In [1]:
import numpy as np
import pandas as pd
In [2]:
CS=pd.read_excel("F:/2019 GB Python/Descstats.xlsx")
In [3]:
CS.head()
Out[3]:
Sample 1 Sample 2 Group Unnamed: 3 Unnamed: 4 Unnamed: 5 Unnamed: 6
0 28.686942 0.627870 A NaN NaN NaN NaN
1 30.811276 50.558054 A NaN NaN NaN NaN
2 28.477675 54.593256 A NaN NaN NaN NaN
3 31.689752 19.613195 A NaN NaN NaN NaN
4 31.132768 48.658675 A NaN NaN NaN NaN
In [4]:
CS1=CS[['Sample 1']]
In [5]:
CS1.head()
Out[5]:
Sample 1
0 28.686942
1 30.811276
2 28.477675
3 31.689752
4 31.132768
In [6]:
import scipy.stats as st
In [8]:
st.norm.interval(0.95, loc=np.mean(CS1), scale=st.sem(CS1))
Out[8]:
(array([29.94752379]), array([30.07663049]))
In [9]:
CS1.describe()
Out[9]:
Sample 1
count 1000.000000
mean 30.012077
std 1.041527
min 26.160543
25% 29.314089
50% 30.014408
75% 30.730071
max 33.757718
In [10]:
st.norm.interval(0.95, loc=np.std(CS1), scale=st.sem(CS1))
Out[10]:
(array([0.97645313]), array([1.10555982]))
In [ ]: