ML之LiR&DNN&EL：基于skflow的LiR、DNN、sklearn的RF对Boston(波士顿房价)数据集进行回归预测(房价)
ML之LiR&DNN&EL：基于skflow的LiR、DNN、sklearn的RF对Boston(波士顿房价)数据集进行回归预测(房价)
输出结果
设计思路
核心代码
tf_lr = skflow.TensorFlowLinearRegressor(steps=10000, learning_rate=0.01, batch_size=50)
tf_lr.fit(X_train, y_train)
tf_lr_y_predict = tf_lr.predict(X_test)
tf_dnn_regressor = skflow.TensorFlowDNNRegressor(hidden_units=[100, 40],
steps=10000, learning_rate=0.01, batch_size=50)
tf_dnn_regressor.fit(X_train, y_train)
tf_dnn_regressor_y_predict = tf_dnn_regressor.predict(X_test)
rfr = RandomForestRegressor()
rfr.fit(X_train, y_train)
rfr_y_predict = rfr.predict(X_test)class TensorFlowLinearRegressor(TensorFlowEstimator, RegressorMixin):
"""TensorFlow Linear Regression model."""
def __init__(self, n_classes=0, tf_master="", batch_size=32, steps=200, optimizer="SGD",
learning_rate=0.1, tf_random_seed=42, continue_training=False,
num_cores=4, verbose=1, early_stopping_rounds=None,
max_to_keep=5, keep_checkpoint_every_n_hours=10000):
super(TensorFlowLinearRegressor, self).__init__(model_fn=models.linear_regression,
n_classes=n_classes, tf_master=tf_master, batch_size=batch_size, steps=steps,
optimizer=optimizer, learning_rate=learning_rate, tf_random_seed=tf_random_seed,
continue_training=continue_training, num_cores=num_cores, verbose=verbose,
early_stopping_rounds=early_stopping_rounds, max_to_keep=max_to_keep,
keep_checkpoint_every_n_hours=keep_checkpoint_every_n_hours)
@property
def weights_(self):
"""Returns weights of the linear regression."""
return self.get_tensor_value('linear_regression/weights:0')
@property
def bias_(self):
"""Returns bias of the linear regression."""
return self.get_tensor_value('linear_regression/bias:0')class TensorFlowDNNRegressor(TensorFlowEstimator, RegressorMixin):
"""TensorFlow DNN Regressor model.
Parameters:
hidden_units: List of hidden units per layer.
tf_master: TensorFlow master. Empty string is default for local.
batch_size: Mini batch size.
steps: Number of steps to run over data.
optimizer: Optimizer name (or class), for example "SGD", "Adam",
"Adagrad".
learning_rate: If this is constant float value, no decay function is used.
Instead, a customized decay function can be passed that accepts
global_step as parameter and returns a Tensor.
e.g. exponential decay function:
def exp_decay(global_step):
return tf.train.exponential_decay(
learning_rate=0.1, global_step,
decay_steps=2, decay_rate=0.001)
tf_random_seed: Random seed for TensorFlow initializers.
Setting this value, allows consistency between reruns.
continue_training: when continue_training is True, once initialized
model will be continuely trained on every call of fit.
num_cores: Number of cores to be used. (default: 4)
early_stopping_rounds: Activates early stopping if this is not None.
Loss needs to decrease at least every every
<early_stopping_rounds>
round(s) to continue training. (default: None)
verbose: Controls the verbosity, possible values:
0: the algorithm and debug information is muted.
1: trainer prints the progress.
2: log device placement is printed.
early_stopping_rounds: Activates early stopping if this is not None.
Loss needs to decrease at least every every
<early_stopping_rounds>
round(s) to continue training. (default: None)
max_to_keep: The maximum number of recent checkpoint files to
keep.
As new files are created, older files are deleted.
If None or 0, all checkpoint files are kept.
Defaults to 5 (that is, the 5 most recent checkpoint files are kept.)
keep_checkpoint_every_n_hours: Number of hours between each
checkpoint
to be saved. The default value of 10,000 hours effectively disables
the feature.
"""
def __init__(self, hidden_units, n_classes=0, tf_master="",
batch_size=32,
steps=200, optimizer="SGD", learning_rate=0.1,
tf_random_seed=42, continue_training=False, num_cores=4,
verbose=1, early_stopping_rounds=None,
max_to_keep=5, keep_checkpoint_every_n_hours=10000):
self.hidden_units = hidden_units
super(TensorFlowDNNRegressor, self).__init__(model_fn=self.
_model_fn, n_classes=n_classes, tf_master=tf_master,
batch_size=batch_size, steps=steps, optimizer=optimizer,
learning_rate=learning_rate, tf_random_seed=tf_random_seed,
continue_training=continue_training, num_cores=num_cores,
verbose=verbose, early_stopping_rounds=early_stopping_rounds,
max_to_keep=max_to_keep,
keep_checkpoint_every_n_hours=keep_checkpoint_every_n_hours)
def _model_fn(self, X, y):
return models.get_dnn_model(self.hidden_units, models.
linear_regression)(X, y)
@property
def weights_(self):
"""Returns weights of the DNN weight layers."""
weights = []
for layer in range(len(self.hidden_units)):
weights.append(self.get_tensor_value('dnn/layer%
d/Linear/Matrix:0' % layer))
weights.append(self.get_tensor_value('linear_regression/weights:
0'))
return weights
@property
def bias_(self):
"""Returns bias of the DNN's bias layers."""
biases = []
for layer in range(len(self.hidden_units)):
biases.append(self.get_tensor_value('dnn/layer%d/Linear/Bias:0'
% layer))
biases.append(self.get_tensor_value('linear_regression/bias:0'))
return biasesclass RandomForestRegressor(ForestRegressor):
"""A random forest regressor.
A random forest is a meta estimator that fits a number of classifying
decision trees on various sub-samples of the dataset and use averaging
to improve the predictive accuracy and control over-fitting.
The sub-sample size is always the same as the original
input sample size but the samples are drawn with replacement if
`bootstrap=True` (default).
Read more in the :ref:`User Guide <forest>`.
Parameters
----------
n_estimators : integer, optional (default=10)
The number of trees in the forest.
criterion : string, optional (default="mse")
The function to measure the quality of a split. Supported criteria
are "mse" for the mean squared error, which is equal to variance
reduction as feature selection criterion, and "mae" for the mean
absolute error.
.. versionadded:: 0.18
Mean Absolute Error (MAE) criterion.
max_features : int, float, string or None, optional (default="auto")
The number of features to consider when looking for the best split:
- If int, then consider `max_features` features at each split.
- If float, then `max_features` is a percentage and
`int(max_features * n_features)` features are considered at each
split.
- If "auto", then `max_features=n_features`.
- If "sqrt", then `max_features=sqrt(n_features)`.
- If "log2", then `max_features=log2(n_features)`.
- If None, then `max_features=n_features`.
Note: the search for a split does not stop until at least one
valid partition of the node samples is found, even if it requires to
effectively inspect more than ``max_features`` features.
max_depth : integer or None, optional (default=None)
The maximum depth of the tree. If None, then nodes are expanded
until
all leaves are pure or until all leaves contain less than
min_samples_split samples.
min_samples_split : int, float, optional (default=2)
The minimum number of samples required to split an internal node:
- If int, then consider `min_samples_split` as the minimum number.
- If float, then `min_samples_split` is a percentage and
`ceil(min_samples_split * n_samples)` are the minimum
number of samples for each split.
.. versionchanged:: 0.18
Added float values for percentages.
min_samples_leaf : int, float, optional (default=1)
The minimum number of samples required to be at a leaf node:
- If int, then consider `min_samples_leaf` as the minimum number.
- If float, then `min_samples_leaf` is a percentage and
`ceil(min_samples_leaf * n_samples)` are the minimum
number of samples for each node.
.. versionchanged:: 0.18
Added float values for percentages.
min_weight_fraction_leaf : float, optional (default=0.)
The minimum weighted fraction of the sum total of weights (of all
the input samples) required to be at a leaf node. Samples have
equal weight when sample_weight is not provided.
max_leaf_nodes : int or None, optional (default=None)
Grow trees with ``max_leaf_nodes`` in best-first fashion.
Best nodes are defined as relative reduction in impurity.
If None then unlimited number of leaf nodes.
min_impurity_split : float,
Threshold for early stopping in tree growth. A node will split
if its impurity is above the threshold, otherwise it is a leaf.
.. deprecated:: 0.19
``min_impurity_split`` has been deprecated in favor of
``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
Use ``min_impurity_decrease`` instead.
min_impurity_decrease : float, optional (default=0.)
A node will be split if this split induces a decrease of the impurity
greater than or equal to this value.
The weighted impurity decrease equation is the following::
N_t / N * (impurity - N_t_R / N_t * right_impurity
- N_t_L / N_t * left_impurity)
where ``N`` is the total number of samples, ``N_t`` is the number of
samples at the current node, ``N_t_L`` is the number of samples in the
left child, and ``N_t_R`` is the number of samples in the right child.
``N``, ``N_t``, ``N_t_R`` and ``N_t_L`` all refer to the weighted sum,
if ``sample_weight`` is passed.
.. versionadded:: 0.19
bootstrap : boolean, optional (default=True)
Whether bootstrap samples are used when building trees.
oob_score : bool, optional (default=False)
whether to use out-of-bag samples to estimate
the R^2 on unseen data.
n_jobs : integer, optional (default=1)
The number of jobs to run in parallel for both `fit` and `predict`.
If -1, then the number of jobs is set to the number of cores.
random_state : int, RandomState instance or None, optional
(default=None)
If int, random_state is the seed used by the random number generator;
If RandomState instance, random_state is the random number
generator;
If None, the random number generator is the RandomState instance
used
by `np.random`.
verbose : int, optional (default=0)
Controls the verbosity of the tree building process.
warm_start : bool, optional (default=False)
When set to ``True``, reuse the solution of the previous call to fit
and add more estimators to the ensemble, otherwise, just fit a whole
new forest.
Attributes
----------
estimators_ : list of DecisionTreeRegressor
The collection of fitted sub-estimators.
feature_importances_ : array of shape = [n_features]
The feature importances (the higher, the more important the feature).
n_features_ : int
The number of features when ``fit`` is performed.
n_outputs_ : int
The number of outputs when ``fit`` is performed.
oob_score_ : float
Score of the training dataset obtained using an out-of-bag estimate.
oob_prediction_ : array of shape = [n_samples]
Prediction computed with out-of-bag estimate on the training set.
Examples
--------
>>> from sklearn.ensemble import RandomForestRegressor
>>> from sklearn.datasets import make_regression
>>>
>>> X, y = make_regression(n_features=4, n_informative=2,
... random_state=0, shuffle=False)
>>> regr = RandomForestRegressor(max_depth=2, random_state=0)
>>> regr.fit(X, y)
RandomForestRegressor(bootstrap=True, criterion='mse',
max_depth=2,
max_features='auto', max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=1,
oob_score=False, random_state=0, verbose=0, warm_start=False)
>>> print(regr.feature_importances_)
[ 0.17339552 0.81594114 0. 0.01066333]
>>> print(regr.predict([[0, 0, 0, 0]]))
[-2.50699856]
Notes
-----
The default values for the parameters controlling the size of the trees
(e.g. ``max_depth``, ``min_samples_leaf``, etc.) lead to fully grown and
unpruned trees which can potentially be very large on some data sets.
To
reduce memory consumption, the complexity and size of the trees
should be
controlled by setting those parameter values.
The features are always randomly permuted at each split. Therefore,
the best found split may vary, even with the same training data,
``max_features=n_features`` and ``bootstrap=False``, if the improvement
of the criterion is identical for several splits enumerated during the
search of the best split. To obtain a deterministic behaviour during
fitting, ``random_state`` has to be fixed.
References
----------
.. [1] L. Breiman, "Random Forests", Machine Learning, 45(1), 5-32,
2001.
See also
--------
DecisionTreeRegressor, ExtraTreesRegressor
"""
def __init__(self,
n_estimators=10,
criterion="mse",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features="auto",
max_leaf_nodes=None,
min_impurity_decrease=0.,
min_impurity_split=None,
bootstrap=True,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False):
super(RandomForestRegressor, self).__init__
(base_estimator=DecisionTreeRegressor(), n_estimators=n_estimators,
estimator_params=("criterion", "max_depth", "min_samples_split",
"min_samples_leaf", "min_weight_fraction_leaf", "max_features",
"max_leaf_nodes", "min_impurity_decrease", "min_impurity_split",
"random_state"), bootstrap=bootstrap, oob_score=oob_score,
n_jobs=n_jobs, random_state=random_state, verbose=verbose,
warm_start=warm_start)
self.criterion = criterion
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.min_weight_fraction_leaf = min_weight_fraction_leaf
self.max_features = max_features
self.max_leaf_nodes = max_leaf_nodes
self.min_impurity_decrease = min_impurity_decrease
self.min_impurity_split = min_impurity_split 赞 (0)