Merge pull request #168 from ContextLab/expose_format_data

Expose format data

.gitignore

@@ -9,4 +9,5 @@ dist/
 .tox/
 *.bak
 tox.ini
-.vscode/
+.vscode/
+\.idea/

docs/_build/html/_downloads/animate.ipynb

@@ -15,7 +15,7 @@
     }, 
     {
       "source": [
-        "\n# Hyperalign a list of arrays and create an animated plot\n\n\nThe sample data is a list of 2D arrays, where each array is fMRI brain activity\nfrom one subject.  The rows are timepoints and the columns are neural\n'features'.  First, the matrices are hyperaligned using hyp.tools.align.\n\n"
+        "\n# Hyperalign a list of arrays and create an animated plot\n\n\nThe sample data is a list of 2D arrays, where each array is fMRI brain activity\nfrom one subject.  The rows are timepoints and the columns are neural\n'features'.  First, the matrices are hyperaligned using hyp.align.  Then, the data\nare split into 2 groups of 18. and averaged.  Finally the aligned data is plotted.\n\n"
       ], 
       "cell_type": "markdown", 
       "metadata": {}

docs/_build/html/_downloads/animate.py

@@ -6,7 +6,8 @@
 
 The sample data is a list of 2D arrays, where each array is fMRI brain activity
 from one subject.  The rows are timepoints and the columns are neural
-'features'.  First, the matrices are hyperaligned using hyp.tools.align.
+'features'.  First, the matrices are hyperaligned using hyp.align.  Then, the data
+are split into 2 groups of 18. and averaged.  Finally the aligned data is plotted.
 """
 
 # Code source: Andrew Heusser

docs/_build/html/_downloads/plot_clusters.ipynb

@@ -15,7 +15,7 @@
     }, 
     {
       "source": [
-        "\n# Discovering clusters\n\n\nThe `n_clusters` kwarg can be used to discover clusters in your dataset.  It\nrelies on scikit-learn's implementation of k-mean clustering to fin clusters,\nand then labels the points accordingly. You must set the number of clusters\nyourself.\n\n"
+        "\n# Discovering clusters\n\n\nThe `n_clusters` kwarg can be used to discover clusters in your dataset.  It\nrelies on scikit-learn's implementation of k-mean clustering to find clusters,\nand then labels the points accordingly. You must set the number of clusters\nyourself.\n\n"
       ], 
       "cell_type": "markdown", 
       "metadata": {}

docs/_build/html/_downloads/plot_clusters.py

@@ -5,7 +5,7 @@
 =============================
 
 The `n_clusters` kwarg can be used to discover clusters in your dataset.  It
-relies on scikit-learn's implementation of k-mean clustering to fin clusters,
+relies on scikit-learn's implementation of k-mean clustering to find clusters,
 and then labels the points accordingly. You must set the number of clusters
 yourself.
 """

docs/_build/html/_downloads/plot_describe.ipynb

@@ -15,7 +15,7 @@
     }, 
     {
       "source": [
-        "\n# Using describe_pca to evaluate the integrity of your visualization\n\n\nThe downside to using PCA to visualize your data is that some variance will\nlikely be removed. To help get a sense for the integrity of your low\ndimensional visualizations, we built the `describe_pca` function, which computes\nthe covariance (samples by samples) of both the raw and reduced datasets, and\nplots their correlation.  The function repeats this analysis from 2:N dimensions\nuntil the correlation reaches a local maximum.  Often times this will be less\nthan the total number of dimensions because the PCA model is whitened.\n\n"
+        "\n# Using describe_pca to evaluate the integrity of your visualization\n\n\nThe downside to using dimensionality reduction to visualize your data is that\nsome variance will likely be removed. To help get a sense for the integrity of your low\ndimensional visualizations, we built the `describe` function, which computes\nthe covariance (samples by samples) of both the raw and reduced datasets, and\nplots their correlation.\n\n"
       ], 
       "cell_type": "markdown", 
       "metadata": {}

docs/_build/html/_downloads/plot_describe.py

@@ -4,13 +4,11 @@
 Using describe_pca to evaluate the integrity of your visualization
 =============================
 
-The downside to using PCA to visualize your data is that some variance will
-likely be removed. To help get a sense for the integrity of your low
-dimensional visualizations, we built the `describe_pca` function, which computes
+The downside to using dimensionality reduction to visualize your data is that
+some variance will likely be removed. To help get a sense for the integrity of your low
+dimensional visualizations, we built the `describe` function, which computes
 the covariance (samples by samples) of both the raw and reduced datasets, and
-plots their correlation.  The function repeats this analysis from 2:N dimensions
-until the correlation reaches a local maximum.  Often times this will be less
-than the total number of dimensions because the PCA model is whitened.
+plots their correlation.
 """
 
 # Code source: Andrew Heusser

docs/_build/html/_downloads/plot_normalize.ipynb

@@ -15,7 +15,7 @@
     }, 
     {
       "source": [
-        "\n# Normalizing your features\n\n\nOften times its useful to normalize (z-score) you features before plotting, so\nthat they are on the same scale.  Otherwise, some features will be weighted more\nheavily than others when doing PCA, and that may or may not be what you want.\nThe `normalize` kwarg can be passed to the plot function.  If `normalize` is\nset to 'across', the zscore will be computed for the column across all of the\nlists passed.  Conversely, if `normalize` is set to 'within', the z-score will\nbe computed separately for each column in each list.  Finally, if `normalize` is\nset to 'row', each row of the matrix will be zscored.  Alternative, you can use\nthe normalize function found in tools (see the third example).\n\n"
+        "\n# Normalizing your features\n\n\nOften times its useful to normalize (z-score) you features before plotting, so\nthat they are on the same scale.  Otherwise, some features will be weighted more\nheavily than others when doing PCA, and that may or may not be what you want.\nThe `normalize` kwarg can be passed to the plot function.  If `normalize` is\nset to 'across', the zscore will be computed for the column across all of the\nlists passed.  Conversely, if `normalize` is set to 'within', the z-score will\nbe computed separately for each column in each list.  Finally, if `normalize` is\nset to 'row', each row of the matrix will be zscored.  Alternatively, you can use\nthe normalize function found in tools (see the third example).\n\n"
       ], 
       "cell_type": "markdown", 
       "metadata": {}

docs/_build/html/_downloads/plot_normalize.py

@@ -11,7 +11,7 @@
 set to 'across', the zscore will be computed for the column across all of the
 lists passed.  Conversely, if `normalize` is set to 'within', the z-score will
 be computed separately for each column in each list.  Finally, if `normalize` is
-set to 'row', each row of the matrix will be zscored.  Alternative, you can use
+set to 'row', each row of the matrix will be zscored.  Alternatively, you can use
 the normalize function found in tools (see the third example).
 """