RFCT Simpler code

Author: luispedro

ch08/corrneighbours.py

@@ -15,8 +15,8 @@
 
 defpredict(otrain):
 binary= (otrain>0)
-norm=NormalizePositive()
-train=norm.fit_transform(otrain.T).T
+norm=NormalizePositive(axis=1)
+train=norm.fit_transform(otrain)
 
 dists=distance.pdist(binary, 'correlation')
 dists=distance.squareform(dists)
@@ -37,9 +37,9 @@ def predict(otrain):
 n//=2
 n+=1
 revs=revs[:n]
-filled[u,m] =revs.mean()
+filled[u,m] =np.mean(revs)
 
-returnnorm.inverse_transform(filled.T).T
+returnnorm.inverse_transform(filled)
 
 defmain(transpose_inputs=False):
 train, test=get_train_test(random_state=12)

ch08/norm.py

@@ -2,37 +2,50 @@
 
 classNormalizePositive(object):
 
+def__init__(self, axis=0):
+self.axis=axis
+
 deffit(self, features, y=None):
-# count features that are greater than zero in axis 0:
+# count features that are greater than zero in axis `self.axis`:
+ifself.axis==1:
+features=features.T
 binary= (features>0)
-count0=binary.sum(axis=0)
+count=binary.sum(axis=0)
 
 # to avoid division by zero, set zero counts to one:
-count0[count0==0] =1.
+count[count==0] =1.
 
-self.mean=features.sum(axis=0)/count0
+self.mean=features.sum(axis=0)/count
 
 # Compute variance by average squared difference to the mean, but only
 # consider differences where binary is True (i.e., where there was a
 # true rating):
 diff= (features-self.mean) *binary
 diff**=2
 # regularize the estimate of std by adding 0.1
-self.std=np.sqrt(0.1+diff.sum(axis=0)/count0)
+self.std=np.sqrt(0.1+diff.sum(axis=0)/count)
 returnself
 
 deftransform(self, features):
+ifself.axis==1:
+features=features.T
 binary= (features>0)
 features=features-self.mean
 features/=self.std
 features*=binary
+ifself.axis==1:
+features=features.T
 returnfeatures
 
 definverse_transform(self, features, copy=True):
 ifcopy:
 features=features.copy()
+ifself.axis==1:
+features=features.T
 features*=self.std
 features+=self.mean
+ifself.axis==1:
+features=features.T
 returnfeatures
 
 deffit_transform(self, features):