wip: multitask api

Author: mrahim

examples/multitask_example.py

@@ -4,17 +4,25 @@
 from sklearn.linear_model import (MultiTaskLassoCV,
                                   MultiTaskElasticNet,
                                   MultiTaskElasticNetCV,
+                                  ElasticNetCV,
                                   LassoCV, LogisticRegression)
 from sklearn.metrics import accuracy_score
+from sklearn.model_selection import ShuffleSplit
 
-X, y = make_classification(random_state=25)
+X, y = make_classification(n_samples=500, random_state=42)
 n = 10
-
 Y = np.array(n*[y]).T
 
 mt = MultiTaskEstimator(
-    estimator=MultiTaskLassoCV(alphas=np.logspace(-3, 3, 7)),
+    estimator=MultiTaskElasticNetCV(alphas=np.logspace(-3, 3, 7)),
     output_types=n//2*['binary']+n//2*['continuous'])
 
-mt.fit(X, Y)
-print(mt.score(X, Y))
+ls = LogisticRegression()
+
+ss = ShuffleSplit(n_splits=10, test_size=0.2, random_state=42)
+
+for train, test in ss.split(X):
+    mt.fit(X[train], Y[train])
+    ls.fit(X[train], y[train])
+    print(ls.score(X[test], y[test]))
+    print(mt.score(X[test], Y[test]))

stlearn/multitask.py

@@ -9,22 +9,26 @@
 import numpy as np
 from sklearn.base import BaseEstimator, TransformerMixin
 from sklearn.metrics import accuracy_score, r2_score
-from sklearn.externals.joblib import Memory, Parallel, delayed
+from sklearn.externals.joblib import Parallel, delayed
 from sklearn.linear_model import (
     MultiTaskLassoCV, MultiTaskElasticNetCV, LogisticRegression)
 
 
 class MultiTaskEstimator(BaseEstimator, TransformerMixin):
     """MultiTask estimator for multiple (continuous / discrete) outputs.
+
+    Parameters
+    ----------
+    estimator : Multitask scikit-learn estimator, can be
+                {"MultiTaskLasso", "MultiTaskLassoCV",
+                 "MultiTaskElasticNet", "MultiTaskElasticNetCV"}
+
+    output_types : shape = (n_outputs,) type of each output, can be
+                    {"binary", "continuous"}
     """
 
-    def __init__(self, estimator=None,
-                 memory=Memory(cachedir=None), memory_level=0,
-                 n_jobs=1, output_types=None):
+    def __init__(self, estimator=None, output_types=None):
         self.estimator = estimator
-        self.memory = memory
-        self.memory_level = memory_level
-        self.n_jobs = n_jobs
         # check if output types are okay
         for output in output_types:
             if output not in ['binary', 'continuous']: