数据分析之numpy介绍1

爬虫没学两天，数据分析课就来了。

使用numpy创建数组

介绍numpy数组的属性和简单操作

import numpy
#delimiter设置定界符
world_alcohol = numpy.genfromtxt("world_alcohol.txt", delimiter=",")
print(type(world_alcohol))#类型是多维数组

<type 'numpy.ndarray'>

#The numpy.array() function can take a list or list of lists as input. When we input a list, we get a one-dimensional array as a result:
#（输入一维列表，得到一位数组。）
vector = numpy.array([5, 10, 15, 20])#创建数组
#When we input a list of lists, we get a matrix as a result:，
#输入多维列表，得到多维数组。
matrix = numpy.array([[5, 10, 15], [20, 25, 30], [35, 40, 45]])
print vector#一维数组
print matrix#二维数组

[ 5 10 15 20]

[[ 5 10 15]
 [20 25 30]
 [35 40 45]]

#We can use the ndarray.shape property to figure out how many elements are in the array
#使用.shape属性来判断数组中有多少个元素)
vector = numpy.array([1, 2, 3, 4])
print(vector.shape)#数组（矩阵结构）,通过结构我们可以看到数据的特征。
#For matrices, the shape property contains a tuple with 2 elements.
#一般矩阵是二维，所以shape属性值是一个两个元素组成的元组。
matrix = numpy.array([[5, 10, 15], [20, 25, 30]])
print(matrix.shape)

(4,)
(2, 3)

#Each value in a NumPy array has to have the same data type
#numpy数组中所有元素的类型必须相同
#NumPy will automatically figure out an appropriate data type when reading in data or converting lists to arrays. 
#numpy创建数组时会自适应的指定数组类型。
#You can check the data type of a NumPy array using the dtype property.
#使用dtype属性查看数组的元素的数据类型
numbers = numpy.array([1, 2, 3, 4])
numbers.dtype#data type 数据元素结构必须相同

dtype('int32')

#When NumPy can't convert a value to a numeric data type like float or integer, it uses a special nan value that stands for Not a Number。
#非数字值以nan代替
#nan is the missing data（nan代表数据缺失）
#1.98600000e+03 is actually 1.986 * 10 ^ 3（科学计数法）
world_alcohol#文件读取

array([[             nan,              nan,              nan,
                     nan,              nan],
       [  1.98600000e+03,              nan,              nan,
                     nan,   0.00000000e+00],
       [  1.98600000e+03,              nan,              nan,
                     nan,   5.00000000e-01],
       ..., 
       [  1.98700000e+03,              nan,              nan,
                     nan,   7.50000000e-01],
       [  1.98900000e+03,              nan,              nan,
                     nan,   1.50000000e+00],
       [  1.98500000e+03,              nan,              nan,
                     nan,   3.10000000e-01]])

world_alcohol = numpy.genfromtxt("world_alcohol.txt", delimiter=",", dtype="U75", skip_header=1)
print(world_alcohol)

[[u'1986' u'Western Pacific' u'Viet Nam' u'Wine' u'0']
 [u'1986' u'Americas' u'Uruguay' u'Other' u'0.5']
 [u'1985' u'Africa' u"Cte d'Ivoire" u'Wine' u'1.62']
 ..., 
 [u'1987' u'Africa' u'Malawi' u'Other' u'0.75']
 [u'1989' u'Americas' u'Bahamas' u'Wine' u'1.5']
 [u'1985' u'Africa' u'Malawi' u'Spirits' u'0.31']]

uruguay_other_1986 = world_alcohol[1,4]
third_country = world_alcohol[2,2]
print uruguay_other_1986
print third_country

0.5
Cte d'Ivoire

vector = numpy.array([5, 10, 15, 20])
print(vector[0:3])  #数组的切片，找出索引为0,1,2的元素

[ 5 10 15]

matrix = numpy.array([
                    [5, 10, 15], 
                    [20, 25, 30],
                    [35, 40, 45]
                 ])
print(matrix[:,1])
#打印所有行的索引为1的元素

[10 25 40]

matrix = numpy.array([
                    [5, 10, 15], 
                    [20, 25, 30],
                    [35, 40, 45]
                 ])
print(matrix[:,0:2])
#打印所有行的索引为0，1的元素

[[ 5 10]
 [20 25]
 [35 40]]

matrix = numpy.array([
                    [5, 10, 15], 
                    [20, 25, 30],
                    [35, 40, 45]
                 ])
print(matrix[1:3,0:2])
#打印索引为1,2的行的列索引为0，1的元素

[[20 25]
 [35 40]]