cvmcore 0.2.2__tar.gz → 0.3.0__tar.gz

cvmcore-0.3.0/.gitignore

@@ -0,0 +1,2 @@
+# 忽略mac文件
+.DS_Store

cvmcore-0.3.0/.python-version

@@ -0,0 +1 @@
+3.10

{cvmcore-0.2.2 → cvmcore-0.3.0}/PKG-INFO

@@ -1,22 +1,17 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: cvmcore
-Version: 0.2.2
-Summary: SZQ lab data analysis core function
-Home-page: https://github.com/hbucqp/cvmplot
-Author: Qingpo Cui
-Author-email: cqp@cau.edu.cn
-License: MIT Licence
-Keywords: pip,mlst,cgmlst,plot
-Platform: any
-Classifier: Development Status :: 3 - Alpha
-Classifier: Intended Audience :: Developers
-Classifier: Topic :: Software Development :: Build Tools
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
+Version: 0.3.0
+Summary: Major plot function used by SZQ lab from China Agricultural University
+Project-URL: Homepage, https://github.com/hbucqp/cvmcore
+Project-URL: Repository, https://github.com/hbucqp/cvmcore
+Author-email: Qingpo Cui <cqp@cau.edu.cn>
+License: MIT
+Requires-Python: >=3.10
+Requires-Dist: biopython>=1.87
+Requires-Dist: numba>=0.65.1
+Requires-Dist: numpy>=2.2.6
+Requires-Dist: pandas>=2.3.3
+Requires-Dist: scipy>=1.15.3
 Description-Content-Type: text/markdown
 
 # cvmcore

cvmcore-0.3.0/pyproject.toml

@@ -0,0 +1,34 @@
+[build-system]
+requires = ["hatchling>=1.20"]
+build-backend = "hatchling.build"
+
+[project]
+name = "cvmcore"
+version = "0.3.0"
+description = "Major plot function used by SZQ lab from China Agricultural University"
+readme = "README.md"
+requires-python = ">=3.10"
+authors = [
+    { name = "Qingpo Cui", email = "cqp@cau.edu.cn" },
+]
+license = { text = "MIT" }
+dependencies = [
+    "biopython>=1.87",
+    "numba>=0.65.1",
+    "numpy>=2.2.6",
+    "pandas>=2.3.3",
+    "scipy>=1.15.3",
+]
+
+[project.urls]
+Homepage = "https://github.com/hbucqp/cvmcore"
+Repository = "https://github.com/hbucqp/cvmcore"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/cvmcore"]
+
+[[tool.uv.index]]
+url = "https://mirrors.aliyun.com/pypi/simple"
+default = true
+
+

{cvmcore-0.2.2 → cvmcore-0.3.0/src}/cvmcore/__init__.py

@@ -3,7 +3,7 @@
 __title__ = 'cvmplot'
 __description__ = 'Major plot function used by SZQ lab from China Agricultural University'
 __url__ = 'https://github.com/hbucqp/cvmplot'
-__version__ = "0.2.2"
+__version__ = "0.3.0"
 __author__ = 'Qingpo Cui'
 __author_email__ = 'cqp@cau.edu.cn'
 __license__ = 'MIT'

{cvmcore-0.2.2 → cvmcore-0.3.0/src}/cvmcore/cvmcore.py

@@ -1,5 +1,4 @@
 import os
-import sys
 import time
 
 # data process
@@ -7,8 +6,6 @@ import numpy as np
 import pandas as pd
 from scipy.cluster.hierarchy import linkage, dendrogram, complete, to_tree
 from scipy.spatial.distance import squareform
-from tabulate import tabulate
-from io import StringIO
 import warnings
 # from Bio.Blast import NCBIWWW
 with warnings.catch_warnings():
@@ -20,21 +17,44 @@ with warnings.catch_warnings():
     from Bio.Blast import NCBIXML
 
