Python handles PDF and CDF

One of the most necessary things to do when you get the data is to look at your data distribution. The distribution of data also includes two types: PDF and CDF.

Here's how to generate PDFs and CDF using Python:

1. Use the Matplotlib Drawing Interface hist () to directly draw the PDF distribution;
2. Using NumPy's data processing function histogram (), the PDF distribution data can be generated to facilitate subsequent data processing, such as the further generation of CDF;
3. The advantage of using Seaborn's Distplot () is that you can fit the PDF distribution to see the distribution type of your data;

Shown is a PDF graph generated using 3 algorithms. Here is the source code.

 fromSciPyImportStatsImportMatplotlib.pyplot as PltImportNumPy as NPImportSeaborn as Snsarr= Np.random.normal (size=100)#Plot histogramPlt.subplot (221) plt.hist (arr)#Obtain histogram dataPlt.subplot (222) hist, Bin_edges=Np.histogram (arr) Plt.plot (hist)#Fit Histogram curvePlt.subplot (223) Sns.distplot (arr, KDE=false, Fit=stats.gamma, rug=True) plt.show ()

Python handles PDF and CDF