做生信分析,肯定需要面对各种数据,像最常见的txt,csv,固定分隔符的矩阵类型的数据,也有像json,通过键-值的方式存储数据,或者xml标记语言,以标签的方式存储数据。
- data.json
{
'name' : 'ACME',
'shares' : 100,
'price' : 542.23,
'books': ['C++', 'Python', 'R']
}
- c.xml
<?xml version="1.0"?>
<stop>
<id>14791</id>
<nm>Clark & Balmoral</nm>
<sri>
<rt>22</rt>
<d>North Bound</d>
<dd>North Bound</dd>
</sri>
<cr>22</cr>
<pre>
<pt>5 MIN</pt>
<fd>Howard</fd>
<v>1378</v>
<rn>22</rn>
</pre>
<pre>
<pt>15 MIN</pt>
<fd>Howard</fd>
<v>1867</v>
<rn>22</rn>
</pre>
</stop>
txt,csv 太常见了就不用说了。那有了这些文件,又该如何读取呢?
下面,简单介绍下 python 的读写操作。
1、读取txt格式数据
- 内置函数a.txt
chr2 29449344 29449368 (A)24 0 +
chr2 39573062 39573089 (A)27 0 +
chr2 42553086 42553096 (A)10 0 +
chr2 47641559 47641586 (A)27 0 +
file = 'a.txt'
# 以读的方式打开文件
f = open(file, 'r')
# 一次性读取整个文件为字符串,然后以 \n 分割字符串,循环每次取出一行
for line in f.read().split('\n'):
# 每行是以 \t 分割, split不加参数默认以一个或多个空白符作为分割
line = line.split()
print(line)
# 最后不要忘记关闭文件
f.close()
# [out]:
['chr2', '29449344', '29449368', '(A)24', '0', '+']
['chr2', '39573062', '39573089', '(A)27', '0', '+']
['chr2', '42553086', '42553096', '(A)10', '0', '+']
['chr2', '47641559', '47641586', '(A)27', '0', '+']
# 上下文管理器 with 的方式打开文件,不需要手动关闭文件
with open('a.txt', 'r') as f:
for line in f.read().split('\n'):
line = line.split()
print(line)
2、读取csv格式数据(其实csv与txt的操作基本互通)
- 内置函数
# 通过 txt 文件构造 csv 格式数据
fc = open('b.csv', 'w')
with open('a.txt', 'r') as f:
for line in f.read().split('\n'):
line = line.split()
fc.write(','.join(line))
fc.write('\n')
fc.close()
b.csv
csv数据的读取方式和txt类似,只需将split()换成split(',')
- csv模块
# employee_birthday.csv
名字,部门,月份
张三,会计,11
李四,IT,3
import csv
with open('employee_birthday.csv') as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
line_count = 0
for row in csv_reader:
if line_count == 0:
print(f'列名:\n {", ".join(row)}')
line_count += 1
else:
print(f'\t{row[0]},{row[1]}部门,{row[2]} 入职。')
line_count += 1
print(f'行数 {line_count}。')
字典形式读取
import csv
with open('employee_birthday.csv') as csv_file:
csv_reader = csv.DictReader(csv_file, delimiter=',')
line_count = 0
for row in csv_reader:
if line_count == 0:
print(f'列名:\n {", ".join(row)}')
line_count += 1
else:
print(f'\t{row["名字"]},{row["部门"]}部门,{row["月份"]} 入职。')
line_count += 1
print(f'行数 {line_count}。')
写入
import csv
with open('employee_file.csv', mode='w') as employee_file:
employee_writer = csv.writer(employee_file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
employee_writer.writerow(['John Smith', 'Accounting', 'November'])
employee_writer.writerow(['Erica Meyers', 'IT', 'March'])
字典形式写入
import csv
with open('employee_file2.csv', mode='w') as csv_file:
# 表头
fieldnames = ['emp_name', 'dept', 'birth_month']
writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
# 写入表头
writer.writeheader()
# 写入字典形式数据,键与表头一致
writer.writerow({'emp_name': 'John Smith', 'dept': 'Accounting', 'birth_month': 'November'})
writer.writerow({'emp_name': 'Erica Meyers', 'dept': 'IT', 'birth_month': 'March'})
- pandas模块
import pandas as pd
# sep 参数指定分隔符, header=None:表示没有表头,name 可指定表头
txt = pd.read_csv('a.txt', sep='\t', header=None,
names=['chrom', 'start', 'end', 'repeat', 'num', 'orientation'])
csv = pd.read_csv('b.csv', sep=',', header=None)
输出文件
# 默认输出行名,index=False,不输出行名
txt.to_csv(filename, index=False)
csv.to_csv(filename)
3、json数据
- 使用json模块
# python 字典与 json 数据相互转换
data = {
'name' : 'ACME',
'shares' : 100,
'price' : 542.23,
'books': ['C++', 'Python', 'R']
}
json_str = json.dumps(data)
# [out]:
'{"name": "ACME", "shares": 100, "price": 542.23, "books": ["C++", "Python", "R"]}'
json.loads(json_str)
# [out]
data = {
'name' : 'ACME',
'shares' : 100,
'price' : 542.23,
'books': ['C++', 'Python', 'R']
}
# 将字典数据保存成 json 文件
with open('data.json', 'w') as f:
json.dump(data, f)
# 将json 文件读取成字典
with open('data.json', 'r') as f:
data = json.load(f)
- pandas
df = pd.read_json('data.json')
df
会将 json 文件转换为 DataFrame 格式数据
4、xml数据
- xml模块
from xml.etree.ElementTree import parse, Element
doc = parse('c.xml')
for item in doc.iterfind('pre'):
print(item.findtext('pt'), end='\t')
print(item.findtext('fd'), end='\t')
print(item.findtext('v'), end='\t')
print(item.findtext('rn'))
from xml.etree.ElementTree import parse, Element
doc = parse('c.xml')
root = doc.getroot()
# 删除两个标签元素
root.remove(root.find('sri'))
root.remove(root.find('cr'))
# 获取 nm 标签所在的位置
idx = root.getchildren().index(root.find('nm'))
# 构造标签元素 <spam> </spam>
e = Element('spam')
e.text = 'This is a spam'
root.insert(idx+1, e)
# 将修改过后的 xml 输出
doc.write('newc.xml', xml_declaration=True)
<--! 输出结果 -->
<?xml version='1.0' encoding='us-ascii'?>
<stop>
<id>14791</id>
<nm>Clark & Balmoral</nm>
<spam>This is a spam</spam>
<pre>
<pt>5 MIN</pt>
<fd>Howard</fd>
<v>1378</v>
<rn>22</rn>
</pre>
<pre>
<pt>15 MIN</pt>
<fd>Howard</fd>
<v>1867</v>
<rn>22</rn>
</pre>
</stop>