Univariate
1, the histogram displot
seaborn.distplot(a, bins=None, hist=True, kde=True, rug=False, fit=None, hist_kws=None, kde_kws=None, rug_kws=None, fit_kws=None, color=None, vertical=False, norm_hist=False, axlabel=None, label=None, ax=None)
Number of bins → box
hist, ked, rug → bool, whether me / density curve / data distribution
norm_hist → density according to whether the histogram display, if the False, the display count
{Hist, kde, rug, fit} _kws: dictionary, portions corresponding to various parameters.
Whether vertical → horizontal display
fit → scipy may be incorporated in the image library does fit
label → Legend
axlabel → x axis labeled
2, kernel density estimate FIG kdeplot
Step kernel density estimation:
Each observation with a near normal distribution curve approximation
All observations superimposed normal distribution curve
Normalized
seaborn.kdeplot（data，data2 = None，shade = False，vertical = False，kernel ='gau'，bw ='scott'，gridsize = 100，cut = 3，clip = None，legend = True，cumulative = False，shade_lowest = True，cbar = False，cbar_ax =无，cbar_kws =无，ax =无， kwargs ）
shade: (contour when filled with a color or bivariate data) If True, then filled with a color of the area under the curve KDE
kernel: { 'gau' | 'cos' | 'biw' | 'epa' | 'tri' | 'triw'} for fitting core, can bivariate Gaussian kernel values (GAU)
bw: { 'scott' | 'silverman' | scalar |} determined one pair of scalar nuclear size, understood as the fit approximation, the larger BW, the more gentle curve.
gridsize: int, discrete grid points
cumulative: whether to draw a cumulative distribution
cbar: If the parameter is True, a color bar is added (color bar image kde bivariate only)
FIG nuclear density distribution can draw only a single variable, the variables can be plotted bis!
Bivariate
1、jointplot
seaborn.jointplot（x，y，data = None，kind ='scatter'，color = None，size = 6，ratio = 5，space = 0.2，dropna = True，xlim = None，ylim = None，joint_kws = None，marginal_kws =None，annot_kws =None， kwargs ）
This function is a lightweight interface JoinGrid class, if you want to draw more flexible, can be used JoinGrid function.
kind: Set Type: "scatter", "reg", "resid", "kde", "hex"
size: int, the size of the image (the image is automatically adjusted to a square)
radio: height ratio int, and a main edge map of FIG.
space: # Set main map and the edge map pitch
{X, y} lim: shaft disposed before the drawing limits
{Joint, marginal, annot} _kws: other keywords assembly drawing parameters dicts
seaborn directly given Pearson correlation coefficient and the variable value P
pearson correlation coefficient calculation:
p: probability of sampling error caused by the difference between the samples is less than p.
2, JointGrid
Recall jointplot JoinGrid actually a package, in order to have a more flexible configuration, may be used JoinGrid class.
init（x，y，data = None，size = 6，ratio = 5，space = 0.2，dropna = True，xlim = None，ylim = None）
method:
plot (joint_func, marginal_func, annot_func) → draw the complete graphic
plot_joint (func, ** kwargs) → bivariate graphical drawing
plot_marginals (func, ** kwargs) → drawing pattern edge univariate
savefig（ args，* kwargs）→ 保存
set_axis_labels ([xlabel, ylabel]) → disposed bivariate shaft axis labels.
Explore the relationship between the two bivariate
In general, our data is not only one or two variables, then for a number of variables, we often need to explore the distribution and bivariate relationship between the two is that we need to use pairplot function or PairGrid class.
3、pairplot
seaborn.pairplot（data，hue = None，hue_order = None，palette = None，vars = None，x_vars = None，y_vars = None，kind ='scatter'，diag_kind ='auto'，markers = None，s = 2.5，aspect = 1，dropna = True，plot_kws = None，diag_kws = None，grid_kws = None）
hue: string (variable names): color will be classified according to the specified variable
hue_order: list set tone color palette variable level
palette: Palette
vars: list variable name list, otherwise use all numeric variables columns
markers: Point Style
sepal_length sepal_width petal_length petal_width species
5.1 3.5 1.4 0.2 silky
4.9 3.0 1.4 0.2 silky
4.7 3.2 1.3 0.2 silky
4.6 3.1 1.5 0.2 silky
5.0 3.6 1.4 0.2 silky
4, PairGrid
Equivalent to the relationship jointplot and JointGrid, PairGrid scatterplot matrix has a more flexible control
init（data，hue = None，hue_order = None，palette = None，hue_kws = None，vars = None，x_vars = None，y_vars = None，diag_sharey = True，size = 2.5，aspect = 1，despine = True，dropna = True）
method:
add_legend ([legend_data, title, label_order]) a drawn legend, may be placed outside the shaft and adjust the pattern size.
map_diag (func, ** kwargs): Drawing FIG univariate function having at each diagonal sub FIG.
map_lower (func, ** kwargs): Drawing FIG bivariate function with the lower sub-diagonal FIG.
map_upper (func, ** kwargs): Drawing with FIG bivariate function on the diagonal submap
map_offdiag (func, ** kwargs): Drawing FIG bivariate function having on-diagonal sub FIG.
set (** kwargs): setting a property on each sub portfolio Axes.
