py2ls 0.1.10.27__py3-none-any.whl → 0.2.1__py3-none-any.whl

py2ls/ips.py

@@ -1276,7 +1276,7 @@ def unzip(dir_path, output_dir=None):
             os.remove(output_dir)  # remove file
 
     # Handle .tar.gz files
-    if dir_path.endswith(".tar.gz"):
+    if dir_path.endswith(".tar.gz") or dir_path.endswith(".tgz"):
         import tarfile
 
         with tarfile.open(dir_path, "r:gz") as tar_ref:
@@ -1399,13 +1399,65 @@ def fload(fpath, kind=None, **kwargs):
         root = tree.getroot()
         return etree.tostring(root, pretty_print=True).decode()
 
-    def load_csv(fpath, engine="pyarrow", **kwargs):
-        print(f"engine={engine}")
-        df = pd.read_csv(fpath, engine=engine, **kwargs)
+    def load_csv(fpath, **kwargs):
+        engine = kwargs.get("engine", "pyarrow")
+        kwargs.pop("engine", None)
+        index_col = kwargs.get("index_col", None)
+        kwargs.pop("index_col", None)
+        memory_map = kwargs.get("memory_map", True)
+        kwargs.pop("memory_map", None)
+        skipinitialspace = kwargs.get("skipinitialspace", True)
+        kwargs.pop("skipinitialspace", None)
+        encoding = kwargs.get("encoding", "utf-8")
+        kwargs.pop("encoding", None)
+        try:
+            if engine == "pyarrow":
+                df = pd.read_csv(
+                    fpath,
+                    engine=engine,
+                    index_col=index_col,
+                    encoding=encoding,
+                    **kwargs,
+                )
+            else:
+                df = pd.read_csv(
+                    fpath,
+                    engine=engine,
+                    index_col=index_col,
+                    memory_map=memory_map,
+                    encoding=encoding,
+                    skipinitialspace=skipinitialspace,
+                    **kwargs,
+                )
+            print("File loaded successfully with utf-8 encoding.")
+        except UnicodeDecodeError:
+            encoding = get_encoding(fpath)
+            print(f"utf-8 failed. Retrying with detected encoding: {encoding}")
+            if engine == "pyarrow":
+                df = pd.read_csv(
+                    fpath,
+                    engine=engine,
+                    index_col=index_col,
+                    encoding=encoding,
+                    **kwargs,
+                )
+            else:
+                df = pd.read_csv(
+                    fpath,
+                    engine=engine,
+                    index_col=index_col,
+                    memory_map=memory_map,
+                    encoding=encoding,
+                    skipinitialspace=skipinitialspace,
+                    **kwargs,
+                )
+            print("File loaded successfully with utf-8 encoding.")
         return df
 
     def load_xlsx(fpath, **kwargs):
-        df = pd.read_excel(fpath, **kwargs)
+        engine = kwargs.get("engine", "openpyxl")
+        kwargs.pop("engine", None)
+        df = pd.read_excel(fpath, engine=engine, **kwargs)
         return df
 
     def load_ipynb(fpath, **kwargs):
@@ -1511,7 +1563,18 @@ def fload(fpath, kind=None, **kwargs):
         "pdf",
         "ipynb",
     ]
-    zip_types = ["gz", "zip", "7z", "tar", "tar.gz", "tar.bz2", "bz2", "xz", "rar"]
+    zip_types = [
+        "gz",
+        "zip",
+        "7z",
+        "tar",
+        "tar.gz",
+        "tar.bz2",
+        "bz2",
+        "xz",
+        "rar",
+        "tgz",
+    ]
     supported_types = [*doc_types, *img_types, *zip_types]
     if kind not in supported_types:
         print(f'Error:\n"{kind}" is not in the supported list {supported_types}')
@@ -1545,6 +1608,14 @@ def fload(fpath, kind=None, **kwargs):
         return load_xml(fpath)
     elif kind == "csv":
         return load_csv(fpath, **kwargs)
+    elif kind in ["ods", "ods", "odt"]:
+        engine = kwargs.get("engine", "odf")
+        kwargs.pop("engine", None)
+        return load_xlsx(fpath, engine=engine, **kwargs)
+    elif kind == "xls":
+        engine = kwargs.get("engine", "xlrd")
+        kwargs.pop("engine", None)
+        return load_xlsx(fpath, engine=engine, **kwargs)
     elif kind == "xlsx":
         return load_xlsx(fpath, **kwargs)
     elif kind == "ipynb":
@@ -1558,17 +1629,51 @@ def fload(fpath, kind=None, **kwargs):
     elif kind.lower() in zip_types:
         keep = kwargs.get("keep", False)
         fpath_unzip = unzip(fpath)
-        content_unzip = fload(fpath_unzip, **kwargs)
-        if not keep:
-            os.remove(fpath_unzip)
-        return content_unzip
+        if os.path.isdir(fpath_unzip):
+            print(f"{fpath_unzip} is a folder. fload stoped.")
+            fpath_list = os.listdir("./datasets/GSE10927_family.xml")
+            print(f"{len(fpath_list)} files within the folder")
+            if len(fpath_list) > 5:
+                pp(fpath_list[:5])
+                print("there are more ...")
+            else:
+                pp(fpath_list)
+            return fpath_list
+        elif os.path.isfile(fpath_unzip):
+            print(f"{fpath_unzip} is a file.")
+            content_unzip = fload(fpath_unzip, **kwargs)
+            if not keep:
+                os.remove(fpath_unzip)
+            return content_unzip
+        else:
+            print(f"{fpath_unzip} does not exist or is a different type.")
+
+    elif kind.lower() == "gmt":
+        import gseapy as gp
+
+        gene_sets = gp.read_gmt(fpath)
+        return gene_sets
     else:
         try:
-            with open(fpath, "r") as f:
-                content = f.readlines()
+            try:
+                with open(fpath, "r", encoding="utf-8") as f:
+                    content = f.readlines()
+            except UnicodeDecodeError:
+                print("Failed to read as utf-8, trying different encoding...")
+                with open(
+                    fpath, "r", encoding=get_encoding(fpath)
+                ) as f:  # Trying with a different encoding
+                    content = f.readlines()
         except:
-            with open(fpath, "r") as f:
-                content = f.read()
+            try:
+                with open(fpath, "r", encoding="utf-8") as f:
+                    content = f.read()
+            except UnicodeDecodeError:
+                print("Failed to read as utf-8, trying different encoding...")
+                with open(
+                    fpath, "r", encoding=get_encoding(fpath)
+                ) as f:  # Trying with a different encoding
+                    content = f.read()
         return content
 
 
@@ -4200,7 +4305,7 @@ def df_as_type(
     columns: Optional[Union[str, List[str]]] = None,
     astype: str = "datetime",
     format: Optional[str] = None,
-    inplace: bool = False,
+    inplace: bool = True,
     errors: str = "coerce",  # Can be "ignore", "raise", or "coerce"
     **kwargs,
 ) -> Optional[pd.DataFrame]:
@@ -4353,8 +4458,7 @@ def df_as_type(
             print(f"Error converting '{column}' to {astype}: {e}")
 
     # Return the modified DataFrame if inplace is False
-    if not inplace:
-        return df
+    return df
 
 
 # ! DataFrame

py2ls/plot.py

@@ -31,7 +31,7 @@ def df_corr(
     row_cluster=True,  # Perform clustering on rows
     col_cluster=True,  # Perform clustering on columns
     dendrogram_ratio=(0.2, 0.1),  # Adjust size of dendrograms
-    cbar_pos=(0.02, 0.8, 0.03, 0.2),  # Adjust colorbar position
+    cbar_pos=(0.02, 1, 0.02, 0.1),  # Adjust colorbar position
     xticklabels=True,  # Show column labels
     yticklabels=True,  # Show row labels
     **kwargs,
@@ -94,7 +94,7 @@ def df_corr(
         )
     else:
         # Create a standard heatmap
-        plt.figure(figsize=(10, 8))
+        plt.figure(figsize=figsize)
         ax = sns.heatmap(
             correlation_matrix,
             mask=mask_array,

{py2ls-0.1.10.27.dist-info → py2ls-0.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py2ls
-Version: 0.1.10.27
+Version: 0.2.1
 Summary: py(thon)2(too)ls
 Author: Jianfeng
 Author-email: Jianfeng.Liu0413@gmail.com

{py2ls-0.1.10.27.dist-info → py2ls-0.2.1.dist-info}/RECORD

@@ -207,15 +207,15 @@ py2ls/doc.py,sha256=xN3g1OWfoaGUhikbJ0NqbN5eKy1VZVvWwRlhHMgyVEc,4243
 py2ls/export_requirements.py,sha256=x2WgUF0jYKz9GfA1MVKN-MdsM-oQ8yUeC6Ua8oCymio,2325
 py2ls/freqanalysis.py,sha256=F4218VSPbgL5tnngh6xNCYuNnfR-F_QjECUUxrPYZss,32594
 py2ls/ich2ls.py,sha256=3E9R8oVpyYZXH5PiIQgT3CN5NxLe4Dwtm2LwaeacE6I,21381
-py2ls/ips.py,sha256=TMmk9kwxY8KWFWLbNpTxD4nad95uMpXgSqke0S-gAMo,161096
+py2ls/ips.py,sha256=HjMZDXzfOiqhgNOdtoX7dxoY2cRsrD78LXilWyIUffE,164940
 py2ls/netfinder.py,sha256=vgOOMhzwbjRuLWMAPyf_kh3HoOhsJ9dlA-tCkMf7kNU,55371
 py2ls/ocr.py,sha256=5lhUbJufIKRSOL6wAWVLEo8TqMYSjoI_Q-IO-_4u3DE,31419
-py2ls/plot.py,sha256=vkKwppGLjErM6s1L0JOhukX54XbfKXUl6ojhVztCBN4,100538
+py2ls/plot.py,sha256=x_bvQyPM6sl7IscgHPUbOEnqR82Iefcyur1JOweEAZw,100536
 py2ls/setuptools-70.1.0-py3-none-any.whl,sha256=2bi3cUVal8ip86s0SOvgspteEF8SKLukECi-EWmFomc,882588
 py2ls/sleep_events_detectors.py,sha256=bQA3HJqv5qnYKJJEIhCyhlDtkXQfIzqksnD0YRXso68,52145
 py2ls/stats.py,sha256=fJmXQ9Lq460StOn-kfEljE97cySq7876HUPTnpB5hLs,38123
 py2ls/translator.py,sha256=zBeq4pYZeroqw3DT-5g7uHfVqKd-EQptT6LJ-Adi8JY,34244
 py2ls/wb_detector.py,sha256=7y6TmBUj9exCZeIgBAJ_9hwuhkDh1x_-yg4dvNY1_GQ,6284
-py2ls-0.1.10.27.dist-info/METADATA,sha256=vby3fz3bfQ7SzPfG49id_MWTInQE1VGqFRxRca7sahs,20040
-py2ls-0.1.10.27.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-py2ls-0.1.10.27.dist-info/RECORD,,
+py2ls-0.2.1.dist-info/METADATA,sha256=Qr6DFCoJWEj0_JrHmUDLJYRtoPqO7GyHth0Apsq5wOk,20036
+py2ls-0.2.1.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+py2ls-0.2.1.dist-info/RECORD,,