利用Python绘制数据的瀑布图的教程

import numpy as npimport pandas as pdimport matplotlib.pyplot as plt %matplotlib inline

index = ['sales','returns','credit fees','rebates','late charges','shipping']data = {'amount': [350000,-30000,-7500,-25000,95000,-7000]}trans = pd.DataFrame(data=data,index=index)

from IPython.display import displaydisplay(trans)

display(trans.amount.cumsum())sales      350000returns     320000credit fees   312500rebates     287500late charges  382500shipping    375500Name: amount, dtype: int64

blank=trans.amount.cumsum().shift(1).fillna(0)display(blank) sales        0returns     350000credit fees   320000rebates     312500late charges  287500shipping    382500Name: amount, dtype: float64

total = trans.sum().amounttrans.loc["net"] = totalblank.loc["net"] = totaldisplay(trans)display(blank)

sales        0returns     350000credit fees   320000rebates     312500late charges  287500shipping    382500net       375500Name: amount, dtype: float64

step = blank.reset_index(drop=True).repeat(3).shift(-1)step[1::3] = np.nandisplay(step) 0     00    NaN0  3500001  3500001    NaN1  3200002  3200002    NaN2  3125003  3125003    NaN3  2875004  2875004    NaN4  3825005  3825005    NaN5  3755006  3755006    NaN6    NaNName: amount, dtype: float64

blank.loc["net"] = 0

my_plot = trans.plot(kind='bar', stacked=True, bottom=blank,legend=None, title="2014 Sales Waterfall")my_plot.plot(step.index, step.values,'k')

def money(x, pos):  'The two args are the value and tick position'  return "${:,.0f}".format(x) from matplotlib.ticker import FuncFormatterformatter = FuncFormatter(money)

my_plot = trans.plot(kind='bar', stacked=True, bottom=blank,legend=None, title="2014 Sales Waterfall")my_plot.plot(step.index, step.values,'k')my_plot.set_xlabel("Transaction Types")my_plot.yaxis.set_major_formatter(formatter)

import numpy as npimport pandas as pdimport matplotlib.pyplot as pltfrom matplotlib.ticker import FuncFormatter #Use python 2.7+ syntax to format currencydef 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 calculatedindex = ['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 waterfalltrans = 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 waterfalltotal = trans.sum().amounttrans.loc["net"]= totalblank.loc["net"] = total #The steps graphically show the levels as well as used for label placementstep = 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 0blank.loc["net"] = 0 #Plot and labelmy_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 dollarsmy_plot.yaxis.set_major_formatter(formatter) #Get the y-axis position for the labelsy_height = trans.amount.cumsum().shift(1).fillna(0) #Get an offset so labels don't sit right on top of the barmax = trans.max()neg_offset = max / 25pos_offset = max / 50plot_offset = int(max / 15) #Start label looploop = 0for 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 labelsmy_plot.set_ylim(0,blank.max()+int(plot_offset))#Rotate the labelsmy_plot.set_xticklabels(trans.index,rotation=0)my_plot.get_figure().savefig("waterfall.png",dpi=200,bbox_inches='tight')