def remove_punctuation(table: str, column: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
remove = RemovePunctuation()
dataframe = download.visit(dataframe)
dataframe = remove.visit(dataframe)
upload.visit(dataframe)
def condense_simple(table: str, column: str, numeric_feature: str = "median"):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
condense_simple = CondenseSimple(column, numeric_feature)
dataframe = download.visit(dataframe)
dataframe = condense_simple.visit(dataframe)
upload.visit(dataframe)
def maxabsscaler(table: str, column: str, copy: bool = True):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
scaler = MaxAbsScaler(copy)
dataframe = download.visit(dataframe)
dataframe = scaler.visit(dataframe)
upload.visit(dataframe)
def mask(table: str, column: str, condition: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
mask = Mask(condition, column)
dataframe = download.visit(dataframe)
dataframe = mask.visit(dataframe)
upload.visit(dataframe)
def uppercase(table: str, column: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
uppercase = UpperCase()
dataframe = download.visit(dataframe)
dataframe = uppercase.visit(dataframe)
upload.visit(dataframe)
def ngram(table: str, column: str, value: int):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
ngram = NGram(n_gram_value=value)
dataframe = download.visit(dataframe)
dataframe = ngram.visit(dataframe)
upload.visit(dataframe)
def fillempty(table: str, column: str, feature_type: str, value: float):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
fillempty = FillEmptyCells(column, feature_type, value)
dataframe = download.visit(dataframe)
dataframe = fillempty.visit(dataframe)
upload.visit(dataframe)
def remove_character(table: str, column: str, char: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
remove = RemoveChar(char=char)
dataframe = download.visit(dataframe)
dataframe = remove.visit(dataframe)
upload.visit(dataframe)
def text_binary(table: str, column: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
binary = TextToBinary(column=column)
dataframe = download.visit(dataframe)
dataframe = binary.visit(dataframe)
upload.visit(dataframe)
def stem(table: str, column: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
stem = Stemmer()
dataframe = download.visit(dataframe)
dataframe = stem.visit(dataframe)
upload.visit(dataframe)
def mean_word(table: str, column: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
word = MeanWord(column=column)
dataframe = download.visit(dataframe)
dataframe = word.visit(dataframe)
upload.visit(dataframe)
def start_number(table: str, column: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
number = StartWithNumber(column=column)
dataframe = download.visit(dataframe)
dataframe = number.visit(dataframe)
upload.visit(dataframe)
def join(table: str, column: str, char: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
join = JoinOperation(value=char)
dataframe = download.visit(dataframe)
dataframe = join.visit(dataframe)
upload.visit(dataframe)
def character_sum(table: str, column: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
sum = CharacterSum(column=column)
dataframe = download.visit(dataframe)
dataframe = sum.visit(dataframe)
upload.visit(dataframe)
def normalize(table: str, column: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
normalize = Normalizer()
dataframe = download.visit(dataframe)
dataframe = normalize.visit(dataframe)
upload.visit(dataframe)
def labelencode(table: str, column: str, mode: str = "shuffle"):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
encode = LabelEncoder(mode, column)
dataframe = download.visit(dataframe)
dataframe = encode.visit(dataframe)
upload.visit(dataframe)
def lemmatize(table: str, column: str):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
lemmatize = Lemmatizer()
dataframe = download.visit(dataframe)
dataframe = lemmatize.visit(dataframe)
upload.visit(dataframe)
def interpolate(table: str, column: str, method: str = "linear"):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
interpolate = Interpolate(method)
dataframe = download.visit(dataframe)
dataframe = interpolate.visit(dataframe)
upload.visit(dataframe)
def sort(table: str, column: str, mode: str = "shuffle"):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
sort = Sort(mode, column)
dataframe = download.visit(dataframe)
dataframe = sort.visit(dataframe)
upload.visit(dataframe)
def minmaxscaler(table: str,
column: str,
feature_range: bytearray = (0, 1),
copy: bool = True):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
scaler = MinMaxScaler(feature_range, copy)
dataframe = download.visit(dataframe)
dataframe = scaler.visit(dataframe)
upload.visit(dataframe)
def split(table: str, column: str, id_split: dict, mode: str = "sequential"):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
split = Split(id_split, mode)
dataframe = download.visit(dataframe)
# Return Dict of Feature sets
# {name, data}
dataframes = split.visit(dataframe)
upload.visit(dataframes)
def standardscale(table: str,
column: str,
copy: bool = True,
with_mean: bool = True,
with_std=True):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
scaler = StandardScaler(copy, with_mean, with_std)
dataframe = download.visit(dataframe)
dataframe = scaler.visit(dataframe)
upload.visit(dataframe)
def labelbinarize(table: str,
column: str,
neg_label: int = 0,
pos_label: int = 1,
sparse_output: bool = False):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
binarize = LabelBinarizer(neg_label, pos_label, sparse_output)
dataframe = download.visit(dataframe)
dataframe = binarize.visit(dataframe)
upload.visit(dataframe)
def onehot(table: str,
column: str,
categories: str = "auto",
sparse: bool = True,
n_values: str = "auto",
categorical_features: str = "all"):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
onehot = OneHotEncoder(categories, sparse, n_values, categorical_features)
dataframe = download.visit(dataframe)
dataframe = onehot.visit(dataframe)
upload.visit(dataframe)
def condense(table: str,
column: str,
sequential: bool = False,
numeric_feature: str = "median",
save_index: bool = True,
string_feature: str = "join"):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
condense = Condense(column, sequential, numeric_feature, save_index,
string_feature)
dataframe = download.visit(dataframe)
dataframe = condense.visit(dataframe)
upload.visit(dataframe)
def nl_processor(table: str,
column: str,
extraction_target: str = "word",
extraction_type: str = "bow",
measure: str = None,
n_gram: bytearray = None):
dataframe = Dataframe()
download = LoadFromDatabase(table=table, column=column)
upload = LoadToDatabase(table=table, column=column)
processor = NaturalLanguageProcessor(column, extraction_target,
extraction_type, measure, n_gram)
dataframe = download.visit(dataframe)
dataframe = processor.visit(dataframe)
upload.visit(dataframe)