描述性统计

1> sum()

返回请求轴的总和

dict_str = {'Name':pd.Series(['meng', 'cai', 'zhang', 'wang']),'Age':pd.Series([20, 21, 22, 25])}
df = pd.DataFrame(dict_str)
print(f'求和:\n{df.sum()}')  # df.sum(0)

# 输出结果:
#  求和:
#  Name    mengcaizhangwang
#  Age                   88
#  dtype: object

# 对列 1 求和
print(f'数据中的行轴求和:\n{df.sum(1)}')

# 输出结果:
#  数据中的行轴求和:
#  0    20
#  1    21
#  2    22
#  3    25
#  dtype: int64

2> mean()

返回平均值

dict_str = {'Name':pd.Series(['meng', 'cai', 'zhang', 'wang']),'Age':pd.Series([20, 21, 22, 25])}
df = pd.DataFrame(dict_str)
print(f'平均值:\n{df.mean()}')

# 输出结果:
#  平均值:
#  Age    22.0
#  dtype: float64

3> std()

标准偏差

dict_str = {'Name':pd.Series(['meng', 'cai', 'zhang', 'wang']),'Age':pd.Series([20, 21, 22, 25])}
df = pd.DataFrame(dict_str)
print(f'标准偏差:\n{df.std()}')

# 输出结果:
#  标准偏差:
#  Age    2.160247
#  dtype: float64

4> describe()

统计信息的摘要

dict_str = {'Name':pd.Series(['meng', 'cai', 'zhang', 'wang']),'Age':pd.Series([20, 21, 22, 25])}
df = pd.DataFrame(dict_str)
print(f'汇总数据:\n{df.describe()}')

# 输出结果:
#  汇总数据:
#               Age
#  count   4.000000
#  #  mean   22.000000
#  std     2.160247
#  min    20.000000
#  #  25%    20.750000
#  50%    21.500000
#  75%    22.750000
#  max    25.000000

dict_str = {'Name':pd.Series(['meng', 'cai', 'zhang', 'wang']),'Age':pd.Series([20, 21, 22, 25])}
df = pd.DataFrame(dict_str)
print(f'汇总数据:\n{df.describe(include = "object")}')

# 输出结果:
#  汇总数据:
#          Name
#  count      4
#  unique     4
#  top     meng
#  freq       1

5> 累计统计函数

stock_rise = data['p_change']
# plot方法集成了前面直方图、条形图、饼图、折线图
stock_rise.cumsum()

# 输出结果:
#  2015-03-02      2.62
#  2015-03-03      4.06
#  2015-03-04      5.63
#  2015-03-05      7.65
#  2015-03-06     16.16