Validation set for Gradient Based Models woohoo

docs/source/examples/plot_dcca_custom_data.py

@@ -24,8 +24,8 @@
 # numpy arrays, each representing a distinct view, and an optional list of labels.
 # Subsequently, these datasets can be converted into dataloaders for use in CCALoss-Zoo models.
 
-from cca_zoo.data.utils import NumpyDataset
 from cca_zoo.deep import DCCA, architectures
+from cca_zoo.deep.utils import NumpyDataset
 
 X = np.random.normal(size=(100, 10))
 Y = np.random.normal(size=(100, 10))

docs/source/examples/plot_gradient.py

@@ -16,8 +16,8 @@
 import matplotlib.pyplot as plt
 import time
 
-from cca_zoo.data.simulated import LinearSimulatedData
-from cca_zoo.linear import CCA, CCA_EYLoss
+from cca_zoo.datasets import JointData
+from cca_zoo.linear import CCA, CCA_EY
 from cca_zoo.visualisation import ScoreScatterDisplay
 
 # %%
@@ -34,7 +34,7 @@
 latent_dims = 1
 correlation = 0.9
 
-(X, Y) = LinearSimulatedData(
+(X, Y) = JointData(
     view_features=[p, q], latent_dims=latent_dims, correlation=[correlation]
 ).sample(n)
 
@@ -80,7 +80,7 @@
 
 # We loop over the batch sizes and create a CCA_EYLoss object for each one
 for batch_size in batch_sizes:
-    ccaey = CCA_EYLoss(
+    ccaey = CCA_EY(
         latent_dimensions=latent_dims,
         epochs=10,
         batch_size=batch_size,

docs/source/examples/plot_hyperparameter_selection.py

@@ -16,7 +16,8 @@
 import numpy as np
 import pandas as pd
 from scipy.stats import loguniform
-from cca_zoo.data.simulated import LinearSimulatedData
+
+from cca_zoo.datasets import JointData
 from cca_zoo.model_selection import GridSearchCV, RandomizedSearchCV
 from cca_zoo.nonparametric import KCCA
 
@@ -34,7 +35,7 @@
 latent_dims = 1
 correlation = 0.9
 
-data = LinearSimulatedData(
+data = JointData(
     view_features=[p, q], latent_dims=latent_dims, correlation=[correlation]
 )
 (X, Y) = data.sample(n)

docs/source/examples/plot_kernel_cca.py

@@ -10,7 +10,8 @@
 # Dependencies
 # ------------
 import numpy as np
-from cca_zoo.data.simulated import LinearSimulatedData
+
+from cca_zoo.datasets import JointData
 from cca_zoo.model_selection import GridSearchCV
 from cca_zoo.nonparametric import KCCA
 
@@ -22,7 +23,7 @@
 
 # Configuring and generating a simulated dataset with given specifications.
 n, p, q, latent_dims, correlation = 200, 100, 100, 1, 0.9
-(X, Y) = LinearSimulatedData(
+(X, Y) = JointData(
     view_features=[p, q], latent_dims=latent_dims, correlation=[correlation]
 ).sample(n)
 

docs/source/examples/plot_many_views.py

@@ -10,7 +10,8 @@
 # Dependencies
 # ------------
 import numpy as np
-from cca_zoo.data.simulated import LinearSimulatedData
+
+from cca_zoo.datasets import JointData
 from cca_zoo.linear import GCCA, MCCA, SCCA_PMD, TCCA
 from cca_zoo.nonparametric import KCCA, KGCCA, KTCCA
 
@@ -23,7 +24,7 @@
 np.random.seed(42)
 n, p, q, r, latent_dims, cv = 30, 3, 3, 3, 1, 3
 
-(X, Y, Z) = LinearSimulatedData(
+(X, Y, Z) = JointData(
     view_features=[p, q, r], latent_dims=latent_dims, correlation=[0.9]
 ).sample(n)
 

docs/source/examples/plot_sparse_cca.py

@@ -12,6 +12,8 @@
 import seaborn as sns
 import matplotlib.pyplot as plt
 from sklearn.model_selection import train_test_split
+
+from cca_zoo.datasets import JointData
 from cca_zoo.linear import (
     CCA,
     PLS,
@@ -20,7 +22,6 @@
     ElasticCCA,
     SCCA_Span,
 )
-from cca_zoo.data.simulated import LinearSimulatedData
 from cca_zoo.model_selection import GridSearchCV
 
 # Plotting Configuration
@@ -88,7 +89,7 @@ def plot_model_weights(wx, wy, tx, ty, title="", save_path=None):
 n, p, q = 500, 200, 200
 latent_dims = 1
 view_1_sparsity, view_2_sparsity = 0.1, 0.1
-data = LinearSimulatedData(
+data = JointData(
     view_features=[p, q],
     latent_dims=latent_dims,
     view_sparsity=[view_1_sparsity, view_2_sparsity],

docs/source/examples/plot_validation.py

@@ -11,7 +11,7 @@
 import matplotlib.pyplot as plt
 from sklearn.model_selection import ShuffleSplit, KFold
 
-from cca_zoo.data import JointDataGenerator
+from cca_zoo.datasets import JointData
 from cca_zoo.linear import CCA
 from cca_zoo.model_selection import learning_curve, permutation_test_score
 
@@ -174,7 +174,7 @@ def plot_learning_curve(
 
 
 # Data generation
-(X, Y) = JointDataGenerator(
+(X, Y) = JointData(
     view_features=[p, q], latent_dims=latent_dims, correlation=correlations
 ).sample(n)