sequenzo 0.1.20__cp39-cp39-win_amd64.whl → 0.1.22__cp39-cp39-win_amd64.whl

sequenzo/multidomain/association_between_domains.py

@@ -307,5 +307,5 @@ def get_association_between_domains(seqdata_dom, assoc=("LRT", "V"), rep_method=
     print("  - v        : Cramer's V statistic (0 to 1, measures association strength).")
     print("  - p(v)     : p-value for Cramer's V (based on chi-squared test) + significance stars: * (p<.05), ** (p<.01), *** (p<.001)")
     print("  - strength : Qualitative label for association strength based on Cramer's V:")
-    print("               0.00–0.09 → None, 0.10–0.29 → Weak, 0.30–0.49 → Moderate, ≥0.50 → Strong")
+    print("               0.00-0.09 -> None, 0.10-0.29 -> Weak, 0.30-0.49 -> Moderate, >=0.50 -> Strong")
 

sequenzo/multidomain/combt.py

@@ -253,7 +253,7 @@ def merge_sparse_combt_types(distance_matrix,
         distance_matrix = distance_matrix.values
 
     if distance_matrix.shape[0] != distance_matrix.shape[1]:
-        raise ValueError("distance_matrix must be square (n × n)")
+        raise ValueError("distance_matrix must be square (n x n)")
 
     labels = np.array(labels)
     if len(labels) != distance_matrix.shape[0]:
@@ -323,7 +323,7 @@ def merge_sparse_combt_types(distance_matrix,
                         best_target = target
                 except Exception as e:
                     if verbose:
-                        print(f"[!] Error computing silhouette for merge {small} → {target}: {e}")
+                        print(f"[!] Error computing silhouette for merge {small} -> {target}: {e}")
                     continue
 
             # Execute merge if it maintains quality threshold
@@ -346,7 +346,7 @@ def merge_sparse_combt_types(distance_matrix,
 
                 if verbose:
                     print(
-                        f"[+] Merged {small} ({reverse_map[small]}, size={old_count}) → {best_target} ({reverse_map[best_target]}) | New ASW: {current_score:.4f}")
+                        f"[+] Merged {small} ({reverse_map[small]}, size={old_count}) -> {best_target} ({reverse_map[best_target]}) | New ASW: {current_score:.4f}")
 
                 merged = True
                 break
@@ -380,7 +380,7 @@ def merge_sparse_combt_types(distance_matrix,
         print("\n[>] Merge History Details:")
         for i, merge in enumerate(merge_info["merge_history"]):
             print(
-                f"  Merge {i + 1}: {merge['source']} (size={merge['source_size']}) → {merge['target']} | ASW: {merge['new_asw']:.4f}")
+                f"  Merge {i + 1}: {merge['source']} (size={merge['source_size']}) -> {merge['target']} | ASW: {merge['new_asw']:.4f}")
 
     # Visualize merge process if requested
     if visualize_process and merge_info["merge_history"]:

sequenzo/multidomain/linked_polyad.py

@@ -158,7 +158,7 @@ def linked_polyadic_sequence_analysis(seqlist: List[SequenceData],
 
     print("[Step 3] Computing all pairwise dissimilarities using method:", method)
     alldist = np.asarray(get_distance_matrix(merged_seqdata, method=method, **distance_parameters))
-    print("         → Dissimilarity matrix shape:", alldist.shape)
+    print("         -> Dissimilarity matrix shape:", alldist.shape)
 
     cj = np.array([n * p for p in range(P)])
 
@@ -199,7 +199,7 @@ def linked_polyadic_sequence_analysis(seqlist: List[SequenceData],
         else:
             raise ValueError("Invalid randomization type 'a'. Should be 1 or 2.")
 
-    iterator = tqdm(range(T), desc="→ Randomizing polyads") if verbose else range(T)
+    iterator = tqdm(range(T), desc="-> Randomizing polyads") if verbose else range(T)
     random_dists = Parallel(n_jobs=n_jobs)(delayed(random_sample_once)(i) for i in iterator)
     random_dists = np.array(random_dists)
 
@@ -231,7 +231,7 @@ def linked_polyadic_sequence_analysis(seqlist: List[SequenceData],
 
     print(
         f"[Step 7] Final summary: mean observed = {np.mean(observed_dists):.2f}, mean randomized = {mean_rand_dist:.2f}")
-    print(f"         → Significant polyads (V > 0.95): {np.sum(V_95)} / {n}")
+    print(f"         -> Significant polyads (V > 0.95): {np.sum(V_95)} / {n}")
 
     result = {
         "mean.dist": {"Obs": np.mean(observed_dists), "Rand": mean_rand_dist},

sequenzo/prefix_tree/__init__.py

@@ -3,7 +3,7 @@
 @File    : __init__.py
 @Time    : 02/05/2025 11:05
 @Desc    :
-    Prefix Tree Framework – exposes core indicators and utilities for sequence divergence analysis.
+    Prefix Tree Framework - exposes core indicators and utilities for sequence divergence analysis.
 """
 from .system_level_indicators import (
     build_prefix_tree,

sequenzo/prefix_tree/individual_level_indicators.py

@@ -609,7 +609,7 @@ class IndividualDivergence:
         Where z_{i,t} are the year-wise standardized prefix rarity scores using column-wise 
         standardization with sample standard deviation (ddof=1, as computed by pandas).
         
-        The standardized scores can be used with a threshold (e.g., z ≥ 1.5) to classify 
+        The standardized scores can be used with a threshold (e.g., z >= 1.5) to classify 
         individuals as diverged/not diverged, and are particularly useful for visualization.
         
         Parameters:
@@ -622,7 +622,7 @@ class IndividualDivergence:
         Returns:
         --------
         List[float]
-            Standardized rarity scores for each individual. Values ≥ z_threshold indicate divergence.
+            Standardized rarity scores for each individual. Values >= z_threshold indicate divergence.
             
         Notes:
         ------

sequenzo/sequence_characteristics/overall_cross_sectional_entropy.py

@@ -31,7 +31,7 @@ def get_cross_sectional_entropy(
         ...
 
     Additional metrics:
-        - per_time_entropy_norm: If norm=True, normalized by maximum entropy (|S|), range 0–1
+        - per_time_entropy_norm: If norm=True, normalized by maximum entropy (|S|), range 0-1
         - effective_states (H_effective): exp(H), equivalent "effective number of states"
         - summary: Key interpretation points (entropy peaks/valleys, dominant state intervals, average entropy, etc.)
 
@@ -199,7 +199,7 @@ def get_cross_sectional_entropy(
         if eff_s is not None:
             out["Effective States"] = eff_s
         return out
-    else:  # "dict" —— try to be more readable too
+    else:  # "dict" -- try to be more readable too
         res = {
             "Frequencies": freq_df_wide,
             "ValidStates": valid_s,

sequenzo/sequence_characteristics/plot_characteristics.py

@@ -360,7 +360,7 @@ def plot_cross_sectional_characteristics(seqdata,
                                           title="Cross-sectional entropy over time",
                                           show_title=True,
                                           xlabel="Time",
-                                          ylabel="Entropy (0–1)",
+                                          ylabel="Entropy (0-1)",
                                           line_color="#74C9B4",
                                           save_as=None,
                                           dpi=200,
@@ -396,7 +396,7 @@ def plot_cross_sectional_characteristics(seqdata,
     xlabel : str, optional (default="Time")
         Label for the x-axis.
         
-    ylabel : str, optional (default="Entropy (0–1)")
+    ylabel : str, optional (default="Entropy (0-1)")
         Label for the y-axis (main entropy axis).
         
     line_color : str, optional (default="#74C9B4")

sequenzo/sequence_characteristics/simple_characteristics.py

@@ -91,7 +91,7 @@ def get_subsequences_all_sequences(seqdata, dss: bool = True, with_missing: bool
     Args:
         seqdata: SequenceData object or pandas DataFrame containing your sequence data
         dss (bool): Whether to apply distinct state sequence preprocessing. 
-                   If True, consecutive identical states are compressed (e.g., [1,1,2,2] → [1,2])
+                   If True, consecutive identical states are compressed (e.g., [1,1,2,2] -> [1,2])
         with_missing (bool): Whether to include missing values in the calculation
         
     Returns:
@@ -266,7 +266,7 @@ def get_number_of_transitions(seqdata, norm=False, pwight=False) -> pd.DataFrame
         seq_3            2
         
         >>> # Example: sequence [1, 1, 2, 2, 1, 3] has 3 transitions:
-        >>> # 1→2 (position 3), 2→1 (position 5), 1→3 (position 6)
+        >>> # 1->2 (position 3), 2->1 (position 5), 1->3 (position 6)
         
     Note:
         Missing values are automatically ignored. Only counts actual state changes

sequenzo/suffix_tree/__init__.py

@@ -3,7 +3,7 @@
 @File    : __init__.py
 @Time    : 08/08/2025 15:50
 @Desc    :
-    Suffix Tree Framework – exposes core indicators and utilities for sequence convergence analysis.
+    Suffix Tree Framework - exposes core indicators and utilities for sequence convergence analysis.
 """
 from .system_level_indicators import (
     build_suffix_tree,

sequenzo/suffix_tree/individual_level_indicators.py

@@ -706,7 +706,7 @@ class IndividualConvergence:
         across individuals with sample standard deviation (ddof=1):
             z_{i,t} = (x_{i,t} - mean_t) / std_t
         
-        The standardized scores can be used with a threshold (e.g., z ≤ -1.5) to classify 
+        The standardized scores can be used with a threshold (e.g., z <= -1.5) to classify 
         individuals as converged/not converged, and are particularly useful for visualization.
         
         Note: For convergence (suffix tree), we look for LOW rarity (more typical patterns),
@@ -725,7 +725,7 @@ class IndividualConvergence:
         Returns:
         --------
         List[float]
-            Standardized rarity scores for each individual. Values ≤ -z_threshold indicate convergence.
+            Standardized rarity scores for each individual. Values <= -z_threshold indicate convergence.
             
         Notes:
         ------
@@ -1539,7 +1539,7 @@ def compute_quantile_thresholds_by_group(scores, group_labels, quantiles=None):
 
 def compute_quantile_thresholds_by_group_year(scores, group_labels, year_labels, quantiles=None, min_group_year_size=30):
     """
-    Compute quantile thresholds by group × year for time-drifting distributions.
+    Compute quantile thresholds by group x year for time-drifting distributions.
 
     Parameters
     ----------

sequenzo/visualization/plot_single_medoid.py

@@ -102,7 +102,7 @@ def compute_medoids_from_distance_matrix(distance_matrix: np.ndarray, seqdata: S
     :return: Tuple containing the medoid sequences and their indices.
     """
     if not isinstance(seqdata, SequenceData):
-        raise TypeError("❌ seqdata must be a SequenceData object.")
+        raise TypeError("[X] seqdata must be a SequenceData object.")
 
     # Process weights
     if isinstance(weights, str) and weights == "auto":
@@ -131,7 +131,7 @@ def compute_medoids_from_distance_matrix(distance_matrix: np.ndarray, seqdata: S
     medoid_indices = medoid_indices.tolist()
 
     if not all(isinstance(idx, int) for idx in medoid_indices):
-        raise ValueError("❌ medoid_indices must be a list of integers.")
+        raise ValueError("[X] medoid_indices must be a list of integers.")
 
     return medoid_sequences, medoid_indices
 

sequenzo/visualization/plot_transition_matrix.py

@@ -112,7 +112,7 @@ def print_transition_matrix(seqdata: SequenceData, transition_rates: np.ndarray)
     # Print each row
     for i, from_state in enumerate(state_labels):
         # Print row label
-        print(f"{from_state:>{max_label_width}} →", end=" ")
+        print(f"{from_state:>{max_label_width}} ->", end=" ")
 
         # Print transition rates
         for prob in transition_rates[i]:
@@ -131,7 +131,7 @@ def plot_transition_matrix(seqdata: SequenceData,
                            fontsize: int = 12,
                            save_as: Optional[str] = None,
                            dpi: int = 200,
-                           format: str = "%.2f") -> None:
+                           format: str = ".2f") -> None:
     """
     Plot state transition rate matrix as a heatmap.
 
