ENH Test various l1_ratio values with ElasticNetCV

Author: luispedro

ch07/README.rst

@@ -30,6 +30,8 @@ figure4.py
 lr10k.py
  Linear regression on 10K dataset, evaluation by cross-validation
 predict10k_en.py
+ Elastic nets (including with inner cross-validation for parameter
+ settings). Produces scatter plot.
 
 
 MovieLens data analysis

ch07/predict10k_en.py

@@ -8,14 +8,16 @@
 importnumpyasnp
 fromsklearn.datasetsimportload_svmlight_file
 fromsklearn.cross_validationimportKFold
-fromsklearn.linear_modelimportElasticNetCV
+fromsklearn.linear_modelimportElasticNetCV, ElasticNet
 fromsklearn.metricsimportmean_squared_error, r2_score
+frommatplotlibimportpyplotasplt
 
 data, target=load_svmlight_file('data/E2006.train')
 
 # Edit the lines below if you want to switch method:
-# met = LinearRegression(fit_intercept=True)
-met=ElasticNetCV()
+# from sklearn.linear_model import Lasso
+# met = Lasso(alpha=0.1)
+met=ElasticNet(alpha=0.1)
 
 kf=KFold(len(target), n_folds=5)
 pred=np.zeros_like(target)
@@ -27,9 +29,44 @@
 print('[EN 0.1] R2 on testing (5 fold),{:.2}'.format(r2_score(target, pred)))
 print('')
 
+# Construct an ElasticNetCV object (use all available CPUs)
+met=ElasticNetCV(n_jobs=-1)
+
+kf=KFold(len(target), n_folds=5)
+pred=np.zeros_like(target)
+fortrain, testinkf:
+met.fit(data[train], target[train])
+pred[test] =met.predict(data[test])
+
+print('[EN CV] RMSE on testing (5 fold),{:.2}'.format(np.sqrt(mean_squared_error(target, pred))))
+print('[EN CV] R2 on testing (5 fold),{:.2}'.format(r2_score(target, pred)))
+print('')
+
 met.fit(data, target)
 pred=met.predict(data)
-print('[EN 0.1] RMSE on training,{:.2}'.format(np.sqrt(mean_squared_error(target, pred))))
-print('[EN 0.1] R2 on training,{:.2}'.format(r2_score(target, pred)))
+print('[EN CV] RMSE on training,{:.2}'.format(np.sqrt(mean_squared_error(target, pred))))
+print('[EN CV] R2 on training,{:.2}'.format(r2_score(target, pred)))
+
+
+# Construct an ElasticNetCV object (use all available CPUs)
+met=ElasticNetCV(n_jobs=-1, l1_ratio=[.01, .05, .25, .5, .75, .95, .99])
+
+kf=KFold(len(target), n_folds=5)
+pred=np.zeros_like(target)
+fortrain, testinkf:
+met.fit(data[train], target[train])
+pred[test] =met.predict(data[test])
+
+
+print('[EN CV l1_ratio] RMSE on testing (5 fold),{:.2}'.format(np.sqrt(mean_squared_error(target, pred))))
+print('[EN CV l1_ratio] R2 on testing (5 fold),{:.2}'.format(r2_score(target, pred)))
+print('')
 
 
+fig, ax=plt.subplots()
+y=target
+ax.scatter(y, pred, c='k')
+ax.plot([-5,-1], [-5,-1], 'r-', lw=2)
+ax.set_xlabel('Actual value')
+ax.set_ylabel('Predicted value')
+fig.savefig('Figure_10k_scatter_EN_l1_ratio.png', dpi=150)