sequenzo 0.1.19__cp312-cp312-win_amd64.whl → 0.1.21__cp312-cp312-win_amd64.whl

sequenzo/clustering/hierarchical_clustering.py

@@ -281,7 +281,7 @@ def _warn_ward_usage_once(matrix, method):
     if not _WARD_WARNING_SHOWN and method.lower() in ["ward", "ward_d", "ward_d2"]:
         if not _check_euclidean_compatibility(matrix, method):
             warnings.warn(
-                "\n⚠️  Ward linkage method detected with potentially non-Euclidean distance matrix!\n"
+                "\n[!] Ward linkage method detected with potentially non-Euclidean distance matrix!\n"
                 "   Ward clustering (both Ward D and Ward D2) assumes Euclidean distances for theoretical validity.\n"
                 "   \n"
                 "   Ward method variants:\n"
@@ -1350,7 +1350,7 @@ if __name__ == '__main__':
     labels = ['further education', 'higher education', 'employment', 'joblessness', 'school', 'training']
 
     # TODO: write a try and error: if no such a parameter, then ask to pass the right ones
-    # sequence_data = SequenceData(df, time=time, time_type="year", id_col="country", ids=df['country'].values, states=states)
+    # sequence_data = SequenceData(df, time=time, id_col="country", ids=df['country'].values, states=states)
 
     sequence_data = SequenceData(df,
                                  time=time_list,

sequenzo/define_sequence_data.py

@@ -13,7 +13,7 @@
 
     However, in this implementation, we require the user to explicitly provide the set of `states`. This explicit control
     is essential for ensuring consistent ordering of states, reproducibility of visualizations, and compatibility across
-    sequence datasets — especially when certain states may not appear in a given subset of the data.
+    sequence datasets - especially when certain states may not appear in a given subset of the data.
 
     As a result, `alphabet` is automatically set to `states` upon initialization, and kept as a semantic alias for clarity
     and potential compatibility. Users should treat `states` as the definitive state space and are not required to provide
@@ -170,7 +170,7 @@ class SequenceData:
             raise ValueError(
                 f"[!] You must specify a valid `id_col` parameter that exists in your dataset.\n"
                 f"    ID is required to uniquely identify each sequence (e.g., individuals).\n"
-                f"    → Hint: If your data does not have an ID column yet, you can use the helper function:\n\n"
+                f"    -> Hint: If your data does not have an ID column yet, you can use the helper function:\n\n"
                 f"        from sequenzo.utils import assign_unique_ids\n"
                 f"        df = assign_unique_ids(df, id_col_name='Entity ID')\n"
                 f"        df.to_csv('your_dataset_with_ids.csv', index=False)\n\n"
@@ -245,7 +245,7 @@ class SequenceData:
 
                 print(
                     "[!] Detected missing values (empty cells) in the sequence data.\n"
-                    f"    → Automatically added {example_missing} to `states` and `labels` for compatibility.\n"
+                    f"    -> Automatically added {example_missing} to `states` and `labels` for compatibility.\n"
                     "    However, it's strongly recommended to manually include it when defining `states` and `labels`.\n"
                     "    For example:\n\n"
                     f"        states = [{quote}At Home{quote}, {quote}Left Home{quote}, {example_missing}]\n"
@@ -519,7 +519,7 @@ class SequenceData:
     def flatten_weights(self) -> np.ndarray:
         """
         Repeat weights across sequence length for 1D alignment with flatten().
-        E.g., 5 sequences × 10 steps → repeat each weight 10 times.
+        E.g., 5 sequences x 10 steps -> repeat each weight 10 times.
         """
         return np.repeat(self.weights, self.n_steps)
 

sequenzo/dissimilarity_measures/get_distance_matrix.py

@@ -641,7 +641,7 @@ if __name__ == '__main__':
     # states = [1.0, 2.0, 3.0, 4.0, 5.0, 6.0]
     # # states = ['A', 'B', 'C', 'D', 'E', 'F', 'G']
     # labels = ['FT+WC', 'FT+BC', 'PT+WC', 'PT+BC', 'U', 'OLF']
-    # sequence_data = SequenceData(df, time=time_list, time_type="age", states=states, labels=labels, id_col="PID")
+    # sequence_data = SequenceData(df, time=time_list, states=states, labels=labels, id_col="PID")
     # om = get_distance_matrix(sequence_data, method="OM", sm="TRATE", indel="auto")
 
     # om.to_csv("D:/college/research/QiQi/sequenzo/files/sequenzo_Sohee_string_OM_TRATE.csv", index=True)

sequenzo/dissimilarity_measures/get_substitution_cost_matrix.py

@@ -231,7 +231,7 @@ if __name__ == "__main__":
 
     states = ['Very Low', 'Low', 'Middle', 'High', 'Very High']
 
-    sequence_data = SequenceData(df, time=time, time_type="year", id_col="country", states=states)
+    sequence_data = SequenceData(df, time=time, id_col="country", states=states)
 
     sm = get_substitution_cost_matrix(sequence_data,
                                       method="CONSTANT",