def test_suppress_validation():
X = np.array([0, np.inf])
assert_raises(ValueError, assert_all_finite, X)
sklearn.set_config(assume_finite=True)
assert_all_finite(X)
sklearn.set_config(assume_finite=False)
assert_raises(ValueError, assert_all_finite, X)
def test_changed_only():
# Make sure the changed_only param is correctly used
set_config(print_changed_only=True)
lr = LogisticRegression(C=99)
expected = """LogisticRegression(C=99)"""
assert lr.__repr__() == expected
# Check with a repr that doesn't fit on a single line
lr = LogisticRegression(C=99, class_weight=.4, fit_intercept=False,
tol=1234, verbose=True)
expected = """
LogisticRegression(C=99, class_weight=0.4, fit_intercept=False, tol=1234,
verbose=True)"""
expected = expected[1:] # remove first \n
assert lr.__repr__() == expected
imputer = SimpleImputer(missing_values=0)
expected = """SimpleImputer(missing_values=0)"""
assert imputer.__repr__() == expected
# Defaults to np.NaN, trying with float('NaN')
imputer = SimpleImputer(missing_values=float('NaN'))
expected = """SimpleImputer()"""
assert imputer.__repr__() == expected
set_config(print_changed_only=False)
def test_changed_only():
# Make sure the changed_only param is correctly used
set_config(print_changed_only=True)
lr = LogisticRegression(C=99)
expected = """LogisticRegression(C=99)"""
assert lr.__repr__() == expected
# Check with a repr that doesn't fit on a single line
lr = LogisticRegression(C=99, class_weight=.4, fit_intercept=False,
tol=1234, verbose=True)
expected = """
LogisticRegression(C=99, class_weight=0.4, fit_intercept=False, tol=1234,
verbose=True)"""
expected = expected[1:] # remove first \n
assert lr.__repr__() == expected
imputer = SimpleImputer(missing_values=0)
expected = """SimpleImputer(missing_values=0)"""
assert imputer.__repr__() == expected
# Defaults to np.NaN, trying with float('NaN')
imputer = SimpleImputer(missing_values=float('NaN'))
expected = """SimpleImputer()"""
assert imputer.__repr__() == expected
# make sure array parameters don't throw error (see #13583)
repr(LogisticRegressionCV(Cs=np.array([0.1, 1])))
set_config(print_changed_only=False)
def prepare(self) -> None:
"""
Print library version, classifier type, training set description
"""
super().prepare()
# print libs' version
self.log.debug(f"[LIB VERSION] {np.__name__} : {np.__version__}")
self.log.debug(f"[LIB VERSION] {pd.__name__} : {pd.__version__}")
self.log.debug(
f"[LIB VERSION] {matplotlib.__name__} : {matplotlib.__version__}")
self.log.debug(
f"[LIB VERSION] {sklearn.__name__} : {sklearn.__version__}")
self.log.debug(
f"[LIB VERSION] {imblearn.__name__} : {imblearn.__version__}")
self.log.debug(f"[LIB VERSION] {scipy.__name__} : {scipy.__version__}")
# mode
self.log.info(
f"[MODE] Classifiers evaluation on test set ({Evaluator.__qualname__})"
)
# dataset description
self.log.debug(
f"[DESCRIPTION] Training set description:\n{self.training.set_.describe(include='all')}"
)
self.log.debug(
f"[DESCRIPTION] Test set description:\n{self.test.set_.describe(include='all')}"
)
# print all parameters for classifiers
set_config(print_changed_only=False)
def test_suppress_validation():
X = np.array([0, np.inf])
assert_raises(ValueError, assert_all_finite, X)
sklearn.set_config(assume_finite=True)
assert_all_finite(X)
sklearn.set_config(assume_finite=False)
assert_raises(ValueError, assert_all_finite, X)
def sklearn_disable_finiteness_check():
try:
sklearn.set_config(assume_finite=True)
except AttributeError:
try:
sklearn._ASSUME_FINITE = True
except AttributeError:
sklearn.utils.validation._assert_all_finite = lambda X: None
def test_config_context():
assert get_config() == {
"assume_finite": False,
"working_memory": 1024,
"print_changed_only": True,
"display": "text",
}
# Not using as a context manager affects nothing
config_context(assume_finite=True)
assert get_config()["assume_finite"] is False
with config_context(assume_finite=True):
assert get_config() == {
"assume_finite": True,
"working_memory": 1024,
"print_changed_only": True,
"display": "text",
}
assert get_config()["assume_finite"] is False
with config_context(assume_finite=True):
with config_context(assume_finite=None):
assert get_config()["assume_finite"] is True
assert get_config()["assume_finite"] is True
with config_context(assume_finite=False):
assert get_config()["assume_finite"] is False
with config_context(assume_finite=None):
assert get_config()["assume_finite"] is False
# global setting will not be retained outside of context that
# did not modify this setting
set_config(assume_finite=True)
assert get_config()["assume_finite"] is True
assert get_config()["assume_finite"] is False
assert get_config()["assume_finite"] is True
assert get_config() == {
"assume_finite": False,
"working_memory": 1024,
"print_changed_only": True,
"display": "text",
}
# No positional arguments
with pytest.raises(TypeError):
config_context(True)
# No unknown arguments
with pytest.raises(TypeError):
config_context(do_something_else=True).__enter__()
def __init__(self, ml_type):
warnings.filterwarnings("ignore")
self.max_features = 25
self.plt_h = 6
self.plt_cols = 2
sns.set_context("talk", font_scale=0.8)
plt.rcParams.update({'font.size': 20})
set_config(display='diagram')
pd.options.display.float_format = '{:,.3f}'.format
self.ml_type = ml_type
def test_config_context():
assert get_config() == {
'assume_finite': False,
'working_memory': 1024,
'print_changed_only': True,
'display': 'text'
}
# Not using as a context manager affects nothing
config_context(assume_finite=True)
assert get_config()['assume_finite'] is False
with config_context(assume_finite=True):
assert get_config() == {
'assume_finite': True,
'working_memory': 1024,
'print_changed_only': True,
'display': 'text'
}
assert get_config()['assume_finite'] is False
with config_context(assume_finite=True):
with config_context(assume_finite=None):
assert get_config()['assume_finite'] is True
assert get_config()['assume_finite'] is True
with config_context(assume_finite=False):
assert get_config()['assume_finite'] is False
with config_context(assume_finite=None):
assert get_config()['assume_finite'] is False
# global setting will not be retained outside of context that
# did not modify this setting
set_config(assume_finite=True)
assert get_config()['assume_finite'] is True
assert get_config()['assume_finite'] is False
assert get_config()['assume_finite'] is True
assert get_config() == {
'assume_finite': False,
'working_memory': 1024,
'print_changed_only': True,
'display': 'text'
}
# No positional arguments
assert_raises(TypeError, config_context, True)
# No unknown arguments
assert_raises(TypeError, config_context(do_something_else=True).__enter__)
def test_set_config():
assert get_config()["assume_finite"] is False
set_config(assume_finite=None)
assert get_config()["assume_finite"] is False
set_config(assume_finite=True)
assert get_config()["assume_finite"] is True
set_config(assume_finite=None)
assert get_config()["assume_finite"] is True
set_config(assume_finite=False)
assert get_config()["assume_finite"] is False
# No unknown arguments
with pytest.raises(TypeError):
set_config(do_something_else=True)
def single(self, *, array_out):
X, y = fetch_openml(data_id=1476, return_X_y=True, as_frame=True)
set_config(array_out=array_out)
pipe = make_pipeline(StandardScaler(), PCA(n_components=64),
SelectKBest(k=30), Ridge())
pipe.fit(X, y)
output = pipe[:-1].transform(X)
# sanity check
if array_out == 'pandas':
assert isinstance(output, pd.DataFrame)
elif array_out == 'xarray':
assert isinstance(output, xr.DataArray)
else: # default
assert isinstance(output, np.ndarray)
def setup(self, runtime, N, nf, opset, dtype, optim):
"asv API"
logger = getLogger('skl2onnx')
logger.disabled = True
register_converters()
register_rewritten_operators()
with open(self._name(nf, opset, dtype), "rb") as f:
stored = pickle.load(f)
self.stored = stored
self.model = stored['model']
self.X, self.y = make_n_rows(stored['X'], N, stored['y'])
onx, rt_, rt_fct_, rt_fct_track_ = self._create_onnx_and_runtime(
runtime, self.model, self.X, opset, dtype, optim)
self.onx = onx
setattr(self, "rt_" + runtime, rt_)
setattr(self, "rt_fct_" + runtime, rt_fct_)
setattr(self, "rt_fct_track_" + runtime, rt_fct_track_)
set_config(assume_finite=True)
def single(self, *, array_out, minmax_scalers):
n_features = 200
X, _ = make_regression(n_samples=300_000,
n_features=n_features,
random_state=42)
df = pd.DataFrame(X, columns=[f"col_{i}" for i in range(n_features)])
set_config(array_out=array_out)
pipe = make_pipeline(*[MinMaxScaler() for _ in range(minmax_scalers)])
output = pipe.fit_transform(df)
# sanity check
if array_out == 'pandas':
assert isinstance(output, pd.DataFrame)
elif array_out == 'xarray':
assert isinstance(output, xr.DataArray)
else: # default
assert isinstance(output, np.ndarray)
def test_set_config():
assert get_config()['assume_finite'] is False
set_config(assume_finite=None)
assert get_config()['assume_finite'] is False
set_config(assume_finite=True)
assert get_config()['assume_finite'] is True
set_config(assume_finite=None)
assert get_config()['assume_finite'] is True
set_config(assume_finite=False)
assert get_config()['assume_finite'] is False
# No unknown arguments
assert_raises(TypeError, set_config, do_something_else=True)
def test_set_config():
assert get_config()['assume_finite'] is False
set_config(assume_finite=None)
assert get_config()['assume_finite'] is False
set_config(assume_finite=True)
assert get_config()['assume_finite'] is True
set_config(assume_finite=None)
assert get_config()['assume_finite'] is True
set_config(assume_finite=False)
assert get_config()['assume_finite'] is False
# No unknown arguments
assert_raises(TypeError, set_config, do_something_else=True)
def main():
X_train, X_test, y_train, y_test = get_data()
lr, X_test_lr, y_test_lr = get_model_lr(X_train, X_test, y_train, y_test)
rf, X_test_rf, y_test_rf = get_model_rf(X_train, X_test, y_train, y_test)
lr_rf, X_test, y_test = get_model(X_train, X_test, y_train, y_test)
plot_compare_calibration([[lr, X_test_lr, y_test_lr, 'LR'],
[rf, X_test_rf, y_test_rf, 'RF'],
[lr_rf, X_test, y_test, 'RF + LR']])
plot_feature_transformation([[lr, X_test_lr, y_test_lr, 'LR'],
[rf, X_test_rf, y_test_rf, 'RF'],
[lr_rf, X_test, y_test, 'RF + LR']])
exit(0)
set_config(print_changed_only=True)
filename = 'finalized_model.sav'
joblib.dump(logistic_regression, filename)
def test_set_config():
assert_equal(get_config(), {'assume_finite': False})
set_config(assume_finite=None)
assert_equal(get_config(), {'assume_finite': False})
set_config(assume_finite=True)
assert_equal(get_config(), {'assume_finite': True})
set_config(assume_finite=None)
assert_equal(get_config(), {'assume_finite': True})
set_config(assume_finite=False)
assert_equal(get_config(), {'assume_finite': False})
# No unknown arguments
assert_raises(TypeError, set_config, do_something_else=True)
def test_config_context():
assert get_config() == {'assume_finite': False, 'working_memory': 1024,
'print_changed_only': False}
# Not using as a context manager affects nothing
config_context(assume_finite=True)
assert get_config()['assume_finite'] is False
with config_context(assume_finite=True):
assert get_config() == {'assume_finite': True, 'working_memory': 1024,
'print_changed_only': False}
assert get_config()['assume_finite'] is False
with config_context(assume_finite=True):
with config_context(assume_finite=None):
assert get_config()['assume_finite'] is True
assert get_config()['assume_finite'] is True
with config_context(assume_finite=False):
assert get_config()['assume_finite'] is False
with config_context(assume_finite=None):
assert get_config()['assume_finite'] is False
# global setting will not be retained outside of context that
# did not modify this setting
set_config(assume_finite=True)
assert get_config()['assume_finite'] is True
assert get_config()['assume_finite'] is False
assert get_config()['assume_finite'] is True
assert get_config() == {'assume_finite': False, 'working_memory': 1024,
'print_changed_only': False}
# No positional arguments
assert_raises(TypeError, config_context, True)
# No unknown arguments
assert_raises(TypeError, config_context(do_something_else=True).__enter__)
def test_ColumnTransformer():
