python编程库

编程库
1.time
import time
print(time.time())
time = time.localtime( time.time() )
print(time)
print(time.tm_year)
"""
1563803665.310865
time.struct_time(tm_year=2019, tm_mon=7, tm_mday=22, tm_hour=21, tm_min=54, tm_sec=25, tm_wday=0, tm_yday=203, tm_isdst=0)
2019
"""
1
2
3
4
5
6
7
8
9
10
2.Matplotlib
绘图工具包

3.Scikit-learn
封装了大量经典以及最新的机器学习模型

4.Pandas
针对于数据处理和分析的python工具包,实现了大量便于数据读写,清洗,填充及分析功能

4.1读取文件
import pandas as pd
# 两个数据类型：Series, DataFrame

data_path = "C:/Users/admin/Desktop/111.csv"
# 读取文件
def read_file(data_path):
datas = pd.read_csv(data_path, encoding="GBK")
datas = datas.dropna()
return datas

data = read_file(data_path)
print(data)

# 获取某一列文字 Python 字典(Dictionary) -->contents_agent 转化成一整段
contents_agent = data["asr_agent_raw"]
contents = contents_agent.values.tolist()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
5.jieba
import jieba
stopwords_file = "D:/gitProject/smartlink-sqc/smartlink-sqc-wordle/python/dict/user_dict.txt"
def seg_word(contents):
contents = contents.values.tolist()
jieba.load_userdict(stopwords_file)
segment = []
for line in contents:
try:
segs = jieba.lcut(line)
for seg in segs:
if len(seg) > 1 and seg != ' ' and
u'u4e00' <= seg <= u'u9fa5' or
u'u0041' <= seg <= u'u005a' or
u'u0061' <= seg <= u'u007a':
segment.append(seg)

except:
print(line)
continue

words_df = pd.DataFrame({'words': segment})
stopwords = pd.read_csv(stopwords_file,
index_col=False,
quoting=3,
sep=" ",
names=['stopwords'],
encoding='utf-8') # quoting=3全不引用
words_df = words_df[~words_df.words.isin(stopwords.stopwords)]
return words_df

# 进行分词
words_agent = seg_word(contents_agent)
print(words_agent)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
6.NumPy & SciPy(http://www.amjmh.com)
NumPy最基础的编程库,提供一些高级的数学运算机制和高效的向量和矩阵运算功能
SciPy是子啊NumPy的基础上构建的,更为强大的科学计算包

import numpy as np
def word_freq(words_df):
words_stat = words_df.groupby(by=['words'])['words'].agg({"count":np.size})
words_stat = words_stat.reset_index().sort_values(by=["count"], ascending=False)
return words_stat

words_stat_agent = word_freq(words_agent)
# 打印词频较高的前10
print(words_stat_agent.head(10))
1
2
3
4
5
6
7
8
9
7.Anaconda平台
一次性获得300多种用于科学和工程计算相关任务的python编程库的支持
---------------------