import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.ticker import FuncFormatter
#Use python 2.7+ syntax to format currency
def money(x, pos):
'The two args are the value and tick position'
return "${:,.0f}".format(x)
formatter = FuncFormatter(money)
#Data to plot. Do not include a total, it will be calculated
index = ['sales','returns','credit fees','rebates','late charges','shipping']
data = {'amount': [350000,-30000,-7500,-25000,95000,-7000]}
#Store data and create a blank series to use for the waterfall
trans = pd.DataFrame(data=data,index=index)
blank = trans.amount.cumsum().shift(1).fillna(0)
#Get the net total number for the final element in the waterfall
total = trans.sum().amount
trans.loc["net"]= total
blank.loc["net"] = total
#The steps graphically show the levels as well as used for label placement
step = blank.reset_index(drop=True).repeat(3).shift(-1)
step[1::3] = np.nan
#When plotting the last element, we want to show the full bar,
#Set the blank to 0
blank.loc["net"] = 0
#Plot and label
my_plot = trans.plot(kind='bar', stacked=True, bottom=blank,legend=None, figsize=(10, 5), title="2014 Sales Waterfall")
my_plot.plot(step.index, step.values,'k')
my_plot.set_xlabel("Transaction Types")
#Format the axis for dollars
my_plot.yaxis.set_major_formatter(formatter)
#Get the y-axis position for the labels
y_height = trans.amount.cumsum().shift(1).fillna(0)
#Get an offset so labels don't sit right on top of the bar
max = trans.max()
neg_offset = max / 25
pos_offset = max / 50
plot_offset = int(max / 15)
#Start label loop
loop = 0
for index, row in trans.iterrows():
# For the last item in the list, we don't want to double count
if row['amount'] == total:
y = y_height[loop]
else:
y = y_height[loop] + row['amount']
# Determine if we want a neg or pos offset
if row['amount'] > 0:
y += pos_offset
else:
y -= neg_offset
my_plot.annotate("{:,.0f}".format(row['amount']),(loop,y),ha="center")
loop+=1
#Scale up the y axis so there is room for the labels
my_plot.set_ylim(0,blank.max()+int(plot_offset))
#Rotate the labels
my_plot.set_xticklabels(trans.index,rotation=0)
my_plot.get_figure().savefig("waterfall.png",dpi=200,bbox_inches='tight')
运行该脚本将生成下面这个漂亮的图表：
最后的想法
如果你之前不熟悉瀑布图，希望这个示例能够向你展示它到底是多么有用。我想，可能一些人会觉得对于一个图表来说需要这么多的脚本代码有点糟糕。在某些方面，我同意这种想法。如果你仅仅只是做一个瀑布图，而以后不会再碰它，那么你还是继续用Excel中的方法吧。
然而，如果瀑布图真的很有用，并且你需要将它复制给100个客户，将会怎么样呢？接下来你将要怎么做呢？此时使用Excel将会是一个挑战，而使用本文中的脚本来创建100个不同的表格将相当容易。再次说明，这一程序的真正价值在于，当你需要扩展这个解决方案时，它能够便于你创建一个易于复制的程序。
我真的很喜欢学习更多Pandas、matplotlib和IPothon的知识。我很高兴这种方法能够帮到你，并希望其他人也可以从中学习到一些知识，并将这一课所学应用到他们的日常工作中。
--------------------------------------分割线 --------------------------------------
CentOS上源码安装Python3.4
《Python核心编程 第二版》.(Wesley J. Chun ).[高清PDF中文版]
《Python开发技术详解》.( 周伟,宗杰).[高清PDF扫描版+随书视频+代码]
在Ubuntu下用Python搭建桌面算法交易研究环境