[root@ichxx ~]# cat /etc/redhat-release
CentOS release 6.10 (Final)
(wx) [test@test wx]$ python -V
Python 3.7.0

        print "var", var
                  ^
    SyntaxError: Missing parentheses in call to 'print'. Did you mean print("var", var)?

pip install web.py==0.40.dev0

(wx) [test@test dev]$ python
Python 3.7.0 (default, Sep 20 2018, 09:26:57) 
[GCC 4.4.7 20120313 (Red Hat 4.4.7-18)] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import web
>>> 

(data) D:\DATA\DEV\env\data>pip install numpy
Collecting numpy
  Downloading https://files.pythonhosted.org/packages/ed/29/d97b6252591da5f8add0d25eecda296ea72729a0aad7998edba1981b47c8/numpy-1.16.2-cp36-cp36m-win_amd64.whl (11.9MB)
    0% |                                | 10kB 467bytes/s eta 7:04:42Exception:
Traceback (most recent call last):
  File "d:\data\dev\env\data\lib\site-packages\pip\_vendor\urllib3\response.py", line 360, in _error_catcher
    yield
 ...
    raise ReadTimeoutError(self._pool, None, 'Read timed out.')
pip._vendor.urllib3.exceptions.ReadTimeoutError: HTTPSConnectionPool(host='files.pythonhosted.org', port=443): Read timed out.

(data) D:\DATA\DEV\env\data>pip install numpy --default-timeout=100
Collecting numpy
  Downloading https://files.pythonhosted.org/packages/ed/29/d97b6252591da5f8add0d25eecda296ea72729a0aad7998edba1981b47c8/numpy-1.16.2-cp36-cp36m-win_amd64.whl (11.9MB)
    100% |████████████████████████████████| 11.9MB 173kB/s
Installing collected packages: numpy
Successfully installed numpy-1.16.2

In [1]: import pandas
   ...: pandas.__version__
Out[1]: '0.24.1'

In [2]: import pandas as pd

In [3]: pd.<TAB>

In [4]: pd?

(data) e:\DEV\env\data\Scripts>pip install ipykernel
...
(data) e:\DEV\env\data\Scripts>python -m ipykernel install --user --name=data
Installed kernelspec data in C:\Users\test\AppData\Roaming\jupyter\kernels\data

# coding: utf-8
import time

import requests
from lxml import etree

# 入口
base_url = 'http://wap.ynpxrz.com/list.aspx?childid=2181&cateid=2160&page={}'
host = 'http://wap.ynpxrz.com'

def get_html(url):

    r = requests.get(url)
    if r.status_code == 200:
        return r
    return None

def get_parse(text):
    return etree.fromstring(text, parser=etree.HTMLParser())

def get_urls(page=1):
    url = base_url.format(page)
    r = get_html(url)
    if r:
        e = get_parse(r.text)
        url_tags = e.xpath('//*[@id="divList"]/li/a')
        urls = [host + url.get('href') for url in url_tags]
        return urls
    else:
        return None


def get_content(url):
    result = []
    r = requests.get(url)

    e = get_parse(r.text)
    # 标题
    h2_tags = e.xpath('/html/body/section/article/h2')
    title = h2_tags[0].text

    result.append(title)
    # 获取不含属性的节点
    p_tags = e.xpath('/html/body/section/article/div/p[not(@*)]')

    for tag in p_tags:
        if tag.text:
            result.append(tag.text.replace('更多信息请查看', ''))
    return result


if __name__ == '__main__':

    result = []
    page = 1
    print('开始')
    while page <= 23:
        urls = get_urls(page)
        for url in urls:
            content = get_content(url)
            title = content[0]
            print('page{}-{}'.format(page, title))
            result.append('\n'.join(content))
            result.append('--'*20)
            result.append('\n\n')
            time.sleep(1)
        # 生成文件
        with open('./data/page{}.txt'.format(page), 'w', encoding='utf-8') as f:
            f.write('\n'.join(result))
        # 重置result
        result = []
        page += 1
    print('结束')

cat /etc/issue
# redhat专用
cat /etc/redhat-release
uname -a

In [1]: import numpy as np
   ...: np.random.seed(0)  # seed for reproducibility
   ...:
   ...: x1 = np.random.randint(10, size=6)  # One-dimensional array
   ...: x2 = np.random.randint(10, size=(3, 4))  # Two-dimensional array
   ...: x3 = np.random.randint(10, size=(3, 4, 5))  # Three-dimensional array

In [2]: print("x3 ndim: ", x3.ndim)
   ...: print("x3 shape:", x3.shape)
   ...: print("x3 size: ", x3.size)
x3 ndim:  3
x3 shape: (3, 4, 5)
x3 size:  60

In [3]: print("dtype:", x3.dtype)
dtype: int32

In [4]: print("itemsize:", x3.itemsize, "bytes")
   ...: print("nbytes:", x3.nbytes, "bytes")
itemsize: 4 bytes
nbytes: 240 bytes

In [5]: x1
Out[5]: array([5, 0, 3, 3, 7, 9])

In [6]: x1[0]
Out[6]: 5

In [7]: x1[4]
Out[7]: 7

In [8]: x1[-1]
Out[8]: 9

In [9]: x1[-2]
Out[9]: 7

In [10]: x2
Out[10]:
array([[3, 5, 2, 4],
       [7, 6, 8, 8],
       [1, 6, 7, 7]])

In [11]: x2[0, 0]
Out[11]: 3

In [12]: x2[2, 0]
Out[12]: 1

In [13]: x2[2, -1]
Out[13]: 7

In [14]: x2[0, 0] = 12
    ...: x2
Out[14]:
array([[12,  5,  2,  4],
       [ 7,  6,  8,  8],
       [ 1,  6,  7,  7]])

In [15]: x1[0] = 3.14159  # this will be truncated!
    ...: x1
Out[15]: array([3, 0, 3, 3, 7, 9])

x[start:stop:step]

In [16]: x = np.arange(10)
    ...: x
Out[16]: array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

In [17]: x[:5]  # first five elements
Out[17]: array([0, 1, 2, 3, 4])

In [18]: x[5:]  # elements after index 5
Out[18]: array([5, 6, 7, 8, 9])

In [19]: x[4:7]  # middle sub-array
Out[19]: array([4, 5, 6])

In [20]: x[::2]  # every other element
Out[20]: array([0, 2, 4, 6, 8])

In [21]: x[1::2]  # every other element, starting at index 1
Out[21]: array([1, 3, 5, 7, 9])

In [22]: x[::-1]  # all elements, reversed
Out[22]: array([9, 8, 7, 6, 5, 4, 3, 2, 1, 0])

In [23]: x[5::-2]  # reversed every other from index 5
Out[23]: array([5, 3, 1])

In [24]: x2
Out[24]:
array([[12,  5,  2,  4],
       [ 7,  6,  8,  8],
       [ 1,  6,  7,  7]])

In [25]: x2[:2, :3]  # two rows, three columns
Out[25]:
array([[12,  5,  2],
       [ 7,  6,  8]])

In [26]: x2[:3, ::2]  # all rows, every other column
Out[26]:
array([[12,  2],
       [ 7,  8],
       [ 1,  7]])

In [27]: x2[::-1, ::-1]
Out[27]:
array([[ 7,  7,  6,  1],
       [ 8,  8,  6,  7],
       [ 4,  2,  5, 12]])

In [28]: print(x2[:, 0])  # first column of x2
[12  7  1]

In [29]: print(x2[0, :])  # first row of x2
[12  5  2  4]

In [30]: print(x2[0])  # equivalent to x2[0, :]
[12  5  2  4]

In [31]: print(x2)
[[12  5  2  4]
 [ 7  6  8  8]
 [ 1  6  7  7]]

In [32]: x2_sub = x2[:2, :2]
    ...: print(x2_sub)
[[12  5]
 [ 7  6]]

In [33]: x2_sub[0, 0] = 99
    ...: print(x2_sub)
[[99  5]
 [ 7  6]]

In [34]: print(x2)
[[99  5  2  4]
 [ 7  6  8  8]
 [ 1  6  7  7]]

In [35]: x2_sub_copy = x2[:2, :2].copy()
    ...: print(x2_sub_copy)
[[99  5]
 [ 7  6]]

In [36]: x2_sub_copy[0, 0] = 42
    ...: print(x2_sub_copy)
[[42  5]
 [ 7  6]]

In [37]: print(x2)
[[99  5  2  4]
 [ 7  6  8  8]
 [ 1  6  7  7]]

In [38]: grid = np.arange(1, 10).reshape((3, 3))
    ...: print(grid)
[[1 2 3]
 [4 5 6]
 [7 8 9]]

In [39]: x = np.array([1, 2, 3])
    ...:
    ...: # row vector via reshape
    ...: x.reshape((1, 3))
Out[39]: array([[1, 2, 3]])

In [40]:

In [40]: # row vector via newaxis
    ...: x[np.newaxis, :]
Out[40]: array([[1, 2, 3]])

In [41]:

In [41]: # column vector via reshape
    ...: x.reshape((3, 1))
Out[41]:
array([[1],
       [2],
       [3]])

In [42]: # column vector via newaxis
    ...: x[:, np.newaxis]
Out[42]:
array([[1],
       [2],
       [3]])

In [43]: x = np.array([1, 2, 3])
    ...: y = np.array([3, 2, 1])
    ...: np.concatenate([x, y])
Out[43]: array([1, 2, 3, 3, 2, 1])

In [44]: z = [99, 99, 99]
    ...: print(np.concatenate([x, y, z]))
[ 1  2  3  3  2  1 99 99 99]

In [45]: grid = np.array([[1, 2, 3],
    ...:                  [4, 5, 6]])

In [46]: # concatenate along the first axis
    ...: np.concatenate([grid, grid])
Out[46]:
array([[1, 2, 3],
       [4, 5, 6],
       [1, 2, 3],
       [4, 5, 6]])
       
In [47]: # concatenate along the second axis (zero-indexed)
    ...: np.concatenate([grid, grid], axis=1)
Out[47]:
array([[1, 2, 3, 1, 2, 3],
       [4, 5, 6, 4, 5, 6]])

In [48]: x = np.array([1, 2, 3])
    ...: grid = np.array([[9, 8, 7],
    ...:                  [6, 5, 4]])
    ...:
    ...: # vertically stack the arrays
    ...: np.vstack([x, grid])
Out[48]:
array([[1, 2, 3],
       [9, 8, 7],
       [6, 5, 4]])

In [49]: # horizontally stack the arrays
    ...: y = np.array([[99],
    ...:               [99]])
    ...: np.hstack([grid, y])
Out[49]:
array([[ 9,  8,  7, 99],
       [ 6,  5,  4, 99]])

In [50]: x = [1, 2, 3, 99, 99, 3, 2, 1]
    ...: x1, x2, x3 = np.split(x, [3, 5])
    ...: print(x1, x2, x3)
[1 2 3] [99 99] [3 2 1]

In [51]: grid = np.arange(16).reshape((4, 4))
    ...: grid
Out[51]:
array([[ 0,  1,  2,  3],
       [ 4,  5,  6,  7],
       [ 8,  9, 10, 11],
       [12, 13, 14, 15]])

In [52]: upper, lower = np.vsplit(grid, [2])
    ...: print(upper)
    ...: print(lower)
[[0 1 2 3]
 [4 5 6 7]]
[[ 8  9 10 11]
 [12 13 14 15]]

In [53]: left, right = np.hsplit(grid, [2])
    ...: print(left)
    ...: print(right)
[[ 0  1]
 [ 4  5]
 [ 8  9]
 [12 13]]
[[ 2  3]
 [ 6  7]
 [10 11]
 [14 15]]

In [54]:

# 1. 查看当前系统的python版本
# python -V
Python 2.6.6

# 2. 下载最新版本的Python3
# cd /usr/local/src
# wget https://www.python.org/ftp/python/3.7.0/Python-3.7.0.tgz

# 3. 解压并编译安装
# 注意3.7以上版本会报ModuleNotFoundError: No module named '_ctypes'错误，需要安装libffi-devel
# yum install -y libffi-devel
# tar zxvf Python-3.7.0.tgz
# cd Python-3.7.0
# ./configure
# make && make install

# 4. 备份老版本python
# mv /usr/bin/python /usr/bin/python2.6.6

# 5. 创建软链接指向
# ln -s /usr/local/bin/python3.7 /usr/bin/python
# python -V
Python 3.7.0

# 6. 修正yum
# 注：升级python后yum会无法使用，需要编辑一下对应文件。
# vim /usr/bin/yum
把第一行中的#!/usr/bin/python 改成#!/usr/bin/python2.6.6。至此，centos中python自2.x升级3.x完成。

7. 升级pip
pip3 install --upgrade pip

注：以上需在root用户下操作

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
sepallength = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0])

# 输入
In [64]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: sepallength = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0])

# 解决方案

In [65]: np.percentile(sepallength, q=[5, 95])
Out[65]: array([4.6  , 7.255])

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris_2d = np.genfromtxt(url, delimiter=',', dtype='object')

In [66]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris_2d = np.genfromtxt(url, delimiter=',', dtype='object')
    
# 法一
In [67]: i, j = np.where(iris_2d)

In [68]: np.random.seed(100)
    ...: iris_2d[np.random.choice((i), 20), np.random.choice((j), 20)] = np.nan
    
# 法二
In [69]: np.random.seed(100)
    ...: iris_2d[np.random.randint(150, size=20), np.random.randint(4, size=20)] = np.nan
    
In [70]: print(iris_2d[:10])
[[b'5.1' b'3.5' b'1.4' b'0.2' b'Iris-setosa']
 [b'4.9' b'3.0' b'1.4' b'0.2' b'Iris-setosa']
 [b'4.7' b'3.2' b'1.3' b'0.2' b'Iris-setosa']
 [b'4.6' b'3.1' b'1.5' b'0.2' b'Iris-setosa']
 [b'5.0' b'3.6' b'1.4' b'0.2' b'Iris-setosa']
 [b'5.4' b'3.9' b'1.7' b'0.4' b'Iris-setosa']
 [b'4.6' b'3.4' b'1.4' b'0.3' b'Iris-setosa']
 [b'5.0' b'3.4' b'1.5' b'0.2' b'Iris-setosa']
 [b'4.4' nan b'1.4' b'0.2' b'Iris-setosa']
 [b'4.9' b'3.1' b'1.5' b'0.1' b'Iris-setosa']]

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris_2d = np.genfromtxt(url, delimiter=',', dtype='float')
iris_2d[np.random.randint(150, size=20), np.random.randint(4, size=20)] = np.nan

In [71]: # Input
    ...: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris_2d = np.genfromtxt(url, delimiter=',', dtype='float')
    ...: iris_2d[np.random.randint(150, size=20), np.random.randint(4, size=20)] = np.nan

In [72]:

In [72]: print("Number of missing values: \n", np.isnan(iris_2d[:, 0]).sum())
    ...: print("Position of missing values: \n", np.where(np.isnan(iris_2d[:, 0])))
Number of missing values:
 5
Position of missing values:
 (array([ 38,  80, 106, 113, 121], dtype=int64),)

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])

In [73]: # Input
    ...: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])

In [74]:

In [74]: condition = (iris_2d[:, 2] > 1.5) & (iris_2d[:, 0] < 5.0)
    ...: iris_2d[condition]
Out[74]:
array([[4.8, 3.4, 1.6, 0.2],
       [4.8, 3.4, 1.9, 0.2],
       [4.7, 3.2, 1.6, 0.2],
       [4.8, 3.1, 1.6, 0.2],
       [4.9, 2.4, 3.3, 1. ],
       [4.9, 2.5, 4.5, 1.7]])

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])

In [75]: # Input
    ...: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])

In [76]: iris_2d[np.random.randint(150, size=20), np.random.randint(4, size=20)] = np.nan

# 没有numpy函数直接解答这问题
# 法一
In [77]: # Method 1:
    ...: any_nan_in_row = np.array([~np.any(np.isnan(row)) for row in iris_2d])
    ...: iris_2d[any_nan_in_row][:5]
    
# 法二

In [78]: # Method 2: (By Rong)
    ...: iris_2d[np.sum(np.isnan(iris_2d), axis = 1) == 0][:5]
Out[78]:
array([[4.9, 3. , 1.4, 0.2],
       [4.7, 3.2, 1.3, 0.2],
       [4.6, 3.1, 1.5, 0.2],
       [5. , 3.6, 1.4, 0.2],
       [4.6, 3.4, 1.4, 0.3]])

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])

In [83]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])
    ...:

# 法一

In [84]: np.corrcoef(iris[:, 0], iris[:, 2])[0, 1]
    ...:
Out[84]: 0.8717541573048712

# 法二
In [85]: from scipy.stats.stats import pearsonr
    ...: corr, p_value = pearsonr(iris[:, 0], iris[:, 2])
    ...: print(corr)
0.8717541573048712

# 相关系数表示两个数值变量之间的线性关系程度。它的范
围在-1到+1之间。
# p-value粗略地表示不相关系统产生的数据集的在极端情况下计算具有相关性的概率。
# p值越低（<0.01），相关的意义越强。它不是表示强弱的指标。

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])

In [86]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])

In [87]:

In [87]: np.isnan(iris_2d).any()
Out[87]: False

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])

In [88]: # Input
    ...: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])
    ...: iris_2d[np.random.randint(150, size=20), np.random.randint(4, size=20)] = np.nan

In [89]: iris_2d[np.isnan(iris_2d)] = 0

In [90]: iris_2d[:4]
Out[90]:
array([[5.1, 3.5, 1.4, 0.2],
       [4.9, 3. , 1.4, 0.2],
       [4.7, 3.2, 1.3, 0.2],
       [4.6, 3.1, 1.5, 0.2]])

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris = np.genfromtxt(url, delimiter=',', dtype='object')
names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

In [91]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris = np.genfromtxt(url, delimiter=',', dtype='object')
    ...: names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

# 解法    
In [92]: # Extract the species column as an array
    ...: species = np.array([row.tolist()[4] for row in iris])

In [93]: # Get the unique values and the counts
    ...: np.unique(species, return_counts=True)
Out[93]:
(array([b'Iris-setosa', b'Iris-versicolor', b'Iris-virginica'],
       dtype='|S15'), array([50, 50, 50], dtype=int64))

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris = np.genfromtxt(url, delimiter=',', dtype='object')
names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

In [91]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris = np.genfromtxt(url, delimiter=',', dtype='object')
    ...: names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

# 解法    
In [94]: petal_length_bin = np.digitize(iris[:, 2].astype('float'), [0, 3, 5, 10])

In [95]: label_map = {1: 'small', 2: 'medium', 3: 'large', 4: np.nan}

In [96]: petal_length_cat = [label_map[x] for x in petal_length_bin]

In [97]: petal_length_cat[:4]
Out[97]: ['small', 'small', 'small', 'small']

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris_2d = np.genfromtxt(url, delimiter=',', dtype='object')
names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

# 输入
In [99]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris_2d = np.genfromtxt(url, delimiter=',', dtype='object')

# 解答
# 计算体积
In [100]: sepallength = iris_2d[:, 0].astype('float')
     ...: petallength = iris_2d[:, 2].astype('float')
     ...: volume = (np.pi * petallength * (sepallength**2))/3

# 引入新维度来匹配iris_2d
In [101]: volume = volume[:, np.newaxis]

# 添加新列
In [102]: out = np.hstack([iris_2d, volume])

In [103]: out[:4]
Out[103]:
array([[b'5.1', b'3.5', b'1.4', b'0.2', b'Iris-setosa',
        38.13265162927291],
       [b'4.9', b'3.0', b'1.4', b'0.2', b'Iris-setosa',
        35.200498485922445],
       [b'4.7', b'3.2', b'1.3', b'0.2', b'Iris-setosa', 30.0723720777127],
       [b'4.6', b'3.1', b'1.5', b'0.2', b'Iris-setosa',
        33.238050274980004]], dtype=object)

# Input
# Import iris keeping the text column intact
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris = np.genfromtxt(url, delimiter=',', dtype='object')

# 导入iris保持文本列不变
In [104]: # Import iris keeping the text column intact
     ...: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
     ...: iris = np.genfromtxt(url, delimiter=',', dtype='object')
# 解答
# Get the species column
In [105]: species = iris[:, 4]

# 法一: Generate Probablistically
In [106]: np.random.seed(100)
     ...: a = np.array(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'])
     ...: species_out = np.random.choice(a, 150, p=[0.5, 0.25, 0.25])

# 法二: Probablistic Sampling (preferred)
In [107]: np.random.seed(100)
     ...: probs = np.r_[np.linspace(0, 0.500, num=50), np.linspace(0.501, .750, num=50), np.linspace(.751, 1.0, num=50)
     ...: ]
     ...: index = np.searchsorted(probs, np.random.random(150))
     ...: species_out = species[index]

In [108]: print(np.unique(species_out, return_counts=True))
(array([b'Iris-setosa', b'Iris-versicolor', b'Iris-virginica'],
      dtype=object), array([77, 37, 36], dtype=int64))

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris = np.genfromtxt(url, delimiter=',', dtype='object')
names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

In [109]: # Input
     ...: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
     ...: iris = np.genfromtxt(url, delimiter=',', dtype='object')
     ...: names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

# 解答
# Get the species and petal length columns
In [110]: petal_len_setosa = iris[iris[:, 4] == b'Iris-setosa', [2]].astype('float')
# 获取倒数第二个值
In [111]: np.unique(np.sort(petal_len_setosa))[-2]
Out[111]: 1.7

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris = np.genfromtxt(url, delimiter=',', dtype='object')
names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

In [109]: # Input
     ...: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
     ...: iris = np.genfromtxt(url, delimiter=',', dtype='object')
     ...: names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

# 解法
In [112]: print(iris[iris[:,0].argsort()][:10])
[[b'4.3' b'3.0' b'1.1' b'0.1' b'Iris-setosa']
 [b'4.4' b'3.2' b'1.3' b'0.2' b'Iris-setosa']
 [b'4.4' b'3.0' b'1.3' b'0.2' b'Iris-setosa']
 [b'4.4' b'2.9' b'1.4' b'0.2' b'Iris-setosa']
 [b'4.5' b'2.3' b'1.3' b'0.3' b'Iris-setosa']
 [b'4.6' b'3.6' b'1.0' b'0.2' b'Iris-setosa']
 [b'4.6' b'3.1' b'1.5' b'0.2' b'Iris-setosa']
 [b'4.6' b'3.4' b'1.4' b'0.3' b'Iris-setosa']
 [b'4.6' b'3.2' b'1.4' b'0.2' b'Iris-setosa']
 [b'4.7' b'3.2' b'1.3' b'0.2' b'Iris-setosa']]

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris = np.genfromtxt(url, delimiter=',', dtype='object')
names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

In [113]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
     ...: iris = np.genfromtxt(url, delimiter=',', dtype='object')

# 解法
In [114]: vals, counts = np.unique(iris[:, 2], return_counts=True)
     ...: print(vals[np.argmax(counts)])
b'1.5'

# Input:
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris = np.genfromtxt(url, delimiter=',', dtype='object')

In [115]: # Input:
     ...: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
     ...: iris = np.genfromtxt(url, delimiter=',', dtype='object')

# 解法
In [116]: np.argwhere(iris[:, 3].astype(float) > 1.0)[0]
Out[116]: array([50], dtype=int64)

# Input:
np.random.seed(100)
a = np.random.uniform(1,50, 20)

# 输入
In [117]: np.random.seed(100)
     ...: a = np.random.uniform(1,50, 20)

# 法一     
In [118]: np.clip(a, a_min=10, a_max=30)
Out[118]:
array([27.626842, 14.6401  , 21.801362, 30.      , 10.      , 10.      ,
       30.      , 30.      , 10.      , 29.179573, 30.      , 11.250904,
       10.081083, 10.      , 11.765177, 30.      , 30.      , 10.      ,
       30.      , 14.429614])

# 法二
In [119]: print(np.where(a < 10, 10, np.where(a > 30, 30, a)))
[27.626842 14.6401   21.801362 30.       10.       10.       30.
 30.       10.       29.179573 30.       11.250904 10.081083 10.
 11.765177 30.       30.       10.       30.       14.429614]

# Input:
np.random.seed(100)
a = np.random.uniform(1,50, 20)

# 输入
In [120]: np.random.seed(100)
     ...: a = np.random.uniform(1,50, 20)

# 法一
In [121]: print(a.argsort())
[ 4 13  5  8 17 12 11 14 19  1  2  0  9  6 16 18  7  3 10 15]

# 法二
In [122]: np.argpartition(-a, 5)[:5]
Out[122]: array([15, 10,  3,  7, 18], dtype=int64)

# 以下方法会返回值 
# 法一
In [123]: a[a.argsort()][-5:]
Out[123]: array([40.995013, 41.466785, 42.39403 , 44.674776, 48.952565])

# 法二
In [124]: np.sort(a)[-5:]
Out[124]: array([40.995013, 41.466785, 42.39403 , 44.674776, 48.952565])

# 法三
In [125]: np.partition(a, kth=-5)[-5:]
Out[125]: array([40.995013, 41.466785, 42.39403 , 44.674776, 48.952565])

# 法四
In [126]: a[np.argpartition(-a, 5)][:5]
Out[126]: array([48.952565, 44.674776, 42.39403 , 41.466785, 40.995013])

np.random.seed(100)
arr = np.random.randint(1,11,size=(6, 10))
arr
> array([[ 9,  9,  4,  8,  8,  1,  5,  3,  6,  3],
>        [ 3,  3,  2,  1,  9,  5,  1, 10,  7,  3],
>        [ 5,  2,  6,  4,  5,  5,  4,  8,  2,  2],
>        [ 8,  8,  1,  3, 10, 10,  4,  3,  6,  9],
>        [ 2,  1,  8,  7,  3,  1,  9,  3,  6,  2],
>        [ 9,  2,  6,  5,  3,  9,  4,  6,  1, 10]])

> [[1, 0, 2, 1, 1, 1, 0, 2, 2, 0],
>  [2, 1, 3, 0, 1, 0, 1, 0, 1, 1],
>  [0, 3, 0, 2, 3, 1, 0, 1, 0, 0],
>  [1, 0, 2, 1, 0, 1, 0, 2, 1, 2],
>  [2, 2, 2, 0, 0, 1, 1, 1, 1, 0],
>  [1, 1, 1, 1, 1, 2, 0, 0, 2, 1]]

# 解答
In [128]: def counts_of_all_values_rowwise(arr2d):
     ...:     # Unique values and its counts row wise
     ...:     num_counts_array = [np.unique(row, return_counts=True) for row in arr2d]
     ...:
     ...:     # Counts of all values row wise
     ...:     return([[int(b[a==i]) if i in a else 0 for i in np.unique(arr2d)] for a, b in num_counts_array])
     ...:

In [129]: print(np.arange(1,11))
     ...: counts_of_all_values_rowwise(arr)
[ 1  2  3  4  5  6  7  8  9 10]
Out[129]:
[[1, 0, 2, 1, 1, 1, 0, 2, 2, 0],
 [2, 1, 3, 0, 1, 0, 1, 0, 1, 1],
 [0, 3, 0, 2, 3, 1, 0, 1, 0, 0],
 [1, 0, 2, 1, 0, 1, 0, 2, 1, 2],
 [2, 2, 2, 0, 0, 1, 1, 1, 1, 0],
 [1, 1, 1, 1, 1, 2, 0, 0, 2, 1]]
 

# 例二
In [130]: arr = np.array([np.array(list('bill clinton')), np.array(list('narendramodi')), np.array(list('jjayalalitha')
     ...: )])
     ...: print(np.unique(arr))
     ...: counts_of_all_values_rowwise(arr)
[' ' 'a' 'b' 'c' 'd' 'e' 'h' 'i' 'j' 'l' 'm' 'n' 'o' 'r' 't' 'y']
Out[130]:
[[1, 0, 1, 1, 0, 0, 0, 2, 0, 3, 0, 2, 1, 0, 1, 0],
 [0, 2, 0, 0, 2, 1, 0, 1, 0, 0, 1, 2, 1, 2, 0, 0],
 [0, 4, 0, 0, 0, 0, 1, 1, 2, 2, 0, 0, 0, 0, 1, 1]]

# Input:
arr1 = np.arange(3)
arr2 = np.arange(3,7)
arr3 = np.arange(7,10)

array_of_arrays = np.array([arr1, arr2, arr3])
array_of_arrays
#> array([array([0, 1, 2]), array([3, 4, 5, 6]), array([7, 8, 9])], dtype=object)

#> array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

In [131]: # Input:
     ...: arr1 = np.arange(3)
     ...: arr2 = np.arange(3,7)
     ...: arr3 = np.arange(7,10)
     ...:
     ...: array_of_arrays = np.array([arr1, arr2, arr3])
     ...: array_of_arrays
     ...: #> array([array([0, 1, 2]), array([3, 4, 5, 6]), array([7, 8, 9])], dtype=object)
Out[131]:
array([array([0, 1, 2]), array([3, 4, 5, 6]), array([7, 8, 9])],
      dtype=object)
# 法一
In [132]: arr_2d = np.array([a for arr in array_of_arrays for a in arr])
# 法二
In [133]: arr_2d = np.concatenate(array_of_arrays)

In [134]: print(arr_2d)
[0 1 2 3 4 5 6 7 8 9]

#!/bin/bash
COUNT=$(ps -ef |grep wechat.py |grep -v "grep" |wc -l)

datetime=`date +'%Y-%m-%d %H:%M:%I'`
logfile="/home/test/dev/itchat/log/kill_wechat.log"

if [ $COUNT -eq 0 ]; then
    echo "[$datetime] no wechat process !" >> $logfile
else
    # 删除itchat.py进程
    pid=`ps -ef | grep 'wechat.py' | grep -v grep | awk '{print $2}'`
    echo "[$datetime] kill wechat process $pid !" >> $logfile
    kill $pid
fi

pip is configured with locations that require TLS/SSL, however the ssl module in Python is not available.

yum -y install \
libjpeg \
libjpeg-devel \
libpng libpng-devel \
freetype \
freetype-devel \
libxml2 \
libxml2-devel \
mysql \
pcre-devel \
curl \
curl-devel \
libxslt-devel

wget http://cn2.php.net/distributions/php-7.2.12.tar.gz
tar -zxvf php-7.2.12.tar.gz
cd php-7.2.12

