csverve.core package

Submodules

csverve.core.csverve_input module

class csverve.core.csverve_input.CsverveInput(filepath: str)[source]

Bases: object

property columns: List[str]

get the list of columns

Returns:

separator

property dtypes: Dict[str, str]

get the data types

Returns:

dtypes

property header: bool

True if file has header

Returns:

header

read_csv(chunksize: Optional[int] = None, usecols=None, dtype=None) → DataFrame[source]

Read CSV.

Parameters:

  • chunksize – Number of rows to read at a time (optional, applies to large datasets).

  • usecols – Restrict to specific columns (optional).

  • dtype – Override the dtypes on specific columns (optional).

Returns:

pandas DataFrame.

property separator: str

get the separator used

Returns:

separator

property yaml_file: str

Append ‘.yaml’ to CSV path.

Returns:

YAML metadata path.

csverve.core.csverve_output module

class csverve.core.csverve_output.CsverveOutput(filepath: str, dtypes: Dict[str, str], columns: List[str], skip_header: bool = False, na_rep: str = 'NaN', sep: str = ',')[source]

Bases: object

write_yaml() → None[source]

Write .yaml file.

Returns:

property yaml_file: str

Append ‘.yaml’ to CSV path.

Returns:

YAML metadata path.

csverve.core.csverve_output_data_frame module

class csverve.core.csverve_output_data_frame.CsverveOutputDataFrame(df: DataFrame, filepath: str, dtypes: Dict[str, str], skip_header: bool = False, na_rep: str = 'NaN', sep: str = ',')[source]

Bases: CsverveOutput

write_df() → None[source]

Write out dataframe to CSV.

Parameters:

  • df – Pandas DataFrames.

  • chunks – bool.

Returns:

csverve.core.csverve_output_file_stream module

class csverve.core.csverve_output_file_stream.CsverveOutputFileStream(filepath: str, dtypes: Dict[str, str], columns: List[str], skip_header: bool = False, na_rep: str = 'NaN', sep: str = ',')[source]

Bases: CsverveOutput

rewrite_csv(csvfile: str) → None[source]

Rewrite CSV. :param csvfile: Filepath of CSV file. :return:

write_data_streams(csvfiles: List[str]) → None[source]

Write data streams. :param csvfiles: List of CSV files paths. :return:

csverve.core.irregular_csv_input module

class csverve.core.irregular_csv_input.IrregularCsverveInput(filepath: str, dtypes: Dict[str, str], sep=',')[source]

Bases: object

get_columns() → List[str][source]

Detect whether file is tab or comma separated from header. :return: ‘ ‘, or ‘,’, or raise error if unable to detect separator.

read_csv(chunksize: Optional[int] = None) → DataFrame[source]

Read CSV.

Parameters:

chunksize – Number of rows to read at a time (optional, applies to large datasets).

Returns:

pandas DataFrame.

property yaml_file: str

Append ‘.yaml’ to CSV path.

Returns:

YAML metadata path.

Module contents