import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.preprocessing import OneHotEncoder
from ML_in_business.hw6.TransformerLib import MyTempEncoder, tempEstimator
from sklearn import set_config
X = pd.DataFrame(
{'city': ['London', 'London', 'Paris', 'Sallisaw'],
'title': ["His Last Bow", "How Watson Learned the Trick", "A Moveable Feast", "The Grapes of Wrath"],
'expert_rating': [5, 3, 4, 5],
'user_rating': [4, 5, 4, 3]})
# column_trans = ColumnTransformer(
# [('city_category', OneHotEncoder(dtype='int'),['city']),
# ('title_bow', CountVectorizer(), 'title')],
# remainder='drop')
# column_trans= Pipeline([
# ('selector', MyTempEncoder())
# ])
column_trans = ColumnTransformer(
[
#('city_category', OneHotEncoder(dtype='int'),['city']),
('myEncoder', tempEstimator('AAAA'), ['title'])],
remainder='passthrough'
#remainder='drop'
)
#HTML representation of Pipeline
#set_config(display='diagram')
set_config(display='text')
column_trans
column_trans.fit_transform(X)
names = column_trans.get_feature_names()
arr = column_trans.transform(X)
assert True
def main(event, context):
# numpy
print("THIS IS FROM numpy!!!")
a = np.arange(15).reshape(3, 5)
print("Your numpy array:")
print(a)
# sklearn
print("THIS IS FROM sklearn!!!")
lr = LogisticRegression(penalty='l1')
print('Default representation:')
print(lr)
# LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
# intercept_scaling=1, l1_ratio=None, max_iter=100,
# multi_class='auto', n_jobs=None, penalty='l1',
# random_state=None, solver='warn', tol=0.0001, verbose=0,
# warm_start=False)
set_config(print_changed_only=True)
print('\nWith changed_only option:')
print(lr)
# LogisticRegression(penalty='l1')
#opencv
print("THIS IS FROM opencv!!!")
image = url_to_image(
"https://stickershop.line-scdn.net/stickershop/v1/product/3242305/LINEStorePC/main.png"
)
height, width, channels = image.shape[:3]
print("width: " + str(width))
print("height: " + str(height))
return {
'isBase64Encoded': False,
'statusCode': 200,
'headers': {},
'body': '{"message": "Hello from AWS Lambda"}'
}
def test_config_context():
assert_equal(get_config(), {'assume_finite': False})
# Not using as a context manager affects nothing
config_context(assume_finite=True)
assert_equal(get_config(), {'assume_finite': False})
with config_context(assume_finite=True):
assert_equal(get_config(), {'assume_finite': True})
assert_equal(get_config(), {'assume_finite': False})
with config_context(assume_finite=True):
with config_context(assume_finite=None):
assert_equal(get_config(), {'assume_finite': True})
assert_equal(get_config(), {'assume_finite': True})
with config_context(assume_finite=False):
assert_equal(get_config(), {'assume_finite': False})
with config_context(assume_finite=None):
assert_equal(get_config(), {'assume_finite': False})
# global setting will not be retained outside of context that
# did not modify this setting
set_config(assume_finite=True)
assert_equal(get_config(), {'assume_finite': True})
assert_equal(get_config(), {'assume_finite': False})
assert_equal(get_config(), {'assume_finite': True})
assert_equal(get_config(), {'assume_finite': False})
# No positional arguments
assert_raises(TypeError, config_context, True)
# No unknown arguments
assert_raises(TypeError, config_context(do_something_else=True).__enter__)
def single(self, *, array_out):
X, y = fetch_openml(data_id=1590, return_X_y=True, as_frame=True)
set_config(array_out=array_out)
cat_prep = make_pipeline(
SimpleImputer(fill_value='sk_missing', strategy='constant'),
OneHotEncoder(handle_unknown='ignore', sparse=False))
prep = make_column_transformer(
(StandardScaler(), make_column_selector(dtype_include='number')),
(cat_prep, make_column_selector(dtype_include='category')))
pipe = make_pipeline(prep, SelectKBest(),
DecisionTreeClassifier(random_state=42))
pipe.fit(X, y)
output = pipe[:-1].transform(X)
# sanity check
if array_out == 'pandas':
assert isinstance(output, pd.DataFrame)
elif array_out == 'xarray':
assert isinstance(output, xr.DataArray)
else: # default
assert isinstance(output, np.ndarray)
from skmultiflow.data.generator.multilabel_generator import MultilabelGenerator
