Update quick start tutorial

aaanalysis/_utils/_utils_check.py

@@ -80,14 +80,13 @@ def check_tuple(name=None, val=None, n=None):
 
 # Array checking functions
 def check_feat_matrix(X=None, names=None, labels=None):
-    """Check if X and y match (y can be labels or names). Otherwise, transpose X or give error."""
-    # TODO type check
-    X = check_array(X)
+    """Transpose matrix and check if X and y match (y can be labels or names). Transpose back otherwise """
+    X = check_array(X).transpose()
     if labels is not None:
         check_consistent_length(X, labels)
     n_samples, n_features = X.shape
     if n_samples == 0 or n_features == 0:
-        raise ValueError(f"Shape of X ({n_samples}, {n_features}) indicates empty feature matrix.")
+        raise ValueError(f"Shape of 'X' ({n_samples}, {n_features}) indicates empty feature matrix.")
     if names is None:
         return X, names
     else:

aaanalysis/_utils/utils_aaclust.py

@@ -37,3 +37,9 @@ def check_merge_metric(merge_metric=None):
         error = f"'merge_metric' should be None or one of following: {LIST_METRICS}"
         raise ValueError(error)
     return merge_metric
+
+def check_feat_matrix_n_clust_match(X=None, n_clusters=None):
+    """"""
+    n_samples, n_features = X.shape
+    if n_samples <= n_clusters:
+        raise ValueError(f"'X' must contain more samples ({n_samples}) then 'n_clusters' ({n_clusters})")

aaanalysis/aaclust/aaclust.py

@@ -11,6 +11,8 @@
 
 
 # I Helper Functions
+
+
 # Obtain centroids and medoids
 def cluster_center(X):
     """Compute cluster center (i.e., arithmetical mean over all data points/observations of a cluster)"""
@@ -29,7 +31,7 @@ def _cluster_medoid(X):
     """Obtain cluster medoids (i.e., scale closest to cluster center used as representative scale for a cluster)"""
     # Create new array with cluster center and given
     center_X = np.concatenate([cluster_center(X), X], axis=0)
-    # Get index for scale with highest correlation with cluster center
+    # Get index for scale with the highest correlation with cluster center
     ind_max = np.corrcoef(center_X)[0, 1:].argmax()
     return ind_max
 
@@ -410,6 +412,7 @@ def fit(self, X, names=None, on_center=True, min_th=0,  merge_metric="euclidean"
         ut.check_min_th(min_th=min_th)
         merge_metric = ut.check_merge_metric(merge_metric=merge_metric)
         X, names = ut.check_feat_matrix(X=X, names=names)
+        ut.check_feat_matrix_n_clust_match(X=X, n_clusters=n_clusters)
         args = dict(model=self.model, model_kwargs=self._model_kwargs, min_th=min_th, on_center=on_center)
         # Clustering using given clustering models
         if n_clusters is not None:

aaanalysis/utils.py

@@ -13,6 +13,7 @@
                                             check_feat_matrix, check_col_in_df)
 from aaanalysis._utils._utils_output import (print_red, print_start_progress, print_progress, print_finished_progress)
 from aaanalysis._utils.utils_aaclust import (check_model, check_min_th, check_merge_metric,
+                                             check_feat_matrix_n_clust_match,
                                              METRIC_CORRELATION, LIST_METRICS)
 from aaanalysis._utils.utils_cpp import (check_color, check_y_categorical, check_labels, check_ylim,
                                          check_args_len, check_args_len, check_list_parts,