Enhance Dataset example (#100)

* Update plot_create_dataset.py

* Enhance datasets example.

* Replace "datasets" with "dependent variables".

Author: tsalo

examples/01_basic_io/plot_create_dataset.py

@@ -22,10 +22,24 @@
 ###############################################################################
 # Datasets can be created from arrays
 # -----------------------------------
+# The simplest way to create a dataset is to pass in arguments as numpy arrays.
+#
+# ``y`` refers to the study-level estimates, ``v`` to the variances,
+# ``X`` to any study-level regressors, and ``n`` to the sample sizes.
+#
+# Not all Estimators require all of these arguments, so not all need to be
+# used in a given Dataset.
+y = [2, 4, 6]
 v = [100, 100, 100]
 X = [[5, 9], [2, 8], [1, 7]]
-y = [2, 4, 6]
-dataset = core.Dataset(y=y, v=v, X=X)
+
+dataset = core.Dataset(y=y, v=v, X=X, X_names=["X1", "X7"])
+
+pprint(vars(dataset))
+
+###############################################################################
+# Datasets have the :meth:`~pymare.core.Dataset.to_df` method.
+dataset.to_df()
 
 ###############################################################################
 # Datasets can also be created from pandas DataFrames
@@ -38,6 +52,32 @@
         "X7": [9, 8, 7],
     }
 )
+
 dataset = core.Dataset(v="v_alt", X=["X1", "X7"], data=df, add_intercept=False)
 
 pprint(vars(dataset))
+
+###############################################################################
+# Datasets can also contain multiple dependent variables
+# ------------------------------------------------------
+# These variables are analyzed in parallel, but as unrelated variables,
+# rather than as potentially correlated ones.
+#
+# This is particularly useful for image-based neuroimaging meta-analyses.
+# For more information about this, see `NiMARE <https://nimare.readthedocs.io>`_.
+y = [
+    [2, 4, 6],  # Estimates for first study's three outcome variables.
+    [3, 2, 1],  # Estimates for second study's three outcome variables.
+]
+v = [
+    [100, 100, 100],  # Estimate variances for first study's three outcome variables.
+    [8, 4, 2],  # Estimate variances for second study's three outcome variables.
+]
+X = [
+    [5, 9],  # Predictors for first study. Same across all three outcome variables.
+    [2, 8],  # Predictors for second study. Same across all three outcome variables.
+]
+
+dataset = core.Dataset(y=y, v=v, X=X, X_names=["X1", "X7"])
+
+pprint(vars(dataset))

examples/02_meta-analysis/plot_run_meta-analysis.py

@@ -37,6 +37,21 @@
 # :meth:`~pymare.estimators.estimators.BaseEstimator.fit_dataset` to fit it to
 # a :class:`~pymare.core.Dataset`.
 #
+# .. tip::
+#   We generally recommend using
+#   :meth:`~pymare.estimators.estimators.BaseEstimator.fit_dataset` over
+#   :meth:`~pymare.estimators.estimators.BaseEstimator.fit`.
+#
+#   There are a number of methods, such as
+#   :meth:`~pymare.results.MetaRegressionResults.get_heterogeneity_stats` and
+#   :meth:`~pymare.results.MetaRegressionResults.permutation_test`,
+#   which only work when the Estimator is fitted to a Dataset.
+#
+#   However, :meth:`~pymare.estimators.estimators.BaseEstimator.fit` requires
+#   less memory than :meth:`~pymare.estimators.estimators.BaseEstimator.fit_dataset`,
+#   so it can be useful for large-scale meta-analyses,
+#   such as neuroimaging image-based meta-analyses.
+#
 # The :meth:`~pymare.estimators.estimators.BaseEstimator.summary` function
 # will return a :class:`~pymare.results.MetaRegressionResults` object,
 # which contains the results of the analysis.