使用numpy和matplotlib绘制和的直方图而非计数

Question

我有一些数据，每行有两列，分别是工作提交时间和区域。

我使用了matplotlib的hist函数，制作了一个图表，x轴是按天分组的时间，y轴是每天的数量：

import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl
import datetime as dt

def timestamp_to_mpl(timestamp):
    return mpl.dates.date2num(dt.datetime.fromtimestamp(timestamp))

nci_file_name = 'out/nci.csv'
jobs = np.genfromtxt(nci_file_name, dtype=int, delimiter=',', names=True, usecols(1,2,3,4,5))

fig, ax = plt.subplots(2, 1, sharex=True)
vect_timestamp_to_mpl = np.vectorize(timestamp_to_mpl)
qtime = vect_timestamp_to_mpl(jobs['queued_time'])
start_date = dt.datetime(2013, 1, 1)
end_date = dt.datetime(2013, 4, 1)
bins = mpl.dates.drange(start_date, end_date, dt.timedelta(days=1))
ax[0].hist(qtime[jobs['charge_rate']==1], bins=bins, label='Normal', color='b')
ax[1].hist(qtime[jobs['charge_rate']==3], bins=bins, label='Express', color='g')
ax[0].grid(True)
ax[1].grid(True)
fig.suptitle('NCI Workload Submission Daily Rate')
ax[0].set_title('Normal Queue')
ax[1].set_title('Express Queue')
ax[1].xaxis.set_major_locator(mpl.dates.AutoDateLocator())
ax[1].xaxis.set_major_formatter(mpl.dates.AutoDateFormatter(ax[1].xaxis.get_major_locator()))
ax[1].set_xlim(mpl.dates.date2num(start_date), mpl.dates.date2num(end_date))
plt.setp(ax[1].xaxis.get_majorticklabels(), rotation=25, ha='right')
ax[1].set_xlabel('Date')
ax[0].set_ylabel('Jobs per Day')
ax[1].set_ylabel('Jobs per Day')
fig.savefig('out/figs/nci_sub_rate_day_sub.png')
plt.show()

现在我想要一个新的图表，x轴还是按天分组的时间，但y轴是按区域汇总的结果。

到目前为止，我用列表推导式做出了这个：

import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl
import datetime as dt

def timestamp_to_mpl(timestamp):
    return mpl.dates.date2num(dt.datetime.fromtimestamp(timestamp))

def binsum(bin_by, sum_by, bins):
    bin_index = np.digitize(bin_by, bins)
    sums = [np.sum(sum_by[bin_index==i]) for i in range(len(bins))]
    return sums

fig, ax = plt.subplots(2, 1, sharex=True)
vect_timestamp_to_mpl = np.vectorize(timestamp_to_mpl)
qtime = vect_timestamp_to_mpl(jobs['queued_time'])
area = jobs['run_time'] * jobs['req_procs']
start_date = dt.datetime(2013, 1, 1)
end_date = dt.datetime(2013, 4, 1)
delta = dt.timedelta(days=1)
bins = mpl.dates.drange(start_date, end_date, delta)
sums_norm = binsum(qtime[jobs['charge_rate']==1], area[jobs['charge_rate']==1], bins)
sums_expr = binsum(qtime[jobs['charge_rate']==3], area[jobs['charge_rate']==3], bins)
ax[0].bar(bins, sums_norm, width=1.0, label='Normal', color='b')
ax[1].bar(bins, sums_expr, width=1.0, label='Express', color='g')
ax[0].grid(True)
ax[1].grid(True)
fig.suptitle('NCI Workload Area Daily Rate')
ax[0].set_title('Normal Queue')
ax[1].set_title('Express Queue')
ax[1].xaxis.set_major_locator(mpl.dates.AutoDateLocator())
ax[1].xaxis.set_major_formatter(mpl.dates.AutoDateFormatter(ax[1].xaxis.get_major_locator()))
ax[1].set_xlim(mpl.dates.date2num(start_date), mpl.dates.date2num(end_date))
plt.setp(ax[1].xaxis.get_majorticklabels(), rotation=25, ha='right')
ax[1].set_xlabel('Date')
ax[0].set_ylabel('Area per Day')
ax[1].set_ylabel('Area per Day')
fig.savefig('out/figs/nci_area_day_sub.png')
plt.show()

我对NumPy还不太熟悉，想知道我是否可以改进一下：

def binsum(bin_by, sum_by, bins):
    bin_index = np.digitize(bin_by, bins)
    sums = [np.sum(sum_by[bin_index==i]) for i in range(len(bins))]
    return sums

这样的话就不使用Python的列表了。

有没有办法把sum_by[bin_index==i]展开成一个数组的数组，这样我就能得到一个长度为len(bins)的数组？然后np.sum()就能返回一个NumPy数组。

Answer 1

Matplotlib的hist函数和NumPy的histogram函数都有一个可选的参数叫weights。我觉得你第一段代码中需要修改的地方应该是这样的：

ax[0].hist(qtime[jobs['charge_rate']==1], weights=area[jobs['charge_rate']==1],
           bins=bins, label='Normal', color='b')
ax[1].hist(qtime[jobs['charge_rate']==3], weights=area[jobs['charge_rate']==3],
           bins=bins, label='Express', color='g')