 
-# matplotlib
-import matplotlib
-import matplotlib as mpl
-from matplotlib import pyplot as plt
-from matplotlib.lines import Line2D
-from matplotlib.patches import Patch, FancyArrow
-from matplotlib.transforms import Affine2D
-from matplotlib.colors import LinearSegmentedColormap
-import matplotlib.collections as mpcollections
-from mpl_toolkits.axes_grid1.inset_locator import inset_axes
-from typing import Optional, List, Dict, Union, Tuple
+# import numba for multithreads compute
+from numba import njit, prange, set_num_threads
+
+
+
+
+@njit(parallel=True)
+def _diff_matrix_numba(array):
+    """
+    计算 cgMLST 两两 allelic distance。
+
+    array:
+        n_samples x n_loci
+        dtype 建议 int32
+        缺失值用 -1 表示
+
+    规则：
+        两个样本同一位点都非缺失，且等位基因不同，则差异 +1
+        任一方缺失，则该位点跳过
+    """
+    n, m = array.shape
+    diff_matrix = np.zeros((n, n), dtype=np.uint16)
+
+    for i in prange(n):
+        row_i = array[i]
+        for j in range(i + 1, n):
+            row_j = array[j]
+            d = 0
+            for k in range(m):
+                a = row_i[k]
+                b = row_j[k]
+                if a != -1 and b != -1 and a != b:
+                    d += 1
+            diff_matrix[i, j] = d
+            diff_matrix[j, i] = d
+
+    return diff_matrix
 
-plt.rcParams['font.family'] = 'sans-serif'
-plt.rcParams['font.sans-serif'] = ['Arial']
-plt.rcParams['svg.fonttype'] = 'none'
 
 
 class cfunc():
@@ -139,3 +159,78 @@ class cfunc():
         # Write the modified sequences to the new fasta file
         with open(output_file, "w") as output_handle:
             SeqIO.write(new_records, output_handle, "fasta")
+
+    @staticmethod
+    def get_diff_matrix(array, threads=None):
+        """
+        Optimized Function for Distance Matrix Calculation
+
+        input:
+            array: numpy array or pandas values
+                the input arraly could contains np.nan
+            threads: number of threads
+
+        out:
+            n x n pairwise diff matrix, dtype=uint16
+
+        note:
+            If the number of input array columns exceeds 65,535, change uint16 to uint32
+        """
+
+        # 1. 转成 numpy array
+        array = np.asarray(array)
+
+        # 2. 把 float/NaN 转成 int32/-1
+        #    cgMLST allele 本质是整数，没必要用 float
+        if np.issubdtype(array.dtype, np.floating):
+            array = np.where(np.isnan(array), -1, array).astype(np.int32)
+        else:
+            array = array.astype(np.int32, copy=False)
+
+        # 3. 如果有线程参数，设置 numba 线程数
+        if threads is not None:
+            set_num_threads(int(threads))
+
+        # 4. 计算距离矩阵
+        return _diff_matrix_numba(array)
+
+
+    @staticmethod
+    def df2matrix(df):
+        """
+        convert np.nan to -1 in the input dataframe and return as numpy array
+        input:
+            pandas dataframe
+        output:
+            numpy array
+        """
+        numeric_df = df.apply(pd.to_numeric, errors="coerce")
+        matrix = numeric_df.to_numpy(dtype=np.float64, copy=False)
+        matrix = np.where(np.isnan(matrix), -1, matrix).astype(np.int32)
+        return matrix
+
+
+    @staticmethod
+    def get_diff_df(df, threads=None):
+        """
+        优化版 DataFrame 输入函数。
+
+        input:
+            df: input dataframe, such as the cgMLST results
+
+        output:
+             n x n pairwise distance dataframe
+        """
+
+        # 比 df.astype('float').values 更稳
+        # 先强制转数值，非法值变成 NaN
+        numeric_df = df.apply(pd.to_numeric, errors="coerce")
+        matrix = numeric_df.to_numpy(dtype=np.float64, copy=False)
+        diff_matrix = cfunc.get_diff_matrix(matrix, threads=threads)
+
+        return pd.DataFrame(
+            diff_matrix,
+            index=df.index,
+            columns=df.index,
+        )
+