[DATALAD RUNCMD] run codespell throughout

yarikoptic · yarikoptic · commit f7641bab6800 · 2023-07-06T16:04:52.000-04:00
=== Do not change lines below ===
{
 "chain": [],
 "cmd": "codespell -w",
 "exit": 0,
 "extra_inputs": [],
 "inputs": [],
 "outputs": [],
 "pwd": "."
}
^^^ Do not change lines above ^^^
diff --git a/causallearn/search/ConstraintBased/PC.py b/causallearn/search/ConstraintBased/PC.py
@@ -394,7 +394,7 @@ def detect_parent(r: int, data_: ndarray, alpha: float, indep_test, stable: bool
 def get_parent(r: int, cg_skel_adj: ndarray) -> ndarray:
     """Get the neighbors of missingness indicators which are the parents
     :param r: the missingness indicator index
-    :param cg_skel_adj: adjacancy matrix of a causal skeleton
+    :param cg_skel_adj: adjacency matrix of a causal skeleton
     :return:
     prt: list, parents of the missingness indicator r
     """
diff --git a/causallearn/search/FCMBased/lingam/causal_effect.py b/causallearn/search/FCMBased/lingam/causal_effect.py
@@ -80,7 +80,7 @@ def _get_propagated_effects(self, En, intervention_index, intervention_value):
 
         Parameters
         ----------
-        En : array-like, shpae (n_features)
+        En : array-like, shape (n_features)
             Expectations of each noise variable.
         intervention_index : int
             Index of variable to apply intervention.
@@ -89,7 +89,7 @@ def _get_propagated_effects(self, En, intervention_index, intervention_value):
 
         Returns
         -------
-        propagated_effects : array-like, shpae (n_features)
+        propagated_effects : array-like, shape (n_features)
             Propagated effects, where ``n_features`` is the number of features.
         """
         effects = np.zeros(len(self._causal_order))
@@ -106,7 +106,7 @@ def _predict(self, X, pred_model):
 
         Parameters
         ----------
-        X : array-like, shpae (n_predictors)
+        X : array-like, shape (n_predictors)
             Predictors, where ``n_predictors`` is the number of variables.
         pred_model : model object implementing 'predict' or 'predict_proba'
             Model to predict the expectation. For linear regression or non-linear reggression, model object must have ``predict`` method.
diff --git a/causallearn/search/FCMBased/lingam/direct_lingam.py b/causallearn/search/FCMBased/lingam/direct_lingam.py
@@ -146,7 +146,7 @@ def _entropy(self, u):
                k2 * (np.mean(u * np.exp((-u ** 2) / 2))) ** 2
 
     def _diff_mutual_info(self, xi_std, xj_std, ri_j, rj_i):
-        """Calculate the difference of the mutual informations."""
+        """Calculate the difference of the mutual information."""
         return (self._entropy(xj_std) + self._entropy(ri_j / np.std(ri_j))) - \
                (self._entropy(xi_std) + self._entropy(rj_i / np.std(rj_i)))
 
@@ -215,7 +215,7 @@ def _search_causal_order(self, X, U):
         return Uc[np.argmax(M_list)]
 
     def _mutual_information(self, x1, x2, param):
-        """Calculate the mutual informations."""
+        """Calculate the mutual information."""
         kappa, sigma = param
         n = len(x1)
         X1 = np.tile(x1, (n, 1))
diff --git a/causallearn/search/FCMBased/lingam/utils/__init__.py b/causallearn/search/FCMBased/lingam/utils/__init__.py
@@ -24,7 +24,7 @@ def print_causal_directions(cdc, n_sampling, labels=None):
     n_sampling : int
         Number of bootstrapping samples.
     labels : array-like, optional (default=None)
-        List of feature lables.
+        List of feature labels.
         If set labels, the output feature name will be the specified label.
     """
     for i, (fr, to, co) in enumerate(zip(cdc['from'], cdc['to'], cdc['count'])):
@@ -47,7 +47,7 @@ def print_dagc(dagc, n_sampling, labels=None):
     n_sampling : int
         Number of bootstrapping samples.
     labels : array-like, optional (default=None)
-        List of feature lables.
+        List of feature labels.
         If set labels, the output feature name will be the specified label.
     """
     for i, (dag, co) in enumerate(zip(dagc['dag'], dagc['count'])):
diff --git a/causallearn/search/ScoreBased/ExactSearch.py b/causallearn/search/ScoreBased/ExactSearch.py
@@ -60,7 +60,7 @@ def bic_exact_search(X, super_graph=None, search_method='astar',
     dag_est :  numpy.ndarray, shape=(d, d)
         Estimated DAG.
     search_stats :  dict
-        Some statistics related to the seach procedure.
+        Some statistics related to the search procedure.
     """
     n, d = X.shape
     if super_graph is None:
@@ -76,7 +76,7 @@ def bic_exact_search(X, super_graph=None, search_method='astar',
     if max_parents is None:
         max_parents = d
 
-    # To store statistics related to the seach procedure
+    # To store statistics related to the search procedure
     search_stats = {}
 
     # Generate parent graphs (without parallel computing)
@@ -102,7 +102,7 @@ def bic_exact_search(X, super_graph=None, search_method='astar',
     if verbose:
         _logger.info("Finished searching for shortest path.")
 
-    # Covnert structures to adjacency matrix
+    # Convert structures to adjacency matrix
     dag_est = np.zeros((d, d))
     for i, parents in enumerate(structures):
         dag_est[parents, i] = 1
@@ -135,14 +135,14 @@ def astar_shortest_path(parent_graphs, use_path_extension=True,
     structures :  tuple, shape=(d,)
         Optimal parents for each variable.
     shortest_path_stats :  dict
-        Some statistics related to the shortest path seach.
+        Some statistics related to the shortest path search.
     """
     d = len(parent_graphs)
     opened = PriorityQueue()
     closed = set()
 
     if use_k_cycle_heuristic:
-        # Create pattern databse
+        # Create pattern database
         PD = create_dynamic_pd(parent_graphs, k)
         if verbose:
             _logger.info('Finished creating pattern database.')
@@ -234,7 +234,7 @@ def dp_shortest_path(parent_graphs, use_path_extension=True, verbose=False):
     structures :  tuple, shape=(d,)
         Optimal parents for each variable.
     shortest_path_stats :  dict
-        Some statistics related to the shortest path seach.
+        Some statistics related to the shortest path search.
     """
     d = len(parent_graphs)
     order_graph = nx.DiGraph()
@@ -320,7 +320,7 @@ def generate_parent_graph(X, i, max_parents=None, parent_set=None, include_paren
         parent_set = tuple(set(parent_set))
 
     if include_parents is None:
-        include_parents = ()  # Emptry tuple
+        include_parents = ()  # Empty tuple
 
     parent_graph = []
     for j in range(len(parent_set) + 1):
diff --git a/causallearn/utils/DAG2CPDAG.py b/causallearn/utils/DAG2CPDAG.py
@@ -8,7 +8,7 @@
 
 def dag2cpdag(G: Dag) -> GeneralGraph:
     """
-    Covert a DAG to its corresponding PDAG
+    Convert a DAG to its corresponding PDAG
 
     Parameters
     ----------
diff --git a/causallearn/utils/DAG2PAG.py b/causallearn/utils/DAG2PAG.py
@@ -15,7 +15,7 @@
 
 def dag2pag(dag: Dag, islatent: List[Node]) -> GeneralGraph:
     """
-    Covert a DAG to its corresponding PAG
+    Convert a DAG to its corresponding PAG
     Parameters
     ----------
     dag : Direct Acyclic Graph
diff --git a/causallearn/utils/KCI/KCI.py b/causallearn/utils/KCI/KCI.py
@@ -520,7 +520,7 @@ def get_uuprod(self, Kx, Ky):
         Returns
         _________
         uu_prod: product of the eigenvectors of Kx and Ky
-        size_u: number of producted eigenvectors
+        size_u: number of produced eigenvectors
 
         """
         wx, vx = eigh(0.5 * (Kx + Kx.T))
@@ -562,7 +562,7 @@ def null_sample_spectral(self, uu_prod, size_u, T):
         Parameters
         ----------
         uu_prod: product of the eigenvectors of Kx and Ky
-        size_u: number of producted eigenvectors
+        size_u: number of produced eigenvectors
         T: sample size
 
         Returns
diff --git a/causallearn/utils/PCUtils/Helper.py b/causallearn/utils/PCUtils/Helper.py
@@ -56,7 +56,7 @@ def recursive_and(L):
     for value_config in range(len(value_config_list)):
         L = list(zip(conditioning_set, value_config_list[value_config]))
         sub_data = recursive_and(L)[:, [X,
-                                        Y]]  # obtain the subset dataset (containing only the X, Y columns) with only rows specifed in value_config
+                                        Y]]  # obtain the subset dataset (containing only the X, Y columns) with only rows specified in value_config
 
