Python笔记 #13# Pandas: Viewing Data

感觉很详细：数据分析：pandas 基础

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

dates = pd.date_range('', periods=3) # 创建 16 17 18 等六个日期

df = pd.DataFrame(np.random.randn(3,4), index=dates, columns=list('ABCD')) # 这是二维的，类似于一个表！
# 通过 numpy 随机了一个 3 * 4 的数据，这和行数、列数是相对应的
# print(df)
#                    A         B         C         D
# 2018-01-16 -0.139759  0.857653  0.754470  0.224313
# 2018-01-17  1.565070  0.521973 -1.265168 -0.278524
# 2018-01-18 -0.668574 -0.527155  0.877785 -1.123334

# print(df.head(1)) # 默认值是 5
#                    A         B         C         D
# 2018-01-16 -0.039203  1.211976  0.664805  0.307147

df.tail(5) # 同上，顾名思义

# print(df.index) # 顾名思义 + 1
# print(df.columns)
# DatetimeIndex(['2018-01-16', '2018-01-17', '2018-01-18'], dtype='datetime64[ns]', freq='D')
# Index(['A', 'B', 'C', 'D'], dtype='object')

# print(df.describe()) # 对每列数据做一些简单的统计学处理
#               A         B         C         D
# count  3.000000  3.000000  3.000000  3.000000
# mean  -0.163883 -0.107242 -0.621706  0.618341
# std    0.360742  0.429078  0.800366  0.609524
# min   -0.505212 -0.502887 -1.352274  0.055032
# 25%   -0.352602 -0.335291 -1.049444  0.294803
# 50%   -0.199991 -0.167695 -0.746613  0.534574
# 75%    0.006782  0.090581 -0.256421  0.899995
# max    0.213556  0.348857  0.233770  1.265416

# print(df.T) # 转置（Transposing）
#    2018-01-16  2018-01-17  2018-01-18
# A   -1.137015   -0.067200    0.737709
# B   -1.141811    0.335953    1.023016
# C    2.481266   -0.957599    0.011144
# D    1.485434   -0.605588    0.592746

# print(df)
# print(df.sort_index(axis=1, ascending=False)) # axis=1 按照列名排序 axis=0 按照行名排序
#                    A         B         C         D
# 2018-01-16 -0.787226  0.321619  1.097938 -0.701082
# 2018-01-17 -0.417257 -0.163390 -0.943166 -0.497475
# 2018-01-18  0.486670 -0.733582  1.923475 -1.145891
#                    D         C         B         A
# 2018-01-16 -0.701082  1.097938  0.321619 -0.787226
# 2018-01-17 -0.497475 -0.943166 -0.163390 -0.417257
# 2018-01-18 -1.145891  1.923475 -0.733582  0.486670

# print(df.sort_values(by='B'))
#                    A         B         C         D
# 2018-01-17  0.817088 -0.792903  1.643429 -0.008784
# 2018-01-18  0.540910  0.662119  0.190846 -0.960926
# 2018-01-16  0.333727  1.196133 -0.527796  0.677337