def __init__(self, name, datasets, clog=None, fLOG=noLOG, path_to_images=".",
cache_file=None, progressbar=None, graphx=None, graphy=None, **params):
"""
@param name name of the test
@param datasets list of dictionary of dataframes
@param clog see @see cl CustomLog or string
@param fLOG logging function
@param params extra parameters
@param path_to_images path to images and intermediate results
@param cache_file cache file
@param progressbar relies on *tqdm*, example *tnrange*
@param graphx list of variables to use as X axis
@param graphy list of variables to use as Y axis
If *cache_file* is specified, the class will store the results of the
method :meth:`bench <pyquickhelper.benchhelper.benchmark.GridBenchMark.bench>`.
On a second run, the function load the cache
and run modified or new run (in *param_list*).
*datasets* should be a dictionary with dataframes a values
with the following keys:
* ``'X'``: features
* ``'Y'``: labels (optional)
"""
GridBenchMark.__init__(self, name=name, datasets=datasets, clog=clog, fLOG=fLOG,
path_to_images=path_to_images, cache_file=cache_file,
progressbar=progressbar, **params)
self._xaxis = graphx
self._yaxis = graphy
def __init__(self,
name,
datasets,
clog=None,
fLOG=noLOG,
path_to_images=".",
cache_file=None,
progressbar=None,
graphx=None,
graphy=None,
**params):
"""
@param name name of the test
@param datasets list of dictionary of dataframes
@param clog see @see cl CustomLog or string
@param fLOG logging function
@param params extra parameters
@param path_to_images path to images and intermediate results
@param cache_file cache file
@param progressbar relies on *tqdm*, example *tnrange*
@param graphx list of variables to use as X axis
@param graphy list of variables to use as Y axis
If *cache_file* is specified, the class will store the results of the
method :meth:`bench <pyquickhelper.benchhelper.benchmark.GridBenchMark.bench>`.
On a second run, the function load the cache
and run modified or new run (in *param_list*).
*datasets* should be a dictionary with dataframes a values
with the following keys:
* ``'X'``: features
* ``'Y'``: labels (optional)
"""
GridBenchMark.__init__(self,
name=name,
datasets=datasets,
clog=clog,
fLOG=fLOG,
path_to_images=path_to_images,
cache_file=cache_file,
progressbar=progressbar,
**params)
self._xaxis = graphx
self._yaxis = graphy
def preprocess_dataset(self, dsi, **params):
"""
Splits the dataset into train and test.
@param params additional parameters
@return dataset (like info), dictionary for metrics
"""
ds, appe, params = GridBenchMark.preprocess_dataset(
self, dsi, **params)
if "no_split" in ds:
no_split = ds["no_split"]
else:
no_split = False
if no_split:
self.fLOG("[MlGridBenchMark.preprocess_dataset] no split")
return (ds, ds), appe, params
else:
self.fLOG("[MlGridBenchMark.preprocess_dataset] split train test")
spl = ["X", "Y", "weight", "group"]
names = [_ for _ in spl if _ in ds]
if len(names) == 0:
raise Exception("No dataframe or matrix was found.")
mats = [ds[_] for _ in names]
pars = {"train_size", "test_size"}
options = {k: v for k, v in params.items() if k in pars}
for k in pars:
if k in params:
del params[k]
res = train_test_split(*mats, **options)
train = {}
for i, n in enumerate(names):
train[n] = res[i * 2]
test = {}
for i, n in enumerate(names):
test[n] = res[i * 2 + 1]
self.fLOG("[MlGridBenchMark.preprocess_dataset] done")
return (train, test), appe, params
def preprocess_dataset(self, dsi, **params):
"""
Splits the dataset into train and test.
@param params additional parameters
@return dataset (like info), dictionary for metrics
"""
ds, appe, params = GridBenchMark.preprocess_dataset(
self, dsi, **params)
if "no_split" in ds:
no_split = ds["no_split"]
else:
no_split = False
if no_split:
self.fLOG("[MlGridBenchMark.preprocess_dataset] no split")
return (ds, ds), appe, params
else:
self.fLOG("[MlGridBenchMark.preprocess_dataset] split train test")
spl = ["X", "Y", "weight", "group"]
names = [_ for _ in spl if _ in ds]
if len(names) == 0:
raise Exception("No dataframe or matrix was found.")
mats = [ds[_] for _ in names]
pars = {"train_size", "test_size"}
options = {k: v for k, v in params.items() if k in pars}
for k in pars:
if k in params:
del params[k]
res = train_test_split(*mats, **options)
train = {}
for i, n in enumerate(names):
train[n] = res[i * 2]
test = {}
for i, n in enumerate(names):
test[n] = res[i * 2 + 1]
self.fLOG("[MlGridBenchMark.preprocess_dataset] done")
return (train, test), appe, params