@@ -157,6 +157,7 @@ def plot_transition_matrix(seqdata: SequenceData,
     # Generate heatmap using pre-formatted annotation strings
     ax = sns.heatmap(
         transition_matrix,
+        annot=True,
         fmt=format,
         cmap=cmap,
         xticklabels=seqdata.labels,

sequenzo/visualization/utils/utils.py

@@ -35,10 +35,10 @@ def set_up_time_labels_for_x_axis(seqdata: SequenceData,
         # If 10 or fewer time points, show all labels
         xtick_positions = np.arange(num_time_steps)
     elif num_time_steps <= 20:
-        # If 10–20 time points, show every 2nd label
+        # If 10-20 time points, show every 2nd label
         xtick_positions = np.arange(0, num_time_steps, step=2)
     else:
-        # More than 20 time points → Pick 10 evenly spaced tick positions
+        # More than 20 time points -> Pick 10 evenly spaced tick positions
         xtick_positions = np.linspace(0, num_time_steps - 1, num=10, dtype=int)
 
     # Set x-ticks and labels dynamically

sequenzo/with_event_history_analysis/sequence_analysis_multi_state_model.py

@@ -117,7 +117,7 @@ def sequence_analysis_multi_state_model(seqdata: SequenceData, sublength: int, c
     **What is person-period data?**
     Instead of having one row per person with all their time points as columns,
     person-period data has one row for each person-time combination. For example,
-    if we track 3 people over 5 time periods, we get 15 rows (3 × 5).
+    if we track 3 people over 5 time periods, we get 15 rows (3 x 5).
     
     **What are subsequences?**
     At each time point, we look ahead and record what happens in the next few time periods.

{sequenzo-0.1.20.dist-info → sequenzo-0.1.22.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sequenzo
-Version: 0.1.20
+Version: 0.1.22
 Summary: A fast, scalable and intuitive Python package for social sequence analysis.
 Author-email: Yuqi Liang <yuqi.liang.1900@gmail.com>, Xinyi Li <1836724126@qq.com>, Jan Heinrich Ernst Meyerhoff-Liang <jan.meyerhoff1@gmail.com>
 License: BSD 3-Clause License
@@ -44,7 +44,7 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: <3.13,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy<2.5,>=1.19.5
+Requires-Dist: numpy>=1.21.0
 Requires-Dist: pandas>=1.2.5
 Requires-Dist: matplotlib>=3.4.3
 Requires-Dist: seaborn>=0.11.2
@@ -54,22 +54,23 @@ Requires-Dist: cython>=0.29.21
 Requires-Dist: scipy>=1.6.3
 Requires-Dist: scikit-learn>=0.24.2
 Requires-Dist: fastcluster>=1.2.6
-Requires-Dist: rpy2>=3.5.12; python_version >= "3.12"
-Requires-Dist: rpy2>=3.5.6; python_version == "3.11"
-Requires-Dist: rpy2>=3.5.6; python_version == "3.10"
-Requires-Dist: rpy2>=3.5.6; python_version == "3.9"
 Requires-Dist: joblib>=1.0.1
 Requires-Dist: docutils>=0.17
 Requires-Dist: tqdm<5.0.0,>=4.62.3
 Requires-Dist: missingno<0.6.0,>=0.5.2
 Requires-Dist: cffi>=1.15.0
+Provides-Extra: r
+Requires-Dist: rpy2>=3.5.12; python_version >= "3.12" and extra == "r"
+Requires-Dist: rpy2>=3.5.6; python_version == "3.11" and extra == "r"
+Requires-Dist: rpy2>=3.5.6; python_version == "3.10" and extra == "r"
+Requires-Dist: rpy2>=3.5.6; python_version == "3.9" and extra == "r"
 Provides-Extra: dev
 Requires-Dist: pytest>=6.2.5; extra == "dev"
 Requires-Dist: flake8>=3.9.2; extra == "dev"
 Dynamic: license-file
 
 <p align="center">
-  <img src="https://raw.githubusercontent.com/Liang-Team/Sequenzo/main/assets/logo/FullLogo_NoBuffer.jpg" alt="Sequenzo Logo" width="400">
+  <img src="https://raw.githubusercontent.com/Liang-Team/Sequenzo/main/assets/logo/FullLogo_NoBuffer.jpg" alt="Sequenzo Logo" width="300">
 </p>
 
 <p align="center">
@@ -133,17 +134,18 @@ Perfect for research, policy, and business, enabling seamless analysis of catego
 
 Sequenzo provides pre-built Python wheels for maximum compatibility — no need to compile from source.
 
-| Platform         | Architecture                  | Python Versions       | Status            |
-|------------------|-------------------------------|-----------------------|-------------------|
-| **macOS**        | `universal2` (Intel + Apple Silicon) | 3.9, 3.10, 3.11, 3.12 | ✅ Pre-built wheel |
-| **Windows**      | `AMD64` (64-bit)              | 3.9, 3.10, 3.11, 3.12 | ✅ Pre-built wheel |
-| **Linux (glibc)**| `x86_64` (standard Linux)     | 3.9, 3.10, 3.11, 3.12 | ✅ Pre-built wheel |
-| **Linux (musl)** | `x86_64` (Alpine Linux)       | 3.9, 3.10, 3.11, 3.12 | ✅ Pre-built wheel |
+| Platform         | Architecture                    | Python Versions       | Status            |
+|------------------|---------------------------------|-----------------------|-------------------|
+| **macOS**        | Intel && Apple Silicon (64-bit) | 3.9, 3.10, 3.11, 3.12 | ✅ Pre-built wheel |
+| **Windows**      | `AMD64` (64-bit)                | 3.9, 3.10, 3.11, 3.12 | ✅ Pre-built wheel |
+| **Linux (glibc)**| `x86_64` (standard Linux)       | 3.9, 3.10, 3.11, 3.12 | ✅ Pre-built wheel |
+| **Linux (musl)** | `x86_64` (Alpine Linux)         | 3.9, 3.10, 3.11, 3.12 | ✅ Pre-built wheel |
 
