相关扩展库
1# -*- coding: UTF-8 -*-
2
3# 导入扩展库
4
5import pandas as pd
6
7import numpy as np
创建空DataFrame对象
1# 自定义列名创建空的DataFrame数据对象
2
3df = pd.DataFrame(columns={"name": "", "age": "", "sex": "", "score": "", "rate": ""})
4
5print(df)
6
7# Empty DataFrame
8# Columns: [name, age, sex, score, rate]
9# Index: []
数组创建DataFrame对象
1# 自定义数组创建DataFrame对象
2
3list_data = [['1', '2', '3']]
4
5df = pd.DataFrame(list_data, columns=['first', 'second', 'third'])
6
7print(df)
8
9# first second third
10# 0 1 2 3
字典创建DataFrame对象
1# 自定义字典类型的数据创建DataFarme对象
2
3data_dict = {'first_col': [1, 2, 3, 4], 'second_col': [5, 6, 7, 8]}
4
5df = pd.DataFrame(data_dict)
6
7print(df)
8
9# first_row second_row
10# 0 1 5
11# 1 2 6
12# 2 3 7
13# 3 4 8
文件返回DataFrame对象
1# 读取数据文件返回DataFrame对象
2
3df=pd.read_csv('/usr/load/data.csv',split=',')
4
5df=pd.read_csv('/usr/load/data.xls',sheet_name='data')
6
7print(df)
np创建DataFrame对象
1# 使用numpy科学计算库提供的二维数组创建DataFrame对象
2
3data_array = np.random.rand(4, 2)
4
5df = pd.DataFrame(data_array, columns=['first', 'second'])
6
7print(df)
8
9# first second
10# 0 0.410413 0.510788
11# 1 0.726956 0.647775
12# 2 0.502573 0.226714
13# 3 0.926117 0.124414