from skmultiflow.data.generator.regression_generator import RegressionGenerator
from skmultiflow.meta.multi_output_learner import MultiOutputLearner
from skmultiflow.metrics.measure_collection import hamming_score
from sklearn.linear_model import SGDClassifier, SGDRegressor
from skmultiflow.utils.utils import get_next_n_samples
from sklearn import __version__ as sklearn_version
from sklearn.metrics import mean_absolute_error
from distutils.version import LooseVersion
from sklearn import set_config
import numpy as np
import pytest
# Force sklearn to show only the parameters whose default value have been changed when
# printing an estimator (backwards compatibility with versions prior to sklearn==0.23)
set_config(print_changed_only=True)
@pytest.mark.filterwarnings('ignore::UserWarning')
def test_multi_output_learner_classifier():
stream = MultilabelGenerator(n_samples=5150,
n_features=15,
n_targets=3,
n_labels=4,
random_state=112)
estimator = SGDClassifier(random_state=112, max_iter=10, loss='log')
classifier = MultiOutputLearner(base_estimator=estimator)
X, y = get_next_n_samples(stream, 150)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=0)
clf.fit(X_train, y_train)
print("model score: %.3f" % clf.score(X_test, y_test))
##############################################################################
# HTML representation of ``Pipeline``
###############################################################################
# When the ``Pipeline`` is printed out in a jupyter notebook an HTML
# representation of the estimator is displayed as follows:
from sklearn import set_config
set_config(display='diagram')
clf
###############################################################################
# Use ``ColumnTransformer`` by selecting column by data types
###############################################################################
# When dealing with a cleaned dataset, the preprocessing can be automatic by
# using the data types of the column to decide whether to treat a column as a
# numerical or categorical feature.
# :func:`sklearn.compose.make_column_selector` gives this possibility.
# First, let's only select a subset of columns to simplify our
# example.
subset_feature = ['embarked', 'sex', 'pclass', 'age', 'fare']
X_train, X_test = X_train[subset_feature], X_test[subset_feature]
from sklearn.base import BaseEstimator
from .bins import (atleast_2d, get_centers, get_grid, get_track_grid,
get_track_interior)
from .core import _acausal_decode, _causal_decode, mask
from .initial_conditions import uniform_on_track
from .misc import NumbaKDE
from .multiunit_likelihood import (estimate_multiunit_likelihood,
fit_multiunit_likelihood)
from .spiking_likelihood import (estimate_place_fields,
estimate_spiking_likelihood)
from .state_transition import CONTINUOUS_TRANSITIONS
logger = getLogger(__name__)
sklearn.set_config(print_changed_only=False)
_DEFAULT_CLUSTERLESS_MODEL_KWARGS = dict(
bandwidth=np.array([24.0, 24.0, 24.0, 24.0, 6.0, 6.0]))
_DEFAULT_TRANSITIONS = ['random_walk', 'uniform', 'identity']
class _DecoderBase(BaseEstimator):
def __init__(self,
place_bin_size=2.0,
replay_speed=40,
movement_var=0.05,
position_range=None,
transition_type='random_walk',
initial_conditions_type='uniform_on_track',
infer_track_interior=True):
searchindex_text = re.sub(r'{__call__.+?}', '{}', searchindex_text)
with open(searchindex_path, 'w') as f:
f.write(searchindex_text)
# Config for sphinx_issues
# we use the issues path for PRs since the issues URL will forward
issues_github_path = 'scikit-learn/scikit-learn'
def setup(app):
# to hide/show the prompt in code examples:
app.connect('build-finished', make_carousel_thumbs)
app.connect('build-finished', filter_search_index)
# The following is used by sphinx.ext.linkcode to provide links to github
linkcode_resolve = make_linkcode_resolve('sklearn',
'https://github.com/scikit-learn/'
'scikit-learn/blob/{revision}/'
'{package}/{path}#L{lineno}')
warnings.filterwarnings("ignore", category=UserWarning,
message='Matplotlib is currently using agg, which is a'
' non-GUI backend, so cannot show the figure.')
# Reduces the output of estimators
sklearn.set_config(print_changed_only=True)
target_train = penguins_train[target_column]
target_test = penguins_test[target_column]
# %% [markdown]
#
# The linear regression that we previously saw will predict a continuous
# output. When the target is a binary outcome, one can use the logistic
# function to model the probability. This model is known as logistic
# regression.
#
# Scikit-learn provides the class `LogisticRegression` which implements this
# algorithm.
# %%
import sklearn
sklearn.set_config(display="diagram")
# %%
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
logistic_regression = make_pipeline(StandardScaler(),
LogisticRegression(penalty="none"))
logistic_regression.fit(data_train, target_train)
accuracy = logistic_regression.score(data_test, target_test)
print(f"Accuracy on test set: {accuracy:.3f}")
# %% [markdown]
#
# Since we are dealing with a classification problem containing only 2
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import make_pipeline, Pipeline
from sklearn.metrics import *
from imblearn.over_sampling import RandomOverSampler
from imblearn.under_sampling import RandomUnderSampler
from sklearn.naive_bayes import GaussianNB
from xgboost import XGBClassifier
from catboost import CatBoostClassifier
get_ipython().run_line_magic('matplotlib', 'inline')
import logging
logger = logging.getLogger()
logger.setLevel(logging.CRITICAL)
import warnings
warnings.filterwarnings("ignore")
from sklearn import set_config
set_config(print_changed_only=False)
# In[3]:
## global seed ##
import random
rnd_state = 42
np.random.seed(rnd_state)
random.seed(rnd_state)
# In[4]:
in one leaf per tree. The sample is encoded by setting feature values for these leaves to 1 and the other feature values to 0. The resulting transformer has then learned a supervised, sparse, high-dimensional categorical embedding of the data. """ # Author: Tim Head <*****@*****.**> # # License: BSD 3 clause print(__doc__) from sklearn import set_config set_config(display="diagram") # %% # First, we will create a large dataset and split it into three sets: # # - a set to train the ensemble methods which are later used to as a feature # engineering transformer; # - a set to train the linear model; # - a set to test the linear model. # # It is important to split the data in such way to avoid overfitting by leaking # data. from sklearn.datasets import make_classification from sklearn.model_selection import train_test_split
# Notice that we are not acting on ``y`` above. We are simply creating features from each window using topology! *Note*: it's two features per window because we used the default value for ``homology_dimensions`` in ``VietorisRipsPersistence``, not because we had two variables in the time series initially! # # We can now put this all together into a ``giotto-tda`` ``Pipeline`` which combines both the sliding window transformation on ``X`` and resampling of ``y`` with the feature extraction from the windows on ``X``. # # *Note*: while we could import the ``Pipeline`` class and use its constructor, we use the convenience function ``make_pipeline`` instead, which is a drop-in replacement for [scikit-learn's](https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.make_pipeline.html). # # 请注意，我们没有对上面的“y”采取行动。我们只是在使用拓扑从每个窗口创建特征！ *注意*：每个窗口有两个特征，因为我们在“VietorisRipsPersistence”中使用了“ homology_dimensions”的默认值，而不是因为我们最初在时间序列中有两个变量！ # # 现在我们可以将所有这些放到giotto-tda“Pipeline”中，它将“X”上的滑动窗口转换和“y”的重采样与从“X”的Windows窗口上提取的特征结合在一起。 # # *注意*：虽然我们可以导入“ Pipeline”类并使用其构造函数，但我们使用便利功能“ make_pipeline”代替，它是[scikit-learn's]（https：// scikit-learn.org/stable/modules/generation/sklearn.pipeline.make_pipeline.html）。 # In[7]: from sklearn import set_config set_config(display='diagram') # For HTML representations of pipelines from gtda.pipeline import make_pipeline pipe = make_pipeline(SW, PD, VR, Ampl) pipe # Finally, if we have a *regression* task on ``y`` we can add a final estimator such as scikit-learn's ``RandomForestRegressor`` as a final step in the previous pipeline, and fit it! # # 最后，如果在y上有回归任务，我们可以添加最终估计量（例如scikit-learn的RandomForestRegressor）作为上一个管道中的最后一步，并将其拟合！ # In[8]: from sklearn.ensemble import RandomForestRegressor RFR = RandomForestRegressor()
from sklearn.linear_model import Ridge
