In [1]:

    

import numpy as np

from sklearn.datasets import load_boston
from sklearn.ensemble import RandomForestRegressor
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import Imputer
from sklearn.cross_validation import cross_val_score


    

In [2]:

    

rng = np.random.RandomState(0)

dataset = load_boston()
X_full, y_full = dataset.data, dataset.target
n_samples = X_full.shape[0]
n_features = X_full.shape[1]


    

In [3]:

    

# Estimate the score on the entire dataset, with no missing values
estimator = RandomForestRegressor(random_state=0, n_estimators=100)
score = cross_val_score(estimator, X_full, y_full).mean()
print("Score with the entire dataset = %.2f" % score)


    

    




Score with the entire dataset = 0.56

In [12]:

    

# Add missing values in 75% of the lines
missing_rate = 0.75
n_missing_samples = np.floor(n_samples * missing_rate)
missing_samples = np.hstack((np.zeros(n_samples - n_missing_samples,
                                      dtype=np.bool),
                             np.ones(n_missing_samples,
                                     dtype=np.bool)))
rng.shuffle(missing_samples)
missing_features = rng.randint(0, n_features, n_missing_samples)


    

In [13]:

    

# Estimate the score without the lines containing missing values
X_filtered = X_full[~missing_samples, :]
y_filtered = y_full[~missing_samples]
estimator = RandomForestRegressor(random_state=0, n_estimators=100)
score = cross_val_score(estimator, X_filtered, y_filtered).mean()
print("Score without the samples containing missing values = %.2f" % score)


    

    




Score without the samples containing missing values = 0.69

In [6]:

    

# Estimate the score after imputation of the missing values
X_missing = X_full.copy()
X_missing[np.where(missing_samples)[0], missing_features] = 0
y_missing = y_full.copy()
estimator = Pipeline([("imputer", Imputer(missing_values=0,
                                          strategy="mean",
                                          axis=0)),
                      ("forest", RandomForestRegressor(random_state=0,
                                                       n_estimators=100))])
score = cross_val_score(estimator, X_missing, y_missing).mean()
print("Score after imputation of the missing values = %.2f" % score)


    

    




Score after imputation of the missing values = 0.57

In [26]:

    




    

In [26]:

    




    

In [24]:

    




    

    
Out[24]:





Pipeline(steps=[('reduce_dim', PCA(copy=True, n_components=None, whiten=False)), ('svm', SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0, degree=3, gamma=0.0,
  kernel='rbf', max_iter=-1, probability=False, random_state=None,
  shrinking=True, tol=0.001, verbose=False))])

In [25]:

    




    

    
Out[25]:





Pipeline(steps=[('binarizer', Binarizer(copy=True, threshold=0.0)), ('multinomialnb', MultinomialNB(alpha=1.0, class_prior=None, fit_prior=True))])

In [26]:

    




    

    
Out[26]:





[('reduce_dim', PCA(copy=True, n_components=None, whiten=False)),
 ('svm',
  SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0, degree=3, gamma=0.0,
    kernel='rbf', max_iter=-1, probability=False, random_state=None,
    shrinking=True, tol=0.001, verbose=False))]

In [27]:

    




    

    
Out[27]:





Pipeline(steps=[('reduce_dim', PCA(copy=True, n_components=None, whiten=False)), ('svm', SVC(C=10, cache_size=200, class_weight=None, coef0=0.0, degree=3, gamma=0.0,
  kernel='rbf', max_iter=-1, probability=False, random_state=None,
  shrinking=True, tol=0.001, verbose=False))])

In [28]:

    




    

In [ ]: