ipyvasp 0.9.83__tar.gz → 0.9.85__tar.gz

{ipyvasp-0.9.83 → ipyvasp-0.9.85}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ipyvasp
-Version: 0.9.83
+Version: 0.9.85
 Summary: A processing tool for VASP DFT input/output processing in Jupyter Notebook.
 Home-page: https://github.com/massgh/ipyvasp
 Author: Abdul Saboor

ipyvasp-0.9.85/ipyvasp/_version.py

@@ -0,0 +1 @@
+__version__ = "0.9.85"

{ipyvasp-0.9.83 → ipyvasp-0.9.85}/ipyvasp/core/parser.py

@@ -1,4 +1,4 @@
-__all__ = ["Vasprun", "Vaspout", "minify_vasprun", "xml2dict"]
+__all__ = ["Vasprun", "Vaspout", "minify_vasprun", "xml2dict","read"]
 
 import re
 from io import StringIO
@@ -114,6 +114,35 @@ class Vaspout(DataSource):
     def __init__(self, path):
         raise NotImplementedError("Vaspout is not implemented yet.")
 
+def read(file, start_match, stop_match=r'\n', nth_match=1, skip_last=False,apply=None):
+    """Reads a part of the file between start_match and stop_match and returns a generator. It is lazy and fast.
+    `start_match` and `stop_match`(default is end of same line) are regular expressions. `nth_match` is the number of occurence of start_match to start reading.
+    `skip_last` is used to determine whether to keep or skip last line.
+    `apply` should be None or `func` to transform each captured line.
+    """
+    if "|" in start_match:
+        raise ValueError(
+            "start_match should be a single match, so '|' character is not allowed."
+        )
+    with Path(file).open("r") as f:
+        lines = islice(f, None)  # this is fast
+        matched = False
+        n_start = 1
+        for line in lines:
+            if re.search(start_match, line, flags=re.DOTALL):
+                if nth_match != n_start:
+                    n_start += 1
+                else:
+                    matched = True
+            if matched and re.search(
+                stop_match, line, flags=re.DOTALL
+            ):  # avoid stop before start
+                matched = False
+                if not skip_last:
+                    yield apply(line) if callable(apply) else line
+                break  # stop reading
+            if matched:  # should be after break to handle last line above
+                yield apply(line) if callable(apply) else line
 
 class Vasprun(DataSource):
     "Reads vasprun.xml file lazily. It reads only the required data from the file when a plot or data access is requested."
@@ -129,36 +158,14 @@ class Vasprun(DataSource):
             skipk if isinstance(skipk, (int, np.integer)) else self.get_skipk()
         )
 
-    def read(self, start_match, stop_match, nth_match=1, skip_last=False):
+    def read(self, start_match, stop_match=r'\n', nth_match=1, skip_last=False,apply=None):
         """Reads a part of the file between start_match and stop_match and returns a generator. It is lazy and fast.
-        `start_match` and `stop_match` are regular expressions. `nth_match` is the number of occurence of start_match to start reading.
+        `start_match` and `stop_match`(default is end of same line) are regular expressions. `nth_match` is the number of occurence of start_match to start reading.
         `skip_last` is used to determine whether to keep or skip last line.
+        `apply` should be None or `func` to transform each captured line.
         """
-        if "|" in start_match:
-            raise ValueError(
-                "start_match should be a single match, so '|' character is not allowed."
-            )
-
-        with self.path.open("r") as f:
-            lines = islice(f, None)  # this is fast
-            matched = False
-            n_start = 1
-            for line in lines:
-                if re.search(start_match, line, flags=re.DOTALL):
-                    if nth_match != n_start:
-                        n_start += 1
-                    else:
-                        matched = True
-                if matched and re.search(
-                    stop_match, line, flags=re.DOTALL
-                ):  # avoid stop before start
-                    matched = False
-                    if not skip_last:
-                        yield line
-
-                    break  # stop reading
-                if matched:  # should be after break to handle last line above
-                    yield line
+        kws = {k:v for k,v in locals().items() if k !='self'}
+        return read(self.path,**kws)
 
     def get_skipk(self):
         "Returns the number of k-points to skip in band structure plot in case of HSE calculation."

{ipyvasp-0.9.83 → ipyvasp-0.9.85}/ipyvasp/core/plot_toolkit.py

@@ -1009,7 +1009,10 @@ def iplot2html(fig, outfile=None, modebar=True):
 
 
 def iplot2widget(fig, fig_widget=None, template=None):
-    "Converts plotly's figure to FigureWidget by copying attributes and data. If fig_widget is provided, it will update it. Adds template if provided."
+    "Converts plotly's figure to FigureWidget by copying attributes and data. If fig_widget is provided, it will update it. Adds template if provided. If fig is FigureWidget, it is just returned"
+    if isinstance(fig, go.FigureWidget):
+        return fig
+    
     if not isinstance(fig, go.Figure):
         raise ValueError("fig must be instance of plotly.graph_objects.Figure")
 

{ipyvasp-0.9.83 → ipyvasp-0.9.85}/ipyvasp/core/serializer.py

@@ -917,13 +917,13 @@ def dump(data, format: str = "pickle", outfile: str = None, indent: int = 1) ->
     if format == "pickle":
         if outfile == None:
             return pickle.dumps(dict_obj)
-        outfile = Path(outfile).stem + ".pickle"
+        outfile = Path(outfile).with_suffix(".pickle")
         with open(outfile, "wb") as f:
             pickle.dump(dict_obj, f)
     if format == "json":
         if outfile == None:
             return json.dumps(dict_obj, cls=EncodeFromNumpy, indent=indent)
-        outfile = Path(outfile).stem + ".json"
+        outfile = Path(outfile).with_suffix(".json")
         with open(outfile, "w") as f:
             json.dump(dict_obj, f, cls=EncodeFromNumpy, indent=indent)
     return None

{ipyvasp-0.9.83 → ipyvasp-0.9.85}/ipyvasp/lattice.py

@@ -14,6 +14,7 @@ from contextlib import redirect_stdout
 from io import StringIO
 from itertools import permutations
 from contextlib import suppress
+from collections import namedtuple
 
 import numpy as np
 from pandas.io.clipboard import clipboard_get, clipboard_set
@@ -630,7 +631,7 @@ class POSCAR:
         return self._cell
     
     def get_plane(self, hkl, d=1/2,tol=1e-2):
-        """Returns Nx3 vertices of a plane bound inside cell. .
+        """Returns tuple `Plane(point, normal, vertices)` of a plane bound inside cell. .
         hkl should be list of three miller indices. d is fractional distance in range 0,1 in direction of hkl. 
         e.g. if there are 8 planes of atoms in a cubic cell, d = 0, 1/8,...7/8, 1 match position of those planes.
         """
@@ -651,13 +652,13 @@ class POSCAR:
         qts = self.cell.to_fractional(pts)
         qts = qts[(qts >= -tol).all(axis=1) & (qts <= 1 + tol).all(axis=1)]
         pts = self.cell.to_cartesian(qts)
-        return pts
+        return namedtuple("Plane","point normal vertices")(point, normal, pts)
     
     def splot_plane(self, hkl, d=1/2,tol=1e-2,ax=None, **kwargs):
         """Provide hkl and a 3D axes to plot plane. kwargs are passed to `mpl_toolkits.mplot3d.art3d.Poly3DCollection`
         Note: You may get wrong plane if your basis are not aligned to axes. So you can use `transpose` or `set_zdir` methods before plottling cell.
         """
-        P = self.get_plane(hkl,d=d,tol=tol)
+        P = self.get_plane(hkl,d=d,tol=tol).vertices
         if ax is None:
             ax = get_axes(axes_3d=True)
             ax.set( # it does not show otherwise
@@ -676,9 +677,9 @@ class POSCAR:
             fig = go.Figure()
 
         P = self.get_plane(hkl,d=d,tol=tol)
-        kwargs['delaunayaxis'] = ('xyz')[np.eye(3).dot(hkl).argmax()] # with alphahull=-1, delaunayaxis to be set properly
+        kwargs['delaunayaxis'] = ('xyz')[np.abs(np.eye(3).dot(P.normal)).argmax()] # with alphahull=-1, delaunayaxis to be set properly
         kwargs = {**dict(color='#8a8',opacity=0.7,alphahull=-1, showlegend=True,name=str(hkl)),**kwargs}
-        fig.add_trace(go.Mesh3d({k:v for v,k in zip(P.T, 'xyz')},**kwargs))
+        fig.add_trace(go.Mesh3d({k:v for v,k in zip(P.vertices.T, 'xyz')},**kwargs))
         return fig
 
     @_sub_doc(stk.get_bz, {"basis :.*loop :": "loop :"})

{ipyvasp-0.9.83 → ipyvasp-0.9.85}/ipyvasp/misc.py

@@ -70,10 +70,8 @@ class OUTCAR:
     def path(self):
         return self._path
 
-    @_sub_doc(vp.Vasprun.read)
-    @_sig_kwargs(vp.Vasprun.read, ("self",))
-    def read(self, start_match, stop_match, **kwargs):
-        return vp.Vasprun.read(
-            self, start_match, stop_match, **kwargs
-        )  # Pass all the arguments to the function
+    @_sub_doc(vp.read)
+    def read(self, start_match, stop_match=r'\n', nth_match=1, skip_last=False,apply=None):
+        kws = {k:v for k,v in locals().items() if k !='self'}
+        return vp.read(self.path, **kws)  # Pass all the arguments to the function
         

{ipyvasp-0.9.83 → ipyvasp-0.9.85}/ipyvasp/utils.py

@@ -26,8 +26,8 @@ import matplotlib.pyplot as plt
 def get_file_size(path: str):
     """Return file size"""
     if (p := Path(path)).is_file():
-        size = p.stat.st_size
-        for unit in ["Bytes", "KB", "MB", "GB", "TB"]:
+        size = p.stat().st_size
+        for unit in ["B", "KB", "MB", "GB", "TB"]:
             if size < 1024.0:
                 return "%3.2f %s" % (size, unit)
             size /= 1024.0
@@ -267,7 +267,7 @@ def prevent_overwrite(path) -> Path:
     if out_path.exists():
         # Check existing files
         i = 0
-        name = out_path.stem + "-{}" + out_path.suffix
+        name = (out_path.parent / out_path.stem) + "-{}" + out_path.suffix
         while Path(name.format(i)).is_file():
             i += 1
         out_path = Path(name.format(i))

{ipyvasp-0.9.83 → ipyvasp-0.9.85}/ipyvasp/widgets.py

@@ -13,6 +13,7 @@ from time import time
 from pathlib import Path
 from collections.abc import Iterable
 from functools import partial
+from pprint import pformat
 
 # Widgets Imports
 from IPython.display import display
@@ -39,7 +40,7 @@ import plotly.graph_objects as go
 from . import utils as gu
 from . import lattice as lat
 from .core import serializer, parser as vp, plot_toolkit as ptk
-from .utils import _sig_kwargs, _sub_doc
+from .utils import _sig_kwargs, _sub_doc, get_file_size
 from ._enplots import _fmt_labels
 
 
@@ -67,7 +68,7 @@ def summarize(files, func, **kwargs):
     for name, path in files.items():
         output = func(path, **kwargs)
         if not isinstance(output, dict):
-            raise TypeError("Function must return a dictionary.")
+            raise TypeError("Function must return a dictionary to create DataFrame.")
 
         if "FILE" in output:
             raise KeyError(
@@ -114,6 +115,8 @@ class Files:
     Use methods on return such as `summarize`, `with_name`, `filtered`, `interact` and others.
 
     >>> Files(root_1, glob_1,...).add(root_2, glob_2,...) # Fully flexible to chain
+
+    WARNING: Don't use write operations on paths in files in batch mode, it can cause unrecoverable data loss.
     """
     def __init__(self, path_or_files = '.', glob = '*', exclude = None,files_only = False, dirs_only=False):
         if isinstance(path_or_files, Files):
@@ -167,10 +170,6 @@ class Files:
     def __add__(self, other):
         raise NotImplementedError("Use self.add method instead!")
 
-    def map(self,func):
-        "Map files to a function!"
-        return map(func, self._files)
-
     def with_name(self, name):
         "Change name of all files. Only keeps existing files."
         return self.__class__([f.with_name(name) for f in self._files])
@@ -262,10 +261,10 @@ class Files:
             If you don't need to interpret the result of the function call, you can use the @self.interact decorator instead.
         """
         info = ipw.HTML().add_class("fprogess")
-        dd = Dropdown(description='File', options=self._files)
+        dd = Dropdown(description='File', options=['Select a File',*self._files]) # allows single file workable
 
         def interact_func(fname, **kws):
-            if fname:  # This would be None if no file is selected
+            if fname and str(fname) != 'Select a File':  # This would be None if no file is selected
                 info.value = _progress_svg
                 try:
                     start = time()
@@ -419,6 +418,52 @@ class Files:
     def bands_widget(self, height='450px'):
         "Get BandsWidget instance with these files."
         return BandsWidget(files=self._files, height=height)
+    
+    def map(self,func, to_df=False):
+        """Map files to a function that takes path as argument. 
+        If `to_df=True`, func may return a dict to create named columns, or just two columns will be created.
+        Otherwise returns generator of elemnets `(path, func(path))`.
+        If you need to operate on opened file pointer, use `.mapf` instead.
+        
+        >>> import ipyvasp as ipv
+        >>> files = ipv.Files(...)
+        >>> files.map(lambda path: ipv.read(path, '<pattern>',apply = lambda line: float(line.split()[0])))
+        >>> files.map(lambda path: ipv.load(path), to_df=True) 
+        """
+        if to_df:
+            return self._try_return_df(func)
+        return ((path, func(path)) for path in self._files) # generator must
+    
+    def _try_return_df(self, func):
+        try: return summarize(self._files,func)
+        except: return pd.DataFrame(((path, func(path)) for path in self._files))
+    
+    def mapf(self, func, to_df=False,mode='r', encoding=None):
+        """Map files to a function that takes opened file pointer as argument. Opened files are automatically closed and should be in readonly mode.
+        Load files content into a generator sequence of  tuples like `(path, func(open(path)))` or DataFrame if `to_df=True`.
+        If `to_df=True`, func may return a dict to create named columns, or just two columns will be created.
+        If you need to operate on just path, use `.map` instead.
+        
+        >>> import json
+        >>> import ipyvasp as ipv
+        >>> files = ipv.Files(...)
+        >>> files.mapf(lambda fp: json.load(fp),to_df=True) 
+        >>> files.mapf(lambda fp: [fp.readline() for _ in range(5)]) # read first five lines
+        """
+        if not mode in 'rb':
+            raise ValueError("Only 'r'/'rb' mode is allowed in this context!")
+        
+        def loader(path):
+            with open(path, mode=mode,encoding=encoding) as f:
+                return func(f)
+
+        if to_df:
+            return self._try_return_df(loader)
+        return ((path, loader(path)) for path in self._files) # generator must
+        
+    def stat(self):
+        "Get files stat as DataFrame. Currently only size is supported."
+        return self.summarize(lambda path: {"size": get_file_size(path)})
 
