DONE

Code for processing datasets using scikit-learn.

"""

import numpy as np

from sklearn.cross_decomposition import PLSRegression

from sklearn.ensemble import RandomForestClassifier

from sklearn.ensemble import RandomForestRegressor

from sklearn.gaussian_process import GaussianProcessRegressor

from sklearn.linear_model import LogisticRegression

from sklearn.linear_model import LinearRegression

from sklearn.linear_model import RidgeCV

from deepchem.utils.save import load_from_disk

from deepchem.utils.save import save_to_disk

NON_WEIGHTED_MODELS = {LogisticRegression, PLSRegression, GaussianProcessRegressor, ElasticNetCV, LassoCV}

class SklearnModel(Model):

  """

  Abstract base class for different ML models.

    y = np.squeeze(dataset.y)

    w = np.squeeze(dataset.w)

    # Logistic regression doesn't support weights

    if not isinstance(self.model_instance, LogisticRegression):

      self.model_instance.fit(X, y, w)

    else:

    for model_instance in NON_WEIGHTED_MODELS:

      if not isinstance(self.model_instance, model_instance):

        continue

      self.model_instance.fit(X, y)

    y_pred_raw = self.model_instance.predict(X)

      return

    self.model_instance.fit(X, y, w)

  def predict_on_batch(self, X, pad_batch=False):

    """