shogun lars,lasso fixes

config.yaml

@@ -1600,7 +1600,17 @@ methods:
                        ['datasets/arcene_X.csv', 'datasets/arcene_y.csv'],
                        ['datasets/madelon_X.csv', 'datasets/madelon_y.csv']]
               options: '-l 0.01'
-
+    LARS:
+        run: ['timing']
+        iteration: 3
+        script: methods/shogun/lars.py
+        format: [csv, txt]
+        datasets:
+            - files: [ ['datasets/diabetes_X.csv', 'datasets/diabetes_y.csv'],
+                       ['datasets/cosExp_X.csv', 'datasets/cosExp_y.csv'],
+                       ['datasets/arcene_X.csv', 'datasets/arcene_y.csv'],
+                       ['datasets/madelon_X.csv', 'datasets/madelon_y.csv']]
+              options: '-l 0.01'
     QDA:
             run: ['timing','metric']
             script: methods/shogun/qda.py

methods/scikit/lars.py

@@ -58,8 +58,8 @@ def RunLARSScikit(q):
       try:
         with totalTimer:
           # Get all the parameters.
-          lambda1 = re.search("-l (\d+)", options)
-          lambda1 = 0.0 if not lambda1 else int(lambda1.group(1))
+          lambda1 = re.search("-l (\d+\.\d+)", options)
+          lambda1 = 0.0 if not lambda1 else float(lambda1.group(1))
 
           # Perform LARS.
           model = LassoLars(alpha=lambda1)

methods/shogun/lars.py

@@ -60,8 +60,8 @@ def RunLARSShogun(q):
         responsesFeat = RegressionLabels(responsesData)
 
         # Get all the parameters.
-        lambda1 = re.search("-l (\d+)", options)
-        lambda1 = 0.0 if not lambda1 else int(lambda1.group(1))
+        lambda1 = re.search("-l (\d+\.\d+)", options)
+        lambda1 = 0.0 if not lambda1 else float(lambda1.group(1))
 
         with totalTimer:
           # Perform LARS.

methods/shogun/lasso.py

@@ -63,22 +63,20 @@ def RunLASSOShogun(q):
       # If the dataset contains two files then the second file is the responses
       # file.
       try:
+        # Load input dataset.
         Log.Info("Loading dataset", self.verbose)
-        if len(self.dataset) == 2:
-          testSet = np.genfromtxt(self.dataset[1], delimiter=',')
+        inputData = np.genfromtxt(self.dataset[0], delimiter=',')
+        responsesData = np.genfromtxt(self.dataset[1], delimiter=',')
 
-          # Get all the parameters.
-          lambda1 = re.search("-l (\d+)", options)
-          lambda1 = 0.0 if not lambda1 else int(lambda1.group(1))
-
-        # Use the last row of the training set as the responses.
-        X, y = SplitTrainData(self.dataset)
+        # Get all the parameters.
+        lambda1 = re.search("-l (\d+\.\d+)", options)
+        lambda1 = 0.0 if not lambda1 else float(lambda1.group(1))
 
         with totalTimer:
-          model = LeastAngleRegression(lasso=True)
+          model = LeastAngleRegression(True)
           model.set_max_l1_norm(lambda1) 
-          model.set_labels(RegressionLabels(y))
-          model.train(RealFeatures(X.T))
+          model.set_labels(RegressionLabels(responsesData))
+          model.train(RealFeatures(inputData.T))
 
       except Exception as e:
         print(e)