def __init__(self, root, split=TRAIN, validation_size=0.2):
dataset_path = os.path.join(root, self.name)
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00363/Dataset.zip'
download_unzip(url, dataset_path)
dataset_path = os.path.join(dataset_path, 'Dataset')
# The 5th variant has the most data
train_path = os.path.join(dataset_path, 'Training', 'Features_Variant_5.csv')
test_path = os.path.join(dataset_path, 'Testing', 'Features_TestSet.csv')
df_train_valid = pd.read_csv(train_path, header=None)
df_test = pd.read_csv(test_path, header=None)
y_columns = df_train_valid.columns[-1:]
# Page ID is not included, but can be derived. Page IDs can not be
# in both training and validation sets
page_columns = list(range(29))
for i, (_, df_group) in enumerate(df_train_valid.groupby(page_columns)):
df_train_valid.loc[df_group.index, 'page_id'] = i
df_train, df_valid = split_df_on_column(df_train_valid, [1 - validation_size, validation_size], 'page_id')
df_train.drop(columns='page_id', inplace=True)
df_valid.drop(columns='page_id', inplace=True)
normalize_df_(df_train, other_dfs=[df_valid, df_test])
df_res = get_split(df_train, df_valid, df_test, split)
self.x, self.y = xy_split(df_res, y_columns)
def __init__(self, root, split=TRAIN, validation_size=0.2):
file_name = 'blogData_train.csv'
dataset_path = os.path.join(root, self.name)
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00304/BlogFeedback.zip'
download_unzip(url, dataset_path)
# Iterate all test csv and concatenate to one DataFrame
test_dfs = []
for fn in os.listdir(dataset_path):
if 'blogData_test' not in fn:
continue
file_path = os.path.join(dataset_path, fn)
test_dfs.append(pd.read_csv(file_path, header=None))
df_test = pd.concat(test_dfs)
file_path = os.path.join(dataset_path, file_name)
df_train_valid = pd.read_csv(file_path, header=None)
y_columns = [280]
df_train_valid[y_columns[0]] = np.log(df_train_valid[y_columns[0]] + 0.01)
df_test[y_columns[0]] = np.log(df_test[y_columns[0]] + 0.01)
page_columns = list(range(50))
for i, (_, df_group) in enumerate(df_train_valid.groupby(page_columns)):
df_train_valid.loc[df_group.index, 'page_id'] = i
df_train, df_valid = split_df_on_column(df_train_valid, [1 - validation_size, validation_size], 'page_id')
df_train.drop(columns='page_id', inplace=True)
df_valid.drop(columns='page_id', inplace=True)
normalize_df_(df_train, other_dfs=[df_valid, df_test])
df_res = get_split(df_train, df_valid, df_test, split)
self.x, self.y = xy_split(df_res, y_columns)
def __init__(self, root, split=TRAIN, validation_size=0.2):
dataset_path = os.path.join(root, self.name)
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00464/superconduct.zip'
download_unzip(url, dataset_path)
file_path = os.path.join(dataset_path, 'train.csv')
df = pd.read_csv(file_path)
y_columns = ['critical_temp']
self.x, self.y = split_normalize_sequence(df, y_columns, validation_size, split, self.type_)
def __init__(self, root, split=TRAIN, validation_size=0.2):
dataset_path = os.path.join(root, self.name)
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00294/CCPP.zip'
download_unzip(url, dataset_path)
file_path = os.path.join(dataset_path, 'CCPP', 'Folds5x2_pp.xlsx')
df = pd.read_excel(file_path)
y_columns = ['PE'] # Not clear if this is the aim of the dataset
self.x, self.y = split_normalize_sequence(df, y_columns, validation_size, split, self.type_)
def __init__(self, root, split=TRAIN, validation_size=0.2):
dataset_path = os.path.join(root, self.name)
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank-additional.zip'
download_unzip(url, dataset_path)
file_path = os.path.join(dataset_path, 'bank-additional', 'bank-additional-full.csv')
df = pd.read_csv(file_path, sep=';')
y_columns = ['y']
one_hot_encode_df_(df, skip_columns=y_columns)
label_encode_df_(df, y_columns[0])
self.x, self.y = split_normalize_sequence(df, y_columns, validation_size, split, self.type_)
def __init__(self, root, split=TRAIN, validation_size=0.2):
dataset_path = os.path.join(root, self.name)
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00332/OnlineNewsPopularity.zip'
download_unzip(url, dataset_path)
file_path = os.path.join(dataset_path, 'OnlineNewsPopularity', 'OnlineNewsPopularity.csv')
df = pd.read_csv(file_path, )
df.drop(columns=['url', ' timedelta'], inplace=True)
y_columns = [' shares']
df[y_columns[0]] = np.log(df[y_columns[0]])
self.x, self. y = split_normalize_sequence(df, y_columns, validation_size, split, self.type_)
def __init__(self, root, split=TRAIN, validation_size=0.2):
dataset_path = os.path.join(root, self.name)
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00206/slice_localization_data.zip'
download_unzip(url, dataset_path)
file_name = 'slice_localization_data.csv'
file_path = os.path.join(dataset_path, file_name)
df = pd.read_csv(file_path)
# No patient should be in both train and test set
df_train_valid = deepcopy(df.loc[df.patientId < 80, :]) # Pandas complains if it is a view
df_test = deepcopy(df.loc[df.patientId >= 80, :]) # - " -
df_train, df_valid = split_df_on_column(df_train_valid, [1 - validation_size, validation_size], 'patientId')
y_columns = ['reference']
normalize_df_(df_train, other_dfs=[df_valid, df_test])
df_res = get_split(df_train, df_valid, df_test, split)
df_res = df_res.drop(columns='patientId')
self.x, self.y = xy_split(df_res, y_columns)
def __init__(self, root, split=TRAIN, validation_size=0.2):
dataset_path = os.path.join(root, self.name)
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00459/avila.zip'
download_unzip(url, dataset_path)
file_path_train = os.path.join(dataset_path, 'avila', 'avila-tr.txt')
file_path_test = os.path.join(dataset_path, 'avila', 'avila-ts.txt')
df_train_valid = pd.read_csv(file_path_train, header=None)
df_test = pd.read_csv(file_path_test, header=None)
y_columns = [10]
label_encode_df_([df_train_valid, df_test], y_columns[0]) # Assumes encoding will be identical for train/test
df_train, df_valid = split_classification_df(df_train_valid,
[1 - validation_size, validation_size],
y_columns[0])
normalize_df_(df_train, other_dfs=[df_valid, df_test], skip_column=y_columns[0])
df_res = get_split(df_train, df_valid, df_test, split)
self.x, self.y = xy_split(df_res, y_columns)
self.y = self.y[:, 0]
def __init__(self, root, split=TRAIN, validation_size=0.2):
dataset_path = os.path.join(root, self.name)
filename = 'AirQualityUCI.csv'
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00360/AirQualityUCI.zip'
download_unzip(url, dataset_path)
file_path = os.path.join(dataset_path, filename)
df = pd.read_csv(file_path, sep=';', parse_dates=[0, 1])
df.dropna(axis=0, how='all', inplace=True)
df.dropna(axis=1, how='all', inplace=True)
df.Date = (df.Date - df.Date.min()).astype('timedelta64[D]') # Days as int
df.Time = df.Time.apply(lambda x: int(x.split('.')[0])) # Hours as int
df['C6H6(GT)'] = df['C6H6(GT)'].apply(lambda x: float(x.replace(',', '.'))) # Target as float
# Some floats are given with ',' instead of '.'
df = df.applymap(lambda x: float(x.replace(',', '.')) if type(x) is str else x) # Target as float
df = df[df['C6H6(GT)'] != -200] # Drop all rows with missing target values
df.loc[df['CO(GT)'] == -200, 'CO(GT)'] = -10 # -200 means missing value, shifting this to be closer to
# the other values for this column
y_columns = ['C6H6(GT)']
self.x, self.y = split_normalize_sequence(df, y_columns, validation_size, split, self.type_)