./configure \
 --prefix=/usr/local/php \
 --with-curl \
 --with-freetype-dir \
 --with-gd \
 --with-gettext \
 --with-iconv-dir \
 --with-kerberos \
 --with-libdir=lib64 \
 --with-libxml-dir \
 --with-openssl \
 --with-pcre-regex \
 --with-mysqli=shared,mysqlnd \
 --with-pdo-mysql=shared,mysqlnd \
 --with-pdo-sqlite \
 --with-pear \
 --with-png-dir \
 --with-xmlrpc \
 --with-xsl \
 --with-zlib \
 --enable-fpm \
 --enable-mysqlnd \
 --enable-bcmath \
 --enable-libxml \
 --enable-inline-optimization \
 --enable-gd-native-ttf \
 --enable-mbregex \
 --enable-mbstring \
 --enable-opcache \
 --enable-pcntl \
 --enable-shmop \
 --enable-soap \
 --enable-sockets \
 --enable-sysvsem \
 --enable-xml \
 --enable-zip \
 --disable-fileinfo \
 --with-apxs2 \
 --with-mysql-sock=/var/lib/mysql/mysql.sock

# wget http://ftp.gnu.org/pub/gnu/libiconv/libiconv-1.14.tar.gz
# tar -xf libiconv-1.14.tar.gz
# ./configure –prefix=/usr/local/libiconv
# make && make install
libiconv库安装完毕后，建议把/usr/local/libiconv/lib库加入到到/etc/ld.so.conf文件中，然后使用/sbin/ldconfig使其生效。如下：
# echo “/usr/local/libiconv/lib” >> /etc/ld.so.conf
# ldconfig
网上提供了其他两种方法，是基于已安装该库后，报错的问题，解决方式如下：
1.在make时添加如下参数：make ZEND_EXTRA_LIBS='-liconv'
2.编辑Makefile，在: EXTRA_LIBS = ..... -lcrypt 在最后加上 -liconv，例如: EXTRA_LIBS = ..... -lcrypt -liconv 然后重新再次 make 即可。
参考以下两篇文章[安装PHP出现make: *** [sapi/cli/php] Error 1 解决办法][1]
[烂泥：php5.6源码安装与apache集成][2]

make ZEND_EXTRA_LIBS='-liconv'
make install

PATH=$PATH:/usr/local/php/bin
export PATH

[root@ichxx php]# php -v
PHP 7.2.12 (cli) (built: Dec  3 2018 17:55:03) ( NTS )
Copyright (c) 1997-2018 The PHP Group
Zend Engine v3.2.0, Copyright (c) 1998-2018 Zend Technologies

cp php.ini-production /usr/local/php/etc/php.ini
cp sapi/fpm/php-fpm /usr/local/php/etc/php-fpm
cp /usr/local/php/etc/php-fpm.conf.default /usr/local/php/etc/php-fpm.conf
cp /usr/local/php/etc/php-fpm.d/www.conf.default /usr/local/php/etc/php-fpm.d/www.conf

AddType application/x-compress .Z
AddType application/x-gzip .gz .tgz

AddType application/x-httpd-php .php
AddType application/x-httpd-php-source .php7

<VirtualHost *:80>
 DocumentRoot /var/www
 ServerName www.你的域名.com
 ServerAlias 你的域名.com
 <Directory /phpstudy/www>
 Options +Indexes +FollowSymLinks +ExecCGI
 AllowOverride All
 Order Deny,Allow
 Allow from all
 </Directory>
</VirtualHost>

service httpd restart

httpd: Syntax error on line 147 of /usr/local/apache/conf/httpd.conf: Cannot load modules/libphp7.so into server: /usr/local/apache/modules/libphp7.so: cannot open shared object file: No such file or directory

<FilesMatch \.php$>
    SetHandler application/x-httpd-php
</FilesMatch>

disable_functions = phpinfo,eval,passthru,exec,system,chroot,scandir,chgrp,chown,shell_exec,proc_open,proc_get_status,ini_alter,ini_alter,ini_restore,dl,pfsockopen,openlog,syslog,readlink,symlink,popepassthru,stream_socket_server,fsocket,fsockopen

[root@ichxx ~]# php -v
PHP 7.2.12 (cli) (built: Dec  3 2018 17:55:03) ( NTS )
Copyright (c) 1997-2018 The PHP Group
Zend Engine v3.2.0, Copyright (c) 1998-2018 Zend Technologies
[root@ichxx ~]# php --ini
Configuration File (php.ini) Path: /usr/local/php/lib
Loaded Configuration File:         (none)
Scan for additional .ini files in: (none)
Additional .ini files parsed:      (none)

Connection failed: The server requested authentication method unknown to the client

rpm -qa | grep mysql

rpm -e mysql80-community-release-el6-1.noarch
rpm -e mysql-libs-5.1.73-8.el6_8.x86_64
rpm -e mysql-community-common-8.0.13-1.el7.x86_64

# https://dev.mysql.com/downloads/repo/yum/
wget https://repo.mysql.com//mysql80-community-release-el6-1.noarch.rpm
rpm -ivh mysql80-community-release-el6-1.noarch.rpm

yum install mysql-server

mysqladmin -V

service mysqld start

cat /var/log/mysqld.log

mysql -uroot -p

alter user user() identified by '123456';

chkconfig mysqld on

-- 创建数据库
create database test;

-- 创建用户
create user 'test'@'%' identified by 'Abc123456$';

-- 授权
grant all on *.* to 'test'@'%' with grant option;

有关某个命令的详细信息，请键入 HELP 命令名
ASSOC          显示或修改文件扩展名关联。
ATTRIB         显示或更改文件属性。
BREAK          设置或清除扩展式 CTRL+C 检查。
BCDEDIT        设置启动数据库中的属性以控制启动加载。
CACLS          显示或修改文件的访问控制列表(ACL)。
CALL           从另一个批处理程序调用这一个。
CD             显示当前目录的名称或将其更改。
CHCP           显示或设置活动代码页数。
CHDIR          显示当前目录的名称或将其更改。
CHKDSK         检查磁盘并显示状态报告。
CHKNTFS        显示或修改启动时间磁盘检查。
CLS            清除屏幕。
CMD            打开另一个 Windows 命令解释程序窗口。
COLOR          设置默认控制台前景和背景颜色。
COMP           比较两个或两套文件的内容。
COMPACT        显示或更改 NTFS 分区上文件的压缩。
CONVERT        将 FAT 卷转换成 NTFS。你不能转换
               当前驱动器。
COPY           将至少一个文件复制到另一个位置。
DATE           显示或设置日期。
DEL            删除至少一个文件。
DIR            显示一个目录中的文件和子目录。
DISKPART       显示或配置磁盘分区属性。
DOSKEY         编辑命令行、撤回 Windows 命令并
               创建宏。
DRIVERQUERY    显示当前设备驱动程序状态和属性。
ECHO           显示消息，或将命令回显打开或关闭。
ENDLOCAL       结束批文件中环境更改的本地化。
ERASE          删除一个或多个文件。
EXIT           退出 CMD.EXE 程序(命令解释程序)。
FC             比较两个文件或两个文件集并显示
               它们之间的不同。
FIND           在一个或多个文件中搜索一个文本字符串。
FINDSTR        在多个文件中搜索字符串。
FOR            为一组文件中的每个文件运行一个指定的命令。
FORMAT         格式化磁盘，以便用于 Windows。
FSUTIL         显示或配置文件系统属性。
FTYPE          显示或修改在文件扩展名关联中使用的文件
               类型。
GOTO           将 Windows 命令解释程序定向到批处理程序
               中某个带标签的行。
GPRESULT       显示计算机或用户的组策略信息。
GRAFTABL       使 Windows 在图形模式下显示扩展
               字符集。
HELP           提供 Windows 命令的帮助信息。
ICACLS         显示、修改、备份或还原文件和
               目录的 ACL。
IF             在批处理程序中执行有条件的处理操作。
LABEL          创建、更改或删除磁盘的卷标。
MD             创建一个目录。
MKDIR          创建一个目录。
MKLINK         创建符号链接和硬链接
MODE           配置系统设备。
MORE           逐屏显示输出。
MOVE           将一个或多个文件从一个目录移动到另一个
               目录。
OPENFILES      显示远程用户为了文件共享而打开的文件。
PATH           为可执行文件显示或设置搜索路径。
PAUSE          暂停批处理文件的处理并显示消息。
POPD           还原通过 PUSHD 保存的当前目录的上一个
               值。
PRINT          打印一个文本文件。
PROMPT         更改 Windows 命令提示。
PUSHD          保存当前目录，然后对其进行更改。
RD             删除目录。
RECOVER        从损坏的或有缺陷的磁盘中恢复可读信息。
REM            记录批处理文件或 CONFIG.SYS 中的注释(批注)。
REN            重命名文件。
RENAME         重命名文件。
REPLACE        替换文件。
RMDIR          删除目录。
ROBOCOPY       复制文件和目录树的高级实用工具
SET            显示、设置或删除 Windows 环境变量。
SETLOCAL       开始本地化批处理文件中的环境更改。
SC             显示或配置服务(后台进程)。
SCHTASKS       安排在一台计算机上运行命令和程序。
SHIFT          调整批处理文件中可替换参数的位置。
SHUTDOWN       允许通过本地或远程方式正确关闭计算机。
SORT           对输入排序。
START          启动单独的窗口以运行指定的程序或命令。
SUBST          将路径与驱动器号关联。
SYSTEMINFO     显示计算机的特定属性和配置。
TASKLIST       显示包括服务在内的所有当前运行的任务。
TASKKILL       中止或停止正在运行的进程或应用程序。
TIME           显示或设置系统时间。
TITLE          设置 CMD.EXE 会话的窗口标题。
TREE           以图形方式显示驱动程序或路径的目录
               结构。
TYPE           显示文本文件的内容。
VER            显示 Windows 的版本。
VERIFY         告诉 Windows 是否进行验证，以确保文件
               正确写入磁盘。
VOL            显示磁盘卷标和序列号。
XCOPY          复制文件和目录树。
WMIC           在交互式命令 shell 中显示 WMI 信息。

# 从c盘切换到e盘
E:\DEV\>c:
C:\Users\Test>

%0 批处理文件本身
%1 第一个参数
%9 第九个参数
%* 从第一个参数开始的所有参数

e:
cd e:\dev\env\%1\scripts
activate

In [1]: import numpy as np
   ...: rand = np.random.RandomState(42)
   ...:
   ...: x = rand.randint(100, size=10)
   ...: print(x)
[51 92 14 71 60 20 82 86 74 74]

In [2]: [x[3], x[7], x[2]]
Out[2]: [71, 86, 14]

In [3]: ind = [3, 7, 4]
   ...: x[ind]
Out[3]: array([71, 86, 60])

In [4]: ind = np.array([[3, 7],
   ...:                 [4, 5]])
   ...: x[ind]
Out[4]:
array([[71, 86],
       [60, 20]])

In [5]: X = np.arange(12).reshape((3, 4))
   ...: X
Out[5]:
array([[ 0,  1,  2,  3],
       [ 4,  5,  6,  7],
       [ 8,  9, 10, 11]])

In [6]: row = np.array([0, 1, 2])
   ...: col = np.array([2, 1, 3])
   ...: X[row, col]
Out[6]: array([ 2,  5, 11])

In [7]: X[row[:, np.newaxis], col]
Out[7]:
array([[ 2,  1,  3],
       [ 6,  5,  7],
       [10,  9, 11]])

In [8]: row[:, np.newaxis] * col
Out[8]:
array([[0, 0, 0],
       [2, 1, 3],
       [4, 2, 6]])

In [9]: print(X)
[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]]

In [10]: X[2, [2, 0, 1]]
Out[10]: array([10,  8,  9])

In [11]: X[1:, [2, 0, 1]]
Out[11]:
array([[ 6,  4,  5],
       [10,  8,  9]])

In [12]: mask = np.array([1, 0, 1, 0], dtype=bool)
    ...: X[row[:, np.newaxis], mask]
Out[12]:
array([[ 0,  2],
       [ 4,  6],
       [ 8, 10]])

In [13]: mean = [0, 0]
    ...: cov = [[1, 2],
    ...:        [2, 5]]
    ...: X = rand.multivariate_normal(mean, cov, 100)
    ...: X.shape
Out[13]: (100, 2)

In [14]: %matplotlib inline
    ...: import matplotlib.pyplot as plt
    ...: import seaborn; seaborn.set()  # for plot styling
    ...:
    ...: plt.scatter(X[:, 0], X[:, 1]);

In [16]: indices = np.random.choice(X.shape[0], 20, replace=False)
    ...: indices
Out[16]:
array([93, 87,  8, 47, 88, 84, 44, 95, 23,  3, 32, 46, 97,  0, 22,  6, 35,
       28, 25, 42])
       
In [17]: selection = X[indices]  # fancy indexing here
    ...: selection.shape
Out[17]: (20, 2)

In [18]: plt.scatter(X[:, 0], X[:, 1], alpha=0.3)
    ...: plt.scatter(selection[:, 0], selection[:, 1],
    ...:             facecolor='none', s=200);

In [19]: plt.show()

In [20]: x = np.arange(10)
    ...: i = np.array([2, 1, 8, 4])
    ...: x[i] = 99
    ...: print(x)
[ 0 99 99  3 99  5  6  7 99  9]

In [21]: x[i] -= 10
    ...: print(x)
[ 0 89 89  3 89  5  6  7 89  9]

In [22]: x = np.zeros(10)
    ...: x[[0, 0]] = [4, 6]
    ...: print(x)
[6. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

In [23]: i = [2, 3, 3, 4, 4, 4]
    ...: x[i] += 1
    ...: x
Out[23]: array([6., 0., 1., 1., 1., 0., 0., 0., 0., 0.])

In [24]: x = np.zeros(10)
    ...: np.add.at(x, i, 1)
    ...: print(x)
[0. 0. 1. 2. 3. 0. 0. 0. 0. 0.]

