我有一些数据,每行有两列。在我的情况下,工作提交时间和地区。
我使用了matplotlib的hist函数来生成一个图表,该图表在x轴上按天分类,在y轴上每天计数:
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()
我现在想要一个图表,在x轴上按天分隔时间,在y轴上按bin区域求和。
到目前为止,我已经使用列表理解来提出这个:
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()
我还是NumPy的新手,想知道我是否可以改进:
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
所以它没有使用Python列表。
是否有可能以某种方式爆炸sum_by[bin_index==i]
所以我得到一个长度为len(bins)
的数组数组?然后np.sum()
将返回一个numpy数组。
答案 0 :(得分:5)
Matplotlib的hist
函数和NumPy的histogram
函数都有weights
个可选的关键字参数。我认为你的第一个代码中唯一相关的改变行应该看起来像:
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')