Linusp

CC_RESET='[00m'
CC_WHITE='[1;37m'
CC_LIGHT_BLUE='[1;34m'
CC_LIGHT_GREEN='[1;32m'
CC_LIGHT_RED='[1;31m'

function get_git_repos_branch()
{
  git branch --no-color 2> /dev/null | sed -e '/^[^*]/d' -e "s/* \(.*\)/\1/"
}

Linusp

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Author     : Linusp
Date       : 2014/08/30
Description: Simple Perceptron Training
"""

import numpy as np
import matplotlib.pyplot as plt

Linusp

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Author     : Linusp
Date       : 2014/08/30
Description: Simple Perceptron Training
"""

import numpy as np
import matplotlib.pyplot as plt

Linusp

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Author     : Linusp
Date       : 2014/08/30
Description: Linear Regression
"""

import numpy as np
import matplotlib as mpl

Linusp

词的分类

• 实词：名词、动词、形容词、状态词、区别词、数词、量词、代词
• 虚词：副词、介词、连词、助词、拟声词、叹词。

ICTPOS3.0词性标记集

n 名词

nr 人名

Linusp

# List unique values in a DataFrame column
pd.unique(df.column_name.ravel())

# Convert Series datatype to numeric, getting rid of any non-numeric values
df['col'] = df['col'].astype(str).convert_objects(convert_numeric=True)

# Grab DataFrame rows where column has certain values
valuelist = ['value1', 'value2', 'value3']
df = df[df.column.isin(valuelist)]

Linusp

Org-mode Org-mode Reference Card

Org mode reference card

Created from the plain text reference card on orgmode.org Download this file, and open it in Emacs org-mode!

Linusp

import re
import pickle
from math import sqrt
from operator import itemgetter
from collections import defaultdict, Counter


import click

Linusp

// ==UserScript==
// @name                Weiboda Redirection
// @name:zh-CN          微博档案真实链接地址重定向
// @description         获取微博档案中的原始链接地址

// @grant               none
// @run-at              document-start
// @include             *//weibo.wbdacdn.com/url/*
// ==/UserScript==

Linusp

from elasticsearch import Elasticsearch
from elasticsearch.helpers import scan

index = 'some-index'
doctype = 'some-doctype'
client = Elasticsearch(hosts=['localhost:9200'])
for item in scan(client, index=index, doc_type=doctype, preserve_order=True):
    print(item['_source'])