 
 What do these terms mean?
-- **universal2 (macOS)**: One wheel supports both Intel (x86_64) and Apple Silicon (arm64) Macs.
-- **manylinux2014 (glibc-based Linux)**: Compatible with most mainstream Linux distributions (e.g., Ubuntu, Debian, CentOS).
+- **macosx_arm64 (macOS)**: One wheel supports Apple Silicon Macs.
+- **macosx_x86_64 (macOS)**: One wheel supports Intel Macs.
+- **manylinux2014_x86_64 (glibc-based Linux)**: Compatible with most mainstream Linux distributions (e.g., Ubuntu, Debian, CentOS).
 - **musllinux_1_2 (musl-based Linux)**: For lightweight Alpine Linux environments, common in Docker containers.
 - **AMD64 (Windows)**: Standard 64-bit Windows system architecture.
 
@@ -181,34 +183,6 @@ If you have some issues with the installation, it might because you have both Py
 pip3 install sequenzo
 ```
 
-### ⚠️ Having Installation or Import Issues?
-
-**Error:** `ImportError: numpy.core.multiarray failed to import`
-
-**Most likely cause:** NumPy version mismatch (you have NumPy 1.x, but need 2.x)
-
-**Quick Fix** (copy-paste these commands):
-```bash
-# Check your NumPy version first
-python -c "import numpy; print(f'NumPy: {numpy.__version__}')"
-
-# If you see 1.x.x, upgrade to 2.x:
-pip install --upgrade "numpy>=2.0.0"
-pip uninstall sequenzo -y
-pip install --no-cache-dir sequenzo
-```
-
-📖 **Still having issues?** 
-1. Run our diagnostic tool to identify the problem:
-   ```bash
-   curl -O https://raw.githubusercontent.com/Liang-Team/Sequenzo/main/diagnose.py
-   python diagnose.py
-   ```
-2. See our detailed guides:
-   - **[QUICK_FIX.md](QUICK_FIX.md)** - Simple step-by-step solutions
-   - **[TROUBLESHOOTING.md](TROUBLESHOOTING.md)** - Comprehensive troubleshooting
-   - **[docs/WHY_IMPORT_FAILS.md](docs/WHY_IMPORT_FAILS.md)** - Technical explanation
-
 ### Optional R Integration
 
 Sequenzo now checks the system environment variables before running ward.D hierarchical clustering.

{sequenzo-0.1.20.dist-info → sequenzo-0.1.22.dist-info}/RECORD

@@ -1,5 +1,5 @@
 sequenzo/__init__.py,sha256=uGmuqHVR8JDseOnN0tHgbly9nRzCeNY7A9OHBusdMP4,6990
-sequenzo/define_sequence_data.py,sha256=xdIekb8nT8dBPyHPpRalIxF44RLYKRXg59Us-tjZu7k,28627
+sequenzo/define_sequence_data.py,sha256=4ON_-Z8AMtqTlezYLKqbn9msBEs2Ba5RoIuJpgWMBpY,28621
 sequenzo/openmp_setup.py,sha256=f_8SxfcRhdI_uj_2RHFwiEw8iizB35Mv-3UUccRDt6U,7059
 sequenzo/big_data/__init__.py,sha256=iSZnGboYhbvsFf75uL8D8XDucXRxYypmFNN1uX5MxJo,152
 sequenzo/big_data/clara/__init__.py,sha256=pDR5_TSDisEhPtsA2gXGaXXBNTmWidJC_nnd9QMkz-U,700
@@ -8,14 +8,13 @@ sequenzo/big_data/clara/visualization.py,sha256=EpSmtAxRHVqcXlcXvSGiUuBjEETR7zK_
 sequenzo/big_data/clara/utils/__init__.py,sha256=2_o1tz8HFZVKFy8w8oJWdWlVKtwGjGY3z4PQylHKjt0,726
 sequenzo/big_data/clara/utils/aggregatecases.py,sha256=ul97pbnRlwxbFbX_0M4j-Bkyxkp7zMAKatSo4eanO24,2899
 sequenzo/big_data/clara/utils/davies_bouldin.py,sha256=4Y6VFjqopG3CaftQ8tDxQPjxxupJ6Hgv-yTXwCvgN7w,3037
-sequenzo/big_data/clara/utils/get_weighted_diss.c,sha256=0GbFqWOW8bmlAXqwH9hyBLjtCurgqBTUc-vzHCkGz5A,483771
-sequenzo/big_data/clara/utils/get_weighted_diss.cp39-win_amd64.pyd,sha256=8hyvAHDQOwohaPKwCJzhFXptO_dJV7kaMqDvCcdSMrk,53248
-sequenzo/big_data/clara/utils/get_weighted_diss.pyx,sha256=UYR-u8MDQEuWID3inKhSpBsuxu7qTFmEwLrjNPBMmUw,430
+sequenzo/big_data/clara/utils/get_weighted_diss.c,sha256=Nj6fZduxi-tdZ9c22NJBAzZRtaV6yYY1he0QTVIp3uE,483794
+sequenzo/big_data/clara/utils/get_weighted_diss.cp39-win_amd64.pyd,sha256=ikQ93kVblKCBPoJ_aYjU_28hQWb_PZgujWD3QK7lM9E,53248
 sequenzo/big_data/clara/utils/wfcmdd.py,sha256=-1H6CbTteTW-CeuQ_ehVDhnKH3ozcCkUobxoCSRIpYg,7074
 sequenzo/clustering/KMedoids.py,sha256=asktGP0KKgP4TsOH4bSYEWfE8yY5b9BfKa1d54KzaXI,7147
 sequenzo/clustering/__init__.py,sha256=duEY0Hq0-7Kc_lv0uFDK3D8IEXby-7Z0Rjff0EgO0KM,875