In [25]: np.random.seed(42)
    ...: x = np.random.randn(100)
    ...:
    ...: # compute a histogram by hand
    ...: bins = np.linspace(-5, 5, 20)
    ...: counts = np.zeros_like(bins)
    ...:
    ...: # find the appropriate bin for each x
    ...: i = np.searchsorted(bins, x)
    ...:
    ...: # add 1 to each of these bins
    ...: np.add.at(counts, i, 1)

# plot the results
In [26]: plt.plot(bins, counts, linestyle='steps');

In [28]: plt.hist(x, bins, histtype='step');

In [30]: print("NumPy routine:")
    ...: %timeit counts, edges = np.histogram(x, bins)
    ...:
    ...: print("Custom routine:")
    ...: %timeit np.add.at(counts, np.searchsorted(bins, x), 1)
NumPy routine:
23.5 µs ± 485 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)
Custom routine:
14.4 µs ± 761 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)

In [31]: x = np.random.randn(1000000)
    ...: print("NumPy routine:")
    ...: %timeit counts, edges = np.histogram(x, bins)
    ...:
    ...: print("Custom routine:")
    ...: %timeit np.add.at(counts, np.searchsorted(bins, x), 1)
NumPy routine:
71 ms ± 613 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)
Custom routine:
115 ms ± 1.43 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)

In [1]: import numpy as np
   ...: np.random.seed(0)
   ...:
   ...: def compute_reciprocals(values):
   ...:     output = np.empty(len(values))
   ...:     for i in range(len(values)):
   ...:         output[i] = 1.0 / values[i]
   ...:     return output
   ...:
   ...: values = np.random.randint(1, 10, size=5)
   ...: compute_reciprocals(values)
Out[1]: array([0.16666667, 1.        , 0.25      , 0.25      , 0.125     ])

In [2]: big_array = np.random.randint(1, 100, size=1000000)
   ...: %timeit compute_reciprocals(big_array)
2.92 s ± 244 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

In [3]: print(compute_reciprocals(values))
   ...: print(1.0 / values)
[0.16666667 1.         0.25       0.25       0.125     ]
[0.16666667 1.         0.25       0.25       0.125     ]

In [4]: %timeit (1.0 / big_array)
7.15 ms ± 217 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

In [5]: np.arange(5) / np.arange(1, 6)
Out[5]: array([0.        , 0.5       , 0.66666667, 0.75      , 0.8       ])

In [6]: x = np.arange(9).reshape((3, 3))
   ...: 2 ** x
Out[6]:
array([[  1,   2,   4],
       [  8,  16,  32],
       [ 64, 128, 256]], dtype=int32)

In [7]: x = np.arange(4)
   ...: print("x     =", x)
   ...: print("x + 5 =", x + 5)
   ...: print("x - 5 =", x - 5)
   ...: print("x * 2 =", x * 2)
   ...: print("x / 2 =", x / 2)
   ...: print("x // 2 =", x // 2)  # floor division
x     = [0 1 2 3]
x + 5 = [5 6 7 8]
x - 5 = [-5 -4 -3 -2]
x * 2 = [0 2 4 6]
x / 2 = [0.  0.5 1.  1.5]
x // 2 = [0 0 1 1]

In [8]: print("-x     = ", -x)
   ...: print("x ** 2 = ", x ** 2)
   ...: print("x % 2  = ", x % 2)
-x     =  [ 0 -1 -2 -3]
x ** 2 =  [0 1 4 9]
x % 2  =  [0 1 0 1]

In [9]: -(0.5*x + 1) ** 2
Out[9]: array([-1.  , -2.25, -4.  , -6.25])

In [10]: np.add(x, 2)
Out[10]: array([2, 3, 4, 5])

In [11]: x = np.array([-2, -1, 0, 1, 2])
    ...: abs(x)
Out[11]: array([2, 1, 0, 1, 2])

In [12]: np.absolute(x)
Out[12]: array([2, 1, 0, 1, 2])

In [13]: np.abs(x)
Out[13]: array([2, 1, 0, 1, 2])

In [14]: x = np.array([3 - 4j, 4 - 3j, 2 + 0j, 0 + 1j])
    ...: np.abs(x)
Out[14]: array([5., 5., 2., 1.])

theta = np.linspace(0, np.pi, 3)

In [16]: print("theta      = ", theta)
    ...: print("sin(theta) = ", np.sin(theta))
    ...: print("cos(theta) = ", np.cos(theta))
    ...: print("tan(theta) = ", np.tan(theta))
theta      =  [0.         1.57079633 3.14159265]
sin(theta) =  [0.0000000e+00 1.0000000e+00 1.2246468e-16]
cos(theta) =  [ 1.000000e+00  6.123234e-17 -1.000000e+00]
tan(theta) =  [ 0.00000000e+00  1.63312394e+16 -1.22464680e-16]

In [17]: x = [-1, 0, 1]
    ...: print("x         = ", x)
    ...: print("arcsin(x) = ", np.arcsin(x))
    ...: print("arccos(x) = ", np.arccos(x))
    ...: print("arctan(x) = ", np.arctan(x))
x         =  [-1, 0, 1]
arcsin(x) =  [-1.57079633  0.          1.57079633]
arccos(x) =  [3.14159265 1.57079633 0.        ]
arctan(x) =  [-0.78539816  0.          0.78539816]

In [18]: x = [1, 2, 3]
    ...: print("x     =", x)
    ...: print("e^x   =", np.exp(x))
    ...: print("2^x   =", np.exp2(x))
    ...: print("3^x   =", np.power(3, x))
x     = [1, 2, 3]
e^x   = [ 2.71828183  7.3890561  20.08553692]
2^x   = [2. 4. 8.]
3^x   = [ 3  9 27]

In [19]: x = [1, 2, 4, 10]
    ...: print("x        =", x)
    ...: print("ln(x)    =", np.log(x))
    ...: print("log2(x)  =", np.log2(x))
    ...: print("log10(x) =", np.log10(x))
x        = [1, 2, 4, 10]
ln(x)    = [0.         0.69314718 1.38629436 2.30258509]
log2(x)  = [0.         1.         2.         3.32192809]
log10(x) = [0.         0.30103    0.60205999 1.        ]

In [20]: x = [0, 0.001, 0.01, 0.1]
    ...: print("exp(x) - 1 =", np.expm1(x))
    ...: print("log(1 + x) =", np.log1p(x))
exp(x) - 1 = [0.         0.0010005  0.01005017 0.10517092]
log(1 + x) = [0.         0.0009995  0.00995033 0.09531018]

In [22]: # Gamma functions (generalized factorials) and related functions
    ...: x = [1, 5, 10]
    ...: print("gamma(x)     =", special.gamma(x))
    ...: print("ln|gamma(x)| =", special.gammaln(x))
    ...: print("beta(x, 2)   =", special.beta(x, 2))
gamma(x)     = [1.0000e+00 2.4000e+01 3.6288e+05]
ln|gamma(x)| = [ 0.          3.17805383 12.80182748]
beta(x, 2)   = [0.5        0.03333333 0.00909091]

In [23]: # Error function (integral of Gaussian)
    ...: # its complement, and its inverse
    ...: x = np.array([0, 0.3, 0.7, 1.0])
    ...: print("erf(x)  =", special.erf(x))
    ...: print("erfc(x) =", special.erfc(x))
    ...: print("erfinv(x) =", special.erfinv(x))
erf(x)  = [0.         0.32862676 0.67780119 0.84270079]
erfc(x) = [1.         0.67137324 0.32219881 0.15729921]
erfinv(x) = [0.         0.27246271 0.73286908        inf]

In [24]: x = np.arange(5)
    ...: y = np.empty(5)
    ...: np.multiply(x, 10, out=y)
    ...: print(y)
[ 0. 10. 20. 30. 40.]

In [25]: y = np.zeros(10)
    ...: np.power(2, x, out=y[::2])
    ...: print(y)
[ 1.  0.  2.  0.  4.  0.  8.  0. 16.  0.]

In [26]: x = np.arange(1, 6)
    ...: np.add.reduce(x)
Out[26]: 15

In [27]: np.multiply.reduce(x)
Out[27]: 120

In [28]: np.add.accumulate(x)
Out[28]: array([ 1,  3,  6, 10, 15], dtype=int32)

In [29]: np.multiply.accumulate(x)
Out[29]: array([  1,   2,   6,  24, 120], dtype=int32)

In [30]: x = np.arange(1, 6)
    ...: np.multiply.outer(x, x)
Out[30]:
array([[ 1,  2,  3,  4,  5],
       [ 2,  4,  6,  8, 10],
       [ 3,  6,  9, 12, 15],
       [ 4,  8, 12, 16, 20],
       [ 5, 10, 15, 20, 25]])

# 安装
[root@test wx]# pip install vitualenv

[root@test wx]# pip install virtualenv
Collecting virtualenv
  Downloading https://files.pythonhosted.org/packages/7c/17/9b7b6cddfd255388b58c61e25b091047f6814183e1d63741c8df8dcd65a2/virtualenv-16.1.0-py2.py3-none-any.whl (1.9MB)
    100% |████████████████████████████████| 1.9MB 12.6MB/s 
Installing collected packages: virtualenv
Successfully installed virtualenv-16.1.0

virtualenv --version

# 创建项目目录，并进入该目录创建虚拟环境
mkdir wx
cd wx
#
[test@test venv]$ virtualenv wx
Using base prefix '/usr/local'
New python executable in /home/test/dev/venv/wx/bin/python3.7
Also creating executable in /home/test setuptools, pip, wheel...
done.

virtualenv -p /usr/bin/python2.7 wx

export VIRTUALENVWRAPPER_PYTHON=/usr/bin/python2.7

[test@test venv]$ source wx/bin/activate
(wx) [test@test venv]$ 

# 系统中的包
[test@test itchat]$ pip -V
pip 18.0 from /usr/local/lib/python3.7/site-packages/pip (python 3.7)

# 虚拟环境中的包
(wx) [test@test venv]$ pip --version
pip 18.1 from /home/test/dev/venv/wx/lib/python3.7/site-packages/pip (python 3.7)

deactivate

rm -rf wx

#!/bin/bash
COUNT=$(ps -ef |grep test.sh |grep -v "grep" |wc -l)

if [ $COUNT -eq 0 ]; then
    nohup sh /home/test/dev/test.sh >> test.log &
else
    now=`date +'%Y-%m-%d %H:%M:%I'`
    echo "$now tesh.sh is running" > check_test.log
fi

# crontab配置
# */2 * * * * nohup sh /home/test/dev/check_test.sh &

    html = etree.parse("index.html")

    html = etree.parse("index.html", etree.HTMLParser())

cd /etc/yum.repos.d
mv CentOS-Base.repo CentOS-Base.20181126.repo

# 阿里云的yum源
wget -O /etc/yum.repos.d/CentOS-Base.repo http://mirrors.aliyun.com/repo/Centos-6.repo

# 网易的yum源
wget -O /etc/yum.repos.d/CentOS-Base.repo http://mirrors.163.com/.help/CentOS6-Base-163.repo

# 搜狐的yum源
wget -O /etc/yum.repos.d/CentOS-Base.repo http://mirrors.sohu.com/help/CentOS-Base-sohu.repo

yum clean all
yum makecache

yum -y update

# vim /usr/bin/yum
把第一行中的#!/usr/bin/python 改成#!/usr/bin/python2.6.6。

create user test with password '123456';

select * from pg_catalog.pg_user;

* psql命令
\du

create schema test
alter schema test owner to test;

 SET search_path TO test, "$user",public;

select * from information_schema.schemata;

create database test owner test;

\l

pip install jupyter

pip install RISE

jupyter-nbextension install rise --py --sys-prefix

jupyter-nbextension enable rise --py --sys-prefix

jupyter notebook

In [1]: import numpy

In [2]: numpy.__version__
Out[2]: '1.16.2'

import numpy as np

In [3]: np.<TAB>

In [4]: np?

# 安装virtualenv（工作目录为/www/services/pgadmin4）
# 使用目标python版本的pip来安装
[root@gp6 services]# pip37 install virtualenv

# 创建虚拟环境时指定python版本
# 由于系统存在多个python版本，且virtualenv的路径没添加以PATH中，需以绝对路径创建  
# 其中python3.7安装的virtualenv路径为/usr/local/python3.7/bin/virtualenv
[root@gp6 services]# /usr/local/python3.7/bin/virtualenv -p /usr/bin/python37 pgadmin4

# 使用系统python直接创建
# virtualenv pgadmin4

# 注意：激活后命令提示符前会带(pgadmin4)字样
[root@gp6 services]# cd pgadmin4
[root@gp6 pgadmin4]# . ./bin/activate
(pgadmin4) [root@gp6 pgadmin4]# 

deactivate

# 
(pgadmin4) [root@gp6 www]# cd /www/services

# 下载
(pgadmin4) [root@gp6 pgadmin4]# wget https://ftp.postgresql.org/pub/pgadmin/pgadmin4/v4.3/pip/pgadmin4-4.3-py2.py3-none-any.whl

python-flask-principal
python-flask-babel
python-flask
python-flask-wtf
python-flask-security
python-flask-gravatar
python-flask-mail 
python-dateutil 
django-htmlmin
babel 
python-flask-login 
python-wsgiref 
python-fixtures 
python-pbr 
python-mimeparse 
python-flask-sqlalchemy 
python-pyrsistent 
python-simplejson 
python-wtforms 
python-beautifulsoup4 
python-itsdangerous 
python-sqlalchemy 
python-werkzeug 
python-markupsafe 
pytz 
python-sqlparse 
python-jinja2

# 激活虚拟环境后就安装pgadmin4
(pgadmin4) [root@gp6 pgadmin4]# pip install pgadmin4-4.3-py2.py3-none-any.whl

# 查出配置文件路径（进入虚拟环境目录 ）
# find . -name "config.py"
# 拷贝配置文件
(pgadmin4) [root@gp6 pgadmin4]# cp ./lib/python3.7/site-packages/pgadmin4/config.py ./lib/python3.7/site-packages/pgadmin4/config_local.py

# 找出pgAdmin4.py的路径
(pgadmin4) [root@gp6 pgadmin4]# find . -name "pgAdmin4.py"
./lib/python3.7/site-packages/pgadmin4/pgAdmin4.py

# 在终端运行pgadmin4后，会显示网页访问的访问方式 ip:port
(pgadmin4) [root@gp6 pgadmin4]# python ./lib/python3.7/site-packages/pgadmin4/pgAdmin4.py
/www/services/pgadmin4/lib/python3.7/site-packages/psycopg2/__init__.py:144: UserWarning: The psycopg2 wheel package will be renamed from release 2.8; in order to keep installing from binary please use "pip install psycopg2-binary" instead. For details see: <http://initd.org/psycopg/docs/install.html#binary-install-from-pypi>.
  """)
Starting pgAdmin 4. Please navigate to http://192.168.99.71:5050 in your browser.
 * Running on http://192.168.99.71:5050/ (Press CTRL+C to quit)

# 在浏览器上输入第5点中的ip:port，输入帐号密码就可以登录pgadmin4管理页面了。

    start_url = 'https://gz.lianjia.com/ershoufang/yuexiu/'
    content = requests.get(start_url).text
    s = etree.parse(content, etree.HTMLParser())
    district = s.xpath('/html/body/div[3]/div/div[1]/dl[2]/dd/div[1]/div/a/@href')
    print(district)

    s = etree.parse('index.html', etree.HTMLParser())

    s = etree.fromstring(content, etree.HTMLParser())

    s = etree.parse(StringIO(content), etree.HTMLParser())

def parse(self, response):
    filename = "teacher.html"
    open(filename, 'w').write(response.body)

def parse(self, response):
    filename = "teacher.html"
    open(filename, 'wb').write(response.body)

def parse(self, response):
    filename = "teacher.html"
    open(filename, 'w').write(response.body.decode('utf-8'))

def parse(self, response):
    filename = "teacher.html"
    open(filename, 'wb').write(response.body.decode('UTF-8-sig').replace(u'\xa0', u' ').encode('utf-8'))

In [1]: import numpy as np
   ...: import pandas as pd

In [2]: data = pd.Series([0.25, 0.5, 0.75, 1.0])
   ...: data
Out[2]:
0    0.25
1    0.50
2    0.75
3    1.00
dtype: float64

In [3]: data.values
Out[3]: array([0.25, 0.5 , 0.75, 1.  ])

In [4]: data.index
Out[4]: RangeIndex(start=0, stop=4, step=1)

In [5]: data[1]
Out[5]: 0.5

In [6]: data[1:3]
Out[6]:
1    0.50
2    0.75
dtype: float64

In [7]: data = pd.Series([0.25, 0.5, 0.75, 1.0],
   ...:                  index=['a', 'b', 'c', 'd'])
   ...: data
Out[7]:
a    0.25
b    0.50
c    0.75
d    1.00
dtype: float64

In [8]: data['b']
Out[8]: 0.5

In [9]: data = pd.Series([0.25, 0.5, 0.75, 1.0],
   ...:                  index=[2, 5, 3, 7])
   ...: data
Out[9]:
2    0.25
5    0.50
3    0.75
7    1.00
dtype: float64

