근처 점의 밀도를 기반으로하는 matplotlib hexbin의 16 진 크기

다음 그림을 생성하는 다음 코드가 있습니다.

import numpy as np
np.random.seed(3)
import pandas as pd
import matplotlib.pyplot as plt
df = pd.DataFrame()
df['X'] = list(np.random.randint(100, size=100)) + list(np.random.randint(30, size=100))
df['Y'] = list(np.random.randint(100, size=100)) + list(np.random.randint(30, size=100))

df['Bin'] = df.apply(lambda row: .1 if row['X'] < 30 and row['Y'] < 30 else .9, axis=1)

fig, ax = plt.subplots(figsize=(10,10))
plt.scatter(df['X'], df['Y'])

아래에 언급 된대로 16 진수를 사용하여 데이터를 그래프로 표시했습니다.

from matplotlib import cm

fig, ax = plt.subplots(figsize=(10,10))
hexbin = ax.hexbin(df['X'], df['Y'], C=df['Bin'], gridsize=20, cmap= cm.get_cmap('RdYlBu_r'),edgecolors='black')
plt.show()

육각형이 덮는 영역에 그려진 점의 밀도를 기준으로 육각형의 크기를 변경하고 싶습니다. 예를 들어 왼쪽 하단의 육각형 (점이 콤팩트 한 위치)은 다른 곳의 육각형 (포인트가 희박한 위치)보다 큽니다. 이것을 할 수있는 방법이 있습니까?

편집 : 이 솔루션을 시도했지만 df [ 'Bin']을 기반으로 16 진수를 채색하는 방법 또는 최소 및 최대 16 진수 크기를 설정하는 방법을 알 수 없습니다.

from matplotlib.collections import PatchCollection
from matplotlib.path import Path
from matplotlib.patches import PathPatch
fig, ax = plt.subplots(figsize=(10,10))
hexbin = ax.hexbin(df['X'], df['Y'], C=df['Bins'], gridsize=20, cmap= cm.get_cmap('RdYlBu_r'),edgecolors='black')
def sized_hexbin(ax,hc):
    offsets = hc.get_offsets()
    orgpath = hc.get_paths()[0]
    verts = orgpath.vertices
    values = hc.get_array()
    ma = values.max()
    patches = []
    for offset,val in zip(offsets,values):
        v1 = verts*val/ma+offset
        path = Path(v1, orgpath.codes)
        patch = PathPatch(path)
        patches.append(patch)

    pc = PatchCollection(patches, cmap=cm.get_cmap('RdYlBu_r'), edgecolors='black')
    pc.set_array(values)
    ax.add_collection(pc)
    hc.remove()

sized_hexbin(ax,hexbin)
plt.show()

색상 매핑을 이해하는 데 시간을 할애 할 수 있습니다.

    import numpy as np
    np.random.seed(3)
    import pandas as pd
    import matplotlib.pyplot as plt
    from matplotlib.collections import PatchCollection
    from matplotlib.path import Path
    from matplotlib.patches import PathPatch
    df = pd.DataFrame()
    df['X'] = list(np.random.randint(100, size=100)) + list(np.random.randint(30, size=100))
    df['Y'] = list(np.random.randint(100, size=100)) + list(np.random.randint(30, size=100))

    df['Bin'] = df.apply(lambda row: .1 if row['X'] < 30 and row['Y'] < 30 else .9, axis=1)

    #fig, ((ax1, ax2)) = plt.subplots(1, 2, sharex=True, sharey=True)
    ax1 = plt.scatter(df['X'], df['Y'])

    fig,ax2 = plt.subplots(figsize=(10,10))
    hexbin = ax2.hexbin(df['X'], df['Y'], C=df['Bin'], gridsize=20,edgecolors='black',cmap= 'RdBu', reduce_C_function=np.bincount) #**

    def sized_hexbin(ax,hc):
        offsets = hc.get_offsets()
        orgpath = hc.get_paths()[0]
        verts = orgpath.vertices
        values = hc.get_array()
        ma = values.max()
        patches = []
        for offset,val in zip(offsets,values):
            v1 = verts*val/ma + offset
            path = Path(v1, orgpath.codes)
            patch = PathPatch(path)
            patches.append(patch)

        pc = PatchCollection(patches, cmap= 'RdBu', edgecolors='black')
        pc.set_array(values)

        ax.add_collection(pc)

        hc.remove()

    sized_hexbin(ax2,hexbin)
    cb = plt.colorbar(hexbin, ax=ax2)

    plt.show()

To plot the chart based on df['bins'] values - 

Need to change the reduce_C_function in #** marked line -

    hexbin = ax2.hexbin(df['X'], df['Y'], C=df['Bin'], gridsize=20,edgecolors='black',cmap= 'RdBu', reduce_C_function=np.sum)

[![enter image description here][2]][2]


  [1]: https://i.stack.imgur.com/kv0U4.png
  [2]: https://i.stack.imgur.com/mb0gD.png

# Another variation of the chart :

# Where size is based on count of points in the bins and color is based on values of the df['bin']./ Also added if condition to control minimum hexbin size.


import numpy as np
np.random.seed(3)
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.collections import PatchCollection
from matplotlib.path import Path
from matplotlib.patches import PathPatch
from functools import partial

mycmp = 'coolwarm'

df = pd.DataFrame()
df['X'] = list(np.random.randint(100, size=100)) + list(np.random.randint(30, size=100))
df['Y'] = list(np.random.randint(100, size=100)) + list(np.random.randint(30, size=100))

df['Bin'] = df.apply(lambda row: .1 if row['X'] < 30 and row['Y'] < 30 else .9, axis=1)

#fig, ((ax1, ax2)) = plt.subplots(1, 2, sharex=True, sharey=True)
ax1 = plt.scatter(df['X'], df['Y'])


fig,ax2 = plt.subplots(figsize=(10,10))
hexbin = ax2.hexbin(df['X'], df['Y'], C=df['Bin'], gridsize=15,edgecolors='black',cmap= newcmp , reduce_C_function=np.bincount)
hexbin2 = ax2.hexbin(df['X'], df['Y'], C=df['Bin'], gridsize=15,edgecolors='black',cmap= newcmp , reduce_C_function=np.mean)

def sized_hexbin(ax,hc,hc2):
    offsets = hc.get_offsets()
    orgpath = hc.get_paths()[0]
    verts = orgpath.vertices
    values1 = hc.get_array()
    values2 = hc2.get_array()
    ma = values1.max()
    patches = []

    for offset,val in zip(offsets,values1):
        # Adding condition for minimum size 
        if (val/ma) < 0.2:
            val_t = 0.2
        else:
            val_t = val/ma
        v1 =  verts*val_t + offset
        path = Path(v1, orgpath.codes)
        print(path)
        patch = PathPatch(path)
        patches.append(patch)

    pc = PatchCollection(patches, cmap=  newcmp)  #edgecolors='black'
    pc.set_array(values2)

    ax.add_collection(pc)
    hc.remove()
    hc2.remove()


sized_hexbin(ax2,hexbin,hexbin2)
cb = plt.colorbar(hexbin2, ax=ax2)

plt.xlim((-5, 100))
plt.ylim((-5, 100))

plt.show()