Numpy包
mat( )函数可以将数组转化为矩阵
randMat=mat(random.rand(4,4))
.I表示求逆
randMat.I
from numpy import *
import operator
tile用法：
Signature: tile(A, reps)Docstring:
Construct an array by repeating A the number of times given by reps.
If `reps` has length ``d``, the result will have dimension of
``max(d, A.ndim)``.
If ``A.ndim < d``, `A` is promoted to be d-dimensional by prepending new
axes. So a shape (3,) array is promoted to (1, 3) for 2-D replication,
or shape (1, 1, 3) for 3-D replication. If this is not the desired
behavior, promote `A` to d-dimensions manually before calling this
function.
If ``A.ndim > d``, `reps` is promoted to `A`.ndim by pre-pending 1's to it.
Thus for an `A` of shape (2, 3, 4, 5), a `reps` of (2, 2) is treated as
(1, 1, 2, 2).
Note : Although tile may be used for broadcasting, it is strongly
recommended to use numpy's broadcasting operations and functions.
Parameters
----------
A : array_like
The input array.
reps : array_like
The number of repetitions of `A` along each axis.
Returns
-------
c : ndarray
The tiled output array.
See Also
--------
repeat : Repeat elements of an array.
broadcast_to : Broadcast an array to a new shape
Examples
--------
>>> a = np.array([0, 1, 2])
>>> np.tile(a, 2)
array([0, 1, 2, 0, 1, 2])
>>> np.tile(a, (2, 2))
array([[0, 1, 2, 0, 1, 2],
[0, 1, 2, 0, 1, 2]])
>>> np.tile(a, (2, 1, 2))
array([[[0, 1, 2, 0, 1, 2]],
[[0, 1, 2, 0, 1, 2]]])
>>> b = np.array([[1, 2], [3, 4]])
>>> np.tile(b, 2)
array([[1, 2, 1, 2],
[3, 4, 3, 4]])
>>> np.tile(b, (2, 1))
array([[1, 2],
[3, 4],
[1, 2],
[3, 4]])
>>> c = np.array([1,2,3,4])
>>> np.tile(c,(4,1))
array([[1, 2, 3, 4],
[1, 2, 3, 4],
[1, 2, 3, 4],
[1, 2, 3, 4]])
File: d:\anaconda3\lib\site-packages\numpy\lib\shape_base.py
Type: function
argsort用法：
Signature: argsort(a, axis=-1, kind='quicksort', order=None)Docstring:
Returns the indices that would sort an array.
Perform an indirect sort along the given axis using the algorithm specified
by the `kind` keyword. It returns an array of indices of the same shape as
`a` that index data along the given axis in sorted order.
Parameters
----------
a : array_like
Array to sort.
axis : int or None, optional
Axis along which to sort. The default is -1 (the last axis). If None,
the flattened array is used.
kind : {'quicksort', 'mergesort', 'heapsort'}, optional
Sorting algorithm.
order : str or list of str, optional
When `a` is an array with fields defined, this argument specifies
which fields to compare first, second, etc. A single field can
be specified as a string, and not all fields need be specified,
but unspecified fields will still be used, in the order in which
they come up in the dtype, to break ties.
Returns
-------
index_array : ndarray, int
Array of indices that sort `a` along the specified axis.
If `a` is one-dimensional, ``a[index_array]`` yields a sorted `a`.
See Also
--------
sort : Describes sorting algorithms used.
lexsort : Indirect stable sort with multiple keys.
ndarray.sort : Inplace sort.
argpartition : Indirect partial sort.
Notes
-----
See `sort` for notes on the different sorting algorithms.
As of NumPy 1.4.0 `argsort` works with real/complex arrays containing
nan values. The enhanced sort order is documented in `sort`.
Examples
--------
One dimensional array:
>>> x = np.array([3, 1, 2])
>>> np.argsort(x)
array([1, 2, 0])
Two-dimensional array:
>>> x = np.array([[0, 3], [2, 2]])
>>> x
array([[0, 3],
[2, 2]])
>>> np.argsort(x, axis=0)
array([[0, 1],
[1, 0]])
>>> np.argsort(x, axis=1)
array([[0, 1],
[0, 1]])
Sorting with keys:
>>> x = np.array([(1, 0), (0, 1)], dtype=[('x', '
>>> x
array([(1, 0), (0, 1)],
dtype=[('x', '
>>> np.argsort(x, order=('x','y'))
array([1, 0])
>>> np.argsort(x, order=('y','x'))
array([0, 1])
File: d:\anaconda3\lib\site-packages\numpy\core\fromnumeric.py
Type: function
operator.itemgetter：
Init signature: operator.itemgetter(self, /, *args, **kwargs)Docstring:
itemgetter(item, ...) --> itemgetter object
Return a callable object that fetches the given item(s) from its operand.
After f = itemgetter(2), the call f(r) returns r[2].
After g = itemgetter(2, 5, 3), the call g(r) returns (r[2], r[5], r[3])
File: d:\anaconda3\lib\operator.py
Type: type
sorted：
Signature: sorted(iterable, /, *, key=None, reverse=False)Docstring:
Return a new list containing all items from the iterable in ascending order.
A custom key function can be supplied to customize the sort order, and the
reverse flag can be set to request the result in descending order.
Type: builtin_function_or_method
classCount={}
花括号表示字典
for i in range(3):
voteIlabel = labels[sortedDistIndicies[i]]
classCount[voteIlabel] = classCount.get(voteIlabel,0)+1
AttributeError: 'dict' object has no attribute 'iteritems'
Python3.5中：iteritems变为items
===============
文件读取
def file2matrix(filename):
fr = open(filename)
arrayOlines=fr.readlines()
numberOfLines = len(arrayOlines)
returnMat = zeros((numberOfLines,3))
classLabelVector = []
index = 0
for line in arrayOlines:
line = line.strip()
listFromLine = line.split('\t')
returnMat[index,:]=listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))
index += 1
return returnMat,classLabelVector
line = line.strip()：截掉回车符
==================================
使用Matplotlib制作原始数据的散点图：
import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2])
plt.show()
=========
ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))
使区分
==============================
def autoNorm(dataSet):
minVals = dataSet.min(0)
maxVals = dataSet.max(0)
ranges = maxVals - minVals
normDataSet = zeros(shape(dataSet))
m = dataSet.shape[0]
normDataSet = dataSet - tile(minVals, (m,1))
normDataSet = normDataSet/tile(ranges,(m,1))
return normDataSet,ranges,minVals
============
normDataSet = normDataSet/tile(ranges,(m,1))不是矩阵除法，在NumPy库中，矩阵除法需要使用函数linalg.solve(matA,matB)
========
reload:
import importlib
importlib.reload(kNN)
=================================