def __init__(self, k=10, n=100, m=50):
Data.__init__(self)
self.k = k
self.m = m
self.means = rnd.uniform(mean_low, mean_high, (self.k, self.m))
self.divs = rnd.uniform(div_low, div_high, (self.k, self.m))
self.data, self.labels = self.generate_data(n)
def __init__2(self):
import numpy as np
iris = load_iris()
feature_vector = iris.data.tolist()
new_column1 = (len(feature_vector) /
2) * ["a"] + (len(feature_vector) / 2) * ["b"]
new_column2 = (len(feature_vector) /
2) * ["c"] + (len(feature_vector) / 2) * ["d"]
feature_vector = [[new_column2[i]] + feature_vector[i] +
[new_column1[i]] for i in range(len(feature_vector))]
feature_vector = np.array(feature_vector, dtype=object)
target_vector = [iris.target_names[i] for i in iris.target]
feature_names = iris.feature_names
feature_names.append("test")
feature_names.append("test2")
Data.__init__(self,
feature_vector,
target_vector,
feature_names,
name="Iris")
def __init__(self, headers, pdata, evals, evecs, means, filename=None):
Data.__init__(self)
self.eigenValues = evals
self.eigenVectors = evecs
self.dataMeans = means
self.dataHeaders = headers
self.matrix_data = pdata
# add to raw_headers and raw data types
for idx in range(len(headers)):
if idx > 9:
self.raw_headers.append("P%d" % (idx))
else:
self.raw_headers.append("P0%d" % (idx))
self.raw_types.append("numeric")
# print self.raw_headers
# add a numpy array to raw_data
self.raw_data = np.squeeze(np.asarray(pdata))
# add to header2raw and header2matrix
for index in range(len(self.raw_headers)):
self.header2raw[self.raw_headers[index]] = index
self.header2matrix[self.raw_headers[index]] = index
def __init__(self, ogDataHeaders, projectedData, eigenValues, eigenVectors, ogDataMeans):
Data.__init__(self)
self.eigenValues = eigenValues
self.eigenVectors = eigenVectors
self.meanDataValues = ogDataMeans
self.projectedHeaders = ogDataHeaders
self.matrix = projectedData
self.rawHeaders = ["P"+`i` for i in range(len(ogDataHeaders))]
def __init__(self):
wine = load_wine()
feature_vector = wine.data
target_vector = [wine.target_names[i] for i in wine.target]
feature_names = wine.feature_names
Data.__init__(self, feature_vector, target_vector, feature_names, name="Wine")
def __init__(self, projected_data, eigenvectors, eigenvalues,
original_means, data_headers):
Data.__init__(self)
self.data = projected_data
self.eigenvalues = eigenvalues
self.eigenvectors = eigenvectors
self.original_means = original_means
self.original_headers = data_headers
self.organize_stuff()
def __init__(self, args):
self.args = args
Data.__init__(self, self.args.input_file)
self.population = []
for _ in range(self.args.population_size):
self.population.append(Individual(self.items, self.args))
self.elite = Elite(self.args, list(self.items.keys()), self.population)
self.registry = Registry(self.elite)
self.runEvolutive()
def __init__(self, m_file, **kwargs):
self.surface = None
Data.__init__(self, m_file, **kwargs)
self.container = gwy.gwy_file_load(self.m_file, gwy.RUN_NONINTERACTIVE)
gwy.gwy_app_data_browser_add(self.container)
self.channel_id = gwy.gwy_app_data_browser_find_data_by_title(
self.container, "*SE*"
)[0]
gwy.gwy_app_data_browser_select_data_field(self.container, self.channel_id)
self.extract_meta(gwyddion.get_meta_ids(self.container)[0])
def __init__(self, m_file, **kwargs):
self.electrolyte = None
self.gas = None
self.surface = None
self.ph = None
self.re = ""
self.ce = None
self.we = None
self.ecell = None
self.icell = None
Data.__init__(self, m_file, **kwargs)
def __init__(self, data, headers, codebooks, codes, errors):
Data.__init__(self)
self.data = data
self.headers = headers
self.codebooks = codebooks
self.codes = codes
self.errors = errors
self.k = self.codebooks.shape[0]
self.N = self.codes.shape[0]
self.organize_stuff()
def __init__(self):
cancer = load_breast_cancer()
feature_vector = cancer.data
target_vector = [cancer.target_names[i] for i in cancer.target]
feature_names = cancer.feature_names
Data.__init__(self,
feature_vector,
target_vector,
feature_names,
name="BreastCancer")
def __init__(self):
iris = load_iris()
feature_vector = iris.data
target_vector = [iris.target_names[i] for i in iris.target]
feature_names = iris.feature_names
Data.__init__(self,
feature_vector,
target_vector,
feature_names,
name="Iris")
def __init__(self):
# Read data from file
df = pd.read_csv("../data/bank_note/data_banknote_authentication.csv", header=None)
# Add all columns as feature vector expect the target column
feature_vector = df.iloc[:, :-1].values
target_vector = df.iloc[:, -1].values
# Set the column names as the feature names
feature_names = ["variance of WTI", "skewness of WTI", "curtosis of Wavelet", "entropy of image"]
Data.__init__(self, feature_vector, target_vector, feature_names, name="BankNote")
def __init__(self):
feature_names = [
"Age", "Workclass", "fnlwgt", "Education", "Education-Num",
"Marital Status", "Occupation", "Relationship", "Race", "Sex",
"Capital Gain", "Capital Loss", "Hours per week", "Country"
]
data = pd.read_csv('../data/adult/adult.data',
na_values="NA",
names=feature_names + ["Salary"],
header=None).values
labels = data[:, 14]
Data.__init__(self, data[:, :-1], labels, feature_names, name="Adult")
def __init__(self, path):
# Read data from file
df = pd.read_csv(path)
# Add all columns as feature vector expect the target vector
feature_vector = df.iloc[:, 0:-1].values
# Get the last column as target vector
target_vector = df.iloc[:, -1].values
# Set the column names as the feature names
feature_names = list(df)[:-1]
Data.__init__(self, feature_vector, target_vector, feature_names)
def __init__(self):
print("Loading digits dataset!!!")