In [10]: data[5]
Out[10]: 0.5

In [11]: population_dict = {'California': 38332521,
    ...:                    'Texas': 26448193,
    ...:                    'New York': 19651127,
    ...:                    'Florida': 19552860,
    ...:                    'Illinois': 12882135}
    ...: population = pd.Series(population_dict)
    ...: population
Out[11]:
California    38332521
Texas         26448193
New York      19651127
Florida       19552860
Illinois      12882135
dtype: int64

In [12]: population['California']
Out[12]: 38332521

In [13]: population['California':'Illinois']
Out[13]:
California    38332521
Texas         26448193
New York      19651127
Florida       19552860
Illinois      12882135
dtype: int64

>>> pd.Series(data, index=index)

In [15]: pd.Series([2, 4, 6])
Out[15]:
0    2
1    4
2    6
dtype: int64

In [16]: pd.Series(5, index=[100, 200, 300])
Out[16]:
100    5
200    5
300    5
dtype: int64

In [17]: pd.Series({2:'a', 1:'b', 3:'c'})
Out[17]:
2    a
1    b
3    c
dtype: object

In [18]: pd.Series({2:'a', 1:'b', 3:'c'}, index=[3, 2])
Out[18]:
3    c
2    a
dtype: object

In [19]: area_dict = {'California': 423967, 'Texas': 695662, 'New York': 141297,
    ...:              'Florida': 170312, 'Illinois': 149995}
    ...: area = pd.Series(area_dict)
    ...: area
Out[19]:
California    423967
Texas         695662
New York      141297
Florida       170312
Illinois      149995
dtype: int64

In [20]: states = pd.DataFrame({'population': population,
    ...:                        'area': area})
    ...: states
Out[20]:
            population    area
California    38332521  423967
Texas         26448193  695662
New York      19651127  141297
Florida       19552860  170312
Illinois      12882135  149995

In [21]: states.index
Out[21]: Index(['California', 'Texas', 'New York', 'Florida', 'Illinois'], dtype='object')

In [22]: states.columns
Out[22]: Index(['population', 'area'], dtype='object')

In [23]: states['area']
Out[23]:
California    423967
Texas         695662
New York      141297
Florida       170312
Illinois      149995
Name: area, dtype: int64

In [24]: pd.DataFrame(population, columns=['population'])
Out[24]:
            population
California    38332521
Texas         26448193
New York      19651127
Florida       19552860
Illinois      12882135

In [25]: data = [{'a': i, 'b': 2 * i}
    ...:         for i in range(3)]
    ...: pd.DataFrame(data)
Out[25]:
   a  b
0  0  0
1  1  2
2  2  4

In [26]: pd.DataFrame([{'a': 1, 'b': 2}, {'b': 3, 'c': 4}])
Out[26]:
     a  b    c
0  1.0  2  NaN
1  NaN  3  4.0

In [27]: pd.DataFrame({'population': population,
    ...:               'area': area})
Out[27]:
            population    area
California    38332521  423967
Texas         26448193  695662
New York      19651127  141297
Florida       19552860  170312
Illinois      12882135  149995

In [28]: pd.DataFrame(np.random.rand(3, 2),
    ...:              columns=['foo', 'bar'],
    ...:              index=['a', 'b', 'c'])
Out[28]:
        foo       bar
a  0.975209  0.685941
b  0.370348  0.502609
c  0.521795  0.358374

In [29]: A = np.zeros(3, dtype=[('A', 'i8'), ('B', 'f8')])
    ...: A
Out[29]: array([(0, 0.), (0, 0.), (0, 0.)], dtype=[('A', '<i8'), ('B', '<f8')])

In [30]: pd.DataFrame(A)
Out[30]:
   A    B
0  0  0.0
1  0  0.0
2  0  0.0

In [31]: ind = pd.Index([2, 3, 5, 7, 11])
    ...: ind
Out[31]: Int64Index([2, 3, 5, 7, 11], dtype='int64')

In [32]: ind[1]
Out[32]: 3

In [33]: ind[::2]
Out[33]: Int64Index([2, 5, 11], dtype='int64')

In [34]: print(ind.size, ind.shape, ind.ndim, ind.dtype)
5 (5,) 1 int64

In [35]: ind[1] = 0
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-35-906a9fa1424c> in <module>
----> 1 ind[1] = 0

e:\dev\env\data\lib\site-packages\pandas\core\indexes\base.py in __setitem__(self, key, value)
   3935
   3936     def __setitem__(self, key, value):
-> 3937         raise TypeError("Index does not support mutable operations")
   3938
   3939     def __getitem__(self, key):

TypeError: Index does not support mutable operations

In [36]: indA = pd.Index([1, 3, 5, 7, 9])
    ...: indB = pd.Index([2, 3, 5, 7, 11])

In [37]: indA & indB  # intersection
Out[37]: Int64Index([3, 5, 7], dtype='int64')

In [38]: indA | indB  # union
Out[38]: Int64Index([1, 2, 3, 5, 7, 9, 11], dtype='int64')

In [39]: indA ^ indB  # symmetric difference
Out[39]: Int64Index([1, 2, 9, 11], dtype='int64')

In [1]: import numpy as np

In [2]: name = ['Alice', 'Bob', 'Cathy', 'Doug']
   ...: age = [25, 45, 37, 19]
   ...: weight = [55.0, 85.5, 68.0, 61.5]

In [3]: x = np.zeros(4, dtype=int)

In [4]: # Use a compound data type for structured arrays
   ...: data = np.zeros(4, dtype={'names':('name', 'age', 'weight'),
   ...:                           'formats':('U10', 'i4', 'f8')})
   ...: print(data.dtype)
[('name', '<U10'), ('age', '<i4'), ('weight', '<f8')]

In [5]: data['name'] = name
   ...: data['age'] = age
   ...: data['weight'] = weight
   ...: print(data)
[('Alice', 25, 55. ) ('Bob', 45, 85.5) ('Cathy', 37, 68. )
 ('Doug', 19, 61.5)]

In [6]: # Get all names
   ...: data['name']
Out[6]: array(['Alice', 'Bob', 'Cathy', 'Doug'], dtype='<U10')

In [7]: # Get first row of data
   ...: data[0]
Out[7]: ('Alice', 25, 55.)

In [8]: # Get the name from the last row
   ...: data[-1]['name']
Out[8]: 'Doug'

In [9]: # Get names where age is under 30
   ...: data[data['age'] < 30]['name']
Out[9]: array(['Alice', 'Doug'], dtype='<U10')

In [10]: np.dtype({'names':('name', 'age', 'weight'),
    ...:           'formats':('U10', 'i4', 'f8')})
Out[10]: dtype([('name', '<U10'), ('age', '<i4'), ('weight', '<f8')])

In [11]: np.dtype({'names':('name', 'age', 'weight'),
    ...:           'formats':((np.str_, 10), int, np.float32)})
Out[11]: dtype([('name', '<U10'), ('age', '<i4'), ('weight', '<f4')])

In [12]: np.dtype([('name', 'S10'), ('age', 'i4'), ('weight', 'f8')])
Out[12]: dtype([('name', 'S10'), ('age', '<i4'), ('weight', '<f8')])

In [13]: np.dtype('S10,i4,f8')
Out[13]: dtype([('f0', 'S10'), ('f1', '<i4'), ('f2', '<f8')])

In [14]: tp = np.dtype([('id', 'i8'), ('mat', 'f8', (3, 3))])
    ...: X = np.zeros(1, dtype=tp)
    ...: print(X[0])
    ...: print(X['mat'][0])
(0, [[0., 0., 0.], [0., 0., 0.], [0., 0., 0.]])
[[0. 0. 0.]
 [0. 0. 0.]
 [0. 0. 0.]]

In [15]: data['age']
Out[15]: array([25, 45, 37, 19])

In [16]: data_rec = data.view(np.recarray)
    ...: data_rec.age
Out[16]: array([25, 45, 37, 19])

In [17]: %timeit data['age']
    ...: %timeit data_rec['age']
    ...: %timeit data_rec.age
133 ns ± 11.4 ns per loop (mean ± std. dev. of 7 runs, 10000000 loops each)
3.83 µs ± 256 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)
5.19 µs ± 477 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)

In [1]: import numpy as np

In [2]: a = np.array([0, 1, 2])
   ...: b = np.array([5, 5, 5])
   ...: a + b
Out[2]: array([5, 6, 7])

In [3]: a + 5
Out[3]: array([5, 6, 7])

In [4]: M = np.ones((3, 3))
   ...: M
Out[4]:
array([[1., 1., 1.],
       [1., 1., 1.],
       [1., 1., 1.]])

In [5]: M + a
Out[5]:
array([[1., 2., 3.],
       [1., 2., 3.],
       [1., 2., 3.]])

In [6]: a = np.arange(3)
   ...: b = np.arange(3)[:, np.newaxis]
   ...:
   ...: print(a)
   ...: print(b)
[0 1 2]
[[0]
 [1]
 [2]]

In [7]: a + b
Out[7]:
array([[0, 1, 2],
       [1, 2, 3],
       [2, 3, 4]])

In [8]: M = np.ones((2, 3))
   ...: a = np.arange(3)

In [9]: M + a
Out[9]:
array([[1., 2., 3.],
       [1., 2., 3.]])

In [10]: a = np.arange(3).reshape((3, 1))
    ...: b = np.arange(3)

In [11]: a + b
Out[11]:
array([[0, 1, 2],
       [1, 2, 3],
       [2, 3, 4]])

In [12]: M = np.ones((3, 2))
    ...: a = np.arange(3)

In [13]: M + a
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-13-8cac1d547906> in <module>
----> 1 M + a

ValueError: operands could not be broadcast together with shapes (3,2) (3,)

In [14]: a[:, np.newaxis].shape
Out[14]: (3, 1)

In [15]: M + a[:, np.newaxis]
Out[15]:
array([[1., 1.],
       [2., 2.],
       [3., 3.]])

In [16]: np.logaddexp(M, a[:, np.newaxis])
Out[16]:
array([[1.31326169, 1.31326169],
       [1.69314718, 1.69314718],
       [2.31326169, 2.31326169]])

In [17]: X = np.random.random((10, 3))

In [18]: Xmean = X.mean(0)
    ...: Xmean
Out[18]: array([0.44645094, 0.54261367, 0.56561384])

In [19]: X_centered = X - Xmean

In [20]: X_centered.mean(0)
Out[20]: array([ 7.77156117e-17, -6.66133815e-17, -9.99200722e-17])

In [21]: # x and y have 50 steps from 0 to 5
    ...: x = np.linspace(0, 5, 50)
    ...: y = np.linspace(0, 5, 50)[:, np.newaxis]
    ...:
    ...: z = np.sin(x) ** 10 + np.cos(10 + y * x) * np.cos(x)

In [22]: %matplotlib inline
    ...: import matplotlib.pyplot as plt

In [23]: plt.imshow(z, origin='lower', extent=[0, 5, 0, 5],
    ...:            cmap='viridis')
    ...: plt.colorbar();

In [1]: help(len)
Help on built-in function len in module builtins:

len(obj, /)
    Return the number of items in a container.

In [2]: len?
Signature: len(obj, /)
Docstring: Return the number of items in a container.
Type:      builtin_function_or_method

In [3]: L = [1 ,2 ,3]

In [4]: L.insert?
Docstring: L.insert(index, object) -- insert object before index
Type:      builtin_function_or_method

In [5]: L?
Type:        list
String form: [1, 2, 3]
Length:      3
Docstring:
list() -> new empty list
list(iterable) -> new list initialized from iterable's items

In [6]: def square(a):
   ...:     """Return the square of a."""
   ...:     return a ** 2
   ...:

In [7]: square?
Signature: square(a)
Docstring: Return the square of a.
File:      c:\users\username\<ipython-input-6-3ed0e8c09915>
Type:      function

In [8]: square??
Signature: square(a)
Source:
def square(a):
    """Return the square of a."""
    return a ** 2
File:      c:\users\username\<ipython-input-6-3ed0e8c09915>
Type:      function

In [9]: len??
Signature: len(obj, /)
Docstring: Return the number of items in a container.
Type:      builtin_function_or_method

In [10]: L.<TAB>
            L.append  L.count   L.insert  L.reverse
            L.clear   L.extend  L.pop     L.sort
            L.copy    L.index   L.remove

In [10]: L.co<TAB>
              L.copy
              L.count

In [10]: L.cou<TAB>

In [10]: L.__
              L.__add__           L.__dir__           L.__getattribute__  L.__imul__          L.__len__
              L.__class__         L.__doc__           L.__getitem__       L.__init__          L.__lt__
              L.__contains__      L.__eq__            L.__gt__            L.__init_subclass__ L.__mul__           
              L.__delattr__       L.__format__        L.__hash__          L.__iter__          L.__ne__
              L.__delitem__       L.__ge__            L.__iadd__          L.__le__            L.__new__

In [10]: from itertools import co<TAB>
                                  combinations                  compress
                                  combinations_with_replacement count

In [10]: import <TAB>
  abc                    anaconda_navigator     asn1crypto             asyncio                babel
  adodbapi               anaconda_project       ast                    asyncore               backports
  afxres                 antigravity            astroid                atexit                 base64                 
  aifc                   argparse               astropy                audioop                bdb
  alabaster              array                  asynchat               autoreload             binascii

In [10]: *Warning?
BytesWarning
DeprecationWarning
FutureWarning
ImportWarning
PendingDeprecationWarning
ResourceWarning
RuntimeWarning
SyntaxWarning
UnicodeWarning
UserWarning
Warning

In [12]: str.*find*?
str.find
str.rfind

You are using pip version 19.0.2, however version 19.0.3 is available.
You should consider upgrading via the 'python -m pip install --upgrade pip' command.

(lianjia) e:\DEV\projects\spider>pip install -U pip
Collecting pip
  Downloading https://files.pythonhosted.org/packages/d8/f3/413bab4ff08e1fc4828dfc59996d721917df8e8583ea85385d51125dceff/pip-19.0.3-py2.py3-none-any.whl (1.4MB)
    100% |████████████████████████████████| 1.4MB 214kB/s
Installing collected packages: pip
  Found existing installation: pip 19.0.2
    Uninstalling pip-19.0.2:
Could not install packages due to an EnvironmentError: [WinError 5] 拒绝访问。: 'e:\\dev\\env\\lianjia\\scripts\\pip.exe'
Consider using the `--user` option or check the permissions.

