sequenzo 0.1.18__cp39-cp39-macosx_10_9_universal2.whl → 0.1.20__cp39-cp39-macosx_10_9_universal2.whl

sequenzo/clustering/KMedoids.py

@@ -14,6 +14,45 @@ clustering_c_code = importlib.import_module("sequenzo.clustering.clustering_c_co
 
 from sequenzo.clustering.utils.disscenter import disscentertrim
 
+import glob
+import os
+import sys
+import cffi
+
+ffi = cffi.FFI()
+
+if sys.platform.startswith("win"):
+    files = glob.glob(os.path.join(os.path.dirname(__file__), "*.pyd"))
+else:
+    files = glob.glob(os.path.join(os.path.dirname(__file__), "*.so"))
+
+if not files:
+    raise FileNotFoundError("No compiled library found")
+
+lib_file = files[0]
+
+try:
+    # 重定向 stderr 来抑制 cffi 的错误信息输出
+    import io
+    old_stderr = sys.stderr
+    sys.stderr = io.StringIO()
+    try:
+        lib = ffi.dlopen(lib_file)
+    finally:
+        # 恢复 stderr
+        sys.stderr = old_stderr
+except ImportError as e:
+    if sys.platform.startswith("win") and 'cffi mode "ANY" is only "ABI"' in str(e):
+        # Windows 降级到 ABI 模式，同样抑制错误信息
+        old_stderr = sys.stderr
+        sys.stderr = io.StringIO()
+        try:
+            lib = ffi.dlopen(lib_file)
+        finally:
+            sys.stderr = old_stderr
+    else:
+        raise
+
 def KMedoids(diss, k, weights=None, npass=1, initialclust=None, method='PAMonce', cluster_only=False):
 
     # Lazily import the c_code module to avoid circular dependencies during installation

sequenzo/clustering/hierarchical_clustering.py

@@ -75,11 +75,25 @@ from scipy.spatial.distance import squareform
 # sklearn metrics no longer needed - using C++ implementation
 from fastcluster import linkage
 
-import rpy2.robjects as ro
-from rpy2.robjects import numpy2ri
-from rpy2.robjects.packages import importr
-from rpy2.robjects.conversion import localconverter
-from rpy2.robjects import FloatVector
+# Optional R integration for Ward D method
+_RPY2_AVAILABLE = False
+ro = None
+importr = None
+
+try:
+    import rpy2.robjects as ro
+    from rpy2.robjects.packages import importr, PackageNotInstalledError
+    _RPY2_AVAILABLE = True
+except Exception:
+    # Catch any error during rpy2 import/initialization (e.g., R not installed / R_HOME missing on Windows)
+    _RPY2_AVAILABLE = False
+
+if not _RPY2_AVAILABLE:
+    print("[!] Warning: rpy2 not available or R not properly configured. Ward D clustering method will not be supported.")
+    print("    To use Ward D: please install R and properly configure rpy2 (make sure `R --version` works).")
+    print("    use 'ward_d2', 'average', 'complete', or 'single' methods.")
+    print("    See CRAN: https://cloud.r-project.org.")
+    print("    Alternatively, use the 'ward_d2', 'average', 'complete', or 'single' method instead.")
 
 # Import C++ cluster quality functions
 try:
@@ -89,12 +103,91 @@ except ImportError:
     _CPP_AVAILABLE = False
     print("[!] Warning: C++ cluster quality functions not available. Using Python fallback.")
 
+
 # Corrected imports: Use relative imports *within* the package.
 from sequenzo.visualization.utils import save_and_show_results
 
