import pandas as pd
import numpy as np
import matplotlib
import scipy.stats as sp
import matplotlib.pyplot as plt
import statistics as st
from decimal import Decimal, ROUND_HALF_UP
rld=pd.read_excel(r"C:\Users\DELL\nagrajun sagar reservoir data - Copy.xlsx")
rld.head()
output:
October 2 October 3 October 4 October 5 October 6 October 7 October 8 October 9 October 10 October ... 22 October 23 October 24 October 25 October 26 October 27 October 28 October 29 October 30 October 31 October
0 2.070 2.070 2.014 2.272 2.464 2.619 2.632 2.638 2.638 2.788 ... 4.442 4.551 4.645 4.753 4.784 4.776 4.776 4.761 4.745 4.730
1 1.520 1.579 1.596 1.620 1.639 1.642 1.654 1.648 1.744 1.897 ... 5.520 5.562 5.595 5.644 5.644 5.611 5.570 5.520 5.495 5.470
2 0.856 0.823 0.779 0.724 0.663 0.619 0.592 0.559 0.534 0.508 ... 0.614 0.646 0.658 0.652 0.647 0.647 0.659 0.686 0.712 0.680
3 0.370 0.370 0.370 0.370 0.370 0.385 0.385 0.390 0.378 0.378 ... 0.355 0.344 0.344 0.344 0.344 0.344 0.344 0.344 0.344 0.344
4 2.713 2.728 2.701 2.692 2.755 2.802 2.948 3.189 3.360 3.456 ... 3.685 3.678 3.649 3.649 3.640 3.670 3.644 3.619 3.592 3.55
rl = rld.iloc[:,1].sort_values().reset_index(drop=True)
0 0.043
1 0.370
2 0.391
3 0.823
4 1.105
5 1.579
6 2.070
7 2.235
8 2.728
9 4.490
10 4.905
11 5.036
12 5.074
13 6.481
14 6.613
15 6.806
16 6.807
17 6.824
18 6.841
Name: 2 October, dtype: float64
我想将不同分布拟合到此数据,并通过执行ks测试找出最佳分布