-sequenzo/clustering/clustering_c_code.cp39-win_amd64.pyd,sha256=YR0DLeo4VTOeehQo08BRy80LAYAvbk3nNPobVwbIuB4,253440
-sequenzo/clustering/hierarchical_clustering.py,sha256=3O2ipqqPMQ0O74H2YpLc2mmldWNFtiQI7Bs16hyXoDk,61572
+sequenzo/clustering/clustering_c_code.cp39-win_amd64.pyd,sha256=6u1PJJnSKfNQXw3ZYBc_YTZuEDirJsGzCYqamT-22kw,253440
+sequenzo/clustering/hierarchical_clustering.py,sha256=D4m3Wg3tPWBNXtPTsauxntD5ctx3hGXF9bjL-cB7VM0,61568
 sequenzo/clustering/src/KMedoid.cpp,sha256=Bb4LaRes004T9vyCmUknRS0NUaNr4ZoEpWvtkYGq-jw,9299
 sequenzo/clustering/src/PAM.cpp,sha256=UFXdTy1wMWheYa-fUoi8ASQPmn0Ew-AO7fqVQVxn_E8,8357
 sequenzo/clustering/src/PAMonce.cpp,sha256=C9HqGBRenmF2tnQofALjjU1As02dTw2oqEnuvdhoJIk,7943
@@ -47,7 +46,7 @@ sequenzo/datasets/polyadic_samplep1.csv,sha256=-2HvKSmevfqe1rWFVJlbnjousEgJRU_PH
 sequenzo/datasets/polyadic_seqc1.csv,sha256=ydZ-U8NTszR4lNBN4hhsH_dHfq0w5VZSMM7t9C5Uado,7028
 sequenzo/datasets/polyadic_seqp1.csv,sha256=sydXCR0JBKJlbMxJyGa46cic9XQstUpYFOtHaLmkp_0,7681
 sequenzo/dissimilarity_measures/__init__.py,sha256=qkWAQ1sBpS2aayO-FSA8Zha7rQ_vjs0_KIHEB60bVg4,958
-sequenzo/dissimilarity_measures/c_code.cp39-win_amd64.pyd,sha256=lJ8RwokDu-iGDu2HB0inKxGNSpIlKmfSf51HStkxOtQ,222208
+sequenzo/dissimilarity_measures/c_code.cp39-win_amd64.pyd,sha256=cCKw6xcnrShAXJAbf-TwhdyOySqXdMSmoU3dQZSBVgw,222208
 sequenzo/dissimilarity_measures/get_distance_matrix.py,sha256=dNZtqg0aN3vAz5r1sTgjS3jwLAzcXGbG4MGWeBEvhag,29886
 sequenzo/dissimilarity_measures/get_substitution_cost_matrix.py,sha256=Yed91VyNHkzeYxIduCTVF8hmJiAmltPH4R0lhvKQoKk,9533
 sequenzo/dissimilarity_measures/src/DHDdistance.cpp,sha256=RbWbSaELxlJiw5ST_JaD-wPx_sD7PGV2VdK4qEhOcxE,4714
@@ -212,43 +211,38 @@ sequenzo/dissimilarity_measures/src/xsimd/test/doc/writing_vectorized_code.cpp,s
 sequenzo/dissimilarity_measures/src/xsimd/test/test_wasm/test_wasm_playwright.py,sha256=9kcOfaW5dDqXs9AJBgmHoUx80tCHdGJ3d2Elr9dOkUo,3980
 sequenzo/dissimilarity_measures/utils/__init__.py,sha256=aZMQJGgJq4GsL1x-pQPLmL7KrJ78cHMH46GVmVE8pJ0,407
 sequenzo/dissimilarity_measures/utils/get_LCP_length_for_2_seq.py,sha256=bJjbEQcjENSAdLv2IMRUWJC4avldwCfHrtSEnlDEACY,1470
-sequenzo/dissimilarity_measures/utils/get_sm_trate_substitution_cost_matrix.c,sha256=ymnTDZAawshZIpG4GNvja8v5qxfzMrFWIg7BpPs-hY4,598371
-sequenzo/dissimilarity_measures/utils/get_sm_trate_substitution_cost_matrix.cp39-win_amd64.pyd,sha256=MnN35Jdn9DCyoRiDPDQc-fSagc9Z9zfQW8eL_1qbAHw,74240
-sequenzo/dissimilarity_measures/utils/get_sm_trate_substitution_cost_matrix.pyx,sha256=pwImh8jgNcbLLb0y1uhYAYNwXP93JPIh-DQ5frVjZUE,3216
-sequenzo/dissimilarity_measures/utils/seqconc.c,sha256=9_xI-P5ID0EPKmqY1bY9P7Vnlwyjwx97DTF06jbwP3o,505939
-sequenzo/dissimilarity_measures/utils/seqconc.cp39-win_amd64.pyd,sha256=ONXmCD6PylG_QrGB1jVqijuXNp-vlloKqHLxCQQf0Uo,56832
-sequenzo/dissimilarity_measures/utils/seqconc.pyx,sha256=7X8jv1kXq9o2pCnBNu5X_NZ0aMpWtxhhqnMsUJzqANo,770
-sequenzo/dissimilarity_measures/utils/seqdss.c,sha256=_VthgFnq5lCTgXDjcVkaxGyYOywcACKids-xrfeJKA8,620064
-sequenzo/dissimilarity_measures/utils/seqdss.cp39-win_amd64.pyd,sha256=KdsrH5f5iXoM5mG40TiPE6VLZ8mloLNHHi8TeU72Ch0,82432
-sequenzo/dissimilarity_measures/utils/seqdss.pyx,sha256=THl9-bw63NqgXAv9_OhlB6DF92A0moszCoA32XyyA0Q,1232
-sequenzo/dissimilarity_measures/utils/seqdur.c,sha256=Ca6dtgx134HyhUUVUp19hnDPR8KGuUwPf-mEvp5C-yM,542361
-sequenzo/dissimilarity_measures/utils/seqdur.cp39-win_amd64.pyd,sha256=oPaSDV_FtgBCzTCChOwla31Qe0xQuKEWmE4CXIRE2mw,67072
-sequenzo/dissimilarity_measures/utils/seqdur.pyx,sha256=RyBqjdO8SdiCYg7cScdT6uEWPjYX_e7-KUrlQkRkBC0,1288
-sequenzo/dissimilarity_measures/utils/seqlength.c,sha256=wPG-Oo7qfoY-pcn9jyNXzMI5amOyJGqae5d_niJfyQI,493532
-sequenzo/dissimilarity_measures/utils/seqlength.cp39-win_amd64.pyd,sha256=ZXVEFQTgqbKO_B157-cXFlsJLNy3fFxCkwGPgFZT5wA,56832