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.preprocessing import MinMaxScaler, MaxAbsScaler
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
from sklearn.svm import LinearSVR
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import Normalizer
from nltk.corpus import stopwords
from sklearn.model_selection import GridSearchCV
import lightgbm as lgb
import sklearn
sklearn.set_config(True) #faster option
NUM_BRANDS = 3000
#NUM_CATEGORIES = 1000
NAME_MIN_DF = 10
MAX_FEATURES_ITEM_DESCRIPTION = 40000
CELL=True
def handle_missing_inplace(dataset):
dataset['category_name'].fillna(value='missing', inplace=True)
dataset['brand_name'].fillna(value='missing', inplace=True)
dataset['item_description'].fillna(value='missing', inplace=True)
def cutting(dataset):
pop_brand = dataset['brand_name'].value_counts().loc[lambda x: x.index != 'missing'].index[:NUM_BRANDS]
# + papermill={"duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed"} tags=[]
# + [markdown] papermill={"duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed"} tags=[]
# # 13. Save / Load Model
# + papermill={"duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed"} tags=[]
#save_model(best, model_name=os.path.join(output_dir, "pycaret_automl"))
# + papermill={"duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed"} tags=[]
#loaded_bestmodel = load_model(os.path.join(output_dir, "pycaret_automl"))
#print(loaded_bestmodel)
# + papermill={"duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed"} tags=[]
from sklearn import set_config
set_config(display="diagram")
loaded_bestmodel[0]
# + papermill={"duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed"} tags=[]
from sklearn import set_config
set_config(display="text")
# + [markdown] papermill={"duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed"} tags=[]
# # 14. Deploy Model
# + papermill={"duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed"} tags=[]
#deploy_model(best, model_name="best-aws", authentication={"bucket": "pycaret-test"})
# + [markdown] papermill={"duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed"} tags=[]
# # 15. Get Config / Set Config
def pytest_runtest_teardown(item, nextitem):
if isinstance(item, DoctestItem):
set_config(print_changed_only=False)
def pytest_runtest_setup(item):
if isinstance(item, DoctestItem):
set_config(print_changed_only=True)
"""
=================================
Compact estimator representations
=================================
This example illustrates the use of the print_changed_only global parameter.
Setting print_changed_only to True will alterate the representation of
estimators to only show the parameters that have been set to non-default
values. This can be used to have more compact representations.
"""
print(__doc__)
from sklearn.linear_model import LogisticRegression
from sklearn import set_config
lr = LogisticRegression(penalty='l1')
print('Default representation:')
print(lr)
# LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
# intercept_scaling=1, l1_ratio=None, max_iter=100,
# multi_class='auto', n_jobs=None, penalty='l1',
# random_state=None, solver='warn', tol=0.0001, verbose=0,
# warm_start=False)
set_config(print_changed_only=True)
print('\nWith changed_only option:')
print(lr)
# LogisticRegression(penalty='l1')
