1 怎样读取/写入csv文件数据?
import pandas as pd
#读取
df = pd.read_csv('c/test/test.csv')
#帮助信息
help(pd.read_csv)
#写入
df.to_csv('...')
#excel同理
#读取
df = pd.read_excel('c/test/test.xlsx', sheet_name = 'scores')
#计算
df['sum'] = df['Python'] + df['Math']
#写入
df.to_excel('c/test/scores.xlsx', sheet_name = 'scores')
2 读取网页中的数据?
# -*- coding: utf-8 -*-
import requests
import re
import pandas as pd
def retrieve_dji_list():
r = requests.get('https://money.cnn.com/data/markets/nasdaq/')
#正则表达式
search_pattern = re.compile()
#正则表达式模块的findall()
dji_list_in_text = re.findall()
#存入dji_list中
dji_list = []
for item in dji_list_in_text:
dji_list.append()
return dji_list
#调用
dji_list = retrieve_dji_list()
djidf = pd.DataFrame(dji_list)
print(djidf)
补充资料:
数据集获取:
kaggle.com/datasets
sklearn模块的datasets
NLTK语料库
参考资料:
https://www.icourse163.org/learn/NJU-1001571005?tid=1463102441&from=study#/learn/content?type=detail&id=1240380188&cid=1261816417 用python玩转数据