digits_data = load_digits()
feature_vector = digits_data.images.reshape(1797, 64)
target_vector = digits_data.target
feature_names = map(lambda index: str((index / 8, index % 8)),
range(64))
Data.__init__(self,
feature_vector,
target_vector,
feature_names,
name="Digits")
print("\tDone!!")
def __init__(self,base,quote):
self.base = base
self.quote = quote
self.pair = self.base + '_' + self.quote
self.price = Poloniex.getPrice(self,self.pair)
Data.__init__(self)
Charter.__init__(self)
#Backtester.__init__(self)
#xmr = FX("BTC","XMR")
#xmr.saveChartData()
#xmr.chartCandles('7D')
#xmr.showChart()
def __init__(self):
# Read data from file
original_df = pd.read_csv("../data/housing/train.csv")
# Get the target vector
# Make the sale price discrete as ["low", "medium", "high"]
target_vector = self.split(original_df["SalePrice"].values)
df = original_df.drop(columns=["SalePrice"])
# Convert null values to string "NA"
df.fillna("NA", inplace=True)
# Merge two columns
df["Bathroom Amount"] = df["BsmtFullBath"] + df["FullBath"]
df["Toilet Amount"] = df["BsmtHalfBath"] + df["HalfBath"]
# Remove not needed columns
df.drop(columns=not_used_columns, inplace=True)
# Change values of the columns to make them more readable
for column_name in useful_categorical_columns.keys():
df[column_name] = df[column_name].map(
categorical_values[column_name])
for column_name in categorical_to_numerical.keys():
df[column_name] = df[column_name].map(
categorical_to_numerical[column_name])
# Convert to numerical values to int
df[useful_numerical_columns.keys() +
new_columns] = df[useful_numerical_columns.keys() +
new_columns].astype(int)
# Change column names to make them more readable
df.rename(columns=useful_numerical_columns, inplace=True)
df.rename(columns=useful_categorical_columns, inplace=True)
feature_vector = df.values
# Set the column names as the feature names
feature_names = list(df)
Data.__init__(self,
feature_vector,
target_vector,
feature_names,
name="Housing")
def __init__(self, m_file, **kwargs):
self.surface = None
self.tip = None
Data.__init__(self, m_file, **kwargs)
self.set_settings()
self.container = gwy.gwy_file_load(self.m_file, gwy.RUN_NONINTERACTIVE)
gwy.gwy_app_data_browser_add(self.container)
self.img_topo_fwd = None
self.img_topo_bwd = None
self.topo_fwd_ch = self.return_topo_fwd_ch()
self.topo_bwd_ch = self.return_topo_bwd_ch()
self.size = None
self.rotation = None
self.line_time = None
self.bias = None
self.current = None
self.xoffset = None
self.yoffset = None
self.scan_duration = None
self.extract_meta(gwyddion.get_meta_ids(self.container)[0])
def __init__(self):
# Read data from file
df = pd.read_csv("../data/abalone/abalone.data", header=None)
# Add all columns as feature vector expect the age and sex
feature_vector = df.iloc[:, 1:-1].values
# Make the sale price discrete as ["young","old"]
target_vector = self.split(df.iloc[:, -1].values)
# Set the column names as the feature names
feature_names = [
"length", "diameter", "height", "whole weight", "shucked weight",
"viscera weight", "shell weight"
]
Data.__init__(self,
feature_vector,
target_vector,
feature_names,
name="Abalone")
def __init__(self, args):
logging.info('==================> Started Stamp-Finder <==================')
Data.__init__(self, args)
# See if a quick run is wanted.
if not self.quick:
Q = raw_input('\nDo you want to skip Hashing for faster run? [yN] ')
if Q == ('y' or 'Y'):
self.quick = True
self.create_files()
if not self.quick:
self.Main_hash()
self.sfinder()
if not self.quick:
self.Main_hash(final=True)
return
def __init__(self, filename, varname, levellist=None, **kwargs):
"""
Data4D class
This class implements the functionality to generate Data4D objekt.
