0

我正在尝试使用scipy.stats获取数据的分布拟合。col_1, col_2, col_3数据在单个 CSV 文件中包含多个列。

  • 问题是分布拟合只需要一列来识别最佳分布拟合，如下面的代码所示。

  • 如何同时获得所有列的分布拟合？例如分布拟合col_1, col_2, col_3

    import warnings
warnings.filterwarnings("ignore")

import pandas as pd
import numpy as np
import scipy
from sklearn.preprocessing import StandardScaler
import scipy.stats
import matplotlib.pyplot as plt

# Load data and select first column

from sklearn import datasets
data_set = datasets.load_breast_cancer()

# Multiple coloumns of csv
col_1=data_set.data[:,0]
col_2=data_set.data[:,1]
col_3=data_set.data[:,2]

# Create an index array (x) for data

x = np.arange(len(col_1))
size = len(col_1)

plt.hist(col_1)
plt.show()


sc=StandardScaler() 
yy = col_1.reshape (-1,1)
sc.fit(yy)
y_std =sc.transform(yy)
y_std = y_std.flatten()
y_std
del yy


dist_names = ['beta',
              'expon',
              'gamma',
              'lognorm',
              'norm',
              'pearson3',
              'triang',
              'uniform',
              'weibull_min', 
              'weibull_max']

# Set up empty lists to stroe results
chi_square = []
p_values = []


# Set up 50 bins for chi-square test
# Observed data will be approximately evenly distrubuted aross all bins
percentile_bins = np.linspace(0,100,51)
percentile_cutoffs = np.percentile(y_std, percentile_bins)
observed_frequency, bins = (np.histogram(y_std, bins=percentile_cutoffs))
cum_observed_frequency = np.cumsum(observed_frequency)



# Loop through candidate distributions

for distribution in dist_names:
    # Set up distribution and get fitted distribution parameters
    dist = getattr(scipy.stats, distribution)
    param = dist.fit(y_std)

    # Obtain the KS test P statistic, round it to 5 decimal places
    p = scipy.stats.kstest(y_std, distribution, args=param)[1]
    p = np.around(p, 5)
    p_values.append(p)    

    # Get expected counts in percentile bins
    # This is based on a 'cumulative distrubution function' (cdf)
    cdf_fitted = dist.cdf(percentile_cutoffs, *param[:-2], loc=param[-2], 
                          scale=param[-1])
    expected_frequency = []
    for bin in range(len(percentile_bins)-1):
        expected_cdf_area = cdf_fitted[bin+1] - cdf_fitted[bin]
        expected_frequency.append(expected_cdf_area)

    # calculate chi-squared
    expected_frequency = np.array(expected_frequency) * size
    cum_expected_frequency = np.cumsum(expected_frequency)
    ss = sum (((cum_expected_frequency - cum_observed_frequency) ** 2) / cum_observed_frequency)
    chi_square.append(ss)

# Collate results and sort by goodness of fit (best at top)

results = pd.DataFrame()
results['Distribution'] = dist_names
results['chi_square'] = chi_square
results['p_value'] = p_values
results.sort_values(['chi_square'], inplace=True)

# Report results

print ('\nDistributions sorted by goodness of fit:')
print ('----------------------------------------')
print (results)
4

0 回答 0