本文共 3916 字，大约阅读时间需要 13 分钟。
文章作者：Tyan
博客： | |本文主要是关于pandas的一些基本用法。
#!/usr/bin/env python# _*_ coding: utf-8 _*_import pandas as pdimport numpy as np# Test 1# 创建DataFramedf1 = pd.DataFrame(np.ones((3, 4)) * 0, columns = ['a', 'b', 'c', 'd'])df2 = pd.DataFrame(np.ones((3, 4)) * 1, columns = ['a', 'b', 'c', 'd'])df3 = pd.DataFrame(np.ones((3, 4)) * 2, columns = ['a', 'b', 'c', 'd'])print df1print df2print df3# Test 1 result a b c d0 0.0 0.0 0.0 0.01 0.0 0.0 0.0 0.02 0.0 0.0 0.0 0.0 a b c d0 1.0 1.0 1.0 1.01 1.0 1.0 1.0 1.02 1.0 1.0 1.0 1.0 a b c d0 2.0 2.0 2.0 2.01 2.0 2.0 2.0 2.02 2.0 2.0 2.0 2.0# Test 2# 竖向合并三个DataFrameres = pd.concat([df1, df2, df3], axis = 0)print res# 横向合并三个DataFrameres = pd.concat([df1, df2, df3], axis = 1)print res# 合并的同时index重新排序res = pd.concat([df1, df2, df3], axis = 0, ignore_index = True)print res# Test 2 result a b c d0 0.0 0.0 0.0 0.01 0.0 0.0 0.0 0.02 0.0 0.0 0.0 0.00 1.0 1.0 1.0 1.01 1.0 1.0 1.0 1.02 1.0 1.0 1.0 1.00 2.0 2.0 2.0 2.01 2.0 2.0 2.0 2.02 2.0 2.0 2.0 2.0 a b c d a b c d a b c d0 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.0 2.0 2.0 2.0 2.01 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.0 2.0 2.0 2.0 2.02 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.0 2.0 2.0 2.0 2.0 a b c d0 0.0 0.0 0.0 0.01 0.0 0.0 0.0 0.02 0.0 0.0 0.0 0.03 1.0 1.0 1.0 1.04 1.0 1.0 1.0 1.05 1.0 1.0 1.0 1.06 2.0 2.0 2.0 2.07 2.0 2.0 2.0 2.08 2.0 2.0 2.0 2.0# Test 3# 创建DataFrame, 部分索引重合df1 = pd.DataFrame(np.ones((3, 4)) * 0, columns = ['a', 'b', 'c', 'd'], index = [1, 2, 3])df2 = pd.DataFrame(np.ones((3, 4)) * 1, columns = ['b', 'c', 'd', 'e'], index = [2, 3, 4])print df1print df2# 直接合并, 默认的join模式为outer, 与pd.concat([df1, df2])是一样的res = pd.concat([df1, df2], join = 'outer')print res# 合并模式为innerres = pd.concat([df1, df2], join = 'inner')print res# 合并模式为inner, 同时重新排序res = pd.concat([df1, df2], join = 'inner', ignore_index = True)print res# Test 3 result a b c d1 0.0 0.0 0.0 0.02 0.0 0.0 0.0 0.03 0.0 0.0 0.0 0.0 b c d e2 1.0 1.0 1.0 1.03 1.0 1.0 1.0 1.04 1.0 1.0 1.0 1.0 a b c d e1 0.0 0.0 0.0 0.0 NaN2 0.0 0.0 0.0 0.0 NaN3 0.0 0.0 0.0 0.0 NaN2 NaN 1.0 1.0 1.0 1.03 NaN 1.0 1.0 1.0 1.04 NaN 1.0 1.0 1.0 1.0 b c d1 0.0 0.0 0.02 0.0 0.0 0.03 0.0 0.0 0.02 1.0 1.0 1.03 1.0 1.0 1.04 1.0 1.0 1.0 b c d0 0.0 0.0 0.01 0.0 0.0 0.02 0.0 0.0 0.03 1.0 1.0 1.04 1.0 1.0 1.05 1.0 1.0 1.0# Test 4# 横向合并res = pd.concat([df1, df2], axis = 1)print res# 横向合并, 按照df1的index, 忽略df2不一致的indexres = pd.concat([df1, df2], axis = 1, join_axes = [df1.index])print res# Test 4 result a b c d b c d e1 0.0 0.0 0.0 0.0 NaN NaN NaN NaN2 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.03 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.04 NaN NaN NaN NaN 1.0 1.0 1.0 1.0 a b c d b c d e1 0.0 0.0 0.0 0.0 NaN NaN NaN NaN2 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.03 0.0 0.0 0.0 0.0 1.0 1.0 1.0 1.0# Test 5# 创建DataFramedf1 = pd.DataFrame(np.ones((3, 4)) * 0, columns = ['a', 'b', 'c', 'd'])df2 = pd.DataFrame(np.ones((3, 4)) * 1, columns = ['a', 'b', 'c', 'd'])df3 = pd.DataFrame(np.ones((3, 4)) * 2, columns = ['a', 'b', 'c', 'd'])# appendprint df1.append(df2, ignore_index = True)# append 多个DataFrameprint df1.append([df2, df3], ignore_index = True)# Test 5 result a b c d0 0.0 0.0 0.0 0.01 0.0 0.0 0.0 0.02 0.0 0.0 0.0 0.03 1.0 1.0 1.0 1.04 1.0 1.0 1.0 1.05 1.0 1.0 1.0 1.0 a b c d0 0.0 0.0 0.0 0.01 0.0 0.0 0.0 0.02 0.0 0.0 0.0 0.03 1.0 1.0 1.0 1.04 1.0 1.0 1.0 1.05 1.0 1.0 1.0 1.06 2.0 2.0 2.0 2.07 2.0 2.0 2.0 2.08 2.0 2.0 2.0 2.0
转载地址：http://fjwui.baihongyu.com/