Python matplotlib scatter 绘制散点图详解与实战

#!/usr/bin/env python
#coding:utf-8

import matplotlib.pyplot as plt 

def pltpicture():
 file = "xxx"                                      
 xlist = []
 ylist = []
 with open(file, "r") as f:
  for line in f.readlines():
   lines = line.strip().split()
   if len(lines) != 2 or int(lines[1]) < 100000:
    continue
   x, y = int(lines[0]), int(lines[1])
   xlist.append(x)
   ylist.append(y)

 plt.xlabel('X')
 plt.ylabel('Y')
 plt.scatter(xlist, ylist)
 plt.show()

from matplotlib import pyplot as plt

file = "/home/mi/wanglei/data/datingTestSet2.txt"
label1X, label1Y, label2X, label2Y, label3X, label3Y = [], [], [], [], [], []

with open(file, "r") as f:
 for line in f:
  lines = line.strip().split()
  if len(lines) != 4:
   continue
  distance, rate, label = lines[0], lines[1], lines[3]
  if label == "1":
   label1X.append(distance)
   label1Y.append(rate)

  elif label == "2":
   label2X.append(distance)
   label2Y.append(rate)

  elif label == "3":
   label3X.append(distance)
   label3Y.append(rate)

plt.figure(figsize=(8, 5), dpi=80)
axes = plt.subplot(111)

label1 = axes.scatter(label1X, label1Y, s=20, c="red")
label2 = axes.scatter(label2X, label2Y, s=40, c="green")
label3 = axes.scatter(label3X, label3Y, s=50, c="blue")

plt.xlabel("every year fly distance")
plt.ylabel("play video game rate")
axes.legend((label1, label2, label3), ("don't like", "attraction common", "attraction perfect"), loc=2)

plt.show()

def scatter(self, x, y, s=None, c=None, marker=None, cmap=None, norm=None,
    vmin=None, vmax=None, alpha=None, linewidths=None,
    verts=None, edgecolors=None,
    **kwargs):
  """
  Make a scatter plot of `x` vs `y`

  Marker size is scaled by `s` and marker color is mapped to `c`

  Parameters
  ----------
  x, y : array_like, shape (n, )
   Input data

  s : scalar or array_like, shape (n, ), optional
   size in points^2. Default is `rcParams['lines.markersize'] ** 2`.

  c : color, sequence, or sequence of color, optional, default: 'b'
   `c` can be a single color format string, or a sequence of color
   specifications of length `N`, or a sequence of `N` numbers to be
   mapped to colors using the `cmap` and `norm` specified via kwargs
   (see below). Note that `c` should not be a single numeric RGB or
   RGBA sequence because that is indistinguishable from an array of
   values to be colormapped. `c` can be a 2-D array in which the
   rows are RGB or RGBA, however, including the case of a single
   row to specify the same color for all points.

  marker : `~matplotlib.markers.MarkerStyle`, optional, default: 'o'
   See `~matplotlib.markers` for more information on the different
   styles of markers scatter supports. `marker` can be either
   an instance of the class or the text shorthand for a particular
   marker.

  cmap : `~matplotlib.colors.Colormap`, optional, default: None
   A `~matplotlib.colors.Colormap` instance or registered name.
   `cmap` is only used if `c` is an array of floats. If None,
   defaults to rc `image.cmap`.

  norm : `~matplotlib.colors.Normalize`, optional, default: None
   A `~matplotlib.colors.Normalize` instance is used to scale
   luminance data to 0, 1. `norm` is only used if `c` is an array of
   floats. If `None`, use the default :func:`normalize`.

  vmin, vmax : scalar, optional, default: None
   `vmin` and `vmax` are used in conjunction with `norm` to normalize
   luminance data. If either are `None`, the min and max of the
   color array is used. Note if you pass a `norm` instance, your
   settings for `vmin` and `vmax` will be ignored.

  alpha : scalar, optional, default: None
   The alpha blending value, between 0 (transparent) and 1 (opaque)

  linewidths : scalar or array_like, optional, default: None
   If None, defaults to (lines.linewidth,).

  verts : sequence of (x, y), optional
   If `marker` is None, these vertices will be used to
   construct the marker. The center of the marker is located
   at (0,0) in normalized units. The overall marker is rescaled
   by ``s``.

  edgecolors : color or sequence of color, optional, default: None
   If None, defaults to 'face'

   If 'face', the edge color will always be the same as
   the face color.

   If it is 'none', the patch boundary will not
   be drawn.

   For non-filled markers, the `edgecolors` kwarg
   is ignored and forced to 'face' internally.

  Returns
  -------
  paths : `~matplotlib.collections.PathCollection`

  Other parameters
  ----------------
  kwargs : `~matplotlib.collections.Collection` properties

  See Also
  --------
  plot : to plot scatter plots when markers are identical in size and
   color

  Notes
  -----

  * The `plot` function will be faster for scatterplots where markers
   don't vary in size or color.

  * Any or all of `x`, `y`, `s`, and `c` may be masked arrays, in which
   case all masks will be combined and only unmasked points will be
   plotted.

   Fundamentally, scatter works with 1-D arrays; `x`, `y`, `s`, and `c`
   may be input as 2-D arrays, but within scatter they will be
   flattened. The exception is `c`, which will be flattened only if its
   size matches the size of `x` and `y`.

  Examples
  --------
  .. plot:: mpl_examples/shapes_and_collections/scatter_demo.py

  """