Untitled

 avatar
unknown
plain_text
2 years ago
2.4 kB
22
Indexable
# Preprocess data - 1

---------------------------------------------------------------------------------------------------------------------------------------------------

# Preprocess data - 2
# clean_data - 1

---------------------------------------------------------------------------------------------------------------------------------------------------

# Preprocess data - 3
# clean_data - 2
    # lowercase_text - 1
    # remove_punctuation - 2

---------------------------------------------------------------------------------------------------------------------------------------------------

# Preprocess data - 4
def preprocess_data(dataset):
    # clean_data - 3
        # lowercase_text - 1
        # remove_punctuation - 2

---------------------------------------------------------------------------------------------------------------------------------------------------


# Preprocess data - 5
def preprocess_data(dataset):
    # clean_data - 4
    def clean_data(dataset):
        # lowercase_text - 3
        # remove_punctuation - 4

---------------------------------------------------------------------------------------------------------------------------------------------------

# Preprocess data - 6
def preprocess_data(dataset):
    # clean_data - 5
    def clean_data(dataset):
        # lowercase_text - 5
        def lowercase_text(dataset):
            pass
        # remove_punctuation - 6
        def remove_punctuation(dataset):
            pass

---------------------------------------------------------------------------------------------------------------------------------------------------

# Preprocess data - 7 (final)
def preprocess_data(dataset):
    def clean_data(dataset):
        def lowercase_text(dataset):
            # Transform text to lowercase - 7 (final)
            return dataset
        def remove_punctuation(dataset):
            # Remove punctuation from text - 8 (final)
            return dataset

      dataset = clean_data(dataset)
        return dataset

---------------------------------------------------------------------------------------------------------------------------------------------------

def preprocess_data(dataset):
    def clean_data(dataset):
        def lowercase_text(dataset):
            return dataset
        def remove_punctuation(dataset):
            return dataset

    dataset = clean_data(dataset)
    return dataset
Editor is loading...