In [1]:

    

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.ticker import FuncFormatter
%matplotlib inline
pd.set_option('display.max_rows',15)

from pandas import *
from pandas.io.parsers import read_csv


    

In [2]:

    

df = read_csv('vault60batch.csv', index_col=False, names=['timestamp','host','size','duration'])


    

In [3]:

    

fig, ax = plt.subplots(figsize=(9, 6))
df['duration'].plot.hist(bins=100,alpha=0.5)
#bnl.hist(ax=ax, bins=bins, label=['bnl'], alpha=0.5)
ax.set(title='Distribution of write duration', xlabel='Duration (s)', ylabel='Count')
ax.legend().set_visible(True)