EXAMPLES
========
"""
self.levellist = {}
if not levellist is None:
level = 0
for k in levellist:
self.levellist[int(k)] = level
level += 1
self.data4D = []
Data.__init__(self, filename, varname, **kwargs)
self.mulc(self.scale_factor, copy=False)
def __init__(self, filename, varname, levellist=None, **kwargs):
"""
Data4D class
This class implements the functionality to generate Data4D objekt.
EXAMPLES
========
"""
self.levellist = {}
if not levellist is None:
level = 0
for k in levellist:
self.levellist[int(k)] = level
level += 1
self.data4D = []
Data.__init__(self, filename, varname, **kwargs)
self.mulc(self.scale_factor, copy=False)
def __init__(self, args):
logging.info(
'==================> Started Stamp-Finder <==================')
Data.__init__(self, args)
# See if a quick run is wanted.
if not self.quick:
Q = raw_input(
'\nDo you want to skip Hashing for faster run? [yN] ')
if Q == ('y' or 'Y'):
self.quick = True
self.create_files()
if not self.quick:
self.Main_hash()
self.sfinder()
if not self.quick:
self.Main_hash(final=True)
return
def __init__(self):
basedir = "../data/"
feature_names = [
"weight", "food_time", "food_cho", "a1_start", "a1_duration_hrs",
"a1_hrs_after_food", "a1_end", "a2_start", "a2_duration_hrs",
"a2_hrs_after_food", "a2_end", "before_food_hyper",
"before_food_hypo", "patient_adolescent", "patient_adult",
"patient_child", "food_name_apple", "food_name_banana",
"food_name_bread_milk", "food_name_cookie",
"food_name_french_fries", "food_name_hamburger_meal",
"food_name_juice_nuts", "food_name_milk_crackers",
"food_name_peach", "food_name_rice_beans",
"food_name_strawberries", "food_name_watermelon", "food_type_meal",
"food_type_snack", "a1_type_0", "a1_type_activity",
"a1_type_sports", "a1_name_0", "a1_name_bicycling_16kph",
"a1_name_chores", "a1_name_dancing", "a1_name_mopping",
"a1_name_mountain_climbing", "a1_name_running", "a1_name_swimming",
"a1_name_walking", "a2_type_0", "a2_type_activity",
"a2_type_sports", "a2_name_0", "a2_name_dancing",
"a2_name_skating", "a2_name_walking"
]
# list(genfromtxt(basedir + 'diabetes_model_feature_names.csv', delimiter=';'))
data = genfromtxt(basedir + 'diabetes_model_x_train.csv',
delimiter=';')
labels = genfromtxt(basedir + 'diabetes_model_y_train.csv',
delimiter=';')
label_names = ['hyper', 'hypo', 'ok']
labels = [label_names[np.argmax(v)] for v in labels]
# data = pd.read_csv('../data/diabetes_model_x_train.csv', na_values="NA", names=feature_names,
# header=None).values
# labels = pd.read_csv('../data/diabetes_model_x_train.csv', na_values="NA", names=['label'],
# header=None).values
Data.__init__(self, data, labels, feature_names, name="Diabetes")
def __init__(self, name=None, description='', kind=None, **kwargs):
Data.__init__(self, name=name, description=description, type=kind)
return
def __init__(self, username, password, url, description): self.username = username self.password = password self.url = url Data.__init__(self, description)
def __init__(self, path_to_data):
start_epoch = 0 # seconds
end_epoch = 1.25 # seconds
sample_rate = 200
Data.__init__(self, path_to_data, start_epoch, end_epoch, sample_rate)
def __init__(self, name=None, description='', kind=None, **kwargs):
Data.__init__(self, name=name, description=description, type=kind)
return
def __init__(self, m_file, **kwargs):
Data.__init__(self, m_file, **kwargs)
def __init__(self, ratings=RATINGS, entity_names=MOVIE_NAMES, debug=False, load_previous=False):
Data.__init__(self, ratings=ratings, entity_names=entity_names, debug=debug, load_previous=load_previous)
def __init__(self, dataset,features):
Data.__init__(self)
self.features = features
self.dataset = dataset
self._compute_features_dataset(dataset)
def __init__(self, x, y, test_ratio=0.1, val_ratio=0.0, k_fold=0, shuffle=True, threshold=0):
Data.__init__(self, x, y, test_ratio, val_ratio, k_fold, shuffle)
self.threshold = threshold
self.vocabulary = {self.UNDEF_WORD: 0}
self.preprocess()
