Pandas and Matplotlib - fill_between() vs datetime64

Question

There is a Pandas DataFrame:

Int64Index: 300 entries, 5220 to 5519
Data columns (total 3 columns):
Date                 


        

Answer 1

As WillZ pointed out, Pandas 0.21 broke unutbu's workaround. Converting datetimes to dates, however, can have significantly negative impacts on data analysis. This solution currently works and keeps datetime:

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

N = 300
dates = pd.date_range('2000-1-1', periods=N, freq='ms')
x = np.linspace(0, 2*np.pi, N)
data = pd.DataFrame({'A': np.sin(x), 'B': np.cos(x),
           'Date': dates})
d = data['Date'].dt.to_pydatetime()
plt.plot_date(d, data['A'], '-')
plt.plot_date(d, data['B'], '-')


plt.fill_between(d, data['A'], data['B'],
            where=data['A'] >= data['B'],
            facecolor='green', alpha=0.2, interpolate=True)
plt.xticks(rotation=25)
plt.show()

EDIT: As per jedi's comment, I set out to determine the fastest approach of the three options below:

• method1 = original answer
• method2 = jedi's comment + original answer
• method3 = jedi's comment

method2 was slightly faster, but much more consistent, and thus I have edited the above answer to reflect the best approach.

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import time


N = 300
dates = pd.date_range('2000-1-1', periods=N, freq='ms')
x = np.linspace(0, 2*np.pi, N)
data = pd.DataFrame({'A': np.sin(x), 'B': np.cos(x),
           'Date': dates})
time_data = pd.DataFrame(columns=['1', '2', '3', '4', '5', '6', '7', '8', '9', '10'])
method1 = []
method2 = []
method3 = []
for i in range(0, 10):
    start = time.clock()
    for i in range(0, 500):
        d = [pd.Timestamp(x).to_pydatetime() for x in data['Date']]
        #d = data['Date'].dt.to_pydatetime()
        plt.plot_date(d, data['A'], '-')
        plt.plot_date(d, data['B'], '-')


        plt.fill_between(d, data['A'], data['B'],
            where=data['A'] >= data['B'],
            facecolor='green', alpha=0.2, interpolate=True)
        plt.xticks(rotation=25)
        plt.gcf().clear()
    method1.append(time.clock() - start)

for i  in range(0, 10):
    start = time.clock()
    for i in range(0, 500):
        #d = [pd.Timestamp(x).to_pydatetime() for x in data['Date']]
        d = data['Date'].dt.to_pydatetime()
        plt.plot_date(d, data['A'], '-')
        plt.plot_date(d, data['B'], '-')


        plt.fill_between(d, data['A'], data['B'],
            where=data['A'] >= data['B'],
            facecolor='green', alpha=0.2, interpolate=True)
        plt.xticks(rotation=25)
        plt.gcf().clear()
    method2.append(time.clock() - start)

for i in range(0, 10):
    start = time.clock()
    for i in range(0, 500):
        #d = [pd.Timestamp(x).to_pydatetime() for x in data['Date']]
        #d = data['Date'].dt.to_pydatetime()
        plt.plot_date(data['Date'].dt.to_pydatetime(), data['A'], '-')
        plt.plot_date(data['Date'].dt.to_pydatetime(), data['B'], '-')


        plt.fill_between(data['Date'].dt.to_pydatetime(), data['A'], data['B'],
            where=data['A'] >= data['B'],
            facecolor='green', alpha=0.2, interpolate=True)
        plt.xticks(rotation=25)
        plt.gcf().clear()
    method3.append(time.clock() - start)

time_data.loc['method1'] = method1
time_data.loc['method2'] = method2
time_data.loc['method3'] = method3
print(time_data)
plt.errorbar(time_data.index, time_data.mean(axis=1), yerr=time_data.std(axis=1))