利用python进行数据分析-pandas（二）Dataframe

from pandas import Series, DataFrame
import numpy as np
from numpy import nan as NA


# pandas中的对齐和运算，都是求交集的。
a1 = Series([1, 2, 3, 4, 5], index=['a', 'b', 'c', 'd', 'e'])
a2 = Series([1, -2, 3, 4], index=list('acef'))

d1 = DataFrame(np.arange(12).reshape(3, 4), columns=list('abcd'))
d2 = DataFrame(np.arange(20).reshape(4, 5), columns=list('abcde'))
# 可以使用fill_value来填充
# print(d1.add(d2, fill_value = 0))
d1 = d1.reindex(columns=d2.columns, fill_value=0)

# 按值排序和按索引排序
s1 = Series([1, 3, 5, 2, 4], index=list('abcde'))
# print(s1.sort_values())
# print(s1.sort_index())

# rank，根据出现的次数，给予一个排序值
s2 = Series([1, 3, 2, 3, 2, 4, 4, 4])
# print(s2.rank())
# 求和
# print(s2.sum())
# # 求columns(纵列)的和，空值会自动排除
# print(d1, d1.sum())
# # 求index(横列)的和
# print(d1, d1.sum(axis=1))
# 统计和，并且累加到下一行（广播累加）
# print(d1.cumsum())
# 清除na值
d3 = DataFrame([[1, 2, 3, NA, 4], [1, 2, 3, 4, NA],
                [1, 2, 3, NA, 4], [1, 2, 3, 4, NA]])
cleaned = d3.dropna()

——————————————————————————————————————————

    ----------------------------------------------------------------------

import pandas as pd
import matplotlib.pyplot as plt
from pandas import Series, DataFrame
import numpy as np

# 读取csv文件
d1 = pd.read_csv(r'd1.csv')
# 或者使用read_table，只不过要指定分隔符号
d2 = pd.read_table(r'd1.csv', sep=',')
# 分配列名，默认分配 header=None
d3 = pd.read_csv(r'd1.csv', names=list('abcde'))
# 分配索引
d4 = pd.read_csv(r'd1.csv', names=list('abcde'), index_col='d')
# 读取行数
d5 = pd.read_csv(r'd1.csv', nrows=3)
# 保存为csv文件
# d1.to_csv('d2.csv', index=False)
d6 = pd.read_csv(r'd2.csv', header=None)