(lianjia) e:\DEV\projects\spider>pip install beautifulsoup4
Traceback (most recent call last):
  File "d:\user\chenwj\apps\anaconda3\Lib\runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "d:\user\chenwj\apps\anaconda3\Lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "E:\DEV\env\lianjia\Scripts\pip.exe\__main__.py", line 5, in <module>
ModuleNotFoundError: No module named 'pip'

(lianjia) e:\DEV\projects\spider>curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100 1659k  100 1659k    0     0   237k      0  0:00:07  0:00:07 --:--:--  363k
(lianjia) e:\DEV\projects\spider>python get-pip.py
Collecting pip
  Using cached https://files.pythonhosted.org/packages/d8/f3/413bab4ff08e1fc4828dfc59996d721917df8e8583ea85385d51125dceff/pip-19.0.3-py2.py3-none-any.whl
Installing collected packages: pip
Successfully installed pip-19.0.3

(lianjia) e:\DEV\projects\spider>pip -V
pip 19.0.3 from e:\dev\env\lianjia\lib\site-packages\pip (python 3.6)

In [1]: import numpy as np

In [2]: L = np.random.random(100)
   ...: sum(L)
   ...:
Out[2]: 50.19656740027611

In [3]: np.sum(L)
Out[3]: 50.1965674002761

In [4]: big_array = np.random.rand(1000000)
   ...: %timeit sum(big_array)
   ...: %timeit np.sum(big_array)
   ...:
74.8 ms ± 542 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)
1.31 ms ± 64.4 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

In [5]: min(big_array), max(big_array)
Out[5]: (5.128750490968059e-07, 0.9999988318220189)

In [7]: %timeit min(big_array)
   ...: %timeit np.min(big_array)
   ...:
59.2 ms ± 4.86 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
517 µs ± 20.4 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

In [8]: print(big_array.min(), big_array.max(), big_array.sum())
5.128750490968059e-07 0.9999988318220189 499989.9197268303

In [9]: M = np.random.random((3, 4))
   ...: print(M)
   ...:
[[0.00728389 0.92617593 0.91146565 0.09980222]
 [0.37296596 0.54088655 0.32771595 0.75633785]
 [0.5521776  0.33464218 0.95525122 0.85253779]]

In [10]: M.sum()
Out[10]: 6.637242775730832

In [11]: M.min(axis=0)
Out[11]: array([0.00728389, 0.33464218, 0.32771595, 0.09980222])

In [12]: M.max(axis=1)
Out[12]: array([0.92617593, 0.75633785, 0.95525122])

!head -4 data/president_heights.csv
order,name,height(cm)
1,George Washington,189
2,John Adams,170
3,Thomas Jefferson,189

In [3]: import pandas as pd
   ...: data = pd.read_csv('data/president_heights.csv')
   ...: heights = np.array(data['height(cm)'])
   ...: print(heights)
[189 170 189 163 183 171 185 168 173 183 173 173 175 178 183 193 178 173
 174 183 183 168 170 178 182 180 183 178 182 188 175 179 183 193 182 183
 177 185 188 188 182 185]

In [4]: print("Mean height:       ", heights.mean())
   ...: print("Standard deviation:", heights.std())
   ...: print("Minimum height:    ", heights.min())
   ...: print("Maximum height:    ", heights.max())
Mean height:        179.73809523809524
Standard deviation: 6.931843442745892
Minimum height:     163
Maximum height:     193

In [5]: print("25th percentile:   ", np.percentile(heights, 25))
   ...: print("Median:            ", np.median(heights))
   ...: print("75th percentile:   ", np.percentile(heights, 75))
25th percentile:    174.25
Median:             182.0
75th percentile:    183.0

In [7]: %matplotlib inline
   ...: import matplotlib.pyplot as plt
   ...: import seaborn; seaborn.set()  # set plot style

In [8]: plt.hist(heights)
   ...: plt.title('Height Distribution of US Presidents')
   ...: plt.xlabel('height (cm)')
   ...: plt.ylabel('number');

    正在生成代码
    已完成代码的生成
    LINK : fatal error LNK1158: 无法运行“rc.exe”
    error: command 'C:\\Program Files (x86)\\Microsoft Visual Studio 14.0\\VC\\BIN\\x86_amd64\\link.exe' failed with exit status 1158

    ----------------------------------------
Command "e:\dev\env\data\scripts\python.exe -u -c "import setuptools, tokenize;__file__='C:\\Users\\test\\AppData\\Local\\Temp\\pip-install-v50c8czo\\line-profiler\\setup.py';f=getattr(tokenize, 'open', open)(__file__);code=f.read().replace('\r\n', '\n');f.close();exec(compile(code, __file__, 'exec'))" install --record C:\Users\test\AppData\Local\Temp\pip-record-oi53nlxu\install-record.txt --single-version-externally-managed --compile --install-headers e:\dev\env\data\include\site\python3.6\line-profiler" failed with error code 1 in C:\Users\test\AppData\Local\Temp\pip-install-v50c8czo\line-profiler\

... 省略 ...
  copying src\twisted\words\xish\xpathparser.g -> build\lib.win-amd64-3.6\twisted\words\xish
  running build_ext
  building 'twisted.test.raiser' extension
  error: Microsoft Visual C++ 14.0 is required. Get it with "Microsoft Visual C++ Build Tools": https://visualstudio.microsoft.com/downloads/
  ----------------------------------------
  Failed building wheel for Twisted
  Running setup.py clean for Twisted
Failed to build Twisted
Installing collected packages: Twisted, cssselect, PyDispatcher, pycparser, cffi, asn1crypto, cryptography, pyasn1, pyasn1-modules, service-identity, queuelib, parsel, pyOpenSSL, scrapy
  Running setup.py install for Twisted ... error

... 省略 ...
    building 'twisted.test.raiser' extension
    error: Microsoft Visual C++ 14.0 is required. Get it with "Microsoft Visual C++ Build Tools": https://visualstudio.microsoft.com/downloads/

    ----------------------------------------
Command "e:\dev\env\lianjia\scripts\python.exe -u -c "import setuptools, tokenize;__file__='C:\\Users\\xxx\\AppData\\Local\\Temp\\pip-install-bg3ya559\\Twisted\\setup.py';f=getattr(tokenize, 'open', open)(__file__);code=f.read().replace('\r\n', '\n');f.close();exec(compile(code, __file__, 'exec'))" install --record C:\Users\xxx\AppData\Local\Temp\pip-record-vfrii9qi\install-record.txt --single-version-externally-managed --compile --install-headers e:\dev\env\lianjia\include\site\python3.6\Twisted" failed with error code 1 in C:\Users\xxx\AppData\Local\Temp\pip-install-bg3ya559\Twisted\

pip install Twisted‑18.9.0‑cp36‑cp36m‑win_amd64.whl

# 法一
In [2]: print(np.__version__)
1.16.2

# 法二
In [3]: print(np.version.version)
1.16.2

#> array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

# 法一
In [4]: arr = np.arange(10)

In [5]: arr
Out[5]: array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

# 法二
In [6]: arr1 = np.array(range(10))

In [7]: arr1
Out[7]: array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

# 法一
In [8]: np.full((3, 3), True, dtype=bool)
Out[8]:
array([[ True,  True,  True],
       [ True,  True,  True],
       [ True,  True,  True]])
      
# 法二 
In [9]: np.ones((3,3), dtype=np.bool)
Out[9]:
array([[ True,  True,  True],
       [ True,  True,  True],
       [ True,  True,  True]])

arr = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

#> array([1, 3, 5, 7, 9])

In [10]: arr = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

In [11]: arr[arr % 2 == 1]
Out[11]: array([1, 3, 5, 7, 9])

arr = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

#>  array([ 0, -1,  2, -1,  4, -1,  6, -1,  8, -1])

In [12]: arr[arr % 2 == 1] = -1

In [13]: arr
Out[13]: array([ 0, -1,  2, -1,  4, -1,  6, -1,  8, -1])

arr = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

out
#>  array([ 0, -1,  2, -1,  4, -1,  6, -1,  8, -1])
arr
#>  array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

In [14]: arr = np.arange(10)
    ...: out = np.where(arr % 2 == 1, -1, arr)
    ...: print(arr)
    ...: out
[0 1 2 3 4 5 6 7 8 9]
Out[14]: array([ 0, -1,  2, -1,  4, -1,  6, -1,  8, -1])

np.arange(10)

#> array([ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

#> array([[0, 1, 2, 3, 4],
#>        [5, 6, 7, 8, 9]])

# 法一
In [17]: arr = np.arange(10)
    ...: arr.reshape(2, -1)  # 设置为-1会自动决定列数
Out[17]:
array([[0, 1, 2, 3, 4],
       [5, 6, 7, 8, 9]])
       
# 法二
In [19]: arr = np.arange(10)

In [20]: arr.shape = (2, -1)

In [21]: arr
Out[21]:
array([[0, 1, 2, 3, 4],
       [5, 6, 7, 8, 9]])

a = np.arange(10).reshape(2,-1)
b = np.repeat(1, 10).reshape(2,-1)

#> array([[0, 1, 2, 3, 4],
#>        [5, 6, 7, 8, 9],
#>        [1, 1, 1, 1, 1],
#>        [1, 1, 1, 1, 1]])

In [25]: a = np.arange(10).reshape(2,-1)
    ...: b = np.repeat(1, 10).reshape(2,-1)

# 法一
In [26]: np.concatenate([a, b], axis=0)
Out[26]:
array([[0, 1, 2, 3, 4],
       [5, 6, 7, 8, 9],
       [1, 1, 1, 1, 1],
       [1, 1, 1, 1, 1]])

# 法二
In [27]: np.vstack([a, b])
Out[27]:
array([[0, 1, 2, 3, 4],
       [5, 6, 7, 8, 9],
       [1, 1, 1, 1, 1],
       [1, 1, 1, 1, 1]])

# 法三
In [28]: np.r_[a, b]
Out[28]:
array([[0, 1, 2, 3, 4],
       [5, 6, 7, 8, 9],
       [1, 1, 1, 1, 1],
       [1, 1, 1, 1, 1]])

a = np.arange(10).reshape(2,-1)
b = np.repeat(1, 10).reshape(2,-1)

#> array([[0, 1, 2, 3, 4, 1, 1, 1, 1, 1],
#>        [5, 6, 7, 8, 9, 1, 1, 1, 1, 1]])

In [25]: a = np.arange(10).reshape(2,-1)
    ...: b = np.repeat(1, 10).reshape(2,-1)

# 法一
In [29]: np.concatenate([a,b], axis=1)
Out[29]:
array([[0, 1, 2, 3, 4, 1, 1, 1, 1, 1],
       [5, 6, 7, 8, 9, 1, 1, 1, 1, 1]])

# 法二
In [30]: np.hstack([a, b])
Out[30]:
array([[0, 1, 2, 3, 4, 1, 1, 1, 1, 1],
       [5, 6, 7, 8, 9, 1, 1, 1, 1, 1]])

# 法三
In [31]: np.c_[a, b]
Out[31]:
array([[0, 1, 2, 3, 4, 1, 1, 1, 1, 1],
       [5, 6, 7, 8, 9, 1, 1, 1, 1, 1]])

a = np.array([1,2,3])

#> array([1, 1, 1, 2, 2, 2, 3, 3, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3])

In [5]: a = np.array([1,2,3])

In [6]: np.r_[np.repeat(a, 3), np.tile(a, 3)]
Out[6]: array([1, 1, 1, 2, 2, 2, 3, 3, 3, 1, 2, 3, 1, 2, 3, 1, 2, 3])

a = np.array([1,2,3,2,3,4,3,4,5,6])
b = np.array([7,2,10,2,7,4,9,4,9,8])

array([2, 4])

In [7]: a = np.array([1,2,3,2,3,4,3,4,5,6])
   ...: b = np.array([7,2,10,2,7,4,9,4,9,8])

In [8]: np.intersect1d(a, b)
Out[8]: array([2, 4])

a = np.array([1,2,3,4,5])
b = np.array([5,6,7,8,9])

array([1,2,3,4])

In [9]: a = np.array([1,2,3,4,5])
   ...: b = np.array([5,6,7,8,9])

In [10]: np.setdiff1d(a, b)
Out[10]: array([1, 2, 3, 4])

a = np.array([1,2,3,2,3,4,3,4,5,6])
b = np.array([7,2,10,2,7,4,9,4,9,8])

#> (array([1, 3, 5, 7]),)

In [11]: a = np.array([1,2,3,2,3,4,3,4,5,6])
    ...: b = np.array([7,2,10,2,7,4,9,4,9,8])

In [12]: np.where(a == b)
Out[12]: (array([1, 3, 5, 7], dtype=int64),)

a = np.array([2, 6, 1, 9, 10, 3, 27])

(array([6, 9, 10]),)

In [13]: a = np.array([2, 6, 1, 9, 10, 3, 27])

# 法一
In [14]: index = np.where((a >= 5) & (a <= 10))
    ...: a[index]
Out[14]: array([ 6,  9, 10])

# 法二
In [15]: index = np.where(np.logical_and(a>=5, a<=10))
    ...: a[index]
Out[15]: array([ 6,  9, 10])

# 法三
In [16]: a[(a >= 5) & (a <= 10)]
Out[16]: array([ 6,  9, 10])

def maxx(x, y):
    """Get the maximum of two items"""
    if x >= y:
        return x
    else:
        return y

maxx(1, 5)
#> 5

a = np.array([5, 7, 9, 8, 6, 4, 5])
b = np.array([6, 3, 4, 8, 9, 7, 1])
pair_max(a, b)
#> array([ 6.,  7.,  9.,  8.,  9.,  7.,  5.])

In [17]: a = np.array([5, 7, 9, 8, 6, 4, 5])
    ...: b = np.array([6, 3, 4, 8, 9, 7, 1])

In [18]: def maxx(x, y):
    ...:     """Get the maximum of two items"""
    ...:     if x >= y:
    ...:         return x
    ...:     else:
    ...:         return y
    ...:
    ...: pair_max = np.vectorize(maxx, otypes=[float])
    ...:
    ...: a = np.array([5, 7, 9, 8, 6, 4, 5])
    ...: b = np.array([6, 3, 4, 8, 9, 7, 1])
    ...:
    ...: pair_max(a, b)
Out[18]: array([6., 7., 9., 8., 9., 7., 5.])

