load_from_tsfile#
- load_from_tsfile(full_file_path_and_name, replace_missing_vals_with='NaN', return_y=True, return_data_type='nested_univ', encoding='utf-8')[source]#
Load time series .ts file into X and (optionally) y.
Data from a .ts file is loaded into a nested pd.DataFrame, or optionally into a 2d np.ndarray (equal length, univariate problem) or 3d np.ndarray (equal length, multivariate problem) if requested. If present, y is loaded into a 1d np.ndarray.
- Parameters:
- full_file_path_and_namestr
The full pathname and file name of the .ts file to read.
- replace_missing_vals_withstr, default NaN
The value that missing values in the text file should be replaced with prior to parsing.
- return_yboolean, default True
whether to return the y variable, if it is present.
- return_data_typestr, optional, default = “nested_univ”
memory data format specification to return X in. str can be any other supported Panel mtype
for list of mtypes, see datatypes.SCITYPE_REGISTER for specifications, see examples/AA_datatypes_and_datasets.ipynb
- commonly used specifications:
“nested_univ: nested pd.DataFrame, pd.Series in cells “numpy3D”/”numpy3d”/”np3D”: 3D np.ndarray (instance, variable, time index) “numpy2d”/”np2d”/”numpyflat”: 2D np.ndarray (instance, time index) “pd-multiindex”: pd.DataFrame with 2-level (instance, time) MultiIndex
Exception is raised if the data cannot be stored in the requested type.
- encoding: str
encoding is the name of the encoding used to read file using the open function.
- Returns:
- Xsktime compatible in-memory container of mtype return_data_type
for list of mtypes, see datatypes.SCITYPE_REGISTER for specifications, see examples/AA_datatypes_and_datasets.ipynb
- yreturned only if return_y=True, np.ndarray
- Raises:
- IOError if the requested file does not exist
- IOError if input series are not all the same dimension (not supported)
- IOError if class labels have been requested but are not present in the file
- IOError if the input file has no cases
- ValueError if return_data_type = numpy3d but the data are unequal length series
- ValueError if return_data_type = numpy2d but the data are multivariate and/
- or unequal length series