问威布尔分布拟合数据

EN

from jtlHandler import *
import warnings
import numpy as np
import pandas as pd
import scipy.stats as st
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt



def get_pdf(latencies):

    a = np.array(latencies)
    ag = st.gaussian_kde(a)
    ak = np.linspace(np.min(a), np.max(a), len(a))
    agv = ag(ak)
    plt.plot(ak,agv)
    plt.show()
    return (ak,agv)

def fit_to_distribution(distribution, data):
    params = distribution.fit(data)
    # Return MLEs for shape (if applicable), location, and scale parameters from data.
    #
    # MLE stands for Maximum Likelihood Estimate. Starting estimates for the fit are given by input arguments; for any arguments not provided with starting estimates, self._fitstart(data) is called to generate such.

    return params

def make_distribution_pdf(dist, params, end):
    arg = params[:-2]
    loc = params[-2]
    scale = params[-1]

    # Build PDF and turn into pandas Series
    x = np.linspace(0, end, end)
    y = dist.pdf(x, loc=loc, scale=scale, *arg)
    pdf = pd.Series(y, x)

    return pdf


latencies = getLatencyList("filename")

latencies = latencies[int(9*(len(latencies)/10)):len(latencies)]
data = pd.Series(latencies)

params = fit_to_distribution(st.weibull_max, data)
print("Parameters for the fit: "+str(params))



# Make PDF
pdf = make_distribution_pdf(st.weibull_max, params, max(latencies))

# Display
plt.figure()
ax = pdf.plot(lw=2, label='PDF', legend=True)
data.plot(kind='hist', bins=200, normed=True, alpha=0.5, label='Data', 
legend=True, ax=ax)

ax.set_title('Weibull distribution')
ax.set_xlabel('Latnecy')
ax.set_ylabel('Frequency')

plt.savefig("image.png")