In [19]: arr = np.arange(9).reshape(3,3)
    ...: arr
Out[19]:
array([[0, 1, 2],
       [3, 4, 5],
       [6, 7, 8]])

In [20]: arr[:, [1,0,2]]
Out[20]:
array([[1, 0, 2],
       [4, 3, 5],
       [7, 6, 8]])

In [19]: arr = np.arange(9).reshape(3,3)
    ...: arr
Out[19]:
array([[0, 1, 2],
       [3, 4, 5],
       [6, 7, 8]])

In [21]: arr[[1,0,2], :]
Out[21]:
array([[3, 4, 5],
       [0, 1, 2],
       [6, 7, 8]])

In [19]: arr = np.arange(9).reshape(3,3)
    ...: arr
Out[19]:
array([[0, 1, 2],
       [3, 4, 5],
       [6, 7, 8]])

In [22]: arr[::-1, :] # arr[::-1]
Out[22]:
array([[6, 7, 8],
       [3, 4, 5],
       [0, 1, 2]])

In [19]: arr = np.arange(9).reshape(3,3)
    ...: arr
Out[19]:
array([[0, 1, 2],
       [3, 4, 5],
       [6, 7, 8]])

In [23]: arr[:, ::-1]
Out[23]:
array([[2, 1, 0],
       [5, 4, 3],
       [8, 7, 6]])

# 法一
In [24]: rand_arr = np.random.randint(low=5, high=10, size=(5,3)) + np.random.random((5,3))

# 法二
In [26]: rand_arr = np.random.uniform(5,10, size=(5,3))

In [27]: print(rand_arr)

rand_arr = np.random.random((5,3))

In [28]: rand_arr = np.random.random([5,3])

In [29]: np.set_printoptions(precision=3)

In [30]: rand_arr[:4]
Out[30]:
array([[0.09 , 0.678, 0.53 ],
       [0.933, 0.234, 0.908],
       [0.409, 0.219, 0.844],
       [0.005, 0.557, 0.639]])

# Create the random array
np.random.seed(100)
rand_arr = np.random.random([3,3])/1e3
rand_arr

#> array([[  5.434049e-04,   2.783694e-04,   4.245176e-04],
#>        [  8.447761e-04,   4.718856e-06,   1.215691e-04],
#>        [  6.707491e-04,   8.258528e-04,   1.367066e-04]])

#> array([[ 0.000543,  0.000278,  0.000425],
#>        [ 0.000845,  0.000005,  0.000122],
#>        [ 0.000671,  0.000826,  0.000137]])

In [31]: np.random.seed(100)
    ...: rand_arr = np.random.random([3,3])/1e3
    ...: rand_arr
Out[31]:
array([[5.434e-04, 2.784e-04, 4.245e-04],
       [8.448e-04, 4.719e-06, 1.216e-04],
       [6.707e-04, 8.259e-04, 1.367e-04]])
       
In [34]: np.set_printoptions(suppress=True, precision=6)

In [35]: rand_arr
Out[35]:
array([[0.000543, 0.000278, 0.000425],
       [0.000845, 0.000005, 0.000122],
       [0.000671, 0.000826, 0.000137]])

a = np.arange(15)
#> array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14])

#> array([ 0,  1,  2, ..., 12, 13, 14])

In [36]: np.set_printoptions(threshold=6)
    ...: a = np.arange(15)
    ...: a
Out[36]: array([ 0,  1,  2, ..., 12, 13, 14])

np.set_printoptions(threshold=6)
a = np.arange(15)
a
#> array([ 0,  1,  2, ..., 12, 13, 14])

a
#> array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14])

In [36]: np.set_printoptions(threshold=6)
    ...: a = np.arange(15)
    ...: a
Out[36]: array([ 0,  1,  2, ..., 12, 13, 14])

# 注：threshold只能是数字和non-NAN
# 原答案np.set_printoptions(threshold=np.nan)会报错
In [42]: np.set_printoptions(threshold=sys.maxsize)
    ...: a
Out[42]: array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14])

In [43]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris = np.genfromtxt(url, delimiter=',', dtype='object')
    ...: names = ('sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species')

In [44]: iris[:3]
Out[44]:
array([[b'5.1', b'3.5', b'1.4', b'0.2', b'Iris-setosa'],
       [b'4.9', b'3.0', b'1.4', b'0.2', b'Iris-setosa'],
       [b'4.7', b'3.2', b'1.3', b'0.2', b'Iris-setosa']], dtype=object)

In [46]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris_1d = np.genfromtxt(url, delimiter=',', dtype=None)
    ...: print(iris_1d.shape)
(150,)

In [47]: species = np.array([row[4] for row in iris_1d])

In [48]: species[:5]
Out[48]:
array([b'Iris-setosa', b'Iris-setosa', b'Iris-setosa', b'Iris-setosa',
       b'Iris-setosa'], dtype='|S18')

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris_1d = np.genfromtxt(url, delimiter=',', dtype=None)

In [49]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris_1d = np.genfromtxt(url, delimiter=',', dtype=None)
    ...:
    
# 法一：将每一行转换为列表并获取前4项
In [50]: iris_2d = np.array([row.tolist()[:4] for row in iris_1d])
    ...: iris_2d[:4]
Out[50]:
array([[5.1, 3.5, 1.4, 0.2],
       [4.9, 3. , 1.4, 0.2],
       [4.7, 3.2, 1.3, 0.2],
       [4.6, 3.1, 1.5, 0.2]])
       
# 法二：仅从源URL导入前4列
In [51]: iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])
    ...: iris_2d[:4]
Out[51]:
array([[5.1, 3.5, 1.4, 0.2],
       [4.9, 3. , 1.4, 0.2],
       [4.7, 3.2, 1.3, 0.2],
       [4.6, 3.1, 1.5, 0.2]])

In [54]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris = np.genfromtxt(url, delimiter=',', dtype='object')
    ...: sepallength = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0])

In [55]: mu, med, sd = np.mean(sepallength), np.median(sepallength), np.std(sepallength)
    ...: print(mu, med, sd)
5.843333333333334 5.8 0.8253012917851409

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
sepallength = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0])

# 输入
In [56]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: sepallength = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0])

# 解答
In [57]: Smax, Smin = sepallength.max(), sepallength.min()
    ...: S = (sepallength - Smin)/(Smax - Smin)

# 或

In [59]: S = (sepallength - Smin)/sepallength.ptp()  # Thanks, David Ojeda!

In [60]: print(S)
[0.222222 0.166667 0.111111 0.083333 0.194444 0.305556 0.083333 0.194444
 0.027778 0.166667 0.305556 0.138889 0.138889 0.       0.416667 0.388889
 0.305556 0.222222 0.388889 0.222222 0.305556 0.222222 0.083333 0.222222
 0.138889 0.194444 0.194444 0.25     0.25     0.111111 0.138889 0.305556
 0.25     0.333333 0.166667 0.194444 0.333333 0.166667 0.027778 0.222222
 0.194444 0.055556 0.027778 0.194444 0.222222 0.138889 0.222222 0.083333
 0.277778 0.194444 0.75     0.583333 0.722222 0.333333 0.611111 0.388889
 0.555556 0.166667 0.638889 0.25     0.194444 0.444444 0.472222 0.5
 0.361111 0.666667 0.361111 0.416667 0.527778 0.361111 0.444444 0.5
 0.555556 0.5      0.583333 0.638889 0.694444 0.666667 0.472222 0.388889
 0.333333 0.333333 0.416667 0.472222 0.305556 0.472222 0.666667 0.555556
 0.361111 0.333333 0.333333 0.5      0.416667 0.194444 0.361111 0.388889
 0.388889 0.527778 0.222222 0.388889 0.555556 0.416667 0.777778 0.555556
 0.611111 0.916667 0.166667 0.833333 0.666667 0.805556 0.611111 0.583333
 0.694444 0.388889 0.416667 0.583333 0.611111 0.944444 0.944444 0.472222
 0.722222 0.361111 0.944444 0.555556 0.666667 0.805556 0.527778 0.5
 0.583333 0.805556 0.861111 1.       0.583333 0.555556 0.5      0.944444
 0.555556 0.583333 0.472222 0.722222 0.666667 0.722222 0.416667 0.694444
 0.666667 0.666667 0.555556 0.611111 0.527778 0.444444]

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
sepallength = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0])

# 输入
In [61]: url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
    ...: iris = np.genfromtxt(url, delimiter=',', dtype='object')
    ...: sepallength = np.array([float(row[0]) for row in iris])

# 解答
In [62]: def softmax(x):
    ...:     """Compute softmax values for each sets of scores in x.
    ...:     https://stackoverflow.com/questions/34968722/how-to-implement-the-softmax-function-in-python"""
    ...:     e_x = np.exp(x - np.max(x))
    ...:     return e_x / e_x.sum(axis=0)
    ...:

In [63]: print(softmax(sepallength))
[0.00222  0.001817 0.001488 0.001346 0.002008 0.002996 0.001346 0.002008
 0.001102 0.001817 0.002996 0.001644 0.001644 0.000997 0.00447  0.004044
 0.002996 0.00222  0.004044 0.00222  0.002996 0.00222  0.001346 0.00222
 0.001644 0.002008 0.002008 0.002453 0.002453 0.001488 0.001644 0.002996
 0.002453 0.003311 0.001817 0.002008 0.003311 0.001817 0.001102 0.00222
 0.002008 0.001218 0.001102 0.002008 0.00222  0.001644 0.00222  0.001346
 0.002711 0.002008 0.01484  0.008144 0.013428 0.003311 0.009001 0.004044
 0.007369 0.001817 0.009947 0.002453 0.002008 0.00494  0.005459 0.006033
 0.003659 0.010994 0.003659 0.00447  0.006668 0.003659 0.00494  0.006033
 0.007369 0.006033 0.008144 0.009947 0.01215  0.010994 0.005459 0.004044
 0.003311 0.003311 0.00447  0.005459 0.002996 0.005459 0.010994 0.007369
 0.003659 0.003311 0.003311 0.006033 0.00447  0.002008 0.003659 0.004044
 0.004044 0.006668 0.00222  0.004044 0.007369 0.00447  0.016401 0.007369
 0.009001 0.02704  0.001817 0.020032 0.010994 0.018126 0.009001 0.008144
 0.01215  0.004044 0.00447  0.008144 0.009001 0.029884 0.029884 0.005459
 0.013428 0.003659 0.029884 0.007369 0.010994 0.018126 0.006668 0.006033
 0.008144 0.018126 0.022139 0.0365   0.008144 0.007369 0.006033 0.029884
 0.007369 0.008144 0.005459 0.013428 0.010994 0.013428 0.00447  0.01215
 0.010994 0.010994 0.007369 0.009001 0.006668 0.00494 ]

# 资源路径：https://yum.postgresql.org/repopackages.php
yum instatll -y https://download.postgresql.org/pub/repos/yum/10/redhat/rhel-6-x86_64/pgdg-centos10-10-2.noarch.rpm

yum list postgresql*
yum install -y postgresql10-server.x86_64

service postgresql-10 initdb

service postgresql-10 start
chkconfig postgresql-10 on

cat /etc/passwd | grep postgre | grep -v grep
cat /etc/group | grep postgre | grep -v grep

su - postgres

# 修改系统用户密码（切换到root用户）
passwd postgres

# 修改数据库用户密码
postgres=# ALTER USER postgres WITH PASSWORD 123456';
ALTER ROLE

In [1]: import numpy as np
   ...:
   ...: def selection_sort(x):
   ...:     for i in range(len(x)):
   ...:         swap = i + np.argmin(x[i:])
   ...:         (x[i], x[swap]) = (x[swap], x[i])
   ...:     return x
   ...:
   
In [2]: x = np.array([2, 1, 4, 3, 5])
   ...: selection_sort(x)
Out[2]: array([1, 2, 3, 4, 5])

In [3]: def bogosort(x):
   ...:     while np.any(x[:-1] > x[1:]):
   ...:         np.random.shuffle(x)
   ...:     return x
   ...:

In [4]:

In [4]: x = np.array([2, 1, 4, 3, 5])
   ...: bogosort(x)
Out[4]: array([1, 2, 3, 4, 5])

In [5]: x = np.array([2, 1, 4, 3, 5])
   ...: np.sort(x)
Out[5]: array([1, 2, 3, 4, 5])

In [6]: x.sort()
   ...: print(x)
[1 2 3 4 5]

In [7]: x = np.array([2, 1, 4, 3, 5])
   ...: i = np.argsort(x)
   ...: print(i)
[1 0 3 2 4]

In [8]: x[i]
Out[8]: array([1, 2, 3, 4, 5])

In [9]: rand = np.random.RandomState(42)
   ...: X = rand.randint(0, 10, (4, 6))
   ...: print(X)
[[6 3 7 4 6 9]
 [2 6 7 4 3 7]
 [7 2 5 4 1 7]
 [5 1 4 0 9 5]]
 
In [10]: # sort each column of X
    ...: np.sort(X, axis=0)
Out[10]:
array([[2, 1, 4, 0, 1, 5],
       [5, 2, 5, 4, 3, 7],
       [6, 3, 7, 4, 6, 7],
       [7, 6, 7, 4, 9, 9]])

In [11]: # sort each row of X
    ...: np.sort(X, axis=1)
Out[11]:
array([[3, 4, 6, 6, 7, 9],
       [2, 3, 4, 6, 7, 7],
       [1, 2, 4, 5, 7, 7],
       [0, 1, 4, 5, 5, 9]])

In [12]: x = np.array([7, 2, 3, 1, 6, 5, 4])
    ...: np.partition(x, 3)
Out[12]: array([2, 1, 3, 4, 6, 5, 7])

In [13]: np.partition(X, 2, axis=1)
Out[13]:
array([[3, 4, 6, 7, 6, 9],
       [2, 3, 4, 7, 6, 7],
       [1, 2, 4, 5, 7, 7],
       [0, 1, 4, 5, 9, 5]])

In [14]: X = rand.rand(10, 2)

In [15]: %matplotlib inline
    ...: import matplotlib.pyplot as plt
    ...: import seaborn; seaborn.set() # Plot styling
    ...: plt.scatter(X[:, 0], X[:, 1], s=100);

In [17]: dist_sq = np.sum((X[:, np.newaxis, :] - X[np.newaxis, :, :]) ** 2, axis=-1)

In [18]: # for each pair of points, compute differences in their coordinates
    ...: differences = X[:, np.newaxis, :] - X[np.newaxis, :, :]
    ...: differences.shape
Out[18]: (10, 10, 2)

In [19]: # square the coordinate differences
    ...: sq_differences = differences ** 2
    ...: sq_differences.shape
Out[19]: (10, 10, 2)

In [20]: # sum the coordinate differences to get the squared distance
    ...: dist_sq = sq_differences.sum(-1)
    ...: dist_sq.shape
Out[20]: (10, 10)

In [21]: dist_sq.diagonal()
Out[21]: array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])

In [22]: nearest = np.argsort(dist_sq, axis=1)
    ...: print(nearest)
[[0 3 9 7 1 4 2 5 6 8]
 [1 4 7 9 3 6 8 5 0 2]
 [2 1 4 6 3 0 8 9 7 5]
 [3 9 7 0 1 4 5 8 6 2]
 [4 1 8 5 6 7 9 3 0 2]
 [5 8 6 4 1 7 9 3 2 0]
 [6 8 5 4 1 7 9 3 2 0]
 [7 9 3 1 4 0 5 8 6 2]
 [8 5 6 4 1 7 9 3 2 0]
 [9 7 3 0 1 4 5 8 6 2]]

In [23]: K = 2
    ...: nearest_partition = np.argpartition(dist_sq, K + 1, axis=1)

In [24]: plt.scatter(X[:, 0], X[:, 1], s=100)
    ...:
    ...: # draw lines from each point to its two nearest neighbors
    ...: K = 2
    ...:
    ...: for i in range(X.shape[0]):
    ...:     for j in nearest_partition[i, :K+1]:
    ...:         # plot a line from X[i] to X[j]
    ...:         # use some zip magic to make it happen:
    ...:         plt.plot(*zip(X[j], X[i]), color='black')

# 
x = np.arange(3).reshape(3, 1)
x
Out[2]: 
array([[0],
       [1],
       [2]])
x.shape
Out[3]: (3, 1)

# 
y = np.ones(4)
y
Out[7]: array([1., 1., 1., 1.])
y.shape
Out[8]: (4,)

# 
z = x + y
z
Out[13]: 
array([[1., 1., 1., 1.],
       [2., 2., 2., 2.],
       [3., 3., 3., 3.]])
z.shape
Out[14]: (3, 4)

# 以下正确
Image (3d array):  256 x 256 x 3
Scale (1d array):              3   # 相当于是 1 x 1 x3
Result (3d array): 256 x 256 x 3

A      (4d array):  8 x 1 x 6 x 1
B      (3d array):      7 x 1 x 5 # 相当于是1 x 7 x 1 x 5
Result (4d array):  8 x 7 x 6 x 5

A      (2d array):  5 x 4
B      (1d array):      1 # 相当于是1 x 1
Result (2d array):  5 x 4

A      (2d array):  15 x 3 x 5
B      (1d array):  15 x 1 x 5
Result (2d array):  15 x 3 x 5

