Pow:{:^8}{:^3}Cap:{:^8}{:^3}Bar:{:^8}"
.format(Helper.human_format(e_power), "|",
Helper.human_format(e_cap), "|",
Helper.human_format(e_bars), "|",
Helper.human_format(m_power), "|",
Helper.human_format(m_cap), "|",
Helper.human_format(m_bars)))
def buy(self):
"""Buy upgrades for hack energy
Requires the confirmation popup button for EXP purchases in settings
to be turned OFF.
This uses all available exp, so use with caution.
"""
if (self.hcap < 10000 or self.hcap % 250 != 0) and self.hcap != 0:
print("Ecap value not divisible by 250 or lower than 10000, not" +
" spending exp.")
return
Stats.set_value_with_ocr("XP")
if Stats.OCR_failed:
print('OCR failed, exiting upgrade routine.')
return
current_exp = Stats.xp
total_price = coords.HPOWER_COST * self.hpower + coords.HCAP_COST * self.hcap + coords.HBAR_COST * self.hbar
# Skip upgrading if we don't have enough exp to buy at least one
# complete set of upgrades, in order to maintain our perfect ratios :)
if total_price > current_exp:
if self.report:
print("No XP Upgrade :{:^8} of {:^8}".format(
Helper.human_format(current_exp),
Helper.human_format(total_price)))
return
amount = int(current_exp // total_price)
h_power = amount * self.hpower
h_cap = amount * self.hcap
h_bars = amount * self.hbar
Navigation.exp_hack()
Inputs.click(*coords.EM_POW_BOX)
Inputs.send_string(str(h_power))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_CAP_BOX)
Inputs.send_string(str(h_cap))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_BAR_BOX)
Inputs.send_string(str(h_bars))
time.sleep(userset.MEDIUM_SLEEP)
if h_power > 0:
Inputs.click(*coords.EM_POW_BUY)
if h_cap > 0:
Inputs.click(*coords.EM_CAP_BUY)
if h_bars > 0:
Inputs.click(*coords.EM_BAR_BUY)
Stats.set_value_with_ocr("XP")
total_spent = coords.HPOWER_COST * h_power + coords.HCAP_COST * h_cap + coords.HBAR_COST * h_bars
if self.report:
print("Spent XP:{:^8}".format(Helper.human_format(total_spent)))
print("New | Pow:{:^8}{:^3}Cap:{:^8}{:^3}Bar:{:^8}".format(
Helper.human_format(h_power), "|", Helper.human_format(h_cap),
"|", Helper.human_format(h_bars)))
def buy(self):
"""Buy upgrades for power, toughness, health and regen
Requires the confirmation popup button for EXP purchases in settings
to be turned OFF.
This uses all available exp, so use with caution.
"""
Stats.set_value_with_ocr("XP")
if Stats.OCR_failed:
print('OCR failed, exiting upgrade routine.')
return
current_exp = Stats.xp
total_price = (coords.APOWER_COST * self.power * self.ratio)
total_price += (coords.ATOUGHNESS_COST * self.toughness * self.ratio)
total_price += (coords.AHEALTH_COST * self.health * 10)
total_price += math.floor(coords.AREGEN_COST * self.regen / 10)
# Skip upgrading if we don't have enough exp to buy at least one
# complete set of upgrades, in order to maintain our perfect ratios :)
if total_price > current_exp:
if self.report:
print("No XP Upgrade :{:^8} of {:^8}".format(
Helper.human_format(current_exp),
Helper.human_format(total_price)))
return
amount = int(current_exp // total_price)
a_power = amount * self.ratio
a_toughness = amount * self.ratio
a_health = amount * 10
a_regen = math.floor(amount / 10)
if a_regen < 1: a_regen = 1.0
Navigation.exp_adventure()
Inputs.click(*coords.EM_ADV_BOX)
Inputs.send_string(str(a_power))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_POW_BOX)
Inputs.send_string(str(a_toughness))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_CAP_BOX)
Inputs.send_string(str(a_health))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_BAR_BOX)
Inputs.send_string(str(a_regen))
time.sleep(userset.MEDIUM_SLEEP)
Inputs.click(*coords.EM_ADV_BUT)
Inputs.click(*coords.EM_POW_BUY)
Inputs.click(*coords.EM_CAP_BUY)
Inputs.click(*coords.EM_BAR_BUY)
Stats.set_value_with_ocr("XP")
total_spent = coords.APOWER_COST * a_power
total_spent += coords.ATOUGHNESS_COST * a_toughness
total_spent += coords.AHEALTH_COST * a_health
total_spent += coords.AREGEN_COST * a_regen
if self.report:
print("Spent XP:{:^8}".format(Helper.human_format(total_spent)))
print(
"Power:{:^8}{:^3} Defense:{:^8}{:^3} Health:{:^8}{:^3} Regen:{:^8}"
.format(Helper.human_format(a_power), "|",
Helper.human_format(a_toughness), "|",
Helper.human_format(a_health), "|",
Helper.human_format(a_regen)))
def save(data, profile, folder):
stats, bio, ribbon = Stats.get_all_season(profile)
for i in range(len(data)):
sheet = Storyboard.draw_sheet(data[i], i, stats, bio, ribbon)
file_name = Files.get_file_name(bio['name'], str(i))
Files.save(sheet, folder, file_name)
pd.options.mode.chained_assignment = None
from classes.preprocessing import Preprocessing
from classes.stats import Stats
if __name__ == '__main__':
# ************************************************** #
# PREPROCESSING OF THE DATASET #
# ************************************************** #
dir = os.path.dirname(os.path.realpath(__file__))
dataset = pd.read_csv(dir + '/dataset/IMDBDataset.csv')
dataset_orig = dataset.copy()
stats = Stats()
prep = Preprocessing(dataset)
# Make a dictionary by tokenizing all words in the dataset
prep.make_dictionary()
# Encode all words with integer IDs
# Encode only the most used words in the dataset, any other words encode as 0
n_top_used_words = 10000
dataset = prep.encode_dataset_column(df=dataset,
field="review",
use_top_words=n_top_used_words)
# Encode target variables to binary representation
dataset = prep.string_to_int(
df=dataset, params={"sentiment": {