Add initial package

LICENSE

@@ -0,0 +1,7 @@
+Copyright (c) 2015 Igor Babuschkin
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

root_pandas/__init__.py

@@ -0,0 +1,109 @@
+
+"""
+A module that extends pandas to support the ROOT data format.
+"""
+
+from pandas import DataFrame
+from root_numpy import root2array, list_trees
+from fnmatch import fnmatch
+from root_numpy import list_branches
+
+__all__ = ['read_root']
+
+def get_matching_variables(fname, tree, patterns):
+    branches = list_branches(fname, tree)
+
+    selected = []
+
+    for p in patterns:
+        for b in branches:
+            if fnmatch(b, p) and not b in selected:
+                selected.append(b)
+    return selected
+
+def read_root(fname, tree_name=None, variables=None, ignore=None, *kargs, **kwargs):
+    """
+    Read a ROOT file into a pandas DataFrame.
+    Further *kargs and *kwargs are passed to root_numpy's root2array.
+    If the root file contains a branch called index, it will become the DataFrame's index.
+
+    Parameters
+    ----------
+    fname: string
+        The filename of the root file
+    tree_name: string
+        The name of the tree to load
+    variables: sequence
+        A sequence of shell-patterns. Matching variables are read.
+    ignore: sequence
+        A sequence of shell-patterns. All matching variables are ignored (overriding the variables argument)
+
+    Returns
+    -------
+        DataFrame from the ROOT file
+
+    Notes
+    -----
+
+        >>> df = read_root('test.root', 'MyTree', variables=['x_*', 'y_*'], selection='x_1 > 100')
+
+    """
+    if not tree_name:
+        branches = list_trees(fname)
+        if len(branches) == 1:
+            tree_name = branches[0]
+        else:
+            raise ValueError('More than one tree found in {}'.format(fname))
+
+    if not variables:
+        all_vars = None
+    else:
+        # index is always loaded if it exists
+        variables.append('index')
+        all_vars = get_matching_variables(fname, tree_name, variables)
+
+    if ignore:
+        if not all_vars:
+            all_vars = get_matching_variables(fname, tree_name, ['*'])
+
+        ignored = get_matching_variables(fname, tree_name, ignore)
+        if 'index' in ignored:
+            raise ValueError('index variable is being ignored!')
+        for var in ignored:
+            all_vars.remove(var)
+
+    arr = root2array(fname, tree_name, all_vars, *kargs, **kwargs)
+    if 'index' in arr.dtype.names:
+        df = DataFrame.from_records(arr, index='index')
+    else:
+        df = DataFrame.from_records(arr)
+    return df
+
+def to_root(df, fname, tree_name="default", *kargs, **kwargs):
+    """
+    Write DataFrame to a ROOT file.
+
+    Parameters
+    ----------
+    fname: string
+        File path to new ROOT file (will be overwritten)
+    tree_name: string
+        Name of tree that the DataFrame will be saved as
+    
+    Notes
+    -----
+
+    Further *kargs and *kwargs are passed to root_numpy's array2root.
+
+    >>> df = DataFrame({'x': [1,2,3], 'y': [4,5,6]})
+    >>> df.to_root('test.root')
+    
+    The DataFrame index will be saved as a branch called 'index'.
+    """
+    from root_numpy import array2root
+    arr = df.to_records()
+    array2root(arr, fname, tree_name, 'recreate', *kargs, **kwargs)
+
+# Patch pandas DataFrame to support to_root method
+DataFrame.to_root = to_root
+

setup.py

@@ -0,0 +1,11 @@
+from setuptools import setup
+
+setup(name='root_pandas',
+      version='0.1',
+      description='Read and save DataFrames from and to ROOT files',
+      url='http://github.com/ibab/root_pandas',
+      author='Igor Babuschkin',
+      author_email='igor@babuschk.in',
+      license='MIT',
+      packages=['root_pandas'],
+      zip_safe=False)