# 以下会报错
A  (1d array): 3        # 相当于是(1, 3)
B  (1d array): 4        # 相当于是(1 ,4)， 最后一维（trailing dimension）不匹配

A  (2d array):      2 x 1   # (1, 2, 1)
B  (3d array):  8 x 4 x 3  # (8, 4, 3)（倒数第二维不匹配）

x     (2d array):      3 x 1
y      (1d array):          4 # 1 x 4
Result (2d array):      3 x 4

# x会由
array([[0],
       [1],
       [2]])

# 扩展成以下的样子
array([[0., 0., 0., 0.],
       [1., 1., 1., 1.],
       [2., 2., 2., 2.]])

# y会由
array([1., 1., 1., 1.])

# 扩展成以下的样子
array([[1., 1., 1., 1.],
       [1., 1., 1., 1.],
       [1., 1., 1., 1.]])

# 所以相加会得到
x + y
Out[21]: 
array([[1., 1., 1., 1.],
       [2., 2., 2., 2.],
       [3., 3., 3., 3.]])

[root@gp6 new]# wget https://www.sqlite.org/snapshot/sqlite-snapshot-201903261308.tar.gz

[root@gp6 new]# tar zxvf sqlite-snapshot-201903261308.tar.gz

[root@gp6 new]# cd sqlite-snapshot-201903261308
[root@gp6 sqlite-snapshot-201903261308]# ./configure --prefix=/usr/local/sqlite 
[root@gp6 sqlite-snapshot-201903261308]# make -j4
[root@gp6 sqlite-snapshot-201903261308]# make install

[root@gp6 new]# wget https://www.python.org/ftp/python/3.7.3/Python-3.7.3.tgz

[root@gp6 new]# tar -zxvf Python-3.7.3.tgz

vi setup.py

        sqlite_inc_paths = [ '/usr/include',
                             '/usr/include/sqlite',
                             '/usr/include/sqlite3',
                             '/usr/local/include',
                             '/usr/local/include/sqlite',
                             '/usr/local/include/sqlite3',
                             ]

        sqlite_inc_paths = [ '/usr/include',
                             '/usr/include/sqlite',
                             '/usr/include/sqlite3',
                             '/usr/local/include',
                             '/usr/local/include/sqlite',
                             '/usr/local/include/sqlite3',
                             '/usr/local/sqlite/include',
                             '/usr/local/sqlite/include/sqlite3',
                             ]

[root@gp6 new]# cd Python-3.7.3
[root@gp6 Python-3.7.3]# ./configure --prefix=/usr/local/python3.7 --enable-loadable-sqlite-extensions
[root@gp6 Python-3.7.3]# make -j4
[root@gp6 Python-3.7.3]# make install

[root@gp6 Python-3.7.3]# ln -s /usr/local/python3.7/bin/python3.7 /usr/bin/python37
[root@gp6 Python-3.7.3]# ln -s /usr/local/python3.7/bin/pip3.7 /usr/bin/pip37

lrwxrwxrwx. 1 root root     7 Feb 15 17:22 /usr/bin/python -> python2
lrwxrwxrwx. 1 root root     9 Feb 15 17:22 /usr/bin/python2 -> python2.7
-rwxr-xr-x. 1 root root  7216 Oct 31 07:46 /usr/bin/python2.7
-rwxr-xr-x  1 root root  1835 Oct 31 07:46 /usr/bin/python2.7-config
lrwxrwxrwx  1 root root    16 Feb 15 17:28 /usr/bin/python2-config -> python2.7-config
lrwxrwxrwx  1 root root    23 Mar 27 12:47 /usr/bin/python3 -> /opt/Python/bin/python3
-rwxr-xr-x  2 root root 11392 Feb  5 22:38 /usr/bin/python3.4
-rwxr-xr-x  2 root root 11392 Feb  5 22:38 /usr/bin/python3.4m
lrwxrwxrwx  1 root root    34 Mar 29 16:19 /usr/bin/python37 -> /usr/local/python3.7/bin/python3.7
lrwxrwxrwx  1 root root    14 Feb 15 17:28 /usr/bin/python-config -> python2-config

[root@gp6 Python-3.7.3]# python37
Python 3.7.3 (default, Mar 29 2019, 16:04:57) 
[GCC 6.3.1 20170216 (Red Hat 6.3.1-3)] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import sqlite3
>>> 

# 安装sqlite-devel
yum install sqlite-devel -y
# 重新编译安装python
./configure
make
make altinstall

/* C code */
int result = 0;
for(int i=0; i<100; i++){
    result += i;
}

# Python code
result = 0
for i in range(100):
    result += i

# Python code
x = 4
x = "four"

/* C code */
int x = 4;
x = "four";  // FAILS

struct _longobject {
    long ob_refcnt;
    PyTypeObject *ob_type;
    size_t ob_size;
    long ob_digit[1];
};

In [1]: L = list(range(10))

In [2]: L
Out[2]: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
In [3]: type(L[0])
Out[3]: int

In [10]: L2 = [str(c) for c in L]
    ...: L2
Out[10]: ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
In [11]: type(L2[0])
Out[11]: str

In [12]: L3 = [True, "2", 3.0, 4]
    ...: [type(item) for item in L3]
Out[12]: [bool, str, float, int]

In [13]: import array
    ...: L = list(range(10))
    ...: A = array.array('i', L)
    ...: A
Out[13]: array('i', [0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

import numpy as np

# integer array:
In [14]: np.array([1, 4, 2, 5, 3])
Out[14]: array([1, 4, 2, 5, 3])

In [15]: np.array([3.14, 4, 2, 3])
Out[15]: array([3.14, 4.  , 2.  , 3.  ])

In [16]: np.array([1, 2, 3, 4], dtype='float32')
Out[16]: array([1., 2., 3., 4.], dtype=float32)

# nested lists result in multi-dimensional arrays
In [17]: np.array([range(i, i + 3) for i in [2, 4, 6]])
Out[17]:
array([[2, 3, 4],
       [4, 5, 6],
       [6, 7, 8]])

# 创建一个用零填充的长度为10的整数数组
In [18]: np.zeros(10, dtype=int)
Out[18]: array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0])

# 创建一个填充了1的3x5的浮点数组
In [19]: np.ones((3, 5), dtype=float)
Out[19]:
array([[1., 1., 1., 1., 1.],
       [1., 1., 1., 1., 1.],
       [1., 1., 1., 1., 1.]])

# 创建一个填充3.14的3x5数组
In [20]: np.full((3, 5), 3.14)
Out[20]:
array([[3.14, 3.14, 3.14, 3.14, 3.14],
       [3.14, 3.14, 3.14, 3.14, 3.14],
       [3.14, 3.14, 3.14, 3.14, 3.14]])

# 创建一个填充线性序列的数组
# 从0开始，到20结束，步进2
# （这类似于内置range（）函数）
In [21]: np.arange(0, 20, 2)
Out[21]: array([ 0,  2,  4,  6,  8, 10, 12, 14, 16, 18])

# 创建一个由0和1均匀分布的五个值的数组
In [22]:  np.linspace(0, 1, 5)
Out[22]: array([0.  , 0.25, 0.5 , 0.75, 1.  ])

# 创建一个均匀分布的3x3数组
# 随机值介于0和1之间
In [23]: np.random.random((3, 3))
Out[23]:
array([[0.91398038, 0.24537985, 0.01826515],
       [0.4294535 , 0.69789859, 0.55493684],
       [0.12512603, 0.49085695, 0.66702286]])

# 创建3x3正态分布随机值数组
# 平均值为0，标准差为1
In [24]: np.random.normal(0, 1, (3, 3))
Out[24]:
array([[ 0.45408335, -1.90310333, -0.33322852],
       [ 0.51879233, -0.03587706,  1.47226021],
       [ 0.07377611,  0.35394745, -0.08673764]])

# 在区间[0,10]中创建3x3随机整数数组
In [25]: np.random.randint(0, 10, (3, 3))
Out[25]:
array([[0, 0, 1],
       [4, 3, 1],
       [0, 8, 5]])

# 创建3x3单位矩阵
In [26]: np.eye(3)
Out[26]:
array([[1., 0., 0.],
       [0., 1., 0.],
       [0., 0., 1.]])

# 创建一个包含三个整数的未初始化数组
# 值将是该内存位置已存在的任何值
In [27]: np.empty(3)
Out[27]: array([1., 1., 1.])

np.zeros(10, dtype='int16')

np.zeros(10, dtype=np.int16)

In [1]: import numpy as np
   ...: import pandas as pd
   ...:
   ...: # use pandas to extract rainfall inches as a NumPy array
   ...: rainfall = pd.read_csv('data/Seattle2014.csv')['PRCP'].values
   ...: inches = rainfall / 254.0  # 1/10mm -> inches
   ...: inches.shape
Out[1]: (365,)

In [2]: %matplotlib inline
   ...: import matplotlib.pyplot as plt
   ...: import seaborn; seaborn.set()  # set plot styles

In [3]: plt.hist(inches, 40);

In [5]: x = np.array([1, 2, 3, 4, 5])

In [6]: x < 3  # less than
Out[6]: array([ True,  True, False, False, False])

In [7]: x > 3  # greater than
Out[7]: array([False, False, False,  True,  True])

In [8]: x <= 3  # less than or equal
Out[8]: array([ True,  True,  True, False, False])

In [9]: x >= 3  # greater than or equal
Out[9]: array([False, False,  True,  True,  True])

In [10]: x != 3  # not equal
Out[10]: array([ True,  True, False,  True,  True])

In [11]: x == 3  # equal
Out[11]: array([False, False,  True, False, False])

In [14]: (2 * x) == (x ** 2)
Out[14]: array([False,  True, False, False, False])

In [15]: rng = np.random.RandomState(0)
    ...: x = rng.randint(10, size=(3, 4))
    ...: x
Out[15]:
array([[5, 0, 3, 3],
       [7, 9, 3, 5],
       [2, 4, 7, 6]])

In [16]: x < 6
Out[16]:
array([[ True,  True,  True,  True],
       [False, False,  True,  True],
       [ True,  True, False, False]])

In [17]: print(x)
[[5 0 3 3]
 [7 9 3 5]
 [2 4 7 6]]

In [18]: # how many values less than 6?
    ...: np.count_nonzero(x < 6)
Out[18]: 8

In [19]: np.sum(x < 6)
Out[19]: 8

In [20]: np.sum(x < 6, axis=1)
Out[20]: array([4, 2, 2])

In [21]: # are there any values greater than 8?
    ...: np.any(x > 8)
Out[21]: True

In [22]: # are there any values less than zero?
    ...: np.any(x < 0)
Out[22]: False

In [23]: # are all values less than 10?
    ...: np.all(x < 10)
Out[23]: True

In [24]: # are all values equal to 6?
    ...: np.all(x == 6)
Out[24]: False

In [25]: # are all values in each row less than 8?
    ...: np.all(x < 8, axis=1)
Out[25]: array([ True, False,  True])

In [26]: np.sum((inches > 0.5) & (inches < 1))
Out[26]: 29

inches > (0.5 & inches) < 1

In [27]: np.sum(~( (inches <= 0.5) | (inches >= 1) ))
Out[27]: 29

In [28]: print("Number days without rain:      ", np.sum(inches == 0))
    ...: print("Number days with rain:         ", np.sum(inches != 0))
    ...: print("Days with more than 0.5 inches:", np.sum(inches > 0.5))
    ...: print("Rainy days with < 0.2 inches  :", np.sum((inches > 0) &
    ...:                                                 (inches < 0.2)))
Number days without rain:       215
Number days with rain:          150
Days with more than 0.5 inches: 37
Rainy days with < 0.2 inches  : 75

In [29]: x
Out[29]:
array([[5, 0, 3, 3],
       [7, 9, 3, 5],
       [2, 4, 7, 6]])

In [30]: x < 5
Out[30]:
array([[False,  True,  True,  True],
       [False, False,  True, False],
       [ True,  True, False, False]])

In [31]: x[x < 5]
Out[31]: array([0, 3, 3, 3, 2, 4])

In [32]: # construct a mask of all rainy days
    ...: rainy = (inches > 0)
    ...:
    ...: # construct a mask of all summer days (June 21st is the 172nd day)
    ...: days = np.arange(365)
    ...: summer = (days > 172) & (days < 262)
    ...:
    ...: print("Median precip on rainy days in 2014 (inches):   ",
    ...:       np.median(inches[rainy]))
    ...: print("Median precip on summer days in 2014 (inches):  ",
    ...:       np.median(inches[summer]))
    ...: print("Maximum precip on summer days in 2014 (inches): ",
    ...:       np.max(inches[summer]))
    ...: print("Median precip on non-summer rainy days (inches):",
    ...:       np.median(inches[rainy & ~summer]))
Median precip on rainy days in 2014 (inches):    0.19488188976377951
Median precip on summer days in 2014 (inches):   0.0
Maximum precip on summer days in 2014 (inches):  0.8503937007874016
Median precip on non-summer rainy days (inches): 0.20078740157480315

In [33]: bool(42), bool(0)
Out[33]: (True, False)

In [34]: bool(42 and 0)
Out[34]: False

In [35]: bool(42 or 0)
Out[35]: True

In [36]: bin(42)
Out[36]: '0b101010'

In [37]: bin(59)
Out[37]: '0b111011'

In [38]: bin(42 & 59)
Out[38]: '0b101010'

In [39]: bin(42 | 59)
Out[39]: '0b111011'

In [40]: A = np.array([1, 0, 1, 0, 1, 0], dtype=bool)
    ...: B = np.array([1, 1, 1, 0, 1, 1], dtype=bool)
    ...: A | B
Out[40]: array([ True,  True,  True, False,  True,  True])

In [41]: A or B
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-41-ea2c97d9d9ee> in <module>
----> 1 A or B

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

In [42]: x = np.arange(10)
    ...: (x > 4) & (x < 8)
Out[42]:
array([False, False, False, False, False,  True,  True,  True, False,
       False])

In [43]: (x > 4) and (x < 8)
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-43-eecf1fdd5fb4> in <module>
----> 1 (x > 4) and (x < 8)

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

In [1]: 
(reverse-i-search)`sqa': square??

In [1]: 
(reverse-i-search)`sqa': def square(a):
    """Return the square of a"""
    return a ** 2

In [1]: def square(a):
    """Return the square of a"""
    return a ** 2

In [2]: square(2)
Out[2]: 4

# coding: utf-8

import requests
from lxml import etree

start_url = 'http://wap.ynpxrz.com/n1413623c2181.aspx'

r = requests.get(start_url)

e = etree.fromstring(r.text)

# print(r.text)
print(e)

Traceback (most recent call last):
  File "E:/DEV/projects/spider/demo.py", line 10, in <module>
    e = etree.fromstring(r.text)
  File "src\lxml\etree.pyx", line 3222, in lxml.etree.fromstring
  File "src\lxml\parser.pxi", line 1877, in lxml.etree._parseMemoryDocument
  File "src\lxml\parser.pxi", line 1758, in lxml.etree._parseDoc
  File "src\lxml\parser.pxi", line 1068, in lxml.etree._BaseParser._parseUnicodeDoc
  File "src\lxml\parser.pxi", line 601, in lxml.etree._ParserContext._handleParseResultDoc
  File "src\lxml\parser.pxi", line 711, in lxml.etree._handleParseResult
  File "src\lxml\parser.pxi", line 640, in lxml.etree._raiseParseError
  File "<string>", line 19
lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: link line 16 and head, line 19, column 8

e = etree.fromstring(r.text, parser=etree.HTMLParser())