You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi,
I try autoxgb but very quickly it returns that error:
2022-03-08 09:22:21.269 | INFO | autoxgb.autoxgb:post_init:42 - Output directory: output2
2022-03-08 09:22:21.276 | WARNING | autoxgb.autoxgb:post_init:49 - No id column specified. Will default to id.
2022-03-08 09:22:21.283 | INFO | autoxgb.autoxgb:_process_data:149 - Reading training data
/usr/local/lib/python3.7/dist-packages/pandas/io/common.py in get_handle(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)
583
584 # read_csv does not know whether the buffer is opened in binary/text mode
--> 585 if _is_binary_mode(path_or_buf, mode) and "b" not in mode:
586 mode += "b"
587
/usr/local/lib/python3.7/dist-packages/pandas/io/common.py in _is_binary_mode(handle, mode)
960 # classes that expect bytes
961 binary_classes = (BufferedIOBase, RawIOBase)
--> 962 return isinstance(handle, binary_classes) or "b" in getattr(handle, "mode", mode)
TypeError: argument of type 'method' is not iterable
Should be because the train_filename is of type str and represents the input path of the csv file. You passed in a dataframe instead so it threw this error.
Hi,
I try autoxgb but very quickly it returns that error:
2022-03-08 09:22:21.269 | INFO | autoxgb.autoxgb:post_init:42 - Output directory: output2
2022-03-08 09:22:21.276 | WARNING | autoxgb.autoxgb:post_init:49 - No id column specified. Will default to
id
.2022-03-08 09:22:21.283 | INFO | autoxgb.autoxgb:_process_data:149 - Reading training data
TypeError Traceback (most recent call last)
in ()
37 fast=fast,
38 )
---> 39 axgb.train()
10 frames
/usr/local/lib/python3.7/dist-packages/autoxgb/autoxgb.py in train(self)
244
245 def train(self):
--> 246 self._process_data()
247 best_params = train_model(self.model_config)
248 logger.info("Training complete")
/usr/local/lib/python3.7/dist-packages/autoxgb/autoxgb.py in _process_data(self)
148 def _process_data(self):
149 logger.info("Reading training data")
--> 150 train_df = pd.read_csv(self.train_filename)
151 train_df = reduce_memory_usage(train_df)
152 problem_type = self._determine_problem_type(train_df)
/usr/local/lib/python3.7/dist-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs)
309 stacklevel=stacklevel,
310 )
--> 311 return func(*args, **kwargs)
312
313 return wrapper
/usr/local/lib/python3.7/dist-packages/pandas/io/parsers/readers.py in read_csv(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, error_bad_lines, warn_bad_lines, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options)
584 kwds.update(kwds_defaults)
585
--> 586 return _read(filepath_or_buffer, kwds)
587
588
/usr/local/lib/python3.7/dist-packages/pandas/io/parsers/readers.py in _read(filepath_or_buffer, kwds)
480
481 # Create the parser.
--> 482 parser = TextFileReader(filepath_or_buffer, **kwds)
483
484 if chunksize or iterator:
/usr/local/lib/python3.7/dist-packages/pandas/io/parsers/readers.py in init(self, f, engine, **kwds)
809 self.options["has_index_names"] = kwds["has_index_names"]
810
--> 811 self._engine = self._make_engine(self.engine)
812
813 def close(self):
/usr/local/lib/python3.7/dist-packages/pandas/io/parsers/readers.py in _make_engine(self, engine)
1038 )
1039 # error: Too many arguments for "ParserBase"
-> 1040 return mapping[engine](self.f, **self.options) # type: ignore[call-arg]
1041
1042 def _failover_to_python(self):
/usr/local/lib/python3.7/dist-packages/pandas/io/parsers/c_parser_wrapper.py in init(self, src, **kwds)
49
50 # open handles
---> 51 self._open_handles(src, kwds)
52 assert self.handles is not None
53
/usr/local/lib/python3.7/dist-packages/pandas/io/parsers/base_parser.py in _open_handles(self, src, kwds)
227 memory_map=kwds.get("memory_map", False),
228 storage_options=kwds.get("storage_options", None),
--> 229 errors=kwds.get("encoding_errors", "strict"),
230 )
231
/usr/local/lib/python3.7/dist-packages/pandas/io/common.py in get_handle(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)
583
584 # read_csv does not know whether the buffer is opened in binary/text mode
--> 585 if _is_binary_mode(path_or_buf, mode) and "b" not in mode:
586 mode += "b"
587
/usr/local/lib/python3.7/dist-packages/pandas/io/common.py in _is_binary_mode(handle, mode)
960 # classes that expect bytes
961 binary_classes = (BufferedIOBase, RawIOBase)
--> 962 return isinstance(handle, binary_classes) or "b" in getattr(handle, "mode", mode)
TypeError: argument of type 'method' is not iterable
Don't know why..??? Thank you all for your help
My code:
from autoxgb import AutoXGB
required parameters:
train_filename = df.iloc[:round(df.shape[0]*.8)]
output = "output2"
optional parameters
test_filename = None
task = None
idx = df.index
targets = ["Goal"]
features = None
categorical_features = None
use_gpu = False
num_folds = 5
seed = 42
num_trials = 100
time_limit = 360
fast = False
Now its time to train the model!
axgb = AutoXGB(
train_filename=train_filename,
output=output,
test_filename=test_filename,
task=task,
idx=idx,
targets=targets,
features=features,
categorical_features=categorical_features,
use_gpu=use_gpu,
num_folds=num_folds,
seed=seed,
num_trials=num_trials,
time_limit=time_limit,
fast=fast,
)
axgb.train()
The text was updated successfully, but these errors were encountered: