Shulou(Shulou.com)06/03 Report--

This article will explain in detail how to operate python to draw lost loss curve plus variance range, the content of the article is of high quality, so the editor will share it for you to do a reference. I hope you will have a certain understanding of the relevant knowledge after reading this article.

1. Import the necessary packages

I use seaborn, through sns.set_style to make the drawing more beautiful, and can switch between different types

Import reimport seaborn as snsimport matplotlib.pyplot as pltimport matplotlib.cm as cmimport shutilimport ossns.set_style ('whitegrid') 2. Access to data (you can skip this step)

The data I use is a return curve obtained through deep reinforcement. The data structure is shown below. What I need is the part that starts with train, which corresponds to the total return, the average return, and the variance of the return. I use the regular expression of re.findall to extract the data I need, the specific mode of operation can see the source code.

10-15 22:23:15 DATA/traffic DEBUG train 0 totalreward:-99477.0 ReturnAvg:-102.55360824742269 ReturnStd: 34.34301970480272

10-15 22:23:29 DATA/traffic DEBUG train 1 totalreward:-83131.0 ReturnAvg:-85.70206185567011 ReturnStd: 53.44299000985545

File_path = 'log.txt'content = [] with open (file_path,' r') as f: for line in f.readlines (): line = line.strip ('\ n') content.append (line) iter = [] totalreward = [] returnavg = [] returnstd = [] for line in content: str1 = re.findall ('train.+', line) v = [float (x) for x in re.findall ('?\ dbath.\ d+ |\ dkeeper' Str1 [0])] iter.append (v [0]) totalreward.append (v [1]) returnavg.append (v [2]) returnstd.append (v [3]) 3. Return drawing

Save the image directly to the Plot folder, where you can't save the jpg format, save it all the time, and finally save it to png format successfully. Set the resolution to 1000, which is about the same, but the line is clearer.

Color= cm.viridis (0.5) f, ax = plt.subplots (1) ax.plot (iter, totalreward, color=color) ax.legend () ax.set_xlabel ('Iteration') ax.set_ylabel (' Return') exp_dir = 'Plot/'if not os.path.exists (exp_dir): os.makedirs (exp_dir, exist_ok=True) else: os.makedirs (exp_dir, exist_ok=True) f.savefig (os.path.join (' Plot', 'reward' +' .png')) Dpi=1000)

The curve is shown below, which can be displayed by plt.show (), or enter f directly in console and enter enter

4. Average return drawing with Variance

In reinforcement learning papers, we often see a convergence line, surrounded by shallow range lines, and those range lines are variance. The drawing code is as follows, which mainly contains fill_between.

Color= cm.viridis (0. 7F, ax = plt.subplots (1) ax.plot (iter, returnavg, color=color) R1 = list (map (lambda x: X [0]-x [1], zip (returnavg, returnstd)) R2 = list (map (lambda x: X [0] + x [1], zip (returnavg, returnstd)) ax.fill_between (iter, R1, R2, color=color) Alpha=0.2) ax.legend () ax.set_xlabel ('Iteration') ax.set_ylabel (' Return') exp_dir = 'Plot/'if not os.path.exists (exp_dir): os.makedirs (exp_dir, exist_ok=True) f.savefig (os.path.join (' Plot', 'avgreward' +' .png'), dpi=50)

You can see that dark green is surrounded by light green lines, which is the function of fill_between, in which alpha can be adjusted to change the color depth.

On how to operate python to draw lost loss curve plus variance range is shared here, I hope the above content can be of some help to you, can learn more knowledge. If you think the article is good, you can share it for more people to see.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.