 # Global flag to ensure Ward warning is only shown once per session
 _WARD_WARNING_SHOWN = False
 
+def _ensure_r_environment_and_fastcluster():
+    """
+    Ensure R runtime is discoverable and R package 'fastcluster' is installed.
+    - If R is not available, raise with platform-specific installation instructions
+    - Choose CRAN mirror
+    - Auto-install 'fastcluster' if not present
+    """
+    print('  - Checking R runtime environment and fastcluster.')
+    # Try to load R runtime via rpy2. If this fails, provide installation instructions.
+    try:
+        utils = importr('utils')
+    except Exception as e:
+        # Build platform-specific guidance
+        if sys.platform == 'darwin':
+            guide = (
+                "No available R runtime environment detected.\n"
+                "Please install and configure R first:\n"
+                "1) Installation: Install R from CRAN (recommended macOS package): https://cloud.r-project.org \n"
+                "   Or use Homebrew: brew install r\n"
+                "2) Verification: Run `R --version` in the terminal to check the version information.\n"
+                "3) If the error persists, you can set the environment variable manually:\n"
+                "   export R_HOME=/Library/Frameworks/R.framework/Resources\n"
+                "   and ensure that `which R` can locate the R executable."
+            )
+        elif sys.platform.startswith('linux'):
+            guide = (
+                "No available R runtime environment detected.\n"
+                "Please install and configure R first:\n"
+                "1) Installation: Use your distribution's package manager "
+                "(e.g., Ubuntu: sudo apt-get install -y r-base; CentOS/RHEL: sudo yum install -y R)\n"
+                "   or download from CRAN: https://cloud.r-project.org \n"
+                "2) Verification: Run `R --version` in the terminal.\n"
+                "3) If necessary, set R_HOME to point to the R installation directory (e.g., /usr/lib/R)."
+            )
+        elif sys.platform == 'win32':
+            guide = (
+                "No available R runtime environment detected.\n"
+                "Please install and configure R first:\n"
+                "1) Installation: Download and install R for Windows from CRAN: https://cloud.r-project.org \n"
+                "2) Verification: Run `R --version` in PowerShell.\n"
+                "3) If the error persists, add the R bin directory to your system PATH environment variable,\n"
+                "   e.g., C:\\Program Files\\R\\R-x.y.z\\bin; if needed, set R_HOME to that R directory."
+            )
+        else:
+            guide = (
+                "No available R runtime environment detected. "
+                "Please install R and ensure that `R --version` can be executed from the command line.\n"
+                "CRAN: https://cloud.r-project.org"
+            )
+        raise RuntimeError(f"{guide}\nOriginal error: {e}")
+
+    # Ensure mirror
+    try:
+        # If a mirror is not chosen, choose the first (may be reset by user later)
+        utils.chooseCRANmirror(ind=1)
+    except Exception:
+        # Fallback to cloud mirror
+        try:
+            ro.r('options(repos = c(CRAN = "https://cloud.r-project.org"))')
+        except Exception:
+            pass
+
+    # Ensure fastcluster installed
+    try:
+        importr('fastcluster')
+    except PackageNotInstalledError:
+        try:
+            # Try install with explicit repo and limited parallelism
+            utils.install_packages('fastcluster', repos='https://cloud.r-project.org', Ncpus=2)
+            importr('fastcluster')
+        except Exception as install_err:
+            raise RuntimeError(
+                "Failed to install R package 'fastcluster' automatically. "
+                "Please ensure internet access and a working R toolchain are available. "
+                f"Original error: {install_err}"
+            )
+
+
 
 def _check_euclidean_compatibility(matrix, method):
     """
@@ -439,6 +532,15 @@ class Cluster:
             fastcluster_method = self._map_method_name(self.clustering_method)
 
             if self.clustering_method == "ward_d" or self.clustering_method == "ward":
+                if not _RPY2_AVAILABLE:
+                    raise ImportError(
+                        "rpy2 is required for Ward D clustering method but is not available or R is not properly configured.\n"
+                        "Install rpy2 and ensure R is properly set up, or install with: pip install sequenzo[r]\n"
+                        "Alternatively, use 'ward_d2', 'average', 'complete', or 'single' methods."
+                    )
+                # Ensure R and R package fastcluster are available (auto-install if needed)
+                _ensure_r_environment_and_fastcluster()
+
                 fastcluster_r = importr("fastcluster")
 
                 # 将 full_matrix 转换为 R 矩阵（直接从 Python 数组创建），避免 rpy2 对大向量长度出错
@@ -1248,7 +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

@@ -462,8 +462,17 @@ class SequenceData:
 
     def plot_legend(self, save_as=None, dpi=200):
         """Displays the saved legend for sequence state colors."""
+        # Ensure legend handles exist even if get_legend() wasn't called
+        legend_handles = getattr(self, "legend_handles", None)
+        if not legend_handles:
+            legend_handles = [
+                plt.Rectangle((0, 0), 1, 1, color=self.color_map[i + 1], label=self.labels[i]
+                              ) for i in range(len(self.states))
+            ]
+            self.legend_handles = legend_handles
+
         fig, ax = plt.subplots(figsize=(2, 2))
-        ax.legend(handles=self.legend_handles, loc='center', title="States", fontsize=10)
+        ax.legend(handles=legend_handles, loc='center', title="States", fontsize=10)
         ax.axis('off')
 
         if save_as:

sequenzo/dissimilarity_measures/get_distance_matrix.py

@@ -42,7 +42,6 @@
                                 Designates a seqcost method to build sm. "CONSTANT" is not relevant for "DHD".
                             sm is mandatory when method is one of "OM", "OMloc", "OMslen", "OMspell", "OMstran", or "TWED".
                             sm is autogenerated when method is one of "HAM" or "DHD" and sm = NULL.
-            with.missing   : Should the non-deleted missing value be added to the alphabet as an additional state?
             full.matrix    : Default: TRUE. When refseq = NULL, if TRUE, the full distance matrix is returned,
                             if FALSE, an object of class dist is returned,
                             that is, a vector containing only values from the lower triangle of the distance matrix.
@@ -277,7 +276,7 @@ def get_distance_matrix(seqdata=None, method=None, refseq=None, norm="none", ind
     # OM, OMspell, HAM, DHD
     if method in om_methods + ["HAM", "DHD"]:
         if sm_type == "matrix":
-            if method in [om_methods, "TWED"]:
+            if method in om_methods + ["TWED"]:
                 # TODO : checkcost()
                 pass
             elif method == "HAM":
@@ -642,7 +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",