first commit with cleaned up code

git-svn-id: http://pandas.googlecode.com/svn/trunk@5 d5231056-7de3-11de-ac95-d976489f1ece

LICENSE

@@ -0,0 +1,30 @@
+Copyright (c) 2008-2009 AQR Capital Management, LLC
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+    * Redistributions of source code must retain the above copyright
+       notice, this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above
+       copyright notice, this list of conditions and the following
+       disclaimer in the documentation and/or other materials provided
+       with the distribution.
+
+    * Neither the name of the copyright holder nor the names of any
+       contributors may be used to endorse or promote products derived
+       from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

MANIFEST.in

@@ -0,0 +1,4 @@
+include TODO LICENSE README
+include setup.py setupegg.py
+include examples/data/*
+recursive-include examples *

pandas/__init__.py

@@ -0,0 +1,36 @@
+"""
+Pandas - a library for panel, time series, or cross-sectional data analysis
+===========================================================================
+
+Main data structures (see docstrings for detailed documentation)
+--------------------
+Index
+    Represent row or column labels in Series / DataFrame structures
+
+Series / TimeSeries
+    Represents standard 1-dimensional cross-section (resp. time series)
+    As an numpy.ndarray subclass, compatible with ufuncs and other NumPy
+    functions
+
+DataFrame / DataMatrix
+    Represent collections of Series objects, enable easy management
+    of multiple time series / cross-sections
+
+DateRange
+    Index subclass for generating arrays of fixed frequency dates
+    
+Subpackages
+-----------
+core
+    Implementations of core data structures, basic building blocks. Most of
+    the user-relevant code is accessible through the top-level namespace
+io
+    Persistence, parsing, and data loading tools
+lib
+    C, Cython, and Fortran extensions for other components
+stats
+    Standard 
+"""
+
+from pandas.core.api import *
+from pandas.io.parsers import parseCSV, parseText, parseExcel

pandas/core/api.py

@@ -0,0 +1,12 @@
+import numpy as np
+
+from pandas.core.daterange import DateRange
+from pandas.core.datetools import DateOffset
+from pandas.core.frame import DataFrame
+from pandas.core.index import Index
+from pandas.core.matrix import DataMatrix
+from pandas.core.series import Series, TimeSeries
+
+import pandas.core.datetools as datetools
+
+from pandas.lib.tseries import isnull, notnull

pandas/core/collection.py

@@ -0,0 +1,88 @@
+from __future__ import with_statement
+
+from collections import defaultdict
+from pandas.core.mixins import Picklable
+from pandas.core.index import Index
+from pandas.core.pytools import rands, adjoin, groupby
+import cPickle
+import os
+
+__all__ = ['PickleContainer']
+
+class PickleContainer(Picklable):
+    """
+    Store collection of objects on disk with this dict-like object.
+    
+    Parameters
+    ----------
+    dirPath: string
+       Directory where to store the objects
+    lruSize: int
+       Number of objects to keep in memory (not implemented yet)
+    """
+    def __init__(self, dirPath, lruSize=5):
+        self.dirPath = dirPath
+        if not os.path.exists(dirPath):
+            os.mkdir(dirPath)
+
+        self._lruSize = lruSize
+
+        self._paths = {}
+        self._classes = {}
+        self._lru = {}
+
+    def __repr__(self):
+        output = str(self.__class__) + '\n'
+        keys, values = zip(*self._classes.iteritems())
+        output += adjoin(5, map(str, keys), map(str, values))
+        return output
+
+    def __setitem__(self, key, value):
+        theKey = rands(10)
+        filePath = self.dirPath + '/' + theKey
+
+        self._paths[key] = filePath
+
+        if isinstance(value, Picklable):
+            value.save(filePath)
+        else:
+            with open(filePath, 'w') as f:
+                cPickle.dump(value, f)
+
+        self._paths[key] = filePath
+        self._classes[key] = value.__class__
+
+    def __getitem__(self, key):
+        if key not in self._paths:
+            raise Exception('Requested key not in this container!')
+
+        thePath = self._paths[key]
+        theClass = self._classes[key]
+
+        if issubclass(theClass, Picklable):
+            obj = theClass.load(thePath)
+        else:
+            with open(thePath, 'rb') as f:
+                obj = cPickle.load(f)
+
+        return obj
+
+    def __delitem__(self, key):
+        del self._paths[key]
+        del self._classes[key]
+
+    def __iter__(self):
+        return iter(self._paths)
+
+    def iteritems(self):
+        for key, path in self._paths.iteritems():
+            yield key, self[key]
+
+    def keys(self):
+        return self._paths.keys()
+
+    def values(self):
+        result = []
+        for key in self._paths:
+            result.append(self[key])
+        return result