 
 @fix_signature
@@ -627,7 +672,7 @@ class BandsWidget(VBox):
         self._tsd = Dropdown(
             description="Style", options=["plotly_white", "plotly_dark"]
         )
-        self._click = Dropdown(description="Click", options=["None", "VBM", "CBM"])
+        self._click = Dropdown(description="Click", options=["None", "vbm", "cbm"])
         self._ktcicks = Text(description="kticks")
         self._brange = ipw.IntRangeSlider(description="bands",min=1, max=1) # number, not index
         self._ppicks = PropsPicker(
@@ -680,9 +725,9 @@ class BandsWidget(VBox):
             )
             self._brange.max = self.bands.source.summary.NBANDS
             if self.bands.source.summary.LSORBIT:
-                self._click.options = ["None", "VBM", "CBM", "so_max", "so_min"]
+                self._click.options = ["None", "vbm", "cbm", "so_max", "so_min"]
             else:
-                self._click.options = ["None", "VBM", "CBM"]
+                self._click.options = ["None", "vbm", "cbm"]
 
             if (file := path.parent / "result.json").is_file():
                 self._result = serializer.load(str(file.absolute()))  # Old data loaded
@@ -692,7 +737,7 @@ class BandsWidget(VBox):
                 {
                     "v": round(pdata.volume, 4),
                     **{k: round(v, 4) for k, v in zip("abc", pdata.norms)},
-                    **{k: round(v, 4) for k, v in zip("αβγ", pdata.angles)},
+                    **{k: round(v, 4) for k, v in zip(["alpha","beta","gamma"], pdata.angles)},
                 }
             )
             self._click_save_data(None)  # Load into view
@@ -771,13 +816,10 @@ class BandsWidget(VBox):
         def _show_and_save(data_dict):
             self._interact.output_widget.clear_output(wait=True)  # Why need again?
             with self._interact.output_widget:
-                print(
-                    ", ".join(
-                        f"{key} = {value}"
+                print(pformat({key: value
                         for key, value in data_dict.items()
                         if key not in ("so_max", "so_min")
-                    )
-                )
+                    }))
 
             serializer.dump(
                 data_dict,
@@ -785,11 +827,9 @@ class BandsWidget(VBox):
                 outfile=self.path.parent / "result.json",
             )
 
-        if (
-            change is None
-        ):  # called from other functions but not from store_clicked_data
+        if change is None:  # called from other functions but not from store_clicked_data
             return _show_and_save(self._result)
-        # Should be after checking chnage
+        # Should be after checking change
         if self._click.value and self._click.value == "None":
             return  # No need to act on None
 
@@ -806,11 +846,11 @@ class BandsWidget(VBox):
                         x, 6
                     )  # Save x to test direct/indirect
 
-            if data_dict.get("VBM", None) and data_dict.get("CBM", None):
-                data_dict["E_gap"] = np.round(data_dict["CBM"] - data_dict["VBM"], 6)
+            if data_dict.get("vbm", None) and data_dict.get("cbm", None):
+                data_dict["gap"] = np.round(data_dict["cbm"] - data_dict["vbm"], 6)
 
             if data_dict.get("so_max", None) and data_dict.get("so_min", None):
-                data_dict["Δ_SO"] = np.round(
+                data_dict["soc"] = np.round(
                     data_dict["so_max"] - data_dict["so_min"], 6
                 )
 

{ipyvasp-0.9.83 → ipyvasp-0.9.85}/ipyvasp.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ipyvasp
-Version: 0.9.83
+Version: 0.9.85
 Summary: A processing tool for VASP DFT input/output processing in Jupyter Notebook.
 Home-page: https://github.com/massgh/ipyvasp
 Author: Abdul Saboor

ipyvasp-0.9.83/ipyvasp/_version.py

@@ -1 +0,0 @@
-__version__ = "0.9.83"