--Python achieve broad summary measure of the statistical review

#导入所需的包
import pandas as pd
import numpy as np
import seaborn as sns
from scipy import stats

#读取数据，并用describe查看数据的分布情况
data = pd.read_excel('./Desktop/实践一.xlsx')
data.describe()

out：
data
count	699.000000
mean	4.417740
std	2.815741
min	1.000000
25%	2.000000
50%	4.000000
75%	6.000000
max	10.000000


#为了方便计算，将数据集转为列表
data1 = list(data['data'])

#通过numpy、stats求得各个指标
print('平均数:',np.mean(data1))
print('下四分位数:',np.quantile(data1,0.25))
print('中位数:',np.median(data1))
print('上四分位数:',np.quantile(data1,0.75))
print('众数:',stats.mode(data1)[0][0])
print('标准差:',np.std(data1))
print('偏态系数:',stats.skew(data1))
print('峰态系数:',stats.kurtosis(data1))

out：
平均数: 4.417739628040057
下四分位数: 2.0
中位数: 4.0
上四分位数: 6.0
众数: 1
标准差: 2.8137258170785375
偏态系数: 0.5915855449527385
峰态系数: -0.6278342838815454


#自定义一个函数，实现以上功能：
def get_data_describe(data):
    n = len(data)
    m = int(n/2)
    m1 = int((n/2))-1
    m2 = int((n/2))+1
    data = sorted(data)
    data_mean = np.sum(data)/n
    if n%2 ==0:
        data_median = (data[m1]+data[m2])/2
    else:
        data_median = data[m]
    data_range = [data[i]-data_mean for i in range(len(data))] 
    data_sd = np.sum([pow(x,2) for x in data_range])/n
    data_std = np.sqrt(data_sd)
    data_sk = np.sum([pow(x,3) for x in data_range])/(n*pow(data_std,3))
    data_kurt=np.sum([pow(x,4) for x in data_range])/(n*pow(data_std,4))-3
    print ('平均数:',data_mean)
    print ('中位数:',data_median)
    print ('方差:',data_sd)
    print ('标准差:',data_std)
    print('偏态系数:',data_sk)
    print('峰态系数:',data_kurt)


get_data_describe(data1)

out：
平均数: 4.417739628040057
中位数: 4
方差: 7.9170529736942825
标准差: 2.8137258170785375
偏态系数: 0.5915855449527385
峰态系数: -0.6278342838815454