-sequenzo/dissimilarity_measures/utils/seqlength.pyx,sha256=y-792z6X1L4zychHJj5IQVHOfM5JibQ_ITFnkYHJO3c,564
+sequenzo/dissimilarity_measures/utils/get_sm_trate_substitution_cost_matrix.c,sha256=4wwXFfZ1rtGinidgo_FEb7VLvNUasC9eITEeklHygH8,598395
+sequenzo/dissimilarity_measures/utils/get_sm_trate_substitution_cost_matrix.cp39-win_amd64.pyd,sha256=jOqxRpZWE7XweIxZAV88mJ8QuWkLL7o14cgMWFg8fbI,74240
+sequenzo/dissimilarity_measures/utils/seqconc.c,sha256=RL_l7FC9pVhmhyV6JOeTE8XC6KRxCYi3_aIhhuNry7g,505901
+sequenzo/dissimilarity_measures/utils/seqconc.cp39-win_amd64.pyd,sha256=0ZxbpJdpGkHpStjvLoZJw_5eh3d7cjA4JbR_E8WJgfs,56832
+sequenzo/dissimilarity_measures/utils/seqdss.c,sha256=taO6RoSucXAnicfDvLMUUsKSsGBKCeLfSC6FNLt_5p4,619965
+sequenzo/dissimilarity_measures/utils/seqdss.cp39-win_amd64.pyd,sha256=nEK-JzNkZsCoOqy12jkowfvT1WAum1tHOc0ER-YjpvI,82432
+sequenzo/dissimilarity_measures/utils/seqdur.c,sha256=cViNFXq8Abr37BFRvaqSGaUHIaQ6AvUQ22aVtfbEDRU,542262
+sequenzo/dissimilarity_measures/utils/seqdur.cp39-win_amd64.pyd,sha256=vh1RcA7En6v8U5vi1BraqaPK_8wH_K2iIKUY2dDEvPo,67072
+sequenzo/dissimilarity_measures/utils/seqlength.c,sha256=64tQJ2WgRnemHCTV4HXYPalBK1g_6C4ESSinCE_hO18,493507
+sequenzo/dissimilarity_measures/utils/seqlength.cp39-win_amd64.pyd,sha256=6U7KbGHnXYCVEmtxyCECVsPj2j6fXKltAT9EDsdnb5k,56832
 sequenzo/multidomain/__init__.py,sha256=bVnbkJXuXj8y5lHreRBQnL1JFcrmlsz2TSt-qFfmWm8,734
-sequenzo/multidomain/association_between_domains.py,sha256=V4I_ILAAwf3cfz2i0HdLF8otAqPtF2LfjcCKo1IkfHA,10855
+sequenzo/multidomain/association_between_domains.py,sha256=tncMzsSn0yhRd9C37-GInHw7FlIucOGdb_affCAc_nk,10844
 sequenzo/multidomain/cat.py,sha256=7QqdEjZSiqDZnXGOWgkOoeRHg0USVAUKPlzXecJeMFQ,18022
-sequenzo/multidomain/combt.py,sha256=aE1OsCE5huJI6VqInBpBjT6WjAIZlgFHFtUwSZt9XLU,22079
+sequenzo/multidomain/combt.py,sha256=RCqk1GvJaZiLzI85FuiQ82xUn61xQTTVXyv3JmWSiqg,22075
 sequenzo/multidomain/dat.py,sha256=ljhc3kbAl8t8tpNh06eu4lAbR36PFUQCkxXBBtx81lo,3477
 sequenzo/multidomain/idcd.py,sha256=kKSGJfL_c0pBPbbDdR1BJ08GIIErGFj5ft7ieHyhnT8,4526
-sequenzo/multidomain/linked_polyad.py,sha256=l2ysDmhKeuHXq2xMVGb-WOq7AStnLd99NZ363gmh3lA,13614
-sequenzo/prefix_tree/__init__.py,sha256=YxMzr5UwM22DmpMDMAmKYI-vjhikDI8Gft_cJ9h1gYo,1126
-sequenzo/prefix_tree/individual_level_indicators.py,sha256=9JPINoPU50UGh9-D2QOAr7GQsxAkZ6qDmhKQtVwvZsU,52788
+sequenzo/multidomain/linked_polyad.py,sha256=efnPq0Jvr4XF_um3En6mEZxPywvrVmTmb75IUK75lgU,13611
+sequenzo/prefix_tree/__init__.py,sha256=Sp6HmMfzzv4C2jrUzAyS3GMW9dSAFwVM79vHtTGrLgU,1124
+sequenzo/prefix_tree/individual_level_indicators.py,sha256=dpzRBjwQboxZhpwscRdlGr19f7jpofepQF1oaxm1V6E,52786
 sequenzo/prefix_tree/system_level_indicators.py,sha256=tGnzRRqwzJbGv-vjOMAzdh6arN6QJkdsybe0Yif57ug,17507
 sequenzo/prefix_tree/utils.py,sha256=7DETf9i_OclRnWel680qD4wO1b8SffJVKq2Kx0zkTaQ,1489
 sequenzo/sequence_characteristics/__init__.py,sha256=dPdBD7K-dhsuLoVYhDDVUj9_DYBLPxSUh9GPJ8y2P4k,1224
 sequenzo/sequence_characteristics/complexity_index.py,sha256=KZ9TpaHtSIkbaqiOqEGRoFDYenrcuIzv34Du_RbL-6A,1762
-sequenzo/sequence_characteristics/overall_cross_sectional_entropy.py,sha256=ipyOVZ_o9xC-VYMLIPU7QcMlpJzyzAYG3qKdlBV5HS0,9302
-sequenzo/sequence_characteristics/plot_characteristics.py,sha256=LYOCNoS5BnFVbY1r-HEJSrQyACOTkxHuxguS4wVLI9o,25612
-sequenzo/sequence_characteristics/simple_characteristics.py,sha256=3dj8R_tDEtC7Wk58PzX4q0nXW9orW4f1hO1Lt2uXeCc,11715
+sequenzo/sequence_characteristics/overall_cross_sectional_entropy.py,sha256=nRRynM11tPD16cOlsw6PaNIvmpiXhLAuWBGLku4AFF4,9296
+sequenzo/sequence_characteristics/plot_characteristics.py,sha256=55I4Hbpko7QR54HeAKBTrW_meOZDezMVW2JpOwuzHOw,25608
+sequenzo/sequence_characteristics/simple_characteristics.py,sha256=pgINV0jvriJ3Zhi6Rm2lzxFZ0Yxzv-JHDuor62m8DjA,11711
 sequenzo/sequence_characteristics/state_frequencies_and_entropy_per_sequence.py,sha256=S5vzqUrJF_tadIlgd-S-jHfwWo3agFzc1ptAB6CXfPE,1313
 sequenzo/sequence_characteristics/turbulence.py,sha256=bixo1wcGNKYhsNmppORwv_fjy7xQxhGHo-OebG_TnYE,6217
 sequenzo/sequence_characteristics/variance_of_spell_durations.py,sha256=hx00o_ypk3VDUU1VHOI8eN_Fy12CKlOd02NeF_fKl04,3299
 sequenzo/sequence_characteristics/within_sequence_entropy.py,sha256=K9uhkTcy7SkW5By1lNX1DS6mREGj49ElgdPs1erJ-bI,1500
-sequenzo/suffix_tree/__init__.py,sha256=rJTkjwxg2Ub_jGxugYmEYWatTxtKu_BTWNDZbJ-KgsI,1148
-sequenzo/suffix_tree/individual_level_indicators.py,sha256=W36tEQEEmzu67gf5BLmau8Ja6-1BEBG5ArzZqbKc-PM,67211
+sequenzo/suffix_tree/__init__.py,sha256=0CSK_oC6xOrkbkScgOxD15HXwnAxaYuvizv0MSbTh-E,1146
+sequenzo/suffix_tree/individual_level_indicators.py,sha256=EQP1dWPsdI3aOedhCxcFIGIDWEt615x1V_SYZIAH_bs,67208
 sequenzo/suffix_tree/system_level_indicators.py,sha256=N4DrjM9fBHFqqcjDN1TAkwbkoDnlZSK2F8F2ERCizIQ,16962
 sequenzo/suffix_tree/utils.py,sha256=G1qYVNTTZHoUbY7x-j1FlZ-XfnXpGVHpaaa_tE4hMAE,1637
 sequenzo/visualization/__init__.py,sha256=JKYTCx4qbXF7oAE0OrfH_Tw5WhzTU_HJEn7XjJncFBw,944
@@ -257,16 +251,16 @@ sequenzo/visualization/plot_modal_state.py,sha256=wTAhdlu4px-dJdxM9LSSgDQioW46r-
 sequenzo/visualization/plot_most_frequent_sequences.py,sha256=UbkCjPUCKRAVY06Hm8HVSBI9_8iKFxkBdWwoMNmy0BE,6317
 sequenzo/visualization/plot_relative_frequency.py,sha256=tUNyIxc8C0SPjRJJYormBbTxWjvbox-pjaH9suzjRwU,16423
 sequenzo/visualization/plot_sequence_index.py,sha256=qc4h6JzQrDeiBsGvK6Cdn3HwDZFLfNzPqyFOon1ZQ6Q,41079
-sequenzo/visualization/plot_single_medoid.py,sha256=yqKzUANkmA-f-oreDZuAVAzMrALxn_uGjg815HAjKag,5971
+sequenzo/visualization/plot_single_medoid.py,sha256=K3d8feYV1S2PmjNdlRD961-bdt-An1-SWw8HKWDcBAc,5971
 sequenzo/visualization/plot_state_distribution.py,sha256=8uH533kwyqxIeGPM4eFJBWJ2eRgqEFPH3EiPJECzvS8,25978
-sequenzo/visualization/plot_transition_matrix.py,sha256=aQVJ61UictR5FtjvDvpzIYQZ0EdllJ0Cw_U3ZgxTgiE,6959
+sequenzo/visualization/plot_transition_matrix.py,sha256=ZmLyKniHROsnp4Xp2fggpofaskja7wiQNjOUL-jfkFE,6977
 sequenzo/visualization/utils/__init__.py,sha256=brrYzeIQm_cEM_TgA8_eRdckzN9WP1pj9g-f1qBzRLY,734
-sequenzo/visualization/utils/utils.py,sha256=9Z1L3PVL-Z41fvCW4tLJ5DaUVHO6C6PAJYlT2Q1jY4k,10249
+sequenzo/visualization/utils/utils.py,sha256=P33amescn1FLcfGwzxDrHpvaELzUHRKt06f3Iky23t0,10246
 sequenzo/with_event_history_analysis/__init__.py,sha256=B2EZhtJ7NEzO8piDwfSbh0l87fQ0ZuesPO5GNJEXKPo,730
-sequenzo/with_event_history_analysis/sequence_analysis_multi_state_model.py,sha256=wtsKnq-82bJhRH78cy49Nzo3yGJKoFD4RckoZ7D-SS8,37301
+sequenzo/with_event_history_analysis/sequence_analysis_multi_state_model.py,sha256=DdNqx8MBaxdLu-n-9RH5q2cSr5sWr18LTNF9qdNaKbM,37300
 sequenzo/with_event_history_analysis/sequence_history_analysis.py,sha256=vv5y2u9cpzhmNJX_fSYgLmFOncPvB7DVhWujljII1vA,10902
-sequenzo-0.1.20.dist-info/licenses/LICENSE,sha256=URRMyLHVeGF2kyDLC1xbRKBBIjDHJyWqF4nWpzfBX10,1497
-sequenzo-0.1.20.dist-info/METADATA,sha256=MCb19RNQA1wRatJpLP7WFhMc6A1lUOc1db5qKmsogl8,15452
-sequenzo-0.1.20.dist-info/WHEEL,sha256=XkFE14KmFh7mutkkb-qn_ueuH2lwfT8rLdfc5xpQ7wE,99
-sequenzo-0.1.20.dist-info/top_level.txt,sha256=yM8eczbPzqB1bRHMYLptvjjQ3p5tYhY6VjgWHUIi9vw,9
-sequenzo-0.1.20.dist-info/RECORD,,
+sequenzo-0.1.22.dist-info/licenses/LICENSE,sha256=URRMyLHVeGF2kyDLC1xbRKBBIjDHJyWqF4nWpzfBX10,1497
+sequenzo-0.1.22.dist-info/METADATA,sha256=wpW8q_ogXcCkfVKqQsOJ1AOzgup4NerTa4Th6IH_UOM,14591
+sequenzo-0.1.22.dist-info/WHEEL,sha256=XkFE14KmFh7mutkkb-qn_ueuH2lwfT8rLdfc5xpQ7wE,99
+sequenzo-0.1.22.dist-info/top_level.txt,sha256=yM8eczbPzqB1bRHMYLptvjjQ3p5tYhY6VjgWHUIi9vw,9
+sequenzo-0.1.22.dist-info/RECORD,,

sequenzo/big_data/clara/utils/get_weighted_diss.pyx

@@ -1,16 +0,0 @@
-import numpy as np
-cimport numpy as cnp
-
