Python Data analysis and visualization

Introduction URL: Https://www.kaggle.com/benhamner/d/uciml/iris/python-data-visualizations/notebook

Import Matplotlib.pyplot as Plt

Import Seaborn as SNS

Import Pandas as PD

Import data:

Iris=pd.read_csv (' E:\\data\\iris.csv ')

Iris.head ()

To make a histogram:

Plt.hist (iris[' SEPALLENGTHCM '],bins=15)

Plt.xlabel (' SEPALLENGTHCM ')

Plt.ylabel (' quantity ')

Plt.title (' Distribution of SEPALLENGTHCM ')

Plt.show ()

To make a scatter plot:

But such a diagram does not indicate the color of the different kinds of words = flowers. So we use another way to sort by species.

Violin chart

Box-type diagram:

Ax=sns.boxplot (x= "species", y= "SEPALWIDTHCM", Data=iris)

The use of jitter=true here makes a little bit less of the vertical line in the middle.

Ax=sns.boxplot (x= "species", y= "SEPALWIDTHCM", Data=iris)

Ax=sns.stripplot (x= "species", y= "SEPALWIDTHCM", data=iris,jitter=true,edgecolor= "gray")

Kdeplot: The linkage between univariate variables and the potential characteristics of the variables assessed by a kernel density

Displays the links between the two variables:

Diag_kind= ' KDE ' shows the kernel density between the two variables and uses it to estimate its characteristics

Boxplot_1: Separate features between variables by species

Andrews curves: Andrew Curve uses the properties of the sample as coefficients of the Fourier transform

Radviz: Multivariate visualization, where each feature is displayed on a plane, and the sample is connected to the image by the dots on the circle

Parallel_coordinates multi-variable visualization with parallel coordinates: For each feature of a data sample, we set the feature on the axis and draw a line.

Python Data analysis and visualization