         # Step 2: Generate contingency table (applying Fienberg's method)
         def make_ctable(D, cat_size):
@@ -692,7 +692,7 @@ def get_sub_correlation_matrix(mvdata):
     -------
     INPUT:
     -------
-    mvdata: data, columns represent variables, rows represnet records/samples
+    mvdata: data, columns represent variables, rows represent records/samples
     -------
     OUTPUT:
     -------
@@ -711,7 +711,7 @@ def get_indx_complete_rows(mvdata):
     -------
     INPUT:
     -------
-    mvdata: data, columns represent variables, rows represnet records/samples
+    mvdata: data, columns represent variables, rows represent records/samples
     -------
     OUTPUT:
     -------
diff --git a/causallearn/utils/PDAG2DAG.py b/causallearn/utils/PDAG2DAG.py
@@ -9,7 +9,7 @@
 
 def pdag2dag(G: GeneralGraph) -> GeneralGraph:
     """
-    Covert a PDAG to its corresponding DAG
+    Convert a PDAG to its corresponding DAG
 
     Parameters
     ----------
diff --git a/causallearn/utils/ScoreUtils.py b/causallearn/utils/ScoreUtils.py
@@ -224,7 +224,7 @@ def minimize(X, f, length, *varargin):
                     if np.isnan(f3) or np.isinf(f3) or np.any(np.isnan(df3)) or np.any(np.isinf(df3)):
                         raise Exception('')
                     success = True
-                except Exception as e:  # catch any error which occured in f
+                except Exception as e:  # catch any error which occurred in f
                     x3 = (x2 + x3) / 2  # bisect and try again
 
             if f3 < F0:
@@ -393,7 +393,7 @@ def gpr_multi_new(logtheta=None, covfunc=None, x=None, y=None, xstar=None, nargo
     # whose mean and variance are returned. Note that in cases where the covariance
     # function has noise contributions, the variance returned in S2 is for noisy
     # test targets; if you want the variance of the noise-free latent function, you
-    # must substract the noise variance.
+    # must subtract the noise variance.
     #
     # usage: [nlml dnlml] = gpr(logtheta, covfunc, x, y)
     #    or: [mu S2]  = gpr(logtheta, covfunc, x, y, xstar)
@@ -472,8 +472,8 @@ def solve_chol(A, B):
     # contained in the file solve_chol.c, and should be compiled using matlabs mex
     # facility. However, this file also contains a (less efficient) matlab
     # implementation, supplied only as a help to people unfamiliar with mex. If
-    # the C code has been properly compiled and is avaiable, it automatically
-    # takes precendence over the matlab code in this file.
+    # the C code has been properly compiled and is available, it automatically
+    # takes precedence over the matlab code in this file.
 
     if A is None or B is None:
         raise Exception('Wrong number of arguments.')
@@ -589,8 +589,8 @@ def sq_dist(a, b=None, Q=None):
     # contained in the file sq_dist.c, and should be compiled using matlabs mex
     # facility. However, this file also contains a (less efficient) matlab
     # implementation, supplied only as a help to people unfamiliar with mex. If
-    # the C code has been properly compiled and is avaiable, it automatically
-    # takes precendence over the matlab code in this file.
+    # the C code has been properly compiled and is available, it automatically
+    # takes precedence over the matlab code in this file.
     #
     # Usage: C = sq_dist(a, b)
     #    or: C = sq_dist(a)  or equiv.: C = sq_dist(a, [])
diff --git a/causallearn/utils/cit.py b/causallearn/utils/cit.py
@@ -300,7 +300,7 @@ def _CalculatePValue(cTables, eTables):
             ----------
             cTables: tensor, (k, m, n) the [c]ounted tables (reflect joint P_XY)
             eTables: tensor, (k, m, n) the [e]xpected tables (reflect product of marginal P_X*P_Y)
-              if there are zero entires in eTables, zero must occur in whole rows or columns.
+              if there are zero entries in eTables, zero must occur in whole rows or columns.
               e.g. w.l.o.g., row eTables[w, i, :] == 0, iff np.sum(cTables[w], axis=1)[i] == 0, i.e. cTables[w, i, :] == 0,
                    i.e. in configuration of conditioning set == w, no X can be in value i.
 
diff --git a/docs/source/search_methods_index/Score-based causal discovery methods/ExactSearch.rst b/docs/source/search_methods_index/Score-based causal discovery methods/ExactSearch.rst
@@ -55,7 +55,7 @@ Returns
 --------------------------------------
 **dag_est**:  numpy.ndarray, shape=(d, d). Estimated DAG.
 
-**search_stats**:  dict. Some statistics related to the seach procedure.
+**search_stats**:  dict. Some statistics related to the search procedure.
 
 .. [1] Silander, T., & Myllymäki, P. (2006, July). A simple approach for finding the globally optimal Bayesian network structure. In Proceedings of the Twenty-Second Conference on Uncertainty in Artificial Intelligence (pp. 445-452).
 .. [2] Yuan, C., & Malone, B. (2013). Learning optimal Bayesian networks: A shortest path perspective. Journal of Artificial Intelligence Research, 48, 23-65.
diff --git a/docs/source/utilities.rst b/docs/source/utilities.rst
@@ -8,7 +8,7 @@ Graph operations
 DAG2CPDAG
 ^^^^^^^^^^^^
 
-Covert a DAG to its corresponding PDAG.
+Convert a DAG to its corresponding PDAG.
 
 Parameters
 """"""""""""""""""""""""""""""""""""
@@ -22,7 +22,7 @@ Returns
 DAG2PAG
 ^^^^^^^^^^^^
 
-Covert a DAG to its corresponding PAG.
+Convert a DAG to its corresponding PAG.
 
 Parameters
 """"""""""""""""""""""""""""""""""""
@@ -38,7 +38,7 @@ Returns
 PDAG2DAG
 ^^^^^^^^^^^^
 
-Covert a PDAG to its corresponding DAG.
+Convert a PDAG to its corresponding DAG.
 
 Parameters
 """"""""""""""""""""""""""""""""""""
diff --git a/docs/source/utilities_index/Evaluations.rst b/docs/source/utilities_index/Evaluations.rst
@@ -49,13 +49,13 @@ Parameters
 Returns
 -------------------
 
-**arrowsTp/Fp/Fn/Tn**: True postive/false positive/false negative/true negative arrows.
+**arrowsTp/Fp/Fn/Tn**: True positive/false positive/false negative/true negative arrows.
 
 **arrowPrec**: Precision for arrows.
 
 **arrowRec**: Recall for arrows.
 
-**adjTp/Fp/Fn/Tn**: True postive/false positive/false negative/true negative edges.
+**adjTp/Fp/Fn/Tn**: True positive/false positive/false negative/true negative edges.
 
 **adjPrec**: Precision for the adjacency matrix.
 
diff --git a/docs/source/utilities_index/Graph operations/DAG2CPDAG.rst b/docs/source/utilities_index/Graph operations/DAG2CPDAG.rst
@@ -1,7 +1,7 @@
 DAG2CPDAG
 ==============
 
-Covert a DAG to its corresponding CPDAG.
+Convert a DAG to its corresponding CPDAG.
 
 Usage
 --------
diff --git a/docs/source/utilities_index/Graph operations/DAG2PAG.rst b/docs/source/utilities_index/Graph operations/DAG2PAG.rst
@@ -1,7 +1,7 @@
 DAG2PAG
 ==================
 
-Covert a DAG to its corresponding PAG.
+Convert a DAG to its corresponding PAG.
 
 Usage
 --------
diff --git a/docs/source/utilities_index/Graph operations/PDAG2DAG.rst b/docs/source/utilities_index/Graph operations/PDAG2DAG.rst
@@ -1,7 +1,7 @@
 PDAG2DAG
 ============
 
-Covert a PDAG to its corresponding DAG.
+Convert a PDAG to its corresponding DAG.
 
 Usage
 --------
diff --git a/tests/TestMVPC_mv_fisherz.py b/tests/TestMVPC_mv_fisherz.py
@@ -111,12 +111,12 @@ def test_pc_with_mv_fisherz_MCAR_data_assertion(self):
 if __name__ == '__main__':
     test = Test_test_wise_deletion_PC()
     print('------------------------------')
-    print('Test test-wise deletion PC and MVPC on full datatsets.')
+    print('Test test-wise deletion PC and MVPC on full datasets.')
     test.test_pc_with_mv_fisherz_full_data()
     print('------------------------------')
-    print('Test test-wise deletion PC and MVPC on MCAR datatsets.')
+    print('Test test-wise deletion PC and MVPC on MCAR datasets.')
     test.test_pc_with_mv_fisherz_MCAR_data()
     print('------------------------------')
-    print('Test test-wise deletion PC on MCAR datatsets where most values are missing.')
+    print('Test test-wise deletion PC on MCAR datasets where most values are missing.')
     test.test_pc_with_mv_fisherz_MCAR_data_assertion()
     