-def get_weighted_diss(cnp.ndarray[double, ndim=2] diss,
-                      cnp.ndarray[double, ndim=1] weights):
-    cdef int n = weights.shape[0]
-    cdef int i, j
-    cdef double factor
-
-    for i in range(n):
-        for j in range(i + 1, n):
-            factor = (weights[i] * weights[j]) ** 0.5
-            diss[i, j] *= factor
-            diss[j, i] = diss[i, j]
-
-    return diss

sequenzo/dissimilarity_measures/utils/get_sm_trate_substitution_cost_matrix.pyx

@@ -1,95 +0,0 @@
-# cython: boundscheck=False, wraparound=False
-import numpy as np
-cimport numpy as np
-
-import pandas as pd
-from libc.math cimport isnan
-
-def get_sm_trate_substitution_cost_matrix(
-    object seqdata,
-    bint time_varying=False,
-    bint weighted=True,
-    int lag=1,
-    bint count=False
-):
-    """
-    Compute substitution cost matrix (transition rate matrix)
-    """
-
-    from sequenzo.define_sequence_data import SequenceData
-    if not isinstance(seqdata, SequenceData):
-        raise ValueError("[x] Seqdata must be a pandas DataFrame wrapped in a SequenceData object.")
-
-    cdef np.ndarray[np.float64_t, ndim=1] weights
-    if weighted:
-        weights = np.asarray(seqdata.weights, dtype=np.float64)
-    else:
-        weights = np.ones(seqdata.seqdata.shape[0], dtype=np.float64)
-
-    states = seqdata.states.copy()
-    statesMapping = seqdata.state_mapping.copy()
-
-    cdef int _size = len(states) + 1
-    df = seqdata.seqdata
-    cdef int n_rows = df.shape[0]
-    cdef int sdur = df.shape[1]
-    cdef int i, j, t, sl, state_x, state_y
-    cdef double PA, PAB
-
-    if lag < 0:
-        all_transition = list(range(abs(lag), sdur))
-    else:
-        all_transition = list(range(sdur - lag))
-
-    cdef int num_transition = len(all_transition)
-
-    # convert df to NumPy 2D array of ints
-    seq_mat = df.to_numpy(dtype=np.float64)
-    cdef np.ndarray[np.float64_t, ndim=2] seq_mat_mv = seq_mat
-
-    if time_varying:
-        tmat = np.zeros((num_transition, _size, _size), dtype=np.float64)
-
-        for idx, sl in enumerate(all_transition):
-            for state_x in statesMapping.values():
-                PA = 0.0
-                for i in range(n_rows):
-                    if seq_mat_mv[i, sl] == state_x and not isnan(seq_mat_mv[i, sl + lag]):
-                        PA += weights[i]
-
-                if PA == 0:
-                    tmat[idx, state_x, :] = 0
-                else:
-                    for state_y in statesMapping.values():
-                        PAB = 0.0
-                        for i in range(n_rows):
-                            if (seq_mat_mv[i, sl] == state_x and
-                                not isnan(seq_mat_mv[i, sl + lag]) and
-                                seq_mat_mv[i, sl + lag] == state_y):
-                                PAB += weights[i]
-
-                        tmat[idx, state_x, state_y] = PAB if count else PAB / PA
-
-    else:
-        tmat = np.zeros((_size, _size), dtype=np.float64)
-
-        for state_x in statesMapping.values():
-            PA = 0.0
-            for i in range(n_rows):
-                for t in all_transition:
-                    if (seq_mat_mv[i, t] == state_x and not isnan(seq_mat_mv[i, t + lag])):
-                        PA += weights[i]
-
-            if PA == 0:
-                tmat[state_x, :] = 0
-            else:
-                for state_y in statesMapping.values():
-                    PAB = 0.0
-                    for i in range(n_rows):
-                        for t in all_transition:
-                            if (seq_mat_mv[i, t] == state_x and seq_mat_mv[i, t + lag] == state_y):
-                                PAB += weights[i]
-
-                    tmat[state_x, state_y] = PAB if count else